Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 230 results for author: <span class="mathjax">Siegwart, R</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Siegwart%2C+R">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Siegwart, R"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Siegwart%2C+R&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Siegwart, R"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Siegwart%2C+R&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Siegwart%2C+R&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Siegwart%2C+R&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Siegwart%2C+R&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Siegwart%2C+R&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Siegwart%2C+R&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.15398">arXiv:2410.15398</a> <span> [<a href="https://arxiv.org/pdf/2410.15398">pdf</a>, <a href="https://arxiv.org/format/2410.15398">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Evaluation of Human-Robot Interfaces based on 2D/3D Visual and Haptic Feedback for Aerial Manipulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mellet%2C+J">Julien Mellet</a>, <a href="/search/cs?searchtype=author&query=Allenspach%2C+M">Mike Allenspach</a>, <a href="/search/cs?searchtype=author&query=Cuniato%2C+E">Eugenio Cuniato</a>, <a href="/search/cs?searchtype=author&query=Pacchierotti%2C+C">Claudio Pacchierotti</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Tognon%2C+M">Marco Tognon</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.15398v1-abstract-short" style="display: inline;"> Most telemanipulation systems for aerial robots provide the operator with only 2D screen visual information. The lack of richer information about the robot's status and environment can limit human awareness and, in turn, task performance. While the pilot's experience can often compensate for this reduced flow of information, providing richer feedback is expected to reduce the cognitive workload an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15398v1-abstract-full').style.display = 'inline'; document.getElementById('2410.15398v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15398v1-abstract-full" style="display: none;"> Most telemanipulation systems for aerial robots provide the operator with only 2D screen visual information. The lack of richer information about the robot's status and environment can limit human awareness and, in turn, task performance. While the pilot's experience can often compensate for this reduced flow of information, providing richer feedback is expected to reduce the cognitive workload and offer a more intuitive experience overall. This work aims to understand the significance of providing additional pieces of information during aerial telemanipulation, namely (i) 3D immersive visual feedback about the robot's surroundings through mixed reality (MR) and (ii) 3D haptic feedback about the robot interaction with the environment. To do so, we developed a human-robot interface able to provide this information. First, we demonstrate its potential in a real-world manipulation task requiring sub-centimeter-level accuracy. Then, we evaluate the individual effect of MR vision and haptic feedback on both dexterity and workload through a human subjects study involving a virtual block transportation task. Results show that both 3D MR vision and haptic feedback improve the operator's dexterity in the considered teleoperated aerial interaction tasks. Nevertheless, pilot experience remains the most significant factor. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15398v1-abstract-full').style.display = 'none'; document.getElementById('2410.15398v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 11 figures, journal paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.00736">arXiv:2410.00736</a> <span> [<a href="https://arxiv.org/pdf/2410.00736">pdf</a>, <a href="https://arxiv.org/format/2410.00736">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Radar Meets Vision: Robustifying Monocular Metric Depth Prediction for Mobile Robotics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Job%2C+M">Marco Job</a>, <a href="/search/cs?searchtype=author&query=Stastny%2C+T">Thomas Stastny</a>, <a href="/search/cs?searchtype=author&query=Kazik%2C+T">Tim Kazik</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Pantic%2C+M">Michael Pantic</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.00736v1-abstract-short" style="display: inline;"> Mobile robots require accurate and robust depth measurements to understand and interact with the environment. While existing sensing modalities address this problem to some extent, recent research on monocular depth estimation has leveraged the information richness, yet low cost and simplicity of monocular cameras. These works have shown significant generalization capabilities, mainly in automotiv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00736v1-abstract-full').style.display = 'inline'; document.getElementById('2410.00736v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.00736v1-abstract-full" style="display: none;"> Mobile robots require accurate and robust depth measurements to understand and interact with the environment. While existing sensing modalities address this problem to some extent, recent research on monocular depth estimation has leveraged the information richness, yet low cost and simplicity of monocular cameras. These works have shown significant generalization capabilities, mainly in automotive and indoor settings. However, robots often operate in environments with limited scale cues, self-similar appearances, and low texture. In this work, we encode measurements from a low-cost mmWave radar into the input space of a state-of-the-art monocular depth estimation model. Despite the radar's extreme point cloud sparsity, our method demonstrates generalization and robustness across industrial and outdoor experiments. Our approach reduces the absolute relative error of depth predictions by 9-64% across a range of unseen, real-world validation datasets. Importantly, we maintain consistency of all performance metrics across all experiments and scene depths where current vision-only approaches fail. We further address the present deficit of training data in mobile robotics environments by introducing a novel methodology for synthesizing rendered, realistic learning datasets based on photogrammetric data that simulate the radar sensor observations for training. Our code, datasets, and pre-trained networks are made available at https://github.com/ethz-asl/radarmeetsvision. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00736v1-abstract-full').style.display = 'none'; document.getElementById('2410.00736v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to ICRA 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.00572">arXiv:2410.00572</a> <span> [<a href="https://arxiv.org/pdf/2410.00572">pdf</a>, <a href="https://arxiv.org/format/2410.00572">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Obstacle-Avoidant Leader Following with a Quadruped Robot </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Scheidemann%2C+C">Carmen Scheidemann</a>, <a href="/search/cs?searchtype=author&query=Werner%2C+L">Lennart Werner</a>, <a href="/search/cs?searchtype=author&query=Reijgwart%2C+V">Victor Reijgwart</a>, <a href="/search/cs?searchtype=author&query=Cramariuc%2C+A">Andrei Cramariuc</a>, <a href="/search/cs?searchtype=author&query=Chomarat%2C+J">Joris Chomarat</a>, <a href="/search/cs?searchtype=author&query=Chiu%2C+J">Jia-Ruei Chiu</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Hutter%2C+M">Marco Hutter</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.00572v1-abstract-short" style="display: inline;"> Personal mobile robotic assistants are expected to find wide applications in industry and healthcare. For example, people with limited mobility can benefit from robots helping with daily tasks, or construction workers can have robots perform precision monitoring tasks on-site. However, manually steering a robot while in motion requires significant concentration from the operator, especially in tig… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00572v1-abstract-full').style.display = 'inline'; document.getElementById('2410.00572v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.00572v1-abstract-full" style="display: none;"> Personal mobile robotic assistants are expected to find wide applications in industry and healthcare. For example, people with limited mobility can benefit from robots helping with daily tasks, or construction workers can have robots perform precision monitoring tasks on-site. However, manually steering a robot while in motion requires significant concentration from the operator, especially in tight or crowded spaces. This reduces walking speed, and the constant need for vigilance increases fatigue and, thus, the risk of accidents. This work presents a virtual leash with which a robot can naturally follow an operator. We use a sensor fusion based on a custom-built RF transponder, RGB cameras, and a LiDAR. In addition, we customize a local avoidance planner for legged platforms, which enables us to navigate dynamic and narrow environments. We successfully validate on the ANYmal platform the robustness and performance of our entire pipeline in real-world experiments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00572v1-abstract-full').style.display = 'none'; document.getElementById('2410.00572v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.15475">arXiv:2409.15475</a> <span> [<a href="https://arxiv.org/pdf/2409.15475">pdf</a>, <a href="https://arxiv.org/format/2409.15475">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Framework for Robust Localization of UUVs and Mapping of Net Pens </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Botta%2C+D">David Botta</a>, <a href="/search/cs?searchtype=author&query=Ebner%2C+L">Luca Ebner</a>, <a href="/search/cs?searchtype=author&query=Studer%2C+A">Andrej Studer</a>, <a href="/search/cs?searchtype=author&query=Reijgwart%2C+V">Victor Reijgwart</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Kelasidi%2C+E">Eleni Kelasidi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.15475v1-abstract-short" style="display: inline;"> This paper presents a general framework integrating vision and acoustic sensor data to enhance localization and mapping in highly dynamic and complex underwater environments, with a particular focus on fish farming. The proposed pipeline is suited to obtain both the net-relative pose estimates of an Unmanned Underwater Vehicle (UUV) and the depth map of the net pen purely based on vision data. Fur… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15475v1-abstract-full').style.display = 'inline'; document.getElementById('2409.15475v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.15475v1-abstract-full" style="display: none;"> This paper presents a general framework integrating vision and acoustic sensor data to enhance localization and mapping in highly dynamic and complex underwater environments, with a particular focus on fish farming. The proposed pipeline is suited to obtain both the net-relative pose estimates of an Unmanned Underwater Vehicle (UUV) and the depth map of the net pen purely based on vision data. Furthermore, this paper presents a method to estimate the global pose of an UUV fusing the net-relative pose estimates with acoustic data. The pipeline proposed in this paper showcases results on datasets obtained from industrial-scale fish farms and successfully demonstrates that the vision-based TRU-Depth model, when provided with sparse depth priors from the FFT method and combined with the Wavemap method, can estimate both net-relative and global position of the UUV in real time and generate detailed 3D maps suitable for autonomous navigation and inspection purposes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15475v1-abstract-full').style.display = 'none'; document.getElementById('2409.15475v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.05764">arXiv:2408.05764</a> <span> [<a href="https://arxiv.org/pdf/2408.05764">pdf</a>, <a href="https://arxiv.org/format/2408.05764">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> A robust baro-radar-inertial odometry m-estimator for multicopter navigation in cities and forests </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Girod%2C+R">Rik Girod</a>, <a href="/search/cs?searchtype=author&query=Hauswirth%2C+M">Marco Hauswirth</a>, <a href="/search/cs?searchtype=author&query=Pfreundschuh%2C+P">Patrick Pfreundschuh</a>, <a href="/search/cs?searchtype=author&query=Biasio%2C+M">Mariano Biasio</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.05764v1-abstract-short" style="display: inline;"> Search and rescue operations require mobile robots to navigate unstructured indoor and outdoor environments. In particular, actively stabilized multirotor drones need precise movement data to balance and avoid obstacles. Combining radial velocities from on-chip radar with MEMS inertial sensing has proven to provide robust, lightweight, and consistent state estimation, even in visually or geometric… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.05764v1-abstract-full').style.display = 'inline'; document.getElementById('2408.05764v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.05764v1-abstract-full" style="display: none;"> Search and rescue operations require mobile robots to navigate unstructured indoor and outdoor environments. In particular, actively stabilized multirotor drones need precise movement data to balance and avoid obstacles. Combining radial velocities from on-chip radar with MEMS inertial sensing has proven to provide robust, lightweight, and consistent state estimation, even in visually or geometrically degraded environments. Statistical tests robustify these estimators against radar outliers. However, available work with binary outlier filters lacks adaptability to various hardware setups and environments. Other work has predominantly been tested in handheld static environments or automotive contexts. This work introduces a robust baro-radar-inertial odometry (BRIO) m-estimator for quadcopter flights in typical GNSS-denied scenarios. Extensive real-world closed-loop flights in cities and forests demonstrate robustness to moving objects and ghost targets, maintaining a consistent performance with 0.5 % to 3.2 % drift per distance traveled. Benchmarks on public datasets validate the system's generalizability. The code, dataset, and video are available at https://github.com/ethz-asl/rio. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.05764v1-abstract-full').style.display = 'none'; document.getElementById('2408.05764v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for publication at IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.13530">arXiv:2407.13530</a> <span> [<a href="https://arxiv.org/pdf/2407.13530">pdf</a>, <a href="https://arxiv.org/format/2407.13530">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Pushing the Limits of Reactive Planning: Learning to Escape Local Minima </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Meijer%2C+I">Isar Meijer</a>, <a href="/search/cs?searchtype=author&query=Pantic%2C+M">Michael Pantic</a>, <a href="/search/cs?searchtype=author&query=Oleynikova%2C+H">Helen Oleynikova</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.13530v1-abstract-short" style="display: inline;"> When does a robot planner need a map? Reactive methods that use only the robot's current sensor data and local information are fast and flexible, but prone to getting stuck in local minima. Is there a middle-ground between fully reactive methods and map-based path planners? In this paper, we investigate feed forward and recurrent networks to augment a purely reactive sensor-based planner, which sh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.13530v1-abstract-full').style.display = 'inline'; document.getElementById('2407.13530v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.13530v1-abstract-full" style="display: none;"> When does a robot planner need a map? Reactive methods that use only the robot's current sensor data and local information are fast and flexible, but prone to getting stuck in local minima. Is there a middle-ground between fully reactive methods and map-based path planners? In this paper, we investigate feed forward and recurrent networks to augment a purely reactive sensor-based planner, which should give the robot geometric intuition about how to escape local minima. We train on a large number of extremely cluttered worlds auto-generated from primitive shapes, and show that our system zero-shot transfers to real 3D man-made environments, and can handle up to 30% sensor noise without degeneration of performance. We also offer a discussion of what role network memory plays in our final system, and what insights can be drawn about the nature of reactive vs. map-based navigation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.13530v1-abstract-full').style.display = 'none'; document.getElementById('2407.13530v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.12207">arXiv:2407.12207</a> <span> [<a href="https://arxiv.org/pdf/2407.12207">pdf</a>, <a href="https://arxiv.org/format/2407.12207">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> NeuSurfEmb: A Complete Pipeline for Dense Correspondence-based 6D Object Pose Estimation without CAD Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Milano%2C+F">Francesco Milano</a>, <a href="/search/cs?searchtype=author&query=Chung%2C+J+J">Jen Jen Chung</a>, <a href="/search/cs?searchtype=author&query=Blum%2C+H">Hermann Blum</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.12207v1-abstract-short" style="display: inline;"> State-of-the-art approaches for 6D object pose estimation assume the availability of CAD models and require the user to manually set up physically-based rendering (PBR) pipelines for synthetic training data generation. Both factors limit the application of these methods in real-world scenarios. In this work, we present a pipeline that does not require CAD models and allows training a state-of-the-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12207v1-abstract-full').style.display = 'inline'; document.getElementById('2407.12207v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.12207v1-abstract-full" style="display: none;"> State-of-the-art approaches for 6D object pose estimation assume the availability of CAD models and require the user to manually set up physically-based rendering (PBR) pipelines for synthetic training data generation. Both factors limit the application of these methods in real-world scenarios. In this work, we present a pipeline that does not require CAD models and allows training a state-of-the-art pose estimator requiring only a small set of real images as input. Our method is based on a NeuS2 object representation, that we learn through a semi-automated procedure based on Structure-from-Motion (SfM) and object-agnostic segmentation. We exploit the novel-view synthesis ability of NeuS2 and simple cut-and-paste augmentation to automatically generate photorealistic object renderings, which we use to train the correspondence-based SurfEmb pose estimator. We evaluate our method on the LINEMOD-Occlusion dataset, extensively studying the impact of its individual components and showing competitive performance with respect to approaches based on CAD models and PBR data. We additionally demonstrate the ease of use and effectiveness of our pipeline on self-collected real-world objects, showing that our method outperforms state-of-the-art CAD-model-free approaches, with better accuracy and robustness to mild occlusions. To allow the robotics community to benefit from this system, we will publicly release it at https://www.github.com/ethz-asl/neusurfemb. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12207v1-abstract-full').style.display = 'none'; document.getElementById('2407.12207v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2024. 8 pages, 4 figures, 5 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.17333">arXiv:2406.17333</a> <span> [<a href="https://arxiv.org/pdf/2406.17333">pdf</a>, <a href="https://arxiv.org/format/2406.17333">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Task Adaptation in Industrial Human-Robot Interaction: Leveraging Riemannian Motion Policies </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Allenspach%2C+M">Mike Allenspach</a>, <a href="/search/cs?searchtype=author&query=Pantic%2C+M">Michael Pantic</a>, <a href="/search/cs?searchtype=author&query=Girod%2C+R">Rik Girod</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.17333v1-abstract-short" style="display: inline;"> In real-world industrial environments, modern robots often rely on human operators for crucial decision-making and mission synthesis from individual tasks. Effective and safe collaboration between humans and robots requires systems that can adjust their motion based on human intentions, enabling dynamic task planning and adaptation. Addressing the needs of industrial applications, we propose a mot… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.17333v1-abstract-full').style.display = 'inline'; document.getElementById('2406.17333v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.17333v1-abstract-full" style="display: none;"> In real-world industrial environments, modern robots often rely on human operators for crucial decision-making and mission synthesis from individual tasks. Effective and safe collaboration between humans and robots requires systems that can adjust their motion based on human intentions, enabling dynamic task planning and adaptation. Addressing the needs of industrial applications, we propose a motion control framework that (i) removes the need for manual control of the robot's movement; (ii) facilitates the formulation and combination of complex tasks; and (iii) allows the seamless integration of human intent recognition and robot motion planning. For this purpose, we leverage a modular and purely reactive approach for task parametrization and motion generation, embodied by Riemannian Motion Policies. The effectiveness of our method is demonstrated, evaluated, and compared to \remove{state-of-the-art approaches}\add{a representative state-of-the-art approach} in experimental scenarios inspired by realistic industrial Human-Robot Interaction settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.17333v1-abstract-full').style.display = 'none'; document.getElementById('2406.17333v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">9 pages; Robotics, Science and Systems (RSS) 2024</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Robotics, Science and Systems (RSS) 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.05313">arXiv:2406.05313</a> <span> [<a href="https://arxiv.org/pdf/2406.05313">pdf</a>, <a href="https://arxiv.org/format/2406.05313">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Traversing Mars: Cooperative Informative Path Planning to Efficiently Navigate Unknown Scenes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rockenbauer%2C+F+M">Friedrich M. Rockenbauer</a>, <a href="/search/cs?searchtype=author&query=Lim%2C+J">Jaeyoung Lim</a>, <a href="/search/cs?searchtype=author&query=M%C3%BCller%2C+M+G">Marcus G. M眉ller</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Schmid%2C+L">Lukas Schmid</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.05313v2-abstract-short" style="display: inline;"> The ability to traverse an unknown environment is crucial for autonomous robot operations. However, due to the limited sensing capabilities and system constraints, approaching this problem with a single robot agent can be slow, costly, and unsafe. For example, in planetary exploration missions, the wear on the wheels of a rover from abrasive terrain should be minimized at all costs as reparations… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05313v2-abstract-full').style.display = 'inline'; document.getElementById('2406.05313v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.05313v2-abstract-full" style="display: none;"> The ability to traverse an unknown environment is crucial for autonomous robot operations. However, due to the limited sensing capabilities and system constraints, approaching this problem with a single robot agent can be slow, costly, and unsafe. For example, in planetary exploration missions, the wear on the wheels of a rover from abrasive terrain should be minimized at all costs as reparations are infeasible. On the other hand, utilizing a scouting robot such as a micro aerial vehicle (MAV) has the potential to reduce wear and time costs and increasing safety of a follower robot. This work proposes a novel cooperative IPP framework that allows a scout (e.g., an MAV) to efficiently explore the minimum-cost-path for a follower (e.g., a rover) to reach the goal. We derive theoretic guarantees for our algorithm, and prove that the algorithm always terminates, always finds the optimal path if it exists, and terminates early when the found path is shown to be optimal or infeasible. We show in thorough experimental evaluation that the guarantees hold in practice, and that our algorithm is 22.5% quicker to find the optimal path and 15% quicker to terminate compared to existing methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05313v2-abstract-full').style.display = 'none'; document.getElementById('2406.05313v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 9 figures, code will be available at https://github.com/ethz-asl/scouting-ipp</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.17844">arXiv:2405.17844</a> <span> [<a href="https://arxiv.org/pdf/2405.17844">pdf</a>, <a href="https://arxiv.org/format/2405.17844">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Sliding Performance with Aerial Robots: Analysis and Solutions for Non-Actuated Multi-Wheel Configurations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hui%2C+T">Tong Hui</a>, <a href="/search/cs?searchtype=author&query=Ghielmini%2C+J">Jefferson Ghielmini</a>, <a href="/search/cs?searchtype=author&query=Papageorgiou%2C+D">Dimitrios Papageorgiou</a>, <a href="/search/cs?searchtype=author&query=Tognon%2C+M">Marco Tognon</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Fumagalli%2C+M">Matteo Fumagalli</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.17844v3-abstract-short" style="display: inline;"> Sliding tasks performed by aerial robots are valuable for inspection and simple maintenance tasks at height, such as non-destructive testing and painting. Although various end-effector designs have been used for such tasks, non-actuated wheel configurations are more frequently applied thanks to their rolling capability for sliding motion, mechanical simplicity, and lightweight design. Moreover, a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.17844v3-abstract-full').style.display = 'inline'; document.getElementById('2405.17844v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.17844v3-abstract-full" style="display: none;"> Sliding tasks performed by aerial robots are valuable for inspection and simple maintenance tasks at height, such as non-destructive testing and painting. Although various end-effector designs have been used for such tasks, non-actuated wheel configurations are more frequently applied thanks to their rolling capability for sliding motion, mechanical simplicity, and lightweight design. Moreover, a non-actuated multi-wheel (more than one wheel) configuration in the end-effector design allows the placement of additional equipment e.g., sensors and tools in the center of the end-effector tip for applications. However, there is still a lack of studies on crucial contact conditions during sliding using aerial robots with such an end-effector design. In this article, we investigate the key challenges associated with sliding operations using aerial robots equipped with multiple non-actuated wheels through in-depth analysis grounded in physical experiments. The experimental data is used to create a simulator that closely captures real-world conditions. We propose solutions from both mechanical design and control perspectives to improve the sliding performance of aerial robots. From a mechanical standpoint, design guidelines are derived from experimental data. From a control perspective, we introduce a novel pressure-sensing-based control framework that ensures reliable task execution, even during sliding maneuvers. The effectiveness and robustness of the proposed approaches are then validated and compared using the built simulator, particularly in high-risk scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.17844v3-abstract-full').style.display = 'none'; document.getElementById('2405.17844v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.16137">arXiv:2405.16137</a> <span> [<a href="https://arxiv.org/pdf/2405.16137">pdf</a>, <a href="https://arxiv.org/format/2405.16137">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Comparison between Behavior Trees and Finite State Machines </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Iovino%2C+M">Matteo Iovino</a>, <a href="/search/cs?searchtype=author&query=F%C3%B6rster%2C+J">Julian F枚rster</a>, <a href="/search/cs?searchtype=author&query=Falco%2C+P">Pietro Falco</a>, <a href="/search/cs?searchtype=author&query=Chung%2C+J+J">Jen Jen Chung</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Smith%2C+C">Christian Smith</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.16137v1-abstract-short" style="display: inline;"> Behavior Trees (BTs) were first conceived in the computer games industry as a tool to model agent behavior, but they received interest also in the robotics community as an alternative policy design to Finite State Machines (FSMs). The advantages of BTs over FSMs had been highlighted in many works, but there is no thorough practical comparison of the two designs. Such a comparison is particularly r… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16137v1-abstract-full').style.display = 'inline'; document.getElementById('2405.16137v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.16137v1-abstract-full" style="display: none;"> Behavior Trees (BTs) were first conceived in the computer games industry as a tool to model agent behavior, but they received interest also in the robotics community as an alternative policy design to Finite State Machines (FSMs). The advantages of BTs over FSMs had been highlighted in many works, but there is no thorough practical comparison of the two designs. Such a comparison is particularly relevant in the robotic industry, where FSMs have been the state-of-the-art policy representation for robot control for many years. In this work we shed light on this matter by comparing how BTs and FSMs behave when controlling a robot in a mobile manipulation task. The comparison is made in terms of reactivity, modularity, readability, and design. We propose metrics for each of these properties, being aware that while some are tangible and objective, others are more subjective and implementation dependent. The practical comparison is performed in a simulation environment with validation on a real robot. We find that although the robot's behavior during task solving is independent on the policy representation, maintaining a BT rather than an FSM becomes easier as the task increases in complexity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16137v1-abstract-full').style.display = 'none'; document.getElementById('2405.16137v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to IEEE Transactions on Robotics (T-RO). arXiv admin note: text overlap with arXiv:2209.07392</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.13617">arXiv:2405.13617</a> <span> [<a href="https://arxiv.org/pdf/2405.13617">pdf</a>, <a href="https://arxiv.org/format/2405.13617">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Waverider: Leveraging Hierarchical, Multi-Resolution Maps for Efficient and Reactive Obstacle Avoidance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Reijgwart%2C+V">Victor Reijgwart</a>, <a href="/search/cs?searchtype=author&query=Pantic%2C+M">Michael Pantic</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.13617v1-abstract-short" style="display: inline;"> Fast and reliable obstacle avoidance is an important task for mobile robots. In this work, we propose an efficient reactive system that provides high-quality obstacle avoidance while running at hundreds of hertz with minimal resource usage. Our approach combines wavemap, a hierarchical volumetric map representation, with a novel hierarchical and parallelizable obstacle avoidance algorithm formulat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.13617v1-abstract-full').style.display = 'inline'; document.getElementById('2405.13617v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.13617v1-abstract-full" style="display: none;"> Fast and reliable obstacle avoidance is an important task for mobile robots. In this work, we propose an efficient reactive system that provides high-quality obstacle avoidance while running at hundreds of hertz with minimal resource usage. Our approach combines wavemap, a hierarchical volumetric map representation, with a novel hierarchical and parallelizable obstacle avoidance algorithm formulated through Riemannian Motion Policies (RMP). Leveraging multi-resolution obstacle avoidance policies, the proposed navigation system facilitates precise, low-latency (36ms), and extremely efficient obstacle avoidance with a very large perceptive radius (30m). We perform extensive statistical evaluations on indoor and outdoor maps, verifying that the proposed system compares favorably to fixed-resolution RMP variants and CHOMP. Finally, the RMP formulation allows the seamless fusion of obstacle avoidance with additional objectives, such as goal-seeking, to obtain a fully-fledged navigation system that is versatile and robust. We deploy the system on a Micro Aerial Vehicle and show how it navigates through an indoor obstacle course. Our complete implementation, called waverider, is made available as open source. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.13617v1-abstract-full').style.display = 'none'; document.getElementById('2405.13617v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 pages, 12 figures, accepted to ICRA 2024, code is open-source: https://github.com/ethz-asl/waverider</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.02011">arXiv:2405.02011</a> <span> [<a href="https://arxiv.org/pdf/2405.02011">pdf</a>, <a href="https://arxiv.org/format/2405.02011">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Autonomous Active Mapping in Steep Alpine Environments with Fixed-wing Aerial Vehicles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lim%2C+J">Jaeyoung Lim</a>, <a href="/search/cs?searchtype=author&query=Achermann%2C+F">Florian Achermann</a>, <a href="/search/cs?searchtype=author&query=Lawrance%2C+N">Nicholas Lawrance</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.02011v1-abstract-short" style="display: inline;"> Monitoring large scale environments is a crucial task for managing remote alpine environments, especially for hazardous events such as avalanches. One key information for avalanche risk forecast is imagery of released avalanches. As these happen in remote and potentially dangerous locations this data is difficult to obtain. Fixed-wing vehicles, due to their long range and travel speeds are a promi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.02011v1-abstract-full').style.display = 'inline'; document.getElementById('2405.02011v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.02011v1-abstract-full" style="display: none;"> Monitoring large scale environments is a crucial task for managing remote alpine environments, especially for hazardous events such as avalanches. One key information for avalanche risk forecast is imagery of released avalanches. As these happen in remote and potentially dangerous locations this data is difficult to obtain. Fixed-wing vehicles, due to their long range and travel speeds are a promising platform to gather aerial imagery to map avalanche activities. However, operating such vehicles in mountainous terrain remains a challenge due to the complex topography, regulations, and uncertain environment. In this work, we present a system that is capable of safely navigating and mapping an avalanche using a fixed-wing aerial system and discuss the challenges arising when executing such a mission. We show in our field experiments that we can effectively navigate in steep terrain environments while maximizing the map quality. We expect our work to enable more autonomous operations of fixed-wing vehicles in alpine environments to maximize the quality of the data gathered. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.02011v1-abstract-full').style.display = 'none'; document.getElementById('2405.02011v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 8 figures, Accepted to the IEEE ICRA Workshop on Field Robotics 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.08785">arXiv:2404.08785</a> <span> [<a href="https://arxiv.org/pdf/2404.08785">pdf</a>, <a href="https://arxiv.org/format/2404.08785">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Under pressure: learning-based analog gauge reading in the wild </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Reitsma%2C+M">Maurits Reitsma</a>, <a href="/search/cs?searchtype=author&query=Keller%2C+J">Julian Keller</a>, <a href="/search/cs?searchtype=author&query=Blomqvist%2C+K">Kenneth Blomqvist</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.08785v1-abstract-short" style="display: inline;"> We propose an interpretable framework for reading analog gauges that is deployable on real world robotic systems. Our framework splits the reading task into distinct steps, such that we can detect potential failures at each step. Our system needs no prior knowledge of the type of gauge or the range of the scale and is able to extract the units used. We show that our gauge reading algorithm is able… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.08785v1-abstract-full').style.display = 'inline'; document.getElementById('2404.08785v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.08785v1-abstract-full" style="display: none;"> We propose an interpretable framework for reading analog gauges that is deployable on real world robotic systems. Our framework splits the reading task into distinct steps, such that we can detect potential failures at each step. Our system needs no prior knowledge of the type of gauge or the range of the scale and is able to extract the units used. We show that our gauge reading algorithm is able to extract readings with a relative reading error of less than 2%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.08785v1-abstract-full').style.display = 'none'; document.getElementById('2404.08785v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 pages, 8 figures, accepted for presentation at the 2024 IEEE International Conference on Robotics and Automation (ICRA) and for inclusion in the conference proceedings, finalist for the IEEE ICRA 2024 Best Paper Award in Automation, source code https://github.com/ethz-asl/analog_gauge_reader, Autonomous Systems Lab, ETH Zurich</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.02077">arXiv:2404.02077</a> <span> [<a href="https://arxiv.org/pdf/2404.02077">pdf</a>, <a href="https://arxiv.org/format/2404.02077">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Energy-Optimized Planning in Non-Uniform Wind Fields with Fixed-Wing Aerial Vehicles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Duan%2C+Y">Yufei Duan</a>, <a href="/search/cs?searchtype=author&query=Achermann%2C+F">Florian Achermann</a>, <a href="/search/cs?searchtype=author&query=Lim%2C+J">Jaeyoung Lim</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.02077v2-abstract-short" style="display: inline;"> Fixed-wing small uncrewed aerial vehicles (sUAVs) possess the capability to remain airborne for extended durations and traverse vast distances. However, their operation is susceptible to wind conditions, particularly in regions of complex terrain where high wind speeds may push the aircraft beyond its operational limitations, potentially raising safety concerns. Moreover, wind impacts the energy r… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.02077v2-abstract-full').style.display = 'inline'; document.getElementById('2404.02077v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.02077v2-abstract-full" style="display: none;"> Fixed-wing small uncrewed aerial vehicles (sUAVs) possess the capability to remain airborne for extended durations and traverse vast distances. However, their operation is susceptible to wind conditions, particularly in regions of complex terrain where high wind speeds may push the aircraft beyond its operational limitations, potentially raising safety concerns. Moreover, wind impacts the energy required to follow a path, especially in locations where the wind direction and speed are not favorable. Incorporating wind information into mission planning is essential to ensure both safety and energy efficiency. In this paper, we propose a sampling-based planner using the kinematic Dubins aircraft paths with respect to the ground, to plan energy-efficient paths in non-uniform wind fields. We study the planner characteristics with synthetic and real-world wind data and compare its performance against baseline cost and path formulations. We demonstrate that the energy-optimized planner effectively utilizes updrafts to minimize energy consumption, albeit at the expense of increased travel time. The ground-relative path formulation facilitates the generation of safe trajectories onboard sUAVs within reasonable computational timeframes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.02077v2-abstract-full').style.display = 'none'; document.getElementById('2404.02077v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">\c{opyright} 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.14279">arXiv:2403.14279</a> <span> [<a href="https://arxiv.org/pdf/2403.14279">pdf</a>, <a href="https://arxiv.org/format/2403.14279">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Di+Felice%2C+F">Francesco Di Felice</a>, <a href="/search/cs?searchtype=author&query=Remus%2C+A">Alberto Remus</a>, <a href="/search/cs?searchtype=author&query=Gasperini%2C+S">Stefano Gasperini</a>, <a href="/search/cs?searchtype=author&query=Busam%2C+B">Benjamin Busam</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a>, <a href="/search/cs?searchtype=author&query=Tombari%2C+F">Federico Tombari</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Avizzano%2C+C+A">Carlo Alberto Avizzano</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.14279v2-abstract-short" style="display: inline;"> Estimating the pose of objects through vision is essential to make robotic platforms interact with the environment. Yet, it presents many challenges, often related to the lack of flexibility and generalizability of state-of-the-art solutions. Diffusion models are a cutting-edge neural architecture transforming 2D and 3D computer vision, outlining remarkable performances in zero-shot novel-view syn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.14279v2-abstract-full').style.display = 'inline'; document.getElementById('2403.14279v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.14279v2-abstract-full" style="display: none;"> Estimating the pose of objects through vision is essential to make robotic platforms interact with the environment. Yet, it presents many challenges, often related to the lack of flexibility and generalizability of state-of-the-art solutions. Diffusion models are a cutting-edge neural architecture transforming 2D and 3D computer vision, outlining remarkable performances in zero-shot novel-view synthesis. Such a use case is particularly intriguing for reconstructing 3D objects. However, localizing objects in unstructured environments is rather unexplored. To this end, this work presents Zero123-6D, the first work to demonstrate the utility of Diffusion Model-based novel-view-synthesizers in enhancing RGB 6D pose estimation at category-level, by integrating them with feature extraction techniques. Novel View Synthesis allows to obtain a coarse pose that is refined through an online optimization method introduced in this work to deal with intra-category geometric differences. In such a way, the outlined method shows reduction in data requirements, removal of the necessity of depth information in zero-shot category-level 6D pose estimation task, and increased performance, quantitatively demonstrated through experiments on the CO3D dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.14279v2-abstract-full').style.display = 'none'; document.getElementById('2403.14279v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 2 reference pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.09477">arXiv:2403.09477</a> <span> [<a href="https://arxiv.org/pdf/2403.09477">pdf</a>, <a href="https://arxiv.org/format/2403.09477">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> VIRUS-NeRF -- Vision, InfraRed and UltraSonic based Neural Radiance Fields </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Schmid%2C+N">Nicolaj Schmid</a>, <a href="/search/cs?searchtype=author&query=von+Einem%2C+C">Cornelius von Einem</a>, <a href="/search/cs?searchtype=author&query=Cadena%2C+C">Cesar Cadena</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Hruby%2C+L">Lorenz Hruby</a>, <a href="/search/cs?searchtype=author&query=Tschopp%2C+F">Florian Tschopp</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.09477v2-abstract-short" style="display: inline;"> Autonomous mobile robots are an increasingly integral part of modern factory and warehouse operations. Obstacle detection, avoidance and path planning are critical safety-relevant tasks, which are often solved using expensive LiDAR sensors and depth cameras. We propose to use cost-effective low-resolution ranging sensors, such as ultrasonic and infrared time-of-flight sensors by developing VIRUS-N… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.09477v2-abstract-full').style.display = 'inline'; document.getElementById('2403.09477v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.09477v2-abstract-full" style="display: none;"> Autonomous mobile robots are an increasingly integral part of modern factory and warehouse operations. Obstacle detection, avoidance and path planning are critical safety-relevant tasks, which are often solved using expensive LiDAR sensors and depth cameras. We propose to use cost-effective low-resolution ranging sensors, such as ultrasonic and infrared time-of-flight sensors by developing VIRUS-NeRF - Vision, InfraRed, and UltraSonic based Neural Radiance Fields. Building upon Instant Neural Graphics Primitives with a Multiresolution Hash Encoding (Instant-NGP), VIRUS-NeRF incorporates depth measurements from ultrasonic and infrared sensors and utilizes them to update the occupancy grid used for ray marching. Experimental evaluation in 2D demonstrates that VIRUS-NeRF achieves comparable mapping performance to LiDAR point clouds regarding coverage. Notably, in small environments, its accuracy aligns with that of LiDAR measurements, while in larger ones, it is bounded by the utilized ultrasonic sensors. An in-depth ablation study reveals that adding ultrasonic and infrared sensors is highly effective when dealing with sparse data and low view variation. Further, the proposed occupancy grid of VIRUS-NeRF improves the mapping capabilities and increases the training speed by 46% compared to Instant-NGP. Overall, VIRUS-NeRF presents a promising approach for cost-effective local mapping in mobile robotics, with potential applications in safety and navigation tasks. The code can be found at https://github.com/ethz-asl/virus nerf. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.09477v2-abstract-full').style.display = 'none'; document.getElementById('2403.09477v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.17434">arXiv:2402.17434</a> <span> [<a href="https://arxiv.org/pdf/2402.17434">pdf</a>, <a href="https://arxiv.org/format/2402.17434">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Passive Aligning Physical Interaction of Fully-Actuated Aerial Vehicles for Pushing Tasks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hui%2C+T">Tong Hui</a>, <a href="/search/cs?searchtype=author&query=Cuniato%2C+E">Eugenio Cuniato</a>, <a href="/search/cs?searchtype=author&query=Pantic%2C+M">Michael Pantic</a>, <a href="/search/cs?searchtype=author&query=Tognon%2C+M">Marco Tognon</a>, <a href="/search/cs?searchtype=author&query=Fumagalli%2C+M">Matteo Fumagalli</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.17434v1-abstract-short" style="display: inline;"> Recently, the utilization of aerial manipulators for performing pushing tasks in non-destructive testing (NDT) applications has seen significant growth. Such operations entail physical interactions between the aerial robotic system and the environment. End-effectors with multiple contact points are often used for placing NDT sensors in contact with a surface to be inspected. Aligning the NDT senso… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.17434v1-abstract-full').style.display = 'inline'; document.getElementById('2402.17434v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.17434v1-abstract-full" style="display: none;"> Recently, the utilization of aerial manipulators for performing pushing tasks in non-destructive testing (NDT) applications has seen significant growth. Such operations entail physical interactions between the aerial robotic system and the environment. End-effectors with multiple contact points are often used for placing NDT sensors in contact with a surface to be inspected. Aligning the NDT sensor and the work surface while preserving contact, requires that all available contact points at the end-effector tip are in contact with the work surface. With a standard full-pose controller, attitude errors often occur due to perturbations caused by modeling uncertainties, sensor noise, and environmental uncertainties. Even small attitude errors can cause a loss of contact points between the end-effector tip and the work surface. To preserve full alignment amidst these uncertainties, we propose a control strategy which selectively deactivates angular motion control and enables direct force control in specific directions. In particular, we derive two essential conditions to be met, such that the robot can passively align with flat work surfaces achieving full alignment through the rotation along non-actively controlled axes. Additionally, these conditions serve as hardware design and control guidelines for effectively integrating the proposed control method for practical usage. Real world experiments are conducted to validate both the control design and the guidelines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.17434v1-abstract-full').style.display = 'none'; document.getElementById('2402.17434v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to the 2024 IEEE International Conference on Robotics and Automation (ICRA2024)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.06143">arXiv:2402.06143</a> <span> [<a href="https://arxiv.org/pdf/2402.06143">pdf</a>, <a href="https://arxiv.org/format/2402.06143">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Reinforcement Learning for Blind Stair Climbing with Legged and Wheeled-Legged Robots </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chamorro%2C+S">Simon Chamorro</a>, <a href="/search/cs?searchtype=author&query=Klemm%2C+V">Victor Klemm</a>, <a href="/search/cs?searchtype=author&query=Valls%2C+M+d+l+I">Miguel de la Iglesia Valls</a>, <a href="/search/cs?searchtype=author&query=Pal%2C+C">Christopher Pal</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.06143v1-abstract-short" style="display: inline;"> In recent years, legged and wheeled-legged robots have gained prominence for tasks in environments predominantly created for humans across various domains. One significant challenge faced by many of these robots is their limited capability to navigate stairs, which hampers their functionality in multi-story environments. This study proposes a method aimed at addressing this limitation, employing r… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.06143v1-abstract-full').style.display = 'inline'; document.getElementById('2402.06143v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.06143v1-abstract-full" style="display: none;"> In recent years, legged and wheeled-legged robots have gained prominence for tasks in environments predominantly created for humans across various domains. One significant challenge faced by many of these robots is their limited capability to navigate stairs, which hampers their functionality in multi-story environments. This study proposes a method aimed at addressing this limitation, employing reinforcement learning to develop a versatile controller applicable to a wide range of robots. In contrast to the conventional velocity-based controllers, our approach builds upon a position-based formulation of the RL task, which we show to be vital for stair climbing. Furthermore, the methodology leverages an asymmetric actor-critic structure, enabling the utilization of privileged information from simulated environments during training while eliminating the reliance on exteroceptive sensors during real-world deployment. Another key feature of the proposed approach is the incorporation of a boolean observation within the controller, enabling the activation or deactivation of a stair-climbing mode. We present our results on different quadrupeds and bipedal robots in simulation and showcase how our method allows the balancing robot Ascento to climb 15cm stairs in the real world, a task that was previously impossible for this robot. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.06143v1-abstract-full').style.display = 'none'; document.getElementById('2402.06143v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Video: https://youtu.be/Ec6ar8BVJh4</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.09944">arXiv:2401.09944</a> <span> [<a href="https://arxiv.org/pdf/2401.09944">pdf</a>, <a href="https://arxiv.org/format/2401.09944">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> WindSeer: Real-time volumetric wind prediction over complex terrain aboard a small UAV </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Achermann%2C+F">Florian Achermann</a>, <a href="/search/cs?searchtype=author&query=Stastny%2C+T">Thomas Stastny</a>, <a href="/search/cs?searchtype=author&query=Danciu%2C+B">Bogdan Danciu</a>, <a href="/search/cs?searchtype=author&query=Kolobov%2C+A">Andrey Kolobov</a>, <a href="/search/cs?searchtype=author&query=Chung%2C+J+J">Jen Jen Chung</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Lawrance%2C+N">Nicholas Lawrance</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.09944v1-abstract-short" style="display: inline;"> Real-time high-resolution wind predictions are beneficial for various applications including safe manned and unmanned aviation. Current weather models require too much compute and lack the necessary predictive capabilities as they are valid only at the scale of multiple kilometers and hours - much lower spatial and temporal resolutions than these applications require. Our work, for the first time,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.09944v1-abstract-full').style.display = 'inline'; document.getElementById('2401.09944v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.09944v1-abstract-full" style="display: none;"> Real-time high-resolution wind predictions are beneficial for various applications including safe manned and unmanned aviation. Current weather models require too much compute and lack the necessary predictive capabilities as they are valid only at the scale of multiple kilometers and hours - much lower spatial and temporal resolutions than these applications require. Our work, for the first time, demonstrates the ability to predict low-altitude wind in real-time on limited-compute devices, from only sparse measurement data. We train a neural network, WindSeer, using only synthetic data from computational fluid dynamics simulations and show that it can successfully predict real wind fields over terrain with known topography from just a few noisy and spatially clustered wind measurements. WindSeer can generate accurate predictions at different resolutions and domain sizes on previously unseen topography without retraining. We demonstrate that the model successfully predicts historical wind data collected by weather stations and wind measured onboard drones. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.09944v1-abstract-full').style.display = 'none'; document.getElementById('2401.09944v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.04831">arXiv:2401.04831</a> <span> [<a href="https://arxiv.org/pdf/2401.04831">pdf</a>, <a href="https://arxiv.org/format/2401.04831">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Safe Low-Altitude Navigation in Steep Terrain with Fixed-Wing Aerial Vehicles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lim%2C+J">Jaeyoung Lim</a>, <a href="/search/cs?searchtype=author&query=Achermann%2C+F">Florian Achermann</a>, <a href="/search/cs?searchtype=author&query=Girod%2C+R">Rik Girod</a>, <a href="/search/cs?searchtype=author&query=Lawrance%2C+N">Nicholas Lawrance</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.04831v2-abstract-short" style="display: inline;"> Fixed-wing aerial vehicles provide an efficient way to navigate long distances or cover large areas for environmental monitoring applications. By design, they also require large open spaces due to limited maneuverability. However, strict regulatory and safety altitude limits constrain the available space. Especially in complex, confined, or steep terrain, ensuring the vehicle does not enter an ine… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.04831v2-abstract-full').style.display = 'inline'; document.getElementById('2401.04831v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.04831v2-abstract-full" style="display: none;"> Fixed-wing aerial vehicles provide an efficient way to navigate long distances or cover large areas for environmental monitoring applications. By design, they also require large open spaces due to limited maneuverability. However, strict regulatory and safety altitude limits constrain the available space. Especially in complex, confined, or steep terrain, ensuring the vehicle does not enter an inevitable collision state(ICS) can be challenging. In this work, we propose a strategy to find safe paths that do not enter an ICS while navigating within tight altitude constraints. The method uses periodic paths to efficiently classify ICSs. A sampling-based planner creates collision-free and kinematically feasible paths that begin and end in safe periodic (circular) paths. We show that, in realistic terrain, using circular periodic paths can simplify the goal selection process by making it yaw agnostic and constraining yaw. We demonstrate our approach by dynamically planning safe paths in real-time while navigating steep terrain on a flight test in complex alpine terrain. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.04831v2-abstract-full').style.display = 'none'; document.getElementById('2401.04831v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to IEEE Robotics and Automation Letters (RA-L)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.14730">arXiv:2312.14730</a> <span> [<a href="https://arxiv.org/pdf/2312.14730">pdf</a>, <a href="https://arxiv.org/format/2312.14730">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> To Fuse or Not to Fuse: Measuring Consistency in Multi-Sensor Fusion for Aerial Robots </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lanegger%2C+C">Christian Lanegger</a>, <a href="/search/cs?searchtype=author&query=Oleynikova%2C+H">Helen Oleynikova</a>, <a href="/search/cs?searchtype=author&query=Pantic%2C+M">Michael Pantic</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.14730v1-abstract-short" style="display: inline;"> Aerial vehicles are no longer limited to flying in open space: recent work has focused on aerial manipulation and up-close inspection. Such applications place stringent requirements on state estimation: the robot must combine state information from many sources, including onboard odometry and global positioning sensors. However, flying close to or in contact with structures is a degenerate case fo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.14730v1-abstract-full').style.display = 'inline'; document.getElementById('2312.14730v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.14730v1-abstract-full" style="display: none;"> Aerial vehicles are no longer limited to flying in open space: recent work has focused on aerial manipulation and up-close inspection. Such applications place stringent requirements on state estimation: the robot must combine state information from many sources, including onboard odometry and global positioning sensors. However, flying close to or in contact with structures is a degenerate case for many sensing modalities, and the robot's state estimation framework must intelligently choose which sensors are currently trustworthy. We evaluate a number of metrics to judge the reliability of sensing modalities in a multi-sensor fusion framework, then introduce a consensus-finding scheme that uses this metric to choose which sensors to fuse or not to fuse. Finally, we show that such a fusion framework is more robust and accurate than fusing all sensors all the time and demonstrate how such metrics can be informative in real-world experiments in indoor-outdoor flight and bridge inspection. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.14730v1-abstract-full').style.display = 'none'; document.getElementById('2312.14730v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted and presented at the 18th International Symposium on Experimental Robotics (ISER 2023)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.06733">arXiv:2312.06733</a> <span> [<a href="https://arxiv.org/pdf/2312.06733">pdf</a>, <a href="https://arxiv.org/format/2312.06733">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> TULIP: Transformer for Upsampling of LiDAR Point Clouds </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+B">Bin Yang</a>, <a href="/search/cs?searchtype=author&query=Pfreundschuh%2C+P">Patrick Pfreundschuh</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Hutter%2C+M">Marco Hutter</a>, <a href="/search/cs?searchtype=author&query=Moghadam%2C+P">Peyman Moghadam</a>, <a href="/search/cs?searchtype=author&query=Patil%2C+V">Vaishakh Patil</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.06733v4-abstract-short" style="display: inline;"> LiDAR Upsampling is a challenging task for the perception systems of robots and autonomous vehicles, due to the sparse and irregular structure of large-scale scene contexts. Recent works propose to solve this problem by converting LiDAR data from 3D Euclidean space into an image super-resolution problem in 2D image space. Although their methods can generate high-resolution range images with fine-g… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.06733v4-abstract-full').style.display = 'inline'; document.getElementById('2312.06733v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.06733v4-abstract-full" style="display: none;"> LiDAR Upsampling is a challenging task for the perception systems of robots and autonomous vehicles, due to the sparse and irregular structure of large-scale scene contexts. Recent works propose to solve this problem by converting LiDAR data from 3D Euclidean space into an image super-resolution problem in 2D image space. Although their methods can generate high-resolution range images with fine-grained details, the resulting 3D point clouds often blur out details and predict invalid points. In this paper, we propose TULIP, a new method to reconstruct high-resolution LiDAR point clouds from low-resolution LiDAR input. We also follow a range image-based approach but specifically modify the patch and window geometries of a Swin-Transformer-based network to better fit the characteristics of range images. We conducted several experiments on three public real-world and simulated datasets. TULIP outperforms state-of-the-art methods in all relevant metrics and generates robust and more realistic point clouds than prior works. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.06733v4-abstract-full').style.display = 'none'; document.getElementById('2312.06733v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The paper was accepted by CVPR2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.05125">arXiv:2312.05125</a> <span> [<a href="https://arxiv.org/pdf/2312.05125">pdf</a>, <a href="https://arxiv.org/format/2312.05125">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Learning to Fly Omnidirectional Micro Aerial Vehicles with an End-To-End Control Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cuniato%2C+E">Eugenio Cuniato</a>, <a href="/search/cs?searchtype=author&query=Andersson%2C+O">Olov Andersson</a>, <a href="/search/cs?searchtype=author&query=Oleynikova%2C+H">Helen Oleynikova</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Pantic%2C+M">Michael Pantic</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.05125v1-abstract-short" style="display: inline;"> Overactuated tilt-rotor platforms offer many advantages over traditional fixed-arm drones, allowing the decoupling of the applied force from the attitude of the robot. This expands their application areas to aerial interaction and manipulation, and allows them to overcome disturbances such as from ground or wall effects by exploiting the additional degrees of freedom available to their controllers… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.05125v1-abstract-full').style.display = 'inline'; document.getElementById('2312.05125v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.05125v1-abstract-full" style="display: none;"> Overactuated tilt-rotor platforms offer many advantages over traditional fixed-arm drones, allowing the decoupling of the applied force from the attitude of the robot. This expands their application areas to aerial interaction and manipulation, and allows them to overcome disturbances such as from ground or wall effects by exploiting the additional degrees of freedom available to their controllers. However, the overactuation also complicates the control problem, especially if the motors that tilt the arms have slower dynamics than those spinning the propellers. Instead of building a complex model-based controller that takes all of these subtleties into account, we attempt to learn an end-to-end pose controller using reinforcement learning, and show its superior behavior in the presence of inertial and force disturbances compared to a state-of-the-art traditional controller. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.05125v1-abstract-full').style.display = 'none'; document.getElementById('2312.05125v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted and presented at the 18th International Symposium on Experimental Robotics (ISER 2023)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.05110">arXiv:2312.05110</a> <span> [<a href="https://arxiv.org/pdf/2312.05110">pdf</a>, <a href="https://arxiv.org/format/2312.05110">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Soliro -- a hybrid dynamic tilt-wing aerial manipulator with minimal actuators </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pantic%2C+M">Michael Pantic</a>, <a href="/search/cs?searchtype=author&query=Hampp%2C+E">Elias Hampp</a>, <a href="/search/cs?searchtype=author&query=Flammer%2C+R">Ramon Flammer</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Weixuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Stastny%2C+T">Thomas Stastny</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.05110v1-abstract-short" style="display: inline;"> The ability to enter in contact with and manipulate physical objects with a flying robot enables many novel applications, such as contact inspection, painting, drilling, and sample collection. Generally, these aerial robots need more degrees of freedom than a standard quadrotor. While there is active research of over-actuated, omnidirectional MAVs and aerial manipulators as well as VTOL and hybrid… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.05110v1-abstract-full').style.display = 'inline'; document.getElementById('2312.05110v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.05110v1-abstract-full" style="display: none;"> The ability to enter in contact with and manipulate physical objects with a flying robot enables many novel applications, such as contact inspection, painting, drilling, and sample collection. Generally, these aerial robots need more degrees of freedom than a standard quadrotor. While there is active research of over-actuated, omnidirectional MAVs and aerial manipulators as well as VTOL and hybrid platforms, the two concepts have not been combined. We address the problem of conceptualization, characterization, control, and testing of a 5DOF rotary-/fixed-wing hybrid, tilt-rotor, split tilt-wing, nearly omnidirectional aerial robot. We present an elegant solution with a minimal set of actuators and that does not need any classical control surfaces or flaps. The concept is validated in a wind tunnel study and in multiple flights with forward and backward transitions. Fixed-wing flight speeds up to 10 m/s were reached, with a power reduction of 30% as compared to rotary wing flight. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.05110v1-abstract-full').style.display = 'none'; document.getElementById('2312.05110v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted and presented at the 18th International Symposium on Experimental Robotics (ISER 2023)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.01988">arXiv:2312.01988</a> <span> [<a href="https://arxiv.org/pdf/2312.01988">pdf</a>, <a href="https://arxiv.org/format/2312.01988">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/MRA.2023.3348306">10.1109/MRA.2023.3348306 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Geranos: a Novel Tilted-Rotors Aerial Robot for the Transportation of Poles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gorlo%2C+N">Nicolas Gorlo</a>, <a href="/search/cs?searchtype=author&query=Bamert%2C+S">Samuel Bamert</a>, <a href="/search/cs?searchtype=author&query=Cathomen%2C+R">Rafael Cathomen</a>, <a href="/search/cs?searchtype=author&query=K%C3%A4ppeli%2C+G">Gabriel K盲ppeli</a>, <a href="/search/cs?searchtype=author&query=M%C3%BCller%2C+M">Mario M眉ller</a>, <a href="/search/cs?searchtype=author&query=Reinhart%2C+T">Tim Reinhart</a>, <a href="/search/cs?searchtype=author&query=Stadler%2C+H">Henriette Stadler</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+H">Hua Shen</a>, <a href="/search/cs?searchtype=author&query=Cuniato%2C+E">Eugenio Cuniato</a>, <a href="/search/cs?searchtype=author&query=Tognon%2C+M">Marco Tognon</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.01988v2-abstract-short" style="display: inline;"> In challenging terrains, constructing structures such as antennas and cable-car masts often requires the use of helicopters to transport loads via ropes. The swinging of the load, exacerbated by wind, impairs positioning accuracy, therefore necessitating precise manual placement by ground crews. This increases costs and risk of injuries. Challenging this paradigm, we present Geranos: a specialized… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.01988v2-abstract-full').style.display = 'inline'; document.getElementById('2312.01988v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.01988v2-abstract-full" style="display: none;"> In challenging terrains, constructing structures such as antennas and cable-car masts often requires the use of helicopters to transport loads via ropes. The swinging of the load, exacerbated by wind, impairs positioning accuracy, therefore necessitating precise manual placement by ground crews. This increases costs and risk of injuries. Challenging this paradigm, we present Geranos: a specialized multirotor Unmanned Aerial Vehicle (UAV) designed to enhance aerial transportation and assembly. Geranos demonstrates exceptional prowess in accurately positioning vertical poles, achieving this through an innovative integration of load transport and precision. Its unique ring design mitigates the impact of high pole inertia, while a lightweight two-part grasping mechanism ensures secure load attachment without active force. With four primary propellers countering gravity and four auxiliary ones enhancing lateral precision, Geranos achieves comprehensive position and attitude control around hovering. Our experimental demonstration mimicking antenna/cable-car mast installations showcases Geranos ability in stacking poles (3 kg, 2 m long) with remarkable sub-5 cm placement accuracy, without the need of human manual intervention. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.01988v2-abstract-full').style.display = 'none'; document.getElementById('2312.01988v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">accepted at IEEE Robotics and Automation Magazine</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.02734">arXiv:2311.02734</a> <span> [<a href="https://arxiv.org/pdf/2311.02734">pdf</a>, <a href="https://arxiv.org/format/2311.02734">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gorlo%2C+N">Nicolas Gorlo</a>, <a href="/search/cs?searchtype=author&query=Blomqvist%2C+K">Kenneth Blomqvist</a>, <a href="/search/cs?searchtype=author&query=Milano%2C+F">Francesco Milano</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.02734v1-abstract-short" style="display: inline;"> Most object-level mapping systems in use today make use of an upstream learned object instance segmentation model. If we want to teach them about a new object or segmentation class, we need to build a large dataset and retrain the system. To build spatial AI systems that can quickly be taught about new objects, we need to effectively solve the problem of single-shot object detection, instance segm… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.02734v1-abstract-full').style.display = 'inline'; document.getElementById('2311.02734v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.02734v1-abstract-full" style="display: none;"> Most object-level mapping systems in use today make use of an upstream learned object instance segmentation model. If we want to teach them about a new object or segmentation class, we need to build a large dataset and retrain the system. To build spatial AI systems that can quickly be taught about new objects, we need to effectively solve the problem of single-shot object detection, instance segmentation and re-identification. So far there is neither a method fulfilling all of these requirements in unison nor a benchmark that could be used to test such a method. Addressing this, we propose ISAR, a benchmark and baseline method for single- and few-shot object Instance Segmentation And Re-identification, in an effort to accelerate the development of algorithms that can robustly detect, segment, and re-identify objects from a single or a few sparse training examples. We provide a semi-synthetic dataset of video sequences with ground-truth semantic annotations, a standardized evaluation pipeline, and a baseline method. Our benchmark aligns with the emerging research trend of unifying Multi-Object Tracking, Video Object Segmentation, and Re-identification. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.02734v1-abstract-full').style.display = 'none'; document.getElementById('2311.02734v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 6 figures, to be published in IEEE WACV 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.00626">arXiv:2311.00626</a> <span> [<a href="https://arxiv.org/pdf/2311.00626">pdf</a>, <a href="https://arxiv.org/format/2311.00626">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> nvblox: GPU-Accelerated Incremental Signed Distance Field Mapping </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Millane%2C+A">Alexander Millane</a>, <a href="/search/cs?searchtype=author&query=Oleynikova%2C+H">Helen Oleynikova</a>, <a href="/search/cs?searchtype=author&query=Wirbel%2C+E">Emilie Wirbel</a>, <a href="/search/cs?searchtype=author&query=Steiner%2C+R">Remo Steiner</a>, <a href="/search/cs?searchtype=author&query=Ramasamy%2C+V">Vikram Ramasamy</a>, <a href="/search/cs?searchtype=author&query=Tingdahl%2C+D">David Tingdahl</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.00626v2-abstract-short" style="display: inline;"> Dense, volumetric maps are essential to enable robot navigation and interaction with the environment. To achieve low latency, dense maps are typically computed onboard the robot, often on computationally constrained hardware. Previous works leave a gap between CPU-based systems for robotic mapping which, due to computation constraints, limit map resolution or scale, and GPU-based reconstruction sy… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.00626v2-abstract-full').style.display = 'inline'; document.getElementById('2311.00626v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.00626v2-abstract-full" style="display: none;"> Dense, volumetric maps are essential to enable robot navigation and interaction with the environment. To achieve low latency, dense maps are typically computed onboard the robot, often on computationally constrained hardware. Previous works leave a gap between CPU-based systems for robotic mapping which, due to computation constraints, limit map resolution or scale, and GPU-based reconstruction systems which omit features that are critical to robotic path planning, such as computation of the Euclidean Signed Distance Field (ESDF). We introduce a library, nvblox, that aims to fill this gap, by GPU-accelerating robotic volumetric mapping. Nvblox delivers a significant performance improvement over the state of the art, achieving up to a 177x speed-up in surface reconstruction, and up to a 31x improvement in distance field computation, and is available open-source. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.00626v2-abstract-full').style.display = 'none'; document.getElementById('2311.00626v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to ICRA 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.10548">arXiv:2310.10548</a> <span> [<a href="https://arxiv.org/pdf/2310.10548">pdf</a>, <a href="https://arxiv.org/format/2310.10548">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> A perching and tilting aerial robot for precise and versatile power tool work on vertical walls </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dautzenberg%2C+R">Roman Dautzenberg</a>, <a href="/search/cs?searchtype=author&query=K%C3%BCster%2C+T">Timo K眉ster</a>, <a href="/search/cs?searchtype=author&query=Mathis%2C+T">Timon Mathis</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+Y">Yann Roth</a>, <a href="/search/cs?searchtype=author&query=Steinauer%2C+C">Curdin Steinauer</a>, <a href="/search/cs?searchtype=author&query=K%C3%A4ppeli%2C+G">Gabriel K盲ppeli</a>, <a href="/search/cs?searchtype=author&query=Santen%2C+J">Julian Santen</a>, <a href="/search/cs?searchtype=author&query=Arranhado%2C+A">Alina Arranhado</a>, <a href="/search/cs?searchtype=author&query=Biffar%2C+F">Friederike Biffar</a>, <a href="/search/cs?searchtype=author&query=K%C3%B6tter%2C+T">Till K枚tter</a>, <a href="/search/cs?searchtype=author&query=Lanegger%2C+C">Christian Lanegger</a>, <a href="/search/cs?searchtype=author&query=Allenspach%2C+M">Mike Allenspach</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=B%C3%A4hnemann%2C+R">Rik B盲hnemann</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.10548v1-abstract-short" style="display: inline;"> Drilling, grinding, and setting anchors on vertical walls are fundamental processes in everyday construction work. Manually doing these works is error-prone, potentially dangerous, and elaborate at height. Today, heavy mobile ground robots can perform automatic power tool work. However, aerial vehicles could be deployed in untraversable environments and reach inaccessible places. Existing drone de… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.10548v1-abstract-full').style.display = 'inline'; document.getElementById('2310.10548v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.10548v1-abstract-full" style="display: none;"> Drilling, grinding, and setting anchors on vertical walls are fundamental processes in everyday construction work. Manually doing these works is error-prone, potentially dangerous, and elaborate at height. Today, heavy mobile ground robots can perform automatic power tool work. However, aerial vehicles could be deployed in untraversable environments and reach inaccessible places. Existing drone designs do not provide the large forces, payload, and high precision required for using power tools. This work presents the first aerial robot design to perform versatile manipulation tasks on vertical concrete walls with continuous forces of up to 150 N. The platform combines a quadrotor with active suction cups for perching on walls and a lightweight, tiltable linear tool table. This combination minimizes weight using the propulsion system for flying, surface alignment, and feed during manipulation and allows precise positioning of the power tool. We evaluate our design in a concrete drilling application - a challenging construction process that requires high forces, accuracy, and precision. In 30 trials, our design can accurately pinpoint a target position despite perching imprecision. Nine visually guided drilling experiments demonstrate a drilling precision of 6 mm without further automation. Aside from drilling, we also demonstrate the versatility of the design by setting an anchor into concrete. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.10548v1-abstract-full').style.display = 'none'; document.getElementById('2310.10548v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Will appear in IEEE International Conference on Intelligent Robots and Systems (IROS) 2023. Winner of IROS Best Paper Award on Mobile Manipulation sponsored by OMRON Sinic X Corp</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.01235">arXiv:2310.01235</a> <span> [<a href="https://arxiv.org/pdf/2310.01235">pdf</a>, <a href="https://arxiv.org/format/2310.01235">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/ICRA57147.2024.10610938">10.1109/ICRA57147.2024.10610938 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> COIN-LIO: Complementary Intensity-Augmented LiDAR Inertial Odometry </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pfreundschuh%2C+P">Patrick Pfreundschuh</a>, <a href="/search/cs?searchtype=author&query=Oleynikova%2C+H">Helen Oleynikova</a>, <a href="/search/cs?searchtype=author&query=Cadena%2C+C">Cesar Cadena</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Andersson%2C+O">Olov Andersson</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.01235v4-abstract-short" style="display: inline;"> We present COIN-LIO, a LiDAR Inertial Odometry pipeline that tightly couples information from LiDAR intensity with geometry-based point cloud registration. The focus of our work is to improve the robustness of LiDAR-inertial odometry in geometrically degenerate scenarios, like tunnels or flat fields. We project LiDAR intensity returns into an intensity image, and propose an image processing pipeli… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.01235v4-abstract-full').style.display = 'inline'; document.getElementById('2310.01235v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.01235v4-abstract-full" style="display: none;"> We present COIN-LIO, a LiDAR Inertial Odometry pipeline that tightly couples information from LiDAR intensity with geometry-based point cloud registration. The focus of our work is to improve the robustness of LiDAR-inertial odometry in geometrically degenerate scenarios, like tunnels or flat fields. We project LiDAR intensity returns into an intensity image, and propose an image processing pipeline that produces filtered images with improved brightness consistency within the image as well as across different scenes. To effectively leverage intensity as an additional modality, we present a novel feature selection scheme that detects uninformative directions in the point cloud registration and explicitly selects patches with complementary image information. Photometric error minimization in the image patches is then fused with inertial measurements and point-to-plane registration in an iterated Extended Kalman Filter. The proposed approach improves accuracy and robustness on a public dataset. We additionally publish a new dataset, that captures five real-world environments in challenging, geometrically degenerate scenes. By using the additional photometric information, our approach shows drastically improved robustness against geometric degeneracy in environments where all compared baseline approaches fail. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.01235v4-abstract-full').style.display = 'none'; document.getElementById('2310.01235v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2024 IEEE International Conference on Robotics and Automation (ICRA) (pp. 1730-1737) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.05448">arXiv:2309.05448</a> <span> [<a href="https://arxiv.org/pdf/2309.05448">pdf</a>, <a href="https://arxiv.org/format/2309.05448">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/LRA.2024.3354624">10.1109/LRA.2024.3354624 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Panoptic Vision-Language Feature Fields </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+H">Haoran Chen</a>, <a href="/search/cs?searchtype=author&query=Blomqvist%2C+K">Kenneth Blomqvist</a>, <a href="/search/cs?searchtype=author&query=Milano%2C+F">Francesco Milano</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.05448v2-abstract-short" style="display: inline;"> Recently, methods have been proposed for 3D open-vocabulary semantic segmentation. Such methods are able to segment scenes into arbitrary classes based on text descriptions provided during runtime. In this paper, we propose to the best of our knowledge the first algorithm for open-vocabulary panoptic segmentation in 3D scenes. Our algorithm, Panoptic Vision-Language Feature Fields (PVLFF), learns… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.05448v2-abstract-full').style.display = 'inline'; document.getElementById('2309.05448v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.05448v2-abstract-full" style="display: none;"> Recently, methods have been proposed for 3D open-vocabulary semantic segmentation. Such methods are able to segment scenes into arbitrary classes based on text descriptions provided during runtime. In this paper, we propose to the best of our knowledge the first algorithm for open-vocabulary panoptic segmentation in 3D scenes. Our algorithm, Panoptic Vision-Language Feature Fields (PVLFF), learns a semantic feature field of the scene by distilling vision-language features from a pretrained 2D model, and jointly fits an instance feature field through contrastive learning using 2D instance segments on input frames. Despite not being trained on the target classes, our method achieves panoptic segmentation performance similar to the state-of-the-art closed-set 3D systems on the HyperSim, ScanNet and Replica dataset and additionally outperforms current 3D open-vocabulary systems in terms of semantic segmentation. We ablate the components of our method to demonstrate the effectiveness of our model architecture. Our code will be available at https://github.com/ethz-asl/pvlff. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.05448v2-abstract-full').style.display = 'none'; document.getElementById('2309.05448v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This work has been accepted by IEEE Robotics and Automation Letters</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.12082">arXiv:2308.12082</a> <span> [<a href="https://arxiv.org/pdf/2308.12082">pdf</a>, <a href="https://arxiv.org/format/2308.12082">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Path-Constrained State Estimation for Rail Vehicles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=von+Einem%2C+C">Cornelius von Einem</a>, <a href="/search/cs?searchtype=author&query=Cramariuc%2C+A">Andrei Cramariuc</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Cadena%2C+C">Cesar Cadena</a>, <a href="/search/cs?searchtype=author&query=Tschopp%2C+F">Florian Tschopp</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.12082v1-abstract-short" style="display: inline;"> Globally rising demand for transportation by rail is pushing existing infrastructure to its capacity limits, necessitating the development of accurate, robust, and high-frequency positioning systems to ensure safe and efficient train operation. As individual sensor modalities cannot satisfy the strict requirements of robustness and safety, a combination thereof is required. We propose a path-const… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.12082v1-abstract-full').style.display = 'inline'; document.getElementById('2308.12082v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.12082v1-abstract-full" style="display: none;"> Globally rising demand for transportation by rail is pushing existing infrastructure to its capacity limits, necessitating the development of accurate, robust, and high-frequency positioning systems to ensure safe and efficient train operation. As individual sensor modalities cannot satisfy the strict requirements of robustness and safety, a combination thereof is required. We propose a path-constrained sensor fusion framework to integrate various modalities while leveraging the unique characteristics of the railway network. To reflect the constrained motion of rail vehicles along their tracks, the state is modeled in 1D along the track geometry. We further leverage the limited action space of a train by employing a novel multi-hypothesis tracking to account for multiple possible trajectories a vehicle can take through the railway network. We demonstrate the reliability and accuracy of our fusion framework on multiple tram datasets recorded in the city of Zurich, utilizing Visual-Inertial Odometry for local motion estimation and a standard GNSS for global localization. We evaluate our results using ground truth localizations recorded with a RTK-GNSS, and compare our method to standard baselines. A Root Mean Square Error of 4.78 m and a track selectivity score of up to 94.9 % have been achieved. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.12082v1-abstract-full').style.display = 'none'; document.getElementById('2308.12082v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.15581">arXiv:2307.15581</a> <span> [<a href="https://arxiv.org/pdf/2307.15581">pdf</a>, <a href="https://arxiv.org/format/2307.15581">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Learning to Open Doors with an Aerial Manipulator </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cuniato%2C+E">Eugenio Cuniato</a>, <a href="/search/cs?searchtype=author&query=Geles%2C+I">Ismail Geles</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Weixuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Andersson%2C+O">Olov Andersson</a>, <a href="/search/cs?searchtype=author&query=Tognon%2C+M">Marco Tognon</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.15581v1-abstract-short" style="display: inline;"> The field of aerial manipulation has seen rapid advances, transitioning from push-and-slide tasks to interaction with articulated objects. So far, when more complex actions are performed, the motion trajectory is usually handcrafted or a result of online optimization methods like Model Predictive Control (MPC) or Model Predictive Path Integral (MPPI) control. However, these methods rely on heurist… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15581v1-abstract-full').style.display = 'inline'; document.getElementById('2307.15581v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.15581v1-abstract-full" style="display: none;"> The field of aerial manipulation has seen rapid advances, transitioning from push-and-slide tasks to interaction with articulated objects. So far, when more complex actions are performed, the motion trajectory is usually handcrafted or a result of online optimization methods like Model Predictive Control (MPC) or Model Predictive Path Integral (MPPI) control. However, these methods rely on heuristics or model simplifications to efficiently run on onboard hardware, producing results in acceptable amounts of time. Moreover, they can be sensitive to disturbances and differences between the real environment and its simulated counterpart. In this work, we propose a Reinforcement Learning (RL) approach to learn motion behaviors for a manipulation task while producing policies that are robust to disturbances and modeling errors. Specifically, we train a policy to perform a door-opening task with an Omnidirectional Micro Aerial Vehicle (OMAV). The policy is trained in a physics simulator and experiments are presented both in simulation and running onboard the real platform, investigating the simulation to real world transfer. We compare our method against a state-of-the-art MPPI solution, showing a considerable increase in robustness and speed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15581v1-abstract-full').style.display = 'none'; document.getElementById('2307.15581v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.15478">arXiv:2307.15478</a> <span> [<a href="https://arxiv.org/pdf/2307.15478">pdf</a>, <a href="https://arxiv.org/format/2307.15478">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Local and Global Information in Obstacle Detection on Railway Tracks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Brucker%2C+M">Matthias Brucker</a>, <a href="/search/cs?searchtype=author&query=Cramariuc%2C+A">Andrei Cramariuc</a>, <a href="/search/cs?searchtype=author&query=von+Einem%2C+C">Cornelius von Einem</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Cadena%2C+C">Cesar Cadena</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.15478v1-abstract-short" style="display: inline;"> Reliable obstacle detection on railways could help prevent collisions that result in injuries and potentially damage or derail the train. Unfortunately, generic object detectors do not have enough classes to account for all possible scenarios, and datasets featuring objects on railways are challenging to obtain. We propose utilizing a shallow network to learn railway segmentation from normal railw… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15478v1-abstract-full').style.display = 'inline'; document.getElementById('2307.15478v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.15478v1-abstract-full" style="display: none;"> Reliable obstacle detection on railways could help prevent collisions that result in injuries and potentially damage or derail the train. Unfortunately, generic object detectors do not have enough classes to account for all possible scenarios, and datasets featuring objects on railways are challenging to obtain. We propose utilizing a shallow network to learn railway segmentation from normal railway images. The limited receptive field of the network prevents overconfident predictions and allows the network to focus on the locally very distinct and repetitive patterns of the railway environment. Additionally, we explore the controlled inclusion of global information by learning to hallucinate obstacle-free images. We evaluate our method on a custom dataset featuring railway images with artificially augmented obstacles. Our proposed method outperforms other learning-based baseline methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15478v1-abstract-full').style.display = 'none'; document.getElementById('2307.15478v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.01279">arXiv:2306.01279</a> <span> [<a href="https://arxiv.org/pdf/2306.01279">pdf</a>, <a href="https://arxiv.org/format/2306.01279">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Efficient volumetric mapping of multi-scale environments using wavelet-based compression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Reijgwart%2C+V">Victor Reijgwart</a>, <a href="/search/cs?searchtype=author&query=Cadena%2C+C">Cesar Cadena</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.01279v1-abstract-short" style="display: inline;"> Volumetric maps are widely used in robotics due to their desirable properties in applications such as path planning, exploration, and manipulation. Constant advances in mapping technologies are needed to keep up with the improvements in sensor technology, generating increasingly vast amounts of precise measurements. Handling this data in a computationally and memory-efficient manner is paramount t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.01279v1-abstract-full').style.display = 'inline'; document.getElementById('2306.01279v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.01279v1-abstract-full" style="display: none;"> Volumetric maps are widely used in robotics due to their desirable properties in applications such as path planning, exploration, and manipulation. Constant advances in mapping technologies are needed to keep up with the improvements in sensor technology, generating increasingly vast amounts of precise measurements. Handling this data in a computationally and memory-efficient manner is paramount to representing the environment at the desired scales and resolutions. In this work, we express the desirable properties of a volumetric mapping framework through the lens of multi-resolution analysis. This shows that wavelets are a natural foundation for hierarchical and multi-resolution volumetric mapping. Based on this insight we design an efficient mapping system that uses wavelet decomposition. The efficiency of the system enables the use of uncertainty-aware sensor models, improving the quality of the maps. Experiments on both synthetic and real-world data provide mapping accuracy and runtime performance comparisons with state-of-the-art methods on both RGB-D and 3D LiDAR data. The framework is open-sourced to allow the robotics community at large to explore this approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.01279v1-abstract-full').style.display = 'none'; document.getElementById('2306.01279v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 6 figures, 2 tables, accepted to RSS 2023, code is open-source: https://github.com/ethz-asl/wavemap</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.01961">arXiv:2305.01961</a> <span> [<a href="https://arxiv.org/pdf/2305.01961">pdf</a>, <a href="https://arxiv.org/format/2305.01961">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Design and Control of a Micro Overactuated Aerial Robot with an Origami Delta Manipulator </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cuniato%2C+E">Eugenio Cuniato</a>, <a href="/search/cs?searchtype=author&query=Geckeler%2C+C">Christian Geckeler</a>, <a href="/search/cs?searchtype=author&query=Brunner%2C+M">Maximilian Brunner</a>, <a href="/search/cs?searchtype=author&query=Str%C3%BCbin%2C+D">Dario Str眉bin</a>, <a href="/search/cs?searchtype=author&query=B%C3%A4hler%2C+E">Elia B盲hler</a>, <a href="/search/cs?searchtype=author&query=Ospelt%2C+F">Fabian Ospelt</a>, <a href="/search/cs?searchtype=author&query=Tognon%2C+M">Marco Tognon</a>, <a href="/search/cs?searchtype=author&query=Mintchev%2C+S">Stefano Mintchev</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.01961v1-abstract-short" style="display: inline;"> This work presents the mechanical design and control of a novel small-size and lightweight Micro Aerial Vehicle (MAV) for aerial manipulation. To our knowledge, with a total take-off mass of only 2.0 kg, the proposed system is the most lightweight Aerial Manipulator (AM) that has 8-DOF independently controllable: 5 for the aerial platform and 3 for the articulated arm. We designed the robot to be… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.01961v1-abstract-full').style.display = 'inline'; document.getElementById('2305.01961v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.01961v1-abstract-full" style="display: none;"> This work presents the mechanical design and control of a novel small-size and lightweight Micro Aerial Vehicle (MAV) for aerial manipulation. To our knowledge, with a total take-off mass of only 2.0 kg, the proposed system is the most lightweight Aerial Manipulator (AM) that has 8-DOF independently controllable: 5 for the aerial platform and 3 for the articulated arm. We designed the robot to be fully-actuated in the body forward direction. This allows independent pitching and instantaneous force generation, improving the platform's performance during physical interaction. The robotic arm is an origami delta manipulator driven by three servomotors, enabling active motion compensation at the end-effector. Its composite multimaterial links help reduce the weight, while their flexibility allow for compliant aerial interaction with the environment. In particular, the arm's stiffness can be changed according to its configuration. We provide an in depth discussion of the system design and characterize the stiffness of the delta arm. A control architecture to deal with the platform's overactuation while exploiting the delta arm is presented. Its capabilities are experimentally illustrated both in free flight and physical interaction, highlighting advantages and disadvantages of the origami's folding mechanism. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.01961v1-abstract-full').style.display = 'none'; document.getElementById('2305.01961v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.00967">arXiv:2305.00967</a> <span> [<a href="https://arxiv.org/pdf/2305.00967">pdf</a>, <a href="https://arxiv.org/format/2305.00967">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> A Comparison of Pneumatic Actuators for Soft Growing Vine Robots </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=K%C3%BCbler%2C+A+M">Alexander M. K眉bler</a>, <a href="/search/cs?searchtype=author&query=Pasquier%2C+C+d">Cosima du Pasquier</a>, <a href="/search/cs?searchtype=author&query=Low%2C+A">Andrew Low</a>, <a href="/search/cs?searchtype=author&query=Djambazi%2C+B">Betim Djambazi</a>, <a href="/search/cs?searchtype=author&query=Aymon%2C+N">Nicolas Aymon</a>, <a href="/search/cs?searchtype=author&query=F%C3%B6rster%2C+J">Julian F枚rster</a>, <a href="/search/cs?searchtype=author&query=Agharese%2C+N">Nathaniel Agharese</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Okamura%2C+A+M">Allison M. Okamura</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.00967v3-abstract-short" style="display: inline;"> Soft pneumatic actuators are used to steer soft growing "vine" robots while being flexible enough to undergo the tip eversion required for growth. In this study, we compared the performance of three types of pneumatic actuators in terms of their ability to perform eversion, quasi-static bending, dynamic motion, and force output: the pouch motor, the cylindrical pneumatic artificial muscle (cPAM),… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.00967v3-abstract-full').style.display = 'inline'; document.getElementById('2305.00967v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.00967v3-abstract-full" style="display: none;"> Soft pneumatic actuators are used to steer soft growing "vine" robots while being flexible enough to undergo the tip eversion required for growth. In this study, we compared the performance of three types of pneumatic actuators in terms of their ability to perform eversion, quasi-static bending, dynamic motion, and force output: the pouch motor, the cylindrical pneumatic artificial muscle (cPAM), and the fabric pneumatic artificial muscle (fPAM). The pouch motor is advantageous for prototyping due to its simple manufacturing process. The cPAM exhibits superior bending behavior and produces the highest forces, while the fPAM actuates fastest and everts at the lowest pressure. We evaluated a range of dimensions for each actuator type. Larger actuators can produce more significant deformations and forces, but smaller actuators inflate faster and can evert at a lower pressure. Because vine robots are lightweight, the effect of gravity on the functionality of different actuators is minimal. We developed a new analytical model that predicts the pressure-to-bending behavior of vine robot actuators. Using the actuator results, we designed and demonstrated a 4.8 m long vine robot equipped with highly maneuverable 60x60 mm cPAMs in a three-dimensional obstacle course. The vine robot was able to move around sharp turns, travel through a passage smaller than its diameter, and lift itself against gravity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.00967v3-abstract-full').style.display = 'none'; document.getElementById('2305.00967v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 8 figures, 3 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.10049">arXiv:2304.10049</a> <span> [<a href="https://arxiv.org/pdf/2304.10049">pdf</a>, <a href="https://arxiv.org/format/2304.10049">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/LRA.2023.3305239">10.1109/LRA.2023.3305239 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Dynablox: Real-time Detection of Diverse Dynamic Objects in Complex Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Schmid%2C+L">Lukas Schmid</a>, <a href="/search/cs?searchtype=author&query=Andersson%2C+O">Olov Andersson</a>, <a href="/search/cs?searchtype=author&query=Sulser%2C+A">Aurelio Sulser</a>, <a href="/search/cs?searchtype=author&query=Pfreundschuh%2C+P">Patrick Pfreundschuh</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2304.10049v3-abstract-short" style="display: inline;"> Real-time detection of moving objects is an essential capability for robots acting autonomously in dynamic environments. We thus propose Dynablox, a novel online mapping-based approach for robust moving object detection in complex environments. The central idea of our approach is to incrementally estimate high confidence free-space areas by modeling and accounting for sensing, state estimation, an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.10049v3-abstract-full').style.display = 'inline'; document.getElementById('2304.10049v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.10049v3-abstract-full" style="display: none;"> Real-time detection of moving objects is an essential capability for robots acting autonomously in dynamic environments. We thus propose Dynablox, a novel online mapping-based approach for robust moving object detection in complex environments. The central idea of our approach is to incrementally estimate high confidence free-space areas by modeling and accounting for sensing, state estimation, and mapping limitations during online robot operation. The spatio-temporally conservative free space estimate enables robust detection of moving objects without making any assumptions on the appearance of objects or environments. This allows deployment in complex scenes such as multi-storied buildings or staircases, and for diverse moving objects such as people carrying various items, doors swinging or even balls rolling around. We thoroughly evaluate our approach on real-world data sets, achieving 86% IoU at 17 FPS in typical robotic settings. The method outperforms a recent appearance-based classifier and approaches the performance of offline methods. We demonstrate its generality on a novel data set with rare moving objects in complex environments. We make our efficient implementation and the novel data set available as open-source. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.10049v3-abstract-full').style.display = 'none'; document.getElementById('2304.10049v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Code released at https://github.com/ethz-asl/dynablox</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> in IEEE Robotics and Automation Letters, vol. 8, no. 10, pp. 6259-6266, Oct. 2023 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.17047">arXiv:2303.17047</a> <span> [<a href="https://arxiv.org/pdf/2303.17047">pdf</a>, <a href="https://arxiv.org/format/2303.17047">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Material-agnostic Shaping of Granular Materials with Optimal Transport </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Alatur%2C+N">Nikhilesh Alatur</a>, <a href="/search/cs?searchtype=author&query=Andersson%2C+O">Olov Andersson</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.17047v1-abstract-short" style="display: inline;"> From construction materials, such as sand or asphalt, to kitchen ingredients, like rice, sugar, or salt; the world is full of granular materials. Despite impressive progress in robotic manipulation, manipulating and interacting with granular material remains a challenge due to difficulties in perceiving, representing, modelling, and planning for these variable materials that have complex internal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.17047v1-abstract-full').style.display = 'inline'; document.getElementById('2303.17047v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.17047v1-abstract-full" style="display: none;"> From construction materials, such as sand or asphalt, to kitchen ingredients, like rice, sugar, or salt; the world is full of granular materials. Despite impressive progress in robotic manipulation, manipulating and interacting with granular material remains a challenge due to difficulties in perceiving, representing, modelling, and planning for these variable materials that have complex internal dynamics. While some prior work has looked into estimating or learning accurate dynamics models for granular materials, the literature is still missing a more abstract planning method that can be used for planning manipulation actions for granular materials with unknown material properties. In this work, we leverage tools from optimal transport and connect them to robot motion planning. We propose a heuristics-based sweep planner that does not require knowledge of the material's properties and directly uses a height map representation to generate promising sweeps. These sweeps transform granular material from arbitrary start shapes into arbitrary target shapes. We apply the sweep planner in a fast and reactive feedback loop and avoid the need for model-based planning over multiple time steps. We validate our approach with a large set of simulation and hardware experiments where we show that our method is capable of efficiently solving several complex tasks, including gathering, separating, and shaping of several types of granular materials into different target shapes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.17047v1-abstract-full').style.display = 'none'; document.getElementById('2303.17047v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.10962">arXiv:2303.10962</a> <span> [<a href="https://arxiv.org/pdf/2303.10962">pdf</a>, <a href="https://arxiv.org/format/2303.10962">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Neural Implicit Vision-Language Feature Fields </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Blomqvist%2C+K">Kenneth Blomqvist</a>, <a href="/search/cs?searchtype=author&query=Milano%2C+F">Francesco Milano</a>, <a href="/search/cs?searchtype=author&query=Chung%2C+J+J">Jen Jen Chung</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.10962v1-abstract-short" style="display: inline;"> Recently, groundbreaking results have been presented on open-vocabulary semantic image segmentation. Such methods segment each pixel in an image into arbitrary categories provided at run-time in the form of text prompts, as opposed to a fixed set of classes defined at training time. In this work, we present a zero-shot volumetric open-vocabulary semantic scene segmentation method. Our method build… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.10962v1-abstract-full').style.display = 'inline'; document.getElementById('2303.10962v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.10962v1-abstract-full" style="display: none;"> Recently, groundbreaking results have been presented on open-vocabulary semantic image segmentation. Such methods segment each pixel in an image into arbitrary categories provided at run-time in the form of text prompts, as opposed to a fixed set of classes defined at training time. In this work, we present a zero-shot volumetric open-vocabulary semantic scene segmentation method. Our method builds on the insight that we can fuse image features from a vision-language model into a neural implicit representation. We show that the resulting feature field can be segmented into different classes by assigning points to natural language text prompts. The implicit volumetric representation enables us to segment the scene both in 3D and 2D by rendering feature maps from any given viewpoint of the scene. We show that our method works on noisy real-world data and can run in real-time on live sensor data dynamically adjusting to text prompts. We also present quantitative comparisons on the ScanNet dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.10962v1-abstract-full').style.display = 'none'; document.getElementById('2303.10962v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.01352">arXiv:2303.01352</a> <span> [<a href="https://arxiv.org/pdf/2303.01352">pdf</a>, <a href="https://arxiv.org/format/2303.01352">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Chasing Millimeters: Design, Navigation and State Estimation for Precise In-flight Marking on Ceilings </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lanegger%2C+C">Christian Lanegger</a>, <a href="/search/cs?searchtype=author&query=Pantic%2C+M">Michael Pantic</a>, <a href="/search/cs?searchtype=author&query=B%C3%A4hnemann%2C+R">Rik B盲hnemann</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.01352v1-abstract-short" style="display: inline;"> Precise markings for drilling and assembly are crucial, laborious construction tasks. Aerial robots with suitable end-effectors are capable of markings at the millimeter scale. However, so far, they have only been demonstrated under laboratory conditions where rigid state estimation and navigation assumptions do not impede robustness and accuracy. This paper presents a complete aerial layouting sy… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.01352v1-abstract-full').style.display = 'inline'; document.getElementById('2303.01352v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.01352v1-abstract-full" style="display: none;"> Precise markings for drilling and assembly are crucial, laborious construction tasks. Aerial robots with suitable end-effectors are capable of markings at the millimeter scale. However, so far, they have only been demonstrated under laboratory conditions where rigid state estimation and navigation assumptions do not impede robustness and accuracy. This paper presents a complete aerial layouting system capable of precise markings on-site under realistic conditions. We use a compliant actuated end-effector on an omnidirectional flying base. Combining a two-stage factor-graph state estimator with a Riemannian Motion Policy-based navigation stack, we avoid the need for a globally consistent estimate and increase robustness. The policy-based navigation is structured into individual behaviors in different state spaces. Through a comprehensive study, we show that the system creates highly precise markings at a relative precision of 1.5 mm and a global accuracy of 5-6 mm and discuss the results in the context of future construction robotics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.01352v1-abstract-full').style.display = 'none'; document.getElementById('2303.01352v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">C. Lanegger and M. Pantic contributed equally. Submitted to Autonomous Robots journal (Springer)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.06547">arXiv:2302.06547</a> <span> [<a href="https://arxiv.org/pdf/2302.06547">pdf</a>, <a href="https://arxiv.org/format/2302.06547">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/ICRA48891.2023.10161511">10.1109/ICRA48891.2023.10161511 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Multi-Agent Path Integral Control for Interaction-Aware Motion Planning in Urban Canals </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Streichenberg%2C+L">Lucas Streichenberg</a>, <a href="/search/cs?searchtype=author&query=Trevisan%2C+E">Elia Trevisan</a>, <a href="/search/cs?searchtype=author&query=Chung%2C+J+J">Jen Jen Chung</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Alonso-Mora%2C+J">Javier Alonso-Mora</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2302.06547v1-abstract-short" style="display: inline;"> Autonomous vehicles that operate in urban environments shall comply with existing rules and reason about the interactions with other decision-making agents. In this paper, we introduce a decentralized and communication-free interaction-aware motion planner and apply it to Autonomous Surface Vessels (ASVs) in urban canals. We build upon a sampling-based method, namely Model Predictive Path Integral… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.06547v1-abstract-full').style.display = 'inline'; document.getElementById('2302.06547v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.06547v1-abstract-full" style="display: none;"> Autonomous vehicles that operate in urban environments shall comply with existing rules and reason about the interactions with other decision-making agents. In this paper, we introduce a decentralized and communication-free interaction-aware motion planner and apply it to Autonomous Surface Vessels (ASVs) in urban canals. We build upon a sampling-based method, namely Model Predictive Path Integral control (MPPI), and employ it to, in each time instance, compute both a collision-free trajectory for the vehicle and a prediction of other agents' trajectories, thus modeling interactions. To improve the method's efficiency in multi-agent scenarios, we introduce a two-stage sample evaluation strategy and define an appropriate cost function to achieve rule compliance. We evaluate this decentralized approach in simulations with multiple vessels in real scenarios extracted from Amsterdam's canals, showing superior performance than a state-of-the-art trajectory optimization framework and robustness when encountering different types of agents. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.06547v1-abstract-full').style.display = 'none'; document.getElementById('2302.06547v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for presentation at the 2023 IEEE International Conference on Robotics and Automation (ICRA)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2023 International Conference on Robotics and Automation (ICRA) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.08068">arXiv:2301.08068</a> <span> [<a href="https://arxiv.org/pdf/2301.08068">pdf</a>, <a href="https://arxiv.org/format/2301.08068">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Obstacle avoidance using raycasting and Riemannian Motion Policies at kHz rates for MAVs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pantic%2C+M">Michael Pantic</a>, <a href="/search/cs?searchtype=author&query=Meijer%2C+I">Isar Meijer</a>, <a href="/search/cs?searchtype=author&query=B%C3%A4hnemann%2C+R">Rik B盲hnemann</a>, <a href="/search/cs?searchtype=author&query=Alatur%2C+N">Nikhilesh Alatur</a>, <a href="/search/cs?searchtype=author&query=Andersson%2C+O">Olov Andersson</a>, <a href="/search/cs?searchtype=author&query=Lerma%2C+C+C">Cesar Cadena Lerma</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2301.08068v1-abstract-short" style="display: inline;"> In this paper, we present a novel method for using Riemannian Motion Policies on volumetric maps, shown in the example of obstacle avoidance for Micro Aerial Vehicles (MAVs). While sampling or optimization-based planners are widely used for obstacle avoidance with volumetric maps, they are computationally expensive and often have inflexible monolithic architectures. Riemannian Motion Policies are… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.08068v1-abstract-full').style.display = 'inline'; document.getElementById('2301.08068v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.08068v1-abstract-full" style="display: none;"> In this paper, we present a novel method for using Riemannian Motion Policies on volumetric maps, shown in the example of obstacle avoidance for Micro Aerial Vehicles (MAVs). While sampling or optimization-based planners are widely used for obstacle avoidance with volumetric maps, they are computationally expensive and often have inflexible monolithic architectures. Riemannian Motion Policies are a modular, parallelizable, and efficient navigation paradigm but are challenging to use with the widely used voxel-based environment representations. We propose using GPU raycasting and a large number of concurrent policies to provide direct obstacle avoidance using Riemannian Motion Policies in voxelized maps without the need for smoothing or pre-processing of the map. Additionally, we present how the same method can directly plan on LiDAR scans without the need for an intermediate map. We show how this reactive approach compares favorably to traditional planning methods and is able to plan using thousands of rays at kilohertz rates. We demonstrate the planner successfully on a real MAV for static and dynamic obstacles. The presented planner is made available as an open-source software package. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.08068v1-abstract-full').style.display = 'none'; document.getElementById('2301.08068v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to IROS 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2212.07132">arXiv:2212.07132</a> <span> [<a href="https://arxiv.org/pdf/2212.07132">pdf</a>, <a href="https://arxiv.org/format/2212.07132">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/ICRA48891.2023.10161253">10.1109/ICRA48891.2023.10161253 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Resilient Terrain Navigation with a 5 DOF Metal Detector Drone </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pfreundschuh%2C+P">Patrick Pfreundschuh</a>, <a href="/search/cs?searchtype=author&query=B%C3%A4hnemann%2C+R">Rik B盲hnemann</a>, <a href="/search/cs?searchtype=author&query=Kazik%2C+T">Tim Kazik</a>, <a href="/search/cs?searchtype=author&query=Mantel%2C+T">Thomas Mantel</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Andersson%2C+O">Olov Andersson</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2212.07132v3-abstract-short" style="display: inline;"> Micro aerial vehicles (MAVs) hold the potential for performing autonomous and contactless land surveys for the detection of landmines and explosive remnants of war (ERW). Metal detectors are the standard detection tool but must be operated close to and parallel to the terrain. A successful combination of MAVs with metal detectors has not been presented yet, as it requires advanced flight capabilit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.07132v3-abstract-full').style.display = 'inline'; document.getElementById('2212.07132v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.07132v3-abstract-full" style="display: none;"> Micro aerial vehicles (MAVs) hold the potential for performing autonomous and contactless land surveys for the detection of landmines and explosive remnants of war (ERW). Metal detectors are the standard detection tool but must be operated close to and parallel to the terrain. A successful combination of MAVs with metal detectors has not been presented yet, as it requires advanced flight capabilities. To this end, we present an autonomous system to survey challenging undulated terrain using a metal detector mounted on a 5 degrees of freedom (DOF) MAV. Based on an online estimate of the terrain, our receding-horizon planner efficiently covers the area, aligning the detector to the surface while considering the kinematic and visibility constraints of the platform. As the survey requires resilient and accurate localization in diverse terrain, we also propose a factor graph-based online fusion of GNSS, IMU, and LiDAR measurements. We validate the robustness of the solution to individual sensor degeneracy by flying under the canopy of trees and over featureless fields. A simulated ablation study shows that the proposed planner reduces coverage duration and improves trajectory smoothness. Real-world flight experiments showcase autonomous mapping of buried metallic objects in undulated and obstructed terrain. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.07132v3-abstract-full').style.display = 'none'; document.getElementById('2212.07132v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to the 2023 IEEE International Conference on Robotics and Automation (ICRA 2023)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2212.03951">arXiv:2212.03951</a> <span> [<a href="https://arxiv.org/pdf/2212.03951">pdf</a>, <a href="https://arxiv.org/format/2212.03951">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> A Multi-Segment, Soft Growing Robot with Selective Steering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=K%C3%BCbler%2C+A+M">Alexander M. K眉bler</a>, <a href="/search/cs?searchtype=author&query=Rivera%2C+S+U">Sebasti谩n Urdaneta Rivera</a>, <a href="/search/cs?searchtype=author&query=Raphael%2C+F+B">Frances B. Raphael</a>, <a href="/search/cs?searchtype=author&query=F%C3%B6rster%2C+J">Julian F枚rster</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Okamura%2C+A+M">Allison M. Okamura</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2212.03951v2-abstract-short" style="display: inline;"> Everting, soft growing vine robots benefit from reduced friction with their environment, which allows them to navigate challenging terrain. Vine robots can use air pouches attached to their sides for lateral steering. However, when all pouches are serially connected, the whole robot can only perform one constant curvature in free space. It must contact the environment to navigate through obstacles… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.03951v2-abstract-full').style.display = 'inline'; document.getElementById('2212.03951v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.03951v2-abstract-full" style="display: none;"> Everting, soft growing vine robots benefit from reduced friction with their environment, which allows them to navigate challenging terrain. Vine robots can use air pouches attached to their sides for lateral steering. However, when all pouches are serially connected, the whole robot can only perform one constant curvature in free space. It must contact the environment to navigate through obstacles along paths with multiple turns. This work presents a multi-segment vine robot that can navigate complex paths without interacting with its environment. This is achieved by a new steering method that selectively actuates each single pouch at the tip, providing high degrees of freedom with few control inputs. A small magnetic valve connects each pouch to a pressure supply line. A motorized tip mount uses an interlocking mechanism and motorized rollers on the outer material of the vine robot. As each valve passes through the tip mount, a permanent magnet inside the tip mount opens the valve so the corresponding pouch is connected to the pressure supply line at the same moment. Novel cylindrical pneumatic artificial muscles (cPAMs) are integrated into the vine robot and inflate to a cylindrical shape for improved bending characteristics compared to other state-of-the-art vine robots. The motorized tip mount controls a continuous eversion speed and enables controlled retraction. A final prototype was able to repeatably grow into different shapes and hold these shapes. We predict the path using a model that assumes a piecewise constant curvature along the outside of the multi-segment vine robot. The proposed multi-segment steering method can be extended to other soft continuum robot designs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.03951v2-abstract-full').style.display = 'none'; document.getElementById('2212.03951v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for presentation at the 6th IEEE-RAS International Conference on Soft Robotics (RoboSoft 2023). 7 pages, 12 figures. For associated video, see ancillary files</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2212.00654">arXiv:2212.00654</a> <span> [<a href="https://arxiv.org/pdf/2212.00654">pdf</a>, <a href="https://arxiv.org/ps/2212.00654">ps</a>, <a href="https://arxiv.org/format/2212.00654">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/LRA.2022.3227865">10.1109/LRA.2022.3227865 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> maplab 2.0 -- A Modular and Multi-Modal Mapping Framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cramariuc%2C+A">Andrei Cramariuc</a>, <a href="/search/cs?searchtype=author&query=Bernreiter%2C+L">Lukas Bernreiter</a>, <a href="/search/cs?searchtype=author&query=Tschopp%2C+F">Florian Tschopp</a>, <a href="/search/cs?searchtype=author&query=Fehr%2C+M">Marius Fehr</a>, <a href="/search/cs?searchtype=author&query=Reijgwart%2C+V">Victor Reijgwart</a>, <a href="/search/cs?searchtype=author&query=Nieto%2C+J">Juan Nieto</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Cadena%2C+C">Cesar Cadena</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2212.00654v2-abstract-short" style="display: inline;"> Integration of multiple sensor modalities and deep learning into Simultaneous Localization And Mapping (SLAM) systems are areas of significant interest in current research. Multi-modality is a stepping stone towards achieving robustness in challenging environments and interoperability of heterogeneous multi-robot systems with varying sensor setups. With maplab 2.0, we provide a versatile open-sour… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.00654v2-abstract-full').style.display = 'inline'; document.getElementById('2212.00654v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.00654v2-abstract-full" style="display: none;"> Integration of multiple sensor modalities and deep learning into Simultaneous Localization And Mapping (SLAM) systems are areas of significant interest in current research. Multi-modality is a stepping stone towards achieving robustness in challenging environments and interoperability of heterogeneous multi-robot systems with varying sensor setups. With maplab 2.0, we provide a versatile open-source platform that facilitates developing, testing, and integrating new modules and features into a fully-fledged SLAM system. Through extensive experiments, we show that maplab 2.0's accuracy is comparable to the state-of-the-art on the HILTI 2021 benchmark. Additionally, we showcase the flexibility of our system with three use cases: i) large-scale (approx. 10 km) multi-robot multi-session (23 missions) mapping, ii) integration of non-visual landmarks, and iii) incorporating a semantic object-based loop closure module into the mapping framework. The code is available open-source at https://github.com/ethz-asl/maplab. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.00654v2-abstract-full').style.display = 'none'; document.getElementById('2212.00654v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.13969">arXiv:2211.13969</a> <span> [<a href="https://arxiv.org/pdf/2211.13969">pdf</a>, <a href="https://arxiv.org/format/2211.13969">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Unsupervised Continual Semantic Adaptation through Neural Rendering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhizheng Liu</a>, <a href="/search/cs?searchtype=author&query=Milano%2C+F">Francesco Milano</a>, <a href="/search/cs?searchtype=author&query=Frey%2C+J">Jonas Frey</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Blum%2C+H">Hermann Blum</a>, <a href="/search/cs?searchtype=author&query=Cadena%2C+C">Cesar Cadena</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2211.13969v2-abstract-short" style="display: inline;"> An increasing amount of applications rely on data-driven models that are deployed for perception tasks across a sequence of scenes. Due to the mismatch between training and deployment data, adapting the model on the new scenes is often crucial to obtain good performance. In this work, we study continual multi-scene adaptation for the task of semantic segmentation, assuming that no ground-truth lab… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.13969v2-abstract-full').style.display = 'inline'; document.getElementById('2211.13969v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.13969v2-abstract-full" style="display: none;"> An increasing amount of applications rely on data-driven models that are deployed for perception tasks across a sequence of scenes. Due to the mismatch between training and deployment data, adapting the model on the new scenes is often crucial to obtain good performance. In this work, we study continual multi-scene adaptation for the task of semantic segmentation, assuming that no ground-truth labels are available during deployment and that performance on the previous scenes should be maintained. We propose training a Semantic-NeRF network for each scene by fusing the predictions of a segmentation model and then using the view-consistent rendered semantic labels as pseudo-labels to adapt the model. Through joint training with the segmentation model, the Semantic-NeRF model effectively enables 2D-3D knowledge transfer. Furthermore, due to its compact size, it can be stored in a long-term memory and subsequently used to render data from arbitrary viewpoints to reduce forgetting. We evaluate our approach on ScanNet, where we outperform both a voxel-based baseline and a state-of-the-art unsupervised domain adaptation method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.13969v2-abstract-full').style.display = 'none'; document.getElementById('2211.13969v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023. Zhizheng Liu and Francesco Milano share first authorship. Hermann Blum and Cesar Cadena share senior authorship. 18 pages, 8 figures, 9 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.13992">arXiv:2210.13992</a> <span> [<a href="https://arxiv.org/pdf/2210.13992">pdf</a>, <a href="https://arxiv.org/format/2210.13992">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> SphNet: A Spherical Network for Semantic Pointcloud Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bernreiter%2C+L">Lukas Bernreiter</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Cadena%2C+C">Cesar Cadena</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2210.13992v1-abstract-short" style="display: inline;"> Semantic segmentation for robotic systems can enable a wide range of applications, from self-driving cars and augmented reality systems to domestic robots. We argue that a spherical representation is a natural one for egocentric pointclouds. Thus, in this work, we present a novel framework exploiting such a representation of LiDAR pointclouds for the task of semantic segmentation. Our approach is… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.13992v1-abstract-full').style.display = 'inline'; document.getElementById('2210.13992v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.13992v1-abstract-full" style="display: none;"> Semantic segmentation for robotic systems can enable a wide range of applications, from self-driving cars and augmented reality systems to domestic robots. We argue that a spherical representation is a natural one for egocentric pointclouds. Thus, in this work, we present a novel framework exploiting such a representation of LiDAR pointclouds for the task of semantic segmentation. Our approach is based on a spherical convolutional neural network that can seamlessly handle observations from various sensor systems (e.g., different LiDAR systems) and provides an accurate segmentation of the environment. We operate in two distinct stages: First, we encode the projected input pointclouds to spherical features. Second, we decode and back-project the spherical features to achieve an accurate semantic segmentation of the pointcloud. We evaluate our method with respect to state-of-the-art projection-based semantic segmentation approaches using well-known public datasets. We demonstrate that the spherical representation enables us to provide more accurate segmentation and to have a better generalization to sensors with different field-of-view and number of beams than what was seen during training. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.13992v1-abstract-full').style.display = 'none'; document.getElementById('2210.13992v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.13856">arXiv:2210.13856</a> <span> [<a href="https://arxiv.org/pdf/2210.13856">pdf</a>, <a href="https://arxiv.org/format/2210.13856">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> A Framework for Collaborative Multi-Robot Mapping using Spectral Graph Wavelets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bernreiter%2C+L">Lukas Bernreiter</a>, <a href="/search/cs?searchtype=author&query=Khattak%2C+S">Shehryar Khattak</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a>, <a href="/search/cs?searchtype=author&query=Hutter%2C+M">Marco Hutter</a>, <a href="/search/cs?searchtype=author&query=Cadena%2C+C">Cesar Cadena</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2210.13856v2-abstract-short" style="display: inline;"> The exploration of large-scale unknown environments can benefit from the deployment of multiple robots for collaborative mapping. Each robot explores a section of the environment and communicates onboard pose estimates and maps to a central server to build an optimized global multi-robot map. Naturally, inconsistencies can arise between onboard and server estimates due to onboard odometry drift, f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.13856v2-abstract-full').style.display = 'inline'; document.getElementById('2210.13856v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.13856v2-abstract-full" style="display: none;"> The exploration of large-scale unknown environments can benefit from the deployment of multiple robots for collaborative mapping. Each robot explores a section of the environment and communicates onboard pose estimates and maps to a central server to build an optimized global multi-robot map. Naturally, inconsistencies can arise between onboard and server estimates due to onboard odometry drift, failures, or degeneracies. The mapping server can correct and overcome such failure cases using computationally expensive operations such as inter-robot loop closure detection and multi-modal mapping. However, the individual robots do not benefit from the collaborative map if the mapping server provides no feedback. Although server updates from the multi-robot map can greatly alleviate the robotic mission strategically, most existing work lacks them, due to their associated computational and bandwidth-related costs. Motivated by this challenge, this paper proposes a novel collaborative mapping framework that enables global mapping consistency among robots and the mapping server. In particular, we propose graph spectral analysis, at different spatial scales, to detect structural differences between robot and server graphs, and to generate necessary constraints for the individual robot pose graphs. Our approach specifically finds the nodes that correspond to the drift's origin rather than the nodes where the error becomes too large. We thoroughly analyze and validate our proposed framework using several real-world multi-robot field deployments where we show improvements of the onboard system up to 90\% and can recover the onboard estimation from localization failures and even from the degeneracies within its estimation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.13856v2-abstract-full').style.display = 'none'; document.getElementById('2210.13856v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">arXiv admin note: text overlap with arXiv:2203.00308</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.12744">arXiv:2209.12744</a> <span> [<a href="https://arxiv.org/pdf/2209.12744">pdf</a>, <a href="https://arxiv.org/format/2209.12744">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Baking in the Feature: Accelerating Volumetric Segmentation by Rendering Feature Maps </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Blomqvist%2C+K">Kenneth Blomqvist</a>, <a href="/search/cs?searchtype=author&query=Ott%2C+L">Lionel Ott</a>, <a href="/search/cs?searchtype=author&query=Chung%2C+J+J">Jen Jen Chung</a>, <a href="/search/cs?searchtype=author&query=Siegwart%2C+R">Roland Siegwart</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2209.12744v1-abstract-short" style="display: inline;"> Methods have recently been proposed that densely segment 3D volumes into classes using only color images and expert supervision in the form of sparse semantically annotated pixels. While impressive, these methods still require a relatively large amount of supervision and segmenting an object can take several minutes in practice. Such systems typically only optimize their representation on the part… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.12744v1-abstract-full').style.display = 'inline'; document.getElementById('2209.12744v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.12744v1-abstract-full" style="display: none;"> Methods have recently been proposed that densely segment 3D volumes into classes using only color images and expert supervision in the form of sparse semantically annotated pixels. While impressive, these methods still require a relatively large amount of supervision and segmenting an object can take several minutes in practice. Such systems typically only optimize their representation on the particular scene they are fitting, without leveraging any prior information from previously seen images. In this paper, we propose to use features extracted with models trained on large existing datasets to improve segmentation performance. We bake this feature representation into a Neural Radiance Field (NeRF) by volumetrically rendering feature maps and supervising on features extracted from each input image. We show that by baking this representation into the NeRF, we make the subsequent classification task much easier. Our experiments show that our method achieves higher segmentation accuracy with fewer semantic annotations than existing methods over a wide range of scenes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.12744v1-abstract-full').style.display = 'none'; document.getElementById('2209.12744v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2022. </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Siegwart%2C+R&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Siegwart%2C+R&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Siegwart%2C+R&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Siegwart%2C+R&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Siegwart%2C+R&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Siegwart%2C+R&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository