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 96 results for author: <span class="mathjax">Kyrki, V</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=Kyrki%2C+V">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="Kyrki, V"> </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=Kyrki%2C+V&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="Kyrki, V"> <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=Kyrki%2C+V&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Kyrki%2C+V&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Kyrki%2C+V&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </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/2411.14950">arXiv:2411.14950</a> <span> [<a href="https://arxiv.org/pdf/2411.14950">pdf</a>, <a href="https://arxiv.org/format/2411.14950">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"> Trajectory Planning and Control for Robotic Magnetic Manipulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Isitman%2C+O">Ogulcan Isitman</a>, <a href="/search/cs?searchtype=author&query=Alcan%2C+G">Gokhan Alcan</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2411.14950v1-abstract-short" style="display: inline;"> Robotic magnetic manipulation offers a minimally invasive approach to gastrointestinal examinations through capsule endoscopy. However, controlling such systems using external permanent magnets (EPM) is challenging due to nonlinear magnetic interactions, especially when there are complex navigation requirements such as avoidance of sensitive tissues. In this work, we present a novel trajectory pla… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14950v1-abstract-full').style.display = 'inline'; document.getElementById('2411.14950v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.14950v1-abstract-full" style="display: none;"> Robotic magnetic manipulation offers a minimally invasive approach to gastrointestinal examinations through capsule endoscopy. However, controlling such systems using external permanent magnets (EPM) is challenging due to nonlinear magnetic interactions, especially when there are complex navigation requirements such as avoidance of sensitive tissues. In this work, we present a novel trajectory planning and control method incorporating dynamics and navigation requirements, using a single EPM fixed to a robotic arm to manipulate an internal permanent magnet (IPM). Our approach employs a constrained iterative linear quadratic regulator that considers the dynamics of the IPM to generate optimal trajectories for both the EPM and IPM. Extensive simulations and real-world experiments, motivated by capsule endoscopy operations, demonstrate the robustness of the method, showcasing resilience to external disturbances and precise control under varying conditions. The experimental results show that the IPM reaches the goal position with a maximum mean error of 0.18 cm and a standard deviation of 0.21 cm. This work introduces a unified framework for constrained trajectory optimization in magnetic manipulation, directly incorporating both the IPM's dynamics and the EPM's manipulability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14950v1-abstract-full').style.display = 'none'; document.getElementById('2411.14950v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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, 6 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/2411.04331">arXiv:2411.04331</a> <span> [<a href="https://arxiv.org/pdf/2411.04331">pdf</a>, <a href="https://arxiv.org/format/2411.04331">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"> Raising Body Ownership in End-to-End Visuomotor Policy Learning via Robot-Centric Pooling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhuang%2C+Z">Zheyu Zhuang</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</a>, <a href="/search/cs?searchtype=author&query=Kragic%2C+D">Danica Kragic</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="2411.04331v1-abstract-short" style="display: inline;"> We present Robot-centric Pooling (RcP), a novel pooling method designed to enhance end-to-end visuomotor policies by enabling differentiation between the robots and similar entities or their surroundings. Given an image-proprioception pair, RcP guides the aggregation of image features by highlighting image regions correlating with the robot's proprioceptive states, thereby extracting robot-centric… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04331v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04331v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04331v1-abstract-full" style="display: none;"> We present Robot-centric Pooling (RcP), a novel pooling method designed to enhance end-to-end visuomotor policies by enabling differentiation between the robots and similar entities or their surroundings. Given an image-proprioception pair, RcP guides the aggregation of image features by highlighting image regions correlating with the robot's proprioceptive states, thereby extracting robot-centric image representations for policy learning. Leveraging contrastive learning techniques, RcP integrates seamlessly with existing visuomotor policy learning frameworks and is trained jointly with the policy using the same dataset, requiring no extra data collection involving self-distractors. We evaluate the proposed method with reaching tasks in both simulated and real-world settings. The results demonstrate that RcP significantly enhances the policies' robustness against various unseen distractors, including self-distractors, positioned at different locations. Additionally, the inherent robot-centric characteristic of RcP enables the learnt policy to be far more resilient to aggressive pixel shifts compared to the baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04331v1-abstract-full').style.display = 'none'; document.getElementById('2411.04331v1-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> 6 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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 at IROS 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/2410.18608">arXiv:2410.18608</a> <span> [<a href="https://arxiv.org/pdf/2410.18608">pdf</a>, <a href="https://arxiv.org/format/2410.18608">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 Transparent Reward Models via Unsupervised Feature Selection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Baimukashev%2C+D">Daulet Baimukashev</a>, <a href="/search/cs?searchtype=author&query=Alcan%2C+G">Gokhan Alcan</a>, <a href="/search/cs?searchtype=author&query=Luck%2C+K+S">Kevin Sebastian Luck</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2410.18608v1-abstract-short" style="display: inline;"> In complex real-world tasks such as robotic manipulation and autonomous driving, collecting expert demonstrations is often more straightforward than specifying precise learning objectives and task descriptions. Learning from expert data can be achieved through behavioral cloning or by learning a reward function, i.e., inverse reinforcement learning. The latter allows for training with additional d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18608v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18608v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18608v1-abstract-full" style="display: none;"> In complex real-world tasks such as robotic manipulation and autonomous driving, collecting expert demonstrations is often more straightforward than specifying precise learning objectives and task descriptions. Learning from expert data can be achieved through behavioral cloning or by learning a reward function, i.e., inverse reinforcement learning. The latter allows for training with additional data outside the training distribution, guided by the inferred reward function. We propose a novel approach to construct compact and transparent reward models from automatically selected state features. These inferred rewards have an explicit form and enable the learning of policies that closely match expert behavior by training standard reinforcement learning algorithms from scratch. We validate our method's performance in various robotic environments with continuous and high-dimensional state spaces. Webpage: \url{https://sites.google.com/view/transparent-reward}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18608v1-abstract-full').style.display = 'none'; document.getElementById('2410.18608v1-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, 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">8 pages, 4 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proceedings of the 8th Annual Conference on Robot Learning (CoRL 2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.04809">arXiv:2410.04809</a> <span> [<a href="https://arxiv.org/pdf/2410.04809">pdf</a>, <a href="https://arxiv.org/format/2410.04809">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"> Data-driven Diffusion Models for Enhancing Safety in Autonomous Vehicle Traffic Simulations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lu%2C+J">Jinxiong Lu</a>, <a href="/search/cs?searchtype=author&query=Azam%2C+S">Shoaib Azam</a>, <a href="/search/cs?searchtype=author&query=Alcan%2C+G">Gokhan Alcan</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2410.04809v1-abstract-short" style="display: inline;"> Safety-critical traffic scenarios are integral to the development and validation of autonomous driving systems. These scenarios provide crucial insights into vehicle responses under high-risk conditions rarely encountered in real-world settings. Recent advancements in critical scenario generation have demonstrated the superiority of diffusion-based approaches over traditional generative models in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04809v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04809v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04809v1-abstract-full" style="display: none;"> Safety-critical traffic scenarios are integral to the development and validation of autonomous driving systems. These scenarios provide crucial insights into vehicle responses under high-risk conditions rarely encountered in real-world settings. Recent advancements in critical scenario generation have demonstrated the superiority of diffusion-based approaches over traditional generative models in terms of effectiveness and realism. However, current diffusion-based methods fail to adequately address the complexity of driver behavior and traffic density information, both of which significantly influence driver decision-making processes. In this work, we present a novel approach to overcome these limitations by introducing adversarial guidance functions for diffusion models that incorporate behavior complexity and traffic density, thereby enhancing the generation of more effective and realistic safety-critical traffic scenarios. The proposed method is evaluated on two evaluation metrics: effectiveness and realism.The proposed method is evaluated on two evaluation metrics: effectiveness and realism, demonstrating better efficacy as compared to other state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04809v1-abstract-full').style.display = 'none'; document.getElementById('2410.04809v1-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> 7 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">6 pages, 1 Figure, 2 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/2409.14412">arXiv:2409.14412</a> <span> [<a href="https://arxiv.org/pdf/2409.14412">pdf</a>, <a href="https://arxiv.org/format/2409.14412">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"> COSBO: Conservative Offline Simulation-Based Policy Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kargar%2C+E">Eshagh Kargar</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2409.14412v1-abstract-short" style="display: inline;"> Offline reinforcement learning allows training reinforcement learning models on data from live deployments. However, it is limited to choosing the best combination of behaviors present in the training data. In contrast, simulation environments attempting to replicate the live environment can be used instead of the live data, yet this approach is limited by the simulation-to-reality gap, resulting… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14412v1-abstract-full').style.display = 'inline'; document.getElementById('2409.14412v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14412v1-abstract-full" style="display: none;"> Offline reinforcement learning allows training reinforcement learning models on data from live deployments. However, it is limited to choosing the best combination of behaviors present in the training data. In contrast, simulation environments attempting to replicate the live environment can be used instead of the live data, yet this approach is limited by the simulation-to-reality gap, resulting in a bias. In an attempt to get the best of both worlds, we propose a method that combines an imperfect simulation environment with data from the target environment, to train an offline reinforcement learning policy. Our experiments demonstrate that the proposed method outperforms state-of-the-art approaches CQL, MOPO, and COMBO, especially in scenarios with diverse and challenging dynamics, and demonstrates robust behavior across a variety of experimental conditions. The results highlight that using simulator-generated data can effectively enhance offline policy learning despite the sim-to-real gap, when direct interaction with the real-world is not possible. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14412v1-abstract-full').style.display = 'none'; document.getElementById('2409.14412v1-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 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/2405.03491">arXiv:2405.03491</a> <span> [<a href="https://arxiv.org/pdf/2405.03491">pdf</a>, <a href="https://arxiv.org/format/2405.03491">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"> Jointly Learning Cost and Constraints from Demonstrations for Safe Trajectory Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chaubey%2C+S">Shivam Chaubey</a>, <a href="/search/cs?searchtype=author&query=Verdoja%2C+F">Francesco Verdoja</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2405.03491v2-abstract-short" style="display: inline;"> Learning from Demonstration allows robots to mimic human actions. However, these methods do not model constraints crucial to ensure safety of the learned skill. Moreover, even when explicitly modelling constraints, they rely on the assumption of a known cost function, which limits their practical usability for task with unknown cost. In this work we propose a two-step optimization process that all… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.03491v2-abstract-full').style.display = 'inline'; document.getElementById('2405.03491v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.03491v2-abstract-full" style="display: none;"> Learning from Demonstration allows robots to mimic human actions. However, these methods do not model constraints crucial to ensure safety of the learned skill. Moreover, even when explicitly modelling constraints, they rely on the assumption of a known cost function, which limits their practical usability for task with unknown cost. In this work we propose a two-step optimization process that allow to estimate cost and constraints by decoupling the learning of cost functions from the identification of unknown constraints within the demonstrated trajectories. Initially, we identify the cost function by isolating the effect of constraints on parts of the demonstrations. Subsequently, a constraint leaning method is used to identify the unknown constraints. Our approach is validated both on simulated trajectories and a real robotic manipulation task. Our experiments show the impact that incorrect cost estimation has on the learned constraints and illustrate how the proposed method is able to infer unknown constraints, such as obstacles, from demonstrated trajectories without any initial knowledge of the cost. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.03491v2-abstract-full').style.display = 'none'; document.getElementById('2405.03491v2-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> 9 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 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">(Accepted/In press) 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.07344">arXiv:2404.07344</a> <span> [<a href="https://arxiv.org/pdf/2404.07344">pdf</a>, <a href="https://arxiv.org/format/2404.07344">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="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Interactive Learning of Physical Object Properties Through Robot Manipulation and Database of Object Measurements </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kruzliak%2C+A">Andrej Kruzliak</a>, <a href="/search/cs?searchtype=author&query=Hartvich%2C+J">Jiri Hartvich</a>, <a href="/search/cs?searchtype=author&query=Patni%2C+S+P">Shubhan P. Patni</a>, <a href="/search/cs?searchtype=author&query=Rustler%2C+L">Lukas Rustler</a>, <a href="/search/cs?searchtype=author&query=Behrens%2C+J+K">Jan Kristof Behrens</a>, <a href="/search/cs?searchtype=author&query=Abu-Dakka%2C+F+J">Fares J. Abu-Dakka</a>, <a href="/search/cs?searchtype=author&query=Mikolajczyk%2C+K">Krystian Mikolajczyk</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</a>, <a href="/search/cs?searchtype=author&query=Hoffmann%2C+M">Matej Hoffmann</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="2404.07344v1-abstract-short" style="display: inline;"> This work presents a framework for automatically extracting physical object properties, such as material composition, mass, volume, and stiffness, through robot manipulation and a database of object measurements. The framework involves exploratory action selection to maximize learning about objects on a table. A Bayesian network models conditional dependencies between object properties, incorporat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07344v1-abstract-full').style.display = 'inline'; document.getElementById('2404.07344v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.07344v1-abstract-full" style="display: none;"> This work presents a framework for automatically extracting physical object properties, such as material composition, mass, volume, and stiffness, through robot manipulation and a database of object measurements. The framework involves exploratory action selection to maximize learning about objects on a table. A Bayesian network models conditional dependencies between object properties, incorporating prior probability distributions and uncertainty associated with measurement actions. The algorithm selects optimal exploratory actions based on expected information gain and updates object properties through Bayesian inference. Experimental evaluation demonstrates effective action selection compared to a baseline and correct termination of the experiments if there is nothing more to be learned. The algorithm proved to behave intelligently when presented with trick objects with material properties in conflict with their appearance. The robot pipeline integrates with a logging module and an online database of objects, containing over 24,000 measurements of 63 objects with different grippers. All code and data are publicly available, facilitating automatic digitization of objects and their physical properties through exploratory manipulations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07344v1-abstract-full').style.display = 'none'; document.getElementById('2404.07344v1-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 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">8 pages, 8 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.9 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.17606">arXiv:2403.17606</a> <span> [<a href="https://arxiv.org/pdf/2403.17606">pdf</a>, <a href="https://arxiv.org/format/2403.17606">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"> Interactive Identification of Granular Materials using Force Measurements </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hynninen%2C+S">Samuli Hynninen</a>, <a href="/search/cs?searchtype=author&query=Le%2C+T+N">Tran Nguyen Le</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2403.17606v1-abstract-short" style="display: inline;"> The ability to identify granular materials facilitates the emergence of various new applications in robotics, ranging from cooking at home to truck loading at mining sites. However, granular material identification remains a challenging and underexplored area. In this work, we present a novel interactive material identification framework that enables robots to identify a wide range of granular mat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.17606v1-abstract-full').style.display = 'inline'; document.getElementById('2403.17606v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.17606v1-abstract-full" style="display: none;"> The ability to identify granular materials facilitates the emergence of various new applications in robotics, ranging from cooking at home to truck loading at mining sites. However, granular material identification remains a challenging and underexplored area. In this work, we present a novel interactive material identification framework that enables robots to identify a wide range of granular materials using only a force-torque sensor for perception. Our framework, comprising interactive exploration, feature extraction, and classification stages, prioritizes simplicity and transparency for seamless integration into various manipulation pipelines. We evaluate the proposed approach through extensive experiments with a real-world dataset comprising 11 granular materials, which we also make publicly available. Additionally, we conducted a comprehensive qualitative analysis of the dataset to offer deeper insights into its nature, aiding future development. Our results show that the proposed method is capable of accurately identifying a wide range of granular materials solely relying on force measurements obtained from direct interaction with the materials. Code and dataset are available at: https://irobotics.aalto.fi/indentify_granular/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.17606v1-abstract-full').style.display = 'none'; document.getElementById('2403.17606v1-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 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">Submitted to 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 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/2403.15079">arXiv:2403.15079</a> <span> [<a href="https://arxiv.org/pdf/2403.15079">pdf</a>, <a href="https://arxiv.org/format/2403.15079">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="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Automated Feature Selection for Inverse Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Baimukashev%2C+D">Daulet Baimukashev</a>, <a href="/search/cs?searchtype=author&query=Alcan%2C+G">Gokhan Alcan</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2403.15079v1-abstract-short" style="display: inline;"> Inverse reinforcement learning (IRL) is an imitation learning approach to learning reward functions from expert demonstrations. Its use avoids the difficult and tedious procedure of manual reward specification while retaining the generalization power of reinforcement learning. In IRL, the reward is usually represented as a linear combination of features. In continuous state spaces, the state varia… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.15079v1-abstract-full').style.display = 'inline'; document.getElementById('2403.15079v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.15079v1-abstract-full" style="display: none;"> Inverse reinforcement learning (IRL) is an imitation learning approach to learning reward functions from expert demonstrations. Its use avoids the difficult and tedious procedure of manual reward specification while retaining the generalization power of reinforcement learning. In IRL, the reward is usually represented as a linear combination of features. In continuous state spaces, the state variables alone are not sufficiently rich to be used as features, but which features are good is not known in general. To address this issue, we propose a method that employs polynomial basis functions to form a candidate set of features, which are shown to allow the matching of statistical moments of state distributions. Feature selection is then performed for the candidates by leveraging the correlation between trajectory probabilities and feature expectations. We demonstrate the approach's effectiveness by recovering reward functions that capture expert policies across non-linear control tasks of increasing complexity. Code, data, and videos are available at https://sites.google.com/view/feature4irl. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.15079v1-abstract-full').style.display = 'none'; document.getElementById('2403.15079v1-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 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">7 pages, 4 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T40; 68T05 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.12685">arXiv:2403.12685</a> <span> [<a href="https://arxiv.org/pdf/2403.12685">pdf</a>, <a href="https://arxiv.org/format/2403.12685">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"> Dynamic Manipulation of Deformable Objects using Imitation Learning with Adaptation to Hardware Constraints </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hannus%2C+E">Eric Hannus</a>, <a href="/search/cs?searchtype=author&query=Le%2C+T+N">Tran Nguyen Le</a>, <a href="/search/cs?searchtype=author&query=Blanco-Mulero%2C+D">David Blanco-Mulero</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2403.12685v1-abstract-short" style="display: inline;"> Imitation Learning (IL) is a promising paradigm for learning dynamic manipulation of deformable objects since it does not depend on difficult-to-create accurate simulations of such objects. However, the translation of motions demonstrated by a human to a robot is a challenge for IL, due to differences in the embodiments and the robot's physical limits. These limits are especially relevant in dynam… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.12685v1-abstract-full').style.display = 'inline'; document.getElementById('2403.12685v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.12685v1-abstract-full" style="display: none;"> Imitation Learning (IL) is a promising paradigm for learning dynamic manipulation of deformable objects since it does not depend on difficult-to-create accurate simulations of such objects. However, the translation of motions demonstrated by a human to a robot is a challenge for IL, due to differences in the embodiments and the robot's physical limits. These limits are especially relevant in dynamic manipulation where high velocities and accelerations are typical. To address this problem, we propose a framework that first maps a dynamic demonstration into a motion that respects the robot's constraints using a constrained Dynamic Movement Primitive. Second, the resulting object state is further optimized by quasi-static refinement motions to optimize task performance metrics. This allows both efficiently altering the object state by dynamic motions and stable small-scale refinements. We evaluate the framework in the challenging task of bag opening, designing the system BILBO: Bimanual dynamic manipulation using Imitation Learning for Bag Opening. Our results show that BILBO can successfully open a wide range of crumpled bags, using a demonstration with a single bag. See supplementary material at https://sites.google.com/view/bilbo-bag. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.12685v1-abstract-full').style.display = 'none'; document.getElementById('2403.12685v1-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 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">Submitted to 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024). 8 pages, 8 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/2403.10117">arXiv:2403.10117</a> <span> [<a href="https://arxiv.org/pdf/2403.10117">pdf</a>, <a href="https://arxiv.org/format/2403.10117">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"> Do Visual-Language Maps Capture Latent Semantics? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pekkanen%2C+M">Matti Pekkanen</a>, <a href="/search/cs?searchtype=author&query=Mihaylova%2C+T">Tsvetomila Mihaylova</a>, <a href="/search/cs?searchtype=author&query=Verdoja%2C+F">Francesco Verdoja</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2403.10117v1-abstract-short" style="display: inline;"> Visual-language models (VLMs) have recently been introduced in robotic mapping by using the latent representations, i.e., embeddings, of the VLMs to represent the natural language semantics in the map. The main benefit is moving beyond a small set of human-created labels toward open-vocabulary scene understanding. While there is anecdotal evidence that maps built this way support downstream tasks,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.10117v1-abstract-full').style.display = 'inline'; document.getElementById('2403.10117v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.10117v1-abstract-full" style="display: none;"> Visual-language models (VLMs) have recently been introduced in robotic mapping by using the latent representations, i.e., embeddings, of the VLMs to represent the natural language semantics in the map. The main benefit is moving beyond a small set of human-created labels toward open-vocabulary scene understanding. While there is anecdotal evidence that maps built this way support downstream tasks, such as navigation, rigorous analysis of the quality of the maps using these embeddings is lacking. We investigate two critical properties of map quality: queryability and consistency. The evaluation of queryability addresses the ability to retrieve information from the embeddings. We investigate two aspects of consistency: intra-map consistency and inter-map consistency. Intra-map consistency captures the ability of the embeddings to represent abstract semantic classes, and inter-map consistency captures the generalization properties of the representation. In this paper, we propose a way to analyze the quality of maps created using VLMs, which forms an open-source benchmark to be used when proposing new open-vocabulary map representations. We demonstrate the benchmark by evaluating the maps created by two state-of-the-art methods, VLMaps and OpenScene, using two encoders, LSeg and OpenSeg, using real-world data from the Matterport3D data set. We find that OpenScene outperforms VLMaps with both encoders, and LSeg outperforms OpenSeg with both methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.10117v1-abstract-full').style.display = 'none'; document.getElementById('2403.10117v1-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">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">Sumitted to IEEE-IROS-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/2403.02974">arXiv:2403.02974</a> <span> [<a href="https://arxiv.org/pdf/2403.02974">pdf</a>, <a href="https://arxiv.org/format/2403.02974">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="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Online Learning of Human Constraints from Feedback in Shared Autonomy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+S">Shibei Zhu</a>, <a href="/search/cs?searchtype=author&query=Le%2C+T+N">Tran Nguyen Le</a>, <a href="/search/cs?searchtype=author&query=Kaski%2C+S">Samuel Kaski</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2403.02974v1-abstract-short" style="display: inline;"> Real-time collaboration with humans poses challenges due to the different behavior patterns of humans resulting from diverse physical constraints. Existing works typically focus on learning safety constraints for collaboration, or how to divide and distribute the subtasks between the participating agents to carry out the main task. In contrast, we propose to learn a human constraints model that, i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.02974v1-abstract-full').style.display = 'inline'; document.getElementById('2403.02974v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.02974v1-abstract-full" style="display: none;"> Real-time collaboration with humans poses challenges due to the different behavior patterns of humans resulting from diverse physical constraints. Existing works typically focus on learning safety constraints for collaboration, or how to divide and distribute the subtasks between the participating agents to carry out the main task. In contrast, we propose to learn a human constraints model that, in addition, considers the diverse behaviors of different human operators. We consider a type of collaboration in a shared-autonomy fashion, where both a human operator and an assistive robot act simultaneously in the same task space that affects each other's actions. The task of the assistive agent is to augment the skill of humans to perform a shared task by supporting humans as much as possible, both in terms of reducing the workload and minimizing the discomfort for the human operator. Therefore, we propose an augmentative assistant agent capable of learning and adapting to human physical constraints, aligning its actions with the ergonomic preferences and limitations of the human operator. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.02974v1-abstract-full').style.display = 'none'; document.getElementById('2403.02974v1-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, 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">Accepted to AAAI-24 Bridge Program on Collaborative AI and Modeling of Humans & AAAI-24 Workshop on Ad Hoc Teamwork</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.04397">arXiv:2401.04397</a> <span> [<a href="https://arxiv.org/pdf/2401.04397">pdf</a>, <a href="https://arxiv.org/format/2401.04397">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="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> The Role of Higher-Order Cognitive Models in Active Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Keurulainen%2C+O">Oskar Keurulainen</a>, <a href="/search/cs?searchtype=author&query=Alcan%2C+G">Gokhan Alcan</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2401.04397v1-abstract-short" style="display: inline;"> Building machines capable of efficiently collaborating with humans has been a longstanding goal in artificial intelligence. Especially in the presence of uncertainties, optimal cooperation often requires that humans and artificial agents model each other's behavior and use these models to infer underlying goals, beliefs or intentions, potentially involving multiple levels of recursion. Empirical e… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.04397v1-abstract-full').style.display = 'inline'; document.getElementById('2401.04397v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.04397v1-abstract-full" style="display: none;"> Building machines capable of efficiently collaborating with humans has been a longstanding goal in artificial intelligence. Especially in the presence of uncertainties, optimal cooperation often requires that humans and artificial agents model each other's behavior and use these models to infer underlying goals, beliefs or intentions, potentially involving multiple levels of recursion. Empirical evidence for such higher-order cognition in human behavior is also provided by previous works in cognitive science, linguistics, and robotics. We advocate for a new paradigm for active learning for human feedback that utilises humans as active data sources while accounting for their higher levels of agency. In particular, we discuss how increasing level of agency results in qualitatively different forms of rational communication between an active learning system and a teacher. Additionally, we provide a practical example of active learning using a higher-order cognitive model. This is accompanied by a computational study that underscores the unique behaviors that this model produces. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.04397v1-abstract-full').style.display = 'none'; document.getElementById('2401.04397v1-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> 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">7 pages, to appear in the CAIHu bridge program at AAAI 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/2401.03236">arXiv:2401.03236</a> <span> [<a href="https://arxiv.org/pdf/2401.03236">pdf</a>, <a href="https://arxiv.org/format/2401.03236">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"> Challenges of Data-Driven Simulation of Diverse and Consistent Human Driving Behaviors </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kujanp%C3%A4%C3%A4%2C+K">Kalle Kujanp盲盲</a>, <a href="/search/cs?searchtype=author&query=Baimukashev%2C+D">Daulet Baimukashev</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+S">Shibei Zhu</a>, <a href="/search/cs?searchtype=author&query=Azam%2C+S">Shoaib Azam</a>, <a href="/search/cs?searchtype=author&query=Munir%2C+F">Farzeen Munir</a>, <a href="/search/cs?searchtype=author&query=Alcan%2C+G">Gokhan Alcan</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2401.03236v1-abstract-short" style="display: inline;"> Building simulation environments for developing and testing autonomous vehicles necessitates that the simulators accurately model the statistical realism of the real-world environment, including the interaction with other vehicles driven by human drivers. To address this requirement, an accurate human behavior model is essential to incorporate the diversity and consistency of human driving behavio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.03236v1-abstract-full').style.display = 'inline'; document.getElementById('2401.03236v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.03236v1-abstract-full" style="display: none;"> Building simulation environments for developing and testing autonomous vehicles necessitates that the simulators accurately model the statistical realism of the real-world environment, including the interaction with other vehicles driven by human drivers. To address this requirement, an accurate human behavior model is essential to incorporate the diversity and consistency of human driving behavior. We propose a mathematical framework for designing a data-driven simulation model that simulates human driving behavior more realistically than the currently used physics-based simulation models. Experiments conducted using the NGSIM dataset validate our hypothesis regarding the necessity of considering the complexity, diversity, and consistency of human driving behavior when aiming to develop realistic simulators. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.03236v1-abstract-full').style.display = 'none'; document.getElementById('2401.03236v1-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> 6 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/2310.19405">arXiv:2310.19405</a> <span> [<a href="https://arxiv.org/pdf/2310.19405">pdf</a>, <a href="https://arxiv.org/format/2310.19405">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"> Radar-Lidar Fusion for Object Detection by Designing Effective Convolution Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Munir%2C+F">Farzeen Munir</a>, <a href="/search/cs?searchtype=author&query=Azam%2C+S">Shoaib Azam</a>, <a href="/search/cs?searchtype=author&query=Kucner%2C+T">Tomasz Kucner</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</a>, <a href="/search/cs?searchtype=author&query=Jeon%2C+M">Moongu Jeon</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="2310.19405v1-abstract-short" style="display: inline;"> Object detection is a core component of perception systems, providing the ego vehicle with information about its surroundings to ensure safe route planning. While cameras and Lidar have significantly advanced perception systems, their performance can be limited in adverse weather conditions. In contrast, millimeter-wave technology enables radars to function effectively in such conditions. However,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.19405v1-abstract-full').style.display = 'inline'; document.getElementById('2310.19405v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.19405v1-abstract-full" style="display: none;"> Object detection is a core component of perception systems, providing the ego vehicle with information about its surroundings to ensure safe route planning. While cameras and Lidar have significantly advanced perception systems, their performance can be limited in adverse weather conditions. In contrast, millimeter-wave technology enables radars to function effectively in such conditions. However, relying solely on radar for building a perception system doesn't fully capture the environment due to the data's sparse nature. To address this, sensor fusion strategies have been introduced. We propose a dual-branch framework to integrate radar and Lidar data for enhanced object detection. The primary branch focuses on extracting radar features, while the auxiliary branch extracts Lidar features. These are then combined using additive attention. Subsequently, the integrated features are processed through a novel Parallel Forked Structure (PFS) to manage scale variations. A region proposal head is then utilized for object detection. We evaluated the effectiveness of our proposed method on the Radiate dataset using COCO metrics. The results show that it surpasses state-of-the-art methods by $1.89\%$ and $2.61\%$ in favorable and adverse weather conditions, respectively. This underscores the value of radar-Lidar fusion in achieving precise object detection and localization, especially in challenging weather conditions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.19405v1-abstract-full').style.display = 'none'; document.getElementById('2310.19405v1-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 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">ITSC conference 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/2310.11439">arXiv:2310.11439</a> <span> [<a href="https://arxiv.org/pdf/2310.11439">pdf</a>, <a href="https://arxiv.org/format/2310.11439">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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bouniot%2C+Q">Quentin Bouniot</a>, <a href="/search/cs?searchtype=author&query=Redko%2C+I">Ievgen Redko</a>, <a href="/search/cs?searchtype=author&query=Mallasto%2C+A">Anton Mallasto</a>, <a href="/search/cs?searchtype=author&query=Laclau%2C+C">Charlotte Laclau</a>, <a href="/search/cs?searchtype=author&query=Arndt%2C+K">Karol Arndt</a>, <a href="/search/cs?searchtype=author&query=Struckmeier%2C+O">Oliver Struckmeier</a>, <a href="/search/cs?searchtype=author&query=Heinonen%2C+M">Markus Heinonen</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</a>, <a href="/search/cs?searchtype=author&query=Kaski%2C+S">Samuel Kaski</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="2310.11439v3-abstract-short" style="display: inline;"> In the last decade, we have witnessed the introduction of several novel deep neural network (DNN) architectures exhibiting ever-increasing performance across diverse tasks. Explaining the upward trend of their performance, however, remains difficult as different DNN architectures of comparable depth and width -- common factors associated with their expressive power -- may exhibit a drastically dif… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.11439v3-abstract-full').style.display = 'inline'; document.getElementById('2310.11439v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.11439v3-abstract-full" style="display: none;"> In the last decade, we have witnessed the introduction of several novel deep neural network (DNN) architectures exhibiting ever-increasing performance across diverse tasks. Explaining the upward trend of their performance, however, remains difficult as different DNN architectures of comparable depth and width -- common factors associated with their expressive power -- may exhibit a drastically different performance even when trained on the same dataset. In this paper, we introduce the concept of the non-linearity signature of DNN, the first theoretically sound solution for approximately measuring the non-linearity of deep neural networks. Built upon a score derived from closed-form optimal transport mappings, this signature provides a better understanding of the inner workings of a wide range of DNN architectures and learning paradigms, with a particular emphasis on the computer vision task. We provide extensive experimental results that highlight the practical usefulness of the proposed non-linearity signature and its potential for long-reaching implications. The code for our work is available at https://github.com/qbouniot/AffScoreDeep <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.11439v3-abstract-full').style.display = 'none'; document.getElementById('2310.11439v3-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 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">Code available at https://github.com/qbouniot/AffScoreDeep</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.09543">arXiv:2310.09543</a> <span> [<a href="https://arxiv.org/pdf/2310.09543">pdf</a>, <a href="https://arxiv.org/format/2310.09543">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> </div> </div> <p class="title is-5 mathjax"> Benchmarking the Sim-to-Real Gap in Cloth Manipulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Blanco-Mulero%2C+D">David Blanco-Mulero</a>, <a href="/search/cs?searchtype=author&query=Barbany%2C+O">Oriol Barbany</a>, <a href="/search/cs?searchtype=author&query=Alcan%2C+G">Gokhan Alcan</a>, <a href="/search/cs?searchtype=author&query=Colom%C3%A9%2C+A">Adri脿 Colom茅</a>, <a href="/search/cs?searchtype=author&query=Torras%2C+C">Carme Torras</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2310.09543v2-abstract-short" style="display: inline;"> Realistic physics engines play a crucial role for learning to manipulate deformable objects such as garments in simulation. By doing so, researchers can circumvent challenges such as sensing the deformation of the object in the realworld. In spite of the extensive use of simulations for this task, few works have evaluated the reality gap between deformable object simulators and real-world data. We… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.09543v2-abstract-full').style.display = 'inline'; document.getElementById('2310.09543v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.09543v2-abstract-full" style="display: none;"> Realistic physics engines play a crucial role for learning to manipulate deformable objects such as garments in simulation. By doing so, researchers can circumvent challenges such as sensing the deformation of the object in the realworld. In spite of the extensive use of simulations for this task, few works have evaluated the reality gap between deformable object simulators and real-world data. We present a benchmark dataset to evaluate the sim-to-real gap in cloth manipulation. The dataset is collected by performing a dynamic as well as a quasi-static cloth manipulation task involving contact with a rigid table. We use the dataset to evaluate the reality gap, computational time, and simulation stability of four popular deformable object simulators: MuJoCo, Bullet, Flex, and SOFA. Additionally, we discuss the benefits and drawbacks of each simulator. The benchmark dataset is open-source. Supplementary material, videos, and code, can be found at https://sites.google.com/view/cloth-sim2real-benchmark. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.09543v2-abstract-full').style.display = 'none'; document.getElementById('2310.09543v2-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 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">Accepted to IEEE Robotics and Automation Letters (RA-L). 8 pages, 6 figures. Supplementary material available at https://sites.google.com/view/cloth-sim2real-benchmark</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.08324">arXiv:2309.08324</a> <span> [<a href="https://arxiv.org/pdf/2309.08324">pdf</a>, <a href="https://arxiv.org/format/2309.08324">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"> Object-Oriented Grid Mapping in Dynamic Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pekkanen%2C+M">Matti Pekkanen</a>, <a href="/search/cs?searchtype=author&query=Verdoja%2C+F">Francesco Verdoja</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2309.08324v2-abstract-short" style="display: inline;"> Grid maps, especially occupancy grid maps, are ubiquitous in many mobile robot applications. To simplify the process of learning the map, grid maps subdivide the world into a grid of cells whose occupancies are independently estimated using measurements in the perceptual field of the particular cell. However, the world consists of objects that span multiple cells, which means that measurements fal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08324v2-abstract-full').style.display = 'inline'; document.getElementById('2309.08324v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.08324v2-abstract-full" style="display: none;"> Grid maps, especially occupancy grid maps, are ubiquitous in many mobile robot applications. To simplify the process of learning the map, grid maps subdivide the world into a grid of cells whose occupancies are independently estimated using measurements in the perceptual field of the particular cell. However, the world consists of objects that span multiple cells, which means that measurements falling onto a cell provide evidence of the occupancy of other cells belonging to the same object. Current models do not capture this correlation and, therefore, do not use object-level information for estimating the state of the environment. In this work, we present a way to generalize the update of grid maps, relaxing the assumption of independence. We propose modeling the relationship between the measurements and the occupancy of each cell as a set of latent variables and jointly estimate those variables and the posterior of the map. We propose a method to estimate the latent variables by clustering based on semantic labels and an extension to the Normal Distributions Transform Occupancy Map (NDT-OM) to facilitate the proposed map update method. We perform comprehensive map creation and localization experiments with real-world data sets and show that the proposed method creates better maps in highly dynamic environments compared to state-of-the-art methods. Finally, we demonstrate the ability of the proposed method to remove occluded objects from the map in a lifelong map update scenario. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08324v2-abstract-full').style.display = 'none'; document.getElementById('2309.08324v2-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 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">IEEE-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/2308.09456">arXiv:2308.09456</a> <span> [<a href="https://arxiv.org/pdf/2308.09456">pdf</a>, <a href="https://arxiv.org/format/2308.09456">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"> Integrating Expert Guidance for Efficient Learning of Safe Overtaking in Autonomous Driving Using Deep Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lu%2C+J">Jinxiong Lu</a>, <a href="/search/cs?searchtype=author&query=Alcan%2C+G">Gokhan Alcan</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2308.09456v1-abstract-short" style="display: inline;"> Overtaking on two-lane roads is a great challenge for autonomous vehicles, as oncoming traffic appearing on the opposite lane may require the vehicle to change its decision and abort the overtaking. Deep reinforcement learning (DRL) has shown promise for difficult decision problems such as this, but it requires massive number of data, especially if the action space is continuous. This paper propos… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.09456v1-abstract-full').style.display = 'inline'; document.getElementById('2308.09456v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.09456v1-abstract-full" style="display: none;"> Overtaking on two-lane roads is a great challenge for autonomous vehicles, as oncoming traffic appearing on the opposite lane may require the vehicle to change its decision and abort the overtaking. Deep reinforcement learning (DRL) has shown promise for difficult decision problems such as this, but it requires massive number of data, especially if the action space is continuous. This paper proposes to incorporate guidance from an expert system into DRL to increase its sample efficiency in the autonomous overtaking setting. The guidance system developed in this study is composed of constrained iterative LQR and PID controllers. The novelty lies in the incorporation of a fading guidance function, which gradually decreases the effect of the expert system, allowing the agent to initially learn an appropriate action swiftly and then improve beyond the performance of the expert system. This approach thus combines the strengths of traditional control engineering with the flexibility of learning systems, expanding the capabilities of the autonomous system. The proposed methodology for autonomous vehicle overtaking does not depend on a particular DRL algorithm and three state-of-the-art algorithms are used as baselines for evaluation. Simulation results show that incorporating expert system guidance improves state-of-the-art DRL algorithms greatly in both sample efficiency and driving safety. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.09456v1-abstract-full').style.display = 'none'; document.getElementById('2308.09456v1-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 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">10 pages, 7 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/2305.16702">arXiv:2305.16702</a> <span> [<a href="https://arxiv.org/pdf/2305.16702">pdf</a>, <a href="https://arxiv.org/format/2305.16702">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"> Localization Under Consistent Assumptions Over Dynamics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pekkanen%2C+M">Matti Pekkanen</a>, <a href="/search/cs?searchtype=author&query=Verdoja%2C+F">Francesco Verdoja</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2305.16702v3-abstract-short" style="display: inline;"> Accurate maps are a prerequisite for virtually all mobile robot tasks. Most state-of-the-art maps assume a static world; therefore, dynamic objects are filtered out of the measurements. However, this division ignores movable but non-moving -- i.e., semi-static -- objects, which are usually recorded in the map and treated as static objects, violating the static world assumption and causing errors i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.16702v3-abstract-full').style.display = 'inline'; document.getElementById('2305.16702v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.16702v3-abstract-full" style="display: none;"> Accurate maps are a prerequisite for virtually all mobile robot tasks. Most state-of-the-art maps assume a static world; therefore, dynamic objects are filtered out of the measurements. However, this division ignores movable but non-moving -- i.e., semi-static -- objects, which are usually recorded in the map and treated as static objects, violating the static world assumption and causing errors in the localization. This paper presents a method for consistently modeling moving and movable objects to match the map and measurements. This reduces the error resulting from inconsistent categorization and treatment of non-static measurements. A semantic segmentation network is used to categorize the measurements into static and semi-static classes, and a background subtraction filter is used to remove dynamic measurements. Finally, we show that consistent assumptions over dynamics improve localization accuracy when compared against a state-of-the-art baseline solution using real-world data from the Oxford Radar RobotCar data set. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.16702v3-abstract-full').style.display = 'none'; document.getElementById('2305.16702v3-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 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">IEEE-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/2305.07500">arXiv:2305.07500</a> <span> [<a href="https://arxiv.org/pdf/2305.07500">pdf</a>, <a href="https://arxiv.org/format/2305.07500">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> </div> </div> <p class="title is-5 mathjax"> Learning representations that are closed-form Monge mapping optimal with application to domain adaptation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Struckmeier%2C+O">Oliver Struckmeier</a>, <a href="/search/cs?searchtype=author&query=Redko%2C+I">Ievgen Redko</a>, <a href="/search/cs?searchtype=author&query=Mallasto%2C+A">Anton Mallasto</a>, <a href="/search/cs?searchtype=author&query=Arndt%2C+K">Karol Arndt</a>, <a href="/search/cs?searchtype=author&query=Heinonen%2C+M">Markus Heinonen</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2305.07500v2-abstract-short" style="display: inline;"> Optimal transport (OT) is a powerful geometric tool used to compare and align probability measures following the least effort principle. Despite its widespread use in machine learning (ML), OT problem still bears its computational burden, while at the same time suffering from the curse of dimensionality for measures supported on general high-dimensional spaces. In this paper, we propose to tackle… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.07500v2-abstract-full').style.display = 'inline'; document.getElementById('2305.07500v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.07500v2-abstract-full" style="display: none;"> Optimal transport (OT) is a powerful geometric tool used to compare and align probability measures following the least effort principle. Despite its widespread use in machine learning (ML), OT problem still bears its computational burden, while at the same time suffering from the curse of dimensionality for measures supported on general high-dimensional spaces. In this paper, we propose to tackle these challenges using representation learning. In particular, we seek to learn an embedding space such that the samples of the two input measures become alignable in it with a simple affine mapping that can be calculated efficiently in closed-form. We then show that such approach leads to results that are comparable to solving the original OT problem when applied to the transfer learning task on which many OT baselines where previously evaluated in both homogeneous and heterogeneous DA settings. The code for our contribution is available at \url{https://github.com/Oleffa/LaOT}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.07500v2-abstract-full').style.display = 'none'; document.getElementById('2305.07500v2-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 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/2303.14012">arXiv:2303.14012</a> <span> [<a href="https://arxiv.org/pdf/2303.14012">pdf</a>, <a href="https://arxiv.org/format/2303.14012">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"> SPONGE: Sequence Planning with Deformable-ON-Rigid Contact Prediction from Geometric Features </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Le%2C+T+N">Tran Nguyen Le</a>, <a href="/search/cs?searchtype=author&query=Abu-Dakka%2C+F+J">Fares J. Abu-Dakka</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2303.14012v1-abstract-short" style="display: inline;"> Planning robotic manipulation tasks, especially those that involve interaction between deformable and rigid objects, is challenging due to the complexity in predicting such interactions. We introduce SPONGE, a sequence planning pipeline powered by a deep learning-based contact prediction model for contacts between deformable and rigid bodies under interactions. The contact prediction model is trai… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.14012v1-abstract-full').style.display = 'inline'; document.getElementById('2303.14012v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.14012v1-abstract-full" style="display: none;"> Planning robotic manipulation tasks, especially those that involve interaction between deformable and rigid objects, is challenging due to the complexity in predicting such interactions. We introduce SPONGE, a sequence planning pipeline powered by a deep learning-based contact prediction model for contacts between deformable and rigid bodies under interactions. The contact prediction model is trained on synthetic data generated by a developed simulation environment to learn the mapping from point-cloud observation of a rigid target object and the pose of a deformable tool, to 3D representation of the contact points between the two bodies. We experimentally evaluated the proposed approach for a dish cleaning task both in simulation and on a real \panda with real-world objects. The experimental results demonstrate that in both scenarios the proposed planning pipeline is capable of generating high-quality trajectories that can accomplish the task by achieving more than 90\% area coverage on different objects of varying sizes and curvatures while minimizing travel distance. Code and video are available at: \url{https://irobotics.aalto.fi/sponge/}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.14012v1-abstract-full').style.display = 'none'; document.getElementById('2303.14012v1-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">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">Submitted to 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.13320">arXiv:2303.13320</a> <span> [<a href="https://arxiv.org/pdf/2303.13320">pdf</a>, <a href="https://arxiv.org/format/2303.13320">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="Artificial Intelligence">cs.AI</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/IROS55552.2023.10342002">10.1109/IROS55552.2023.10342002 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> QDP: Learning to Sequentially Optimise Quasi-Static and Dynamic Manipulation Primitives for Robotic Cloth Manipulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Blanco-Mulero%2C+D">David Blanco-Mulero</a>, <a href="/search/cs?searchtype=author&query=Alcan%2C+G">Gokhan Alcan</a>, <a href="/search/cs?searchtype=author&query=Abu-Dakka%2C+F+J">Fares J. Abu-Dakka</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2303.13320v2-abstract-short" style="display: inline;"> Pre-defined manipulation primitives are widely used for cloth manipulation. However, cloth properties such as its stiffness or density can highly impact the performance of these primitives. Although existing solutions have tackled the parameterisation of pick and place locations, the effect of factors such as the velocity or trajectory of quasi-static and dynamic manipulation primitives has been n… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.13320v2-abstract-full').style.display = 'inline'; document.getElementById('2303.13320v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.13320v2-abstract-full" style="display: none;"> Pre-defined manipulation primitives are widely used for cloth manipulation. However, cloth properties such as its stiffness or density can highly impact the performance of these primitives. Although existing solutions have tackled the parameterisation of pick and place locations, the effect of factors such as the velocity or trajectory of quasi-static and dynamic manipulation primitives has been neglected. Choosing appropriate values for these parameters is crucial to cope with the range of materials present in house-hold cloth objects. To address this challenge, we introduce the Quasi-Dynamic Parameterisable (QDP) method, which optimises parameters such as the motion velocity in addition to the pick and place positions of quasi-static and dynamic manipulation primitives. In this work, we leverage the framework of Sequential Reinforcement Learning to decouple sequentially the parameters that compose the primitives. To evaluate the effectiveness of the method we focus on the task of cloth unfolding with a robotic arm in simulation and real-world experiments. Our results in simulation show that by deciding the optimal parameters for the primitives the performance can improve by 20% compared to sub-optimal ones. Real-world results demonstrate the advantage of modifying the velocity and height of manipulation primitives for cloths with different mass, stiffness, shape and size. Supplementary material, videos, and code, can be found at https://sites.google.com/view/qdp-srl. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.13320v2-abstract-full').style.display = 'none'; document.getElementById('2303.13320v2-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 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 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">Accepted to IEEE/RSJ IROS 2023. 8 pages, 7 figures. Supplementary material available at https://sites.google.com/view/qdp-srl</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.10745">arXiv:2302.10745</a> <span> [<a href="https://arxiv.org/pdf/2302.10745">pdf</a>, <a href="https://arxiv.org/format/2302.10745">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"> Constrained Generative Sampling of 6-DoF Grasps </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lundell%2C+J">Jens Lundell</a>, <a href="/search/cs?searchtype=author&query=Verdoja%2C+F">Francesco Verdoja</a>, <a href="/search/cs?searchtype=author&query=Le%2C+T+N">Tran Nguyen Le</a>, <a href="/search/cs?searchtype=author&query=Mousavian%2C+A">Arsalan Mousavian</a>, <a href="/search/cs?searchtype=author&query=Fox%2C+D">Dieter Fox</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2302.10745v2-abstract-short" style="display: inline;"> Most state-of-the-art data-driven grasp sampling methods propose stable and collision-free grasps uniformly on the target object. For bin-picking, executing any of those reachable grasps is sufficient. However, for completing specific tasks, such as squeezing out liquid from a bottle, we want the grasp to be on a specific part of the object's body while avoiding other locations, such as the cap. T… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.10745v2-abstract-full').style.display = 'inline'; document.getElementById('2302.10745v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.10745v2-abstract-full" style="display: none;"> Most state-of-the-art data-driven grasp sampling methods propose stable and collision-free grasps uniformly on the target object. For bin-picking, executing any of those reachable grasps is sufficient. However, for completing specific tasks, such as squeezing out liquid from a bottle, we want the grasp to be on a specific part of the object's body while avoiding other locations, such as the cap. This work presents a generative grasp sampling network, VCGS, capable of constrained 6 Degrees of Freedom (DoF) grasp sampling. In addition, we also curate a new dataset designed to train and evaluate methods for constrained grasping. The new dataset, called CONG, consists of over 14 million training samples of synthetically rendered point clouds and grasps at random target areas on 2889 objects. VCGS is benchmarked against GraspNet, a state-of-the-art unconstrained grasp sampler, in simulation and on a real robot. The results demonstrate that VCGS achieves a 10-15% higher grasp success rate than the baseline while being 2-3 times as sample efficient. Supplementary material is available on our project website. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.10745v2-abstract-full').style.display = 'none'; document.getElementById('2302.10745v2-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> 17 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 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 at the International Conference on Intelligent Robots and Systems (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/2301.03956">arXiv:2301.03956</a> <span> [<a href="https://arxiv.org/pdf/2301.03956">pdf</a>, <a href="https://arxiv.org/ps/2301.03956">ps</a>, <a href="https://arxiv.org/format/2301.03956">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/IROS47612.2022.9982050">10.1109/IROS47612.2022.9982050 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Towards High-Definition Maps: a Framework Leveraging Semantic Segmentation to Improve NDT Map Compression and Descriptivity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Manninen%2C+P">Petri Manninen</a>, <a href="/search/cs?searchtype=author&query=Hyyti%2C+H">Heikki Hyyti</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</a>, <a href="/search/cs?searchtype=author&query=Maanp%C3%A4%C3%A4%2C+J">Jyri Maanp盲盲</a>, <a href="/search/cs?searchtype=author&query=Taher%2C+J">Josef Taher</a>, <a href="/search/cs?searchtype=author&query=Hyypp%C3%A4%2C+J">Juha Hyypp盲</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="2301.03956v1-abstract-short" style="display: inline;"> High-Definition (HD) maps are needed for robust navigation of autonomous vehicles, limited by the on-board storage capacity. To solve this, we propose a novel framework, Environment-Aware Normal Distributions Transform (EA-NDT), that significantly improves compression of standard NDT map representation. The compressed representation of EA-NDT is based on semantic-aided clustering of point clouds r… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.03956v1-abstract-full').style.display = 'inline'; document.getElementById('2301.03956v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.03956v1-abstract-full" style="display: none;"> High-Definition (HD) maps are needed for robust navigation of autonomous vehicles, limited by the on-board storage capacity. To solve this, we propose a novel framework, Environment-Aware Normal Distributions Transform (EA-NDT), that significantly improves compression of standard NDT map representation. The compressed representation of EA-NDT is based on semantic-aided clustering of point clouds resulting in more optimal cells compared to grid cells of standard NDT. To evaluate EA-NDT, we present an open-source implementation that extracts planar and cylindrical primitive features from a point cloud and further divides them into smaller cells to represent the data as an EA-NDT HD map. We collected an open suburban environment dataset and evaluated EA-NDT HD map representation against the standard NDT representation. Compared to the standard NDT, EA-NDT achieved consistently at least 1.5x higher map compression while maintaining the same descriptive capability. Moreover, we showed that EA-NDT is capable of producing maps with significantly higher descriptivity score when using the same number of cells than the standard NDT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.03956v1-abstract-full').style.display = 'none'; document.getElementById('2301.03956v1-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 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">8 pages, 8 figures, IROS22</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.02018">arXiv:2301.02018</a> <span> [<a href="https://arxiv.org/pdf/2301.02018">pdf</a>, <a href="https://arxiv.org/format/2301.02018">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</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"> Constrained Trajectory Optimization on Matrix Lie Groups via Lie-Algebraic Differential Dynamic Programming </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Alcan%2C+G">Gokhan Alcan</a>, <a href="/search/cs?searchtype=author&query=Abu-Dakka%2C+F+J">Fares J. Abu-Dakka</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2301.02018v3-abstract-short" style="display: inline;"> Matrix Lie groups are an important class of manifolds commonly used in control and robotics, and optimizing control policies on these manifolds is a fundamental problem. In this work, we propose a novel computationally efficient approach for trajectory optimization on matrix Lie groups using an augmented Lagrangian-based constrained discrete Differential Dynamic Programming (DDP). The method invol… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.02018v3-abstract-full').style.display = 'inline'; document.getElementById('2301.02018v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.02018v3-abstract-full" style="display: none;"> Matrix Lie groups are an important class of manifolds commonly used in control and robotics, and optimizing control policies on these manifolds is a fundamental problem. In this work, we propose a novel computationally efficient approach for trajectory optimization on matrix Lie groups using an augmented Lagrangian-based constrained discrete Differential Dynamic Programming (DDP). The method involves lifting the optimization problem to the Lie algebra during the backward pass and retracting back to the manifold during the forward pass. Unlike previous approaches that addressed constraint handling only for specific classes of matrix Lie groups, the proposed method provides a general solution for nonlinear constraint handling across generic matrix Lie groups. We evaluate the effectiveness of the proposed DDP method in handling constraints within a mechanical system characterized by rigid body dynamics in SE(3), assessing its computational efficiency compared to existing direct optimization solvers. Additionally, the method demonstrates robustness under external disturbances when applied as a Lie-algebraic feedback control policy on SE(3), and in optimizing a quadrotor's trajectory in a challenging realistic scenario. Experiments show that the proposed approach effectively manages general constraints defined on configuration, velocity, and inputs during optimization, while also maintaining stability under external disturbances when executing the resultant control policy in closed-loop. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.02018v3-abstract-full').style.display = 'none'; document.getElementById('2301.02018v3-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 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">12 pages, 6 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/2212.03581">arXiv:2212.03581</a> <span> [<a href="https://arxiv.org/pdf/2212.03581">pdf</a>, <a href="https://arxiv.org/format/2212.03581">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"> LSVL: Large-scale season-invariant visual localization for UAVs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kinnari%2C+J">Jouko Kinnari</a>, <a href="/search/cs?searchtype=author&query=Renzulli%2C+R">Riccardo Renzulli</a>, <a href="/search/cs?searchtype=author&query=Verdoja%2C+F">Francesco Verdoja</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2212.03581v1-abstract-short" style="display: inline;"> Localization of autonomous unmanned aerial vehicles (UAVs) relies heavily on Global Navigation Satellite Systems (GNSS), which are susceptible to interference. Especially in security applications, robust localization algorithms independent of GNSS are needed to provide dependable operations of autonomous UAVs also in interfered conditions. Typical non-GNSS visual localization approaches rely on kn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.03581v1-abstract-full').style.display = 'inline'; document.getElementById('2212.03581v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.03581v1-abstract-full" style="display: none;"> Localization of autonomous unmanned aerial vehicles (UAVs) relies heavily on Global Navigation Satellite Systems (GNSS), which are susceptible to interference. Especially in security applications, robust localization algorithms independent of GNSS are needed to provide dependable operations of autonomous UAVs also in interfered conditions. Typical non-GNSS visual localization approaches rely on known starting pose, work only on a small-sized map, or require known flight paths before a mission starts. We consider the problem of localization with no information on initial pose or planned flight path. We propose a solution for global visual localization on a map at scale up to 100 km2, based on matching orthoprojected UAV images to satellite imagery using learned season-invariant descriptors. We show that the method is able to determine heading, latitude and longitude of the UAV at 12.6-18.7 m lateral translation error in as few as 23.2-44.4 updates from an uninformed initialization, also in situations of significant seasonal appearance difference (winter-summer) between the UAV image and the map. We evaluate the characteristics of multiple neural network architectures for generating the descriptors, and likelihood estimation methods that are able to provide fast convergence and low localization error. We also evaluate the operation of the algorithm using real UAV data and evaluate running time on a real-time embedded platform. We believe this is the first work that is able to recover the pose of an UAV at this scale and rate of convergence, while allowing significant seasonal difference between camera observations and map. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.03581v1-abstract-full').style.display = 'none'; document.getElementById('2212.03581v1-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> 7 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/2210.06758">arXiv:2210.06758</a> <span> [<a href="https://arxiv.org/pdf/2210.06758">pdf</a>, <a href="https://arxiv.org/format/2210.06758">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Exploring Contextual Representation and Multi-Modality for End-to-End Autonomous Driving </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Azam%2C+S">Shoaib Azam</a>, <a href="/search/cs?searchtype=author&query=Munir%2C+F">Farzeen Munir</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</a>, <a href="/search/cs?searchtype=author&query=Jeon%2C+M">Moongu Jeon</a>, <a href="/search/cs?searchtype=author&query=Pedrycz%2C+W">Witold Pedrycz</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="2210.06758v2-abstract-short" style="display: inline;"> Learning contextual and spatial environmental representations enhances autonomous vehicle's hazard anticipation and decision-making in complex scenarios. Recent perception systems enhance spatial understanding with sensor fusion but often lack full environmental context. Humans, when driving, naturally employ neural maps that integrate various factors such as historical data, situational subtletie… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.06758v2-abstract-full').style.display = 'inline'; document.getElementById('2210.06758v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.06758v2-abstract-full" style="display: none;"> Learning contextual and spatial environmental representations enhances autonomous vehicle's hazard anticipation and decision-making in complex scenarios. Recent perception systems enhance spatial understanding with sensor fusion but often lack full environmental context. Humans, when driving, naturally employ neural maps that integrate various factors such as historical data, situational subtleties, and behavioral predictions of other road users to form a rich contextual understanding of their surroundings. This neural map-based comprehension is integral to making informed decisions on the road. In contrast, even with their significant advancements, autonomous systems have yet to fully harness this depth of human-like contextual understanding. Motivated by this, our work draws inspiration from human driving patterns and seeks to formalize the sensor fusion approach within an end-to-end autonomous driving framework. We introduce a framework that integrates three cameras (left, right, and center) to emulate the human field of view, coupled with top-down bird-eye-view semantic data to enhance contextual representation. The sensor data is fused and encoded using a self-attention mechanism, leading to an auto-regressive waypoint prediction module. We treat feature representation as a sequential problem, employing a vision transformer to distill the contextual interplay between sensor modalities. The efficacy of the proposed method is experimentally evaluated in both open and closed-loop settings. Our method achieves displacement error by 0.67m in open-loop settings, surpassing current methods by 6.9% on the nuScenes dataset. In closed-loop evaluations on CARLA's Town05 Long and Longest6 benchmarks, the proposed method enhances driving performance, route completion, and reduces infractions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.06758v2-abstract-full').style.display = 'none'; document.getElementById('2210.06758v2-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 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/2209.01207">arXiv:2209.01207</a> <span> [<a href="https://arxiv.org/pdf/2209.01207">pdf</a>, <a href="https://arxiv.org/format/2209.01207">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"> Co-Imitation: Learning Design and Behaviour by Imitation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajani%2C+C">Chang Rajani</a>, <a href="/search/cs?searchtype=author&query=Arndt%2C+K">Karol Arndt</a>, <a href="/search/cs?searchtype=author&query=Blanco-Mulero%2C+D">David Blanco-Mulero</a>, <a href="/search/cs?searchtype=author&query=Luck%2C+K+S">Kevin Sebastian Luck</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2209.01207v2-abstract-short" style="display: inline;"> The co-adaptation of robots has been a long-standing research endeavour with the goal of adapting both body and behaviour of a system for a given task, inspired by the natural evolution of animals. Co-adaptation has the potential to eliminate costly manual hardware engineering as well as improve the performance of systems. The standard approach to co-adaptation is to use a reward function for opti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.01207v2-abstract-full').style.display = 'inline'; document.getElementById('2209.01207v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.01207v2-abstract-full" style="display: none;"> The co-adaptation of robots has been a long-standing research endeavour with the goal of adapting both body and behaviour of a system for a given task, inspired by the natural evolution of animals. Co-adaptation has the potential to eliminate costly manual hardware engineering as well as improve the performance of systems. The standard approach to co-adaptation is to use a reward function for optimizing behaviour and morphology. However, defining and constructing such reward functions is notoriously difficult and often a significant engineering effort. This paper introduces a new viewpoint on the co-adaptation problem, which we call co-imitation: finding a morphology and a policy that allow an imitator to closely match the behaviour of a demonstrator. To this end we propose a co-imitation methodology for adapting behaviour and morphology by matching state distributions of the demonstrator. Specifically, we focus on the challenging scenario with mismatched state- and action-spaces between both agents. We find that co-imitation increases behaviour similarity across a variety of tasks and settings, and demonstrate co-imitation by transferring human walking, jogging and kicking skills onto a simulated humanoid. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.01207v2-abstract-full').style.display = 'none'; document.getElementById('2209.01207v2-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> 6 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 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">14 pages, 11 figures, accepted for AAAI-23</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.13267">arXiv:2208.13267</a> <span> [<a href="https://arxiv.org/pdf/2208.13267">pdf</a>, <a href="https://arxiv.org/format/2208.13267">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/10.1016/j.robot.2023.104510">10.1016/j.robot.2023.104510 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Learning Stable Robotic Skills on Riemannian Manifolds </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Saveriano%2C+M">Matteo Saveriano</a>, <a href="/search/cs?searchtype=author&query=Abu-Dakka%2C+F+J">Fares J. Abu-Dakka</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2208.13267v2-abstract-short" style="display: inline;"> In this paper, we propose an approach to learn stable dynamical systems evolving on Riemannian manifolds. The approach leverages a data-efficient procedure to learn a diffeomorphic transformation that maps simple stable dynamical systems onto complex robotic skills. By exploiting mathematical tools from differential geometry, the method ensures that the learned skills fulfill the geometric constra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.13267v2-abstract-full').style.display = 'inline'; document.getElementById('2208.13267v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.13267v2-abstract-full" style="display: none;"> In this paper, we propose an approach to learn stable dynamical systems evolving on Riemannian manifolds. The approach leverages a data-efficient procedure to learn a diffeomorphic transformation that maps simple stable dynamical systems onto complex robotic skills. By exploiting mathematical tools from differential geometry, the method ensures that the learned skills fulfill the geometric constraints imposed by the underlying manifolds, such as unit quaternion (UQ) for orientation and symmetric positive definite (SPD) matrices for impedance, while preserving the convergence to a given target. The proposed approach is firstly tested in simulation on a public benchmark, obtained by projecting Cartesian data into UQ and SPD manifolds, and compared with existing approaches. Apart from evaluating the approach on a public benchmark, several experiments were performed on a real robot performing bottle stacking in different conditions and a drilling task in cooperation with a human operator. The evaluation shows promising results in terms of learning accuracy and task adaptation capabilities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.13267v2-abstract-full').style.display = 'none'; document.getElementById('2208.13267v2-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> 31 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">16 pages, 10 figures, journal</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.10851">arXiv:2208.10851</a> <span> [<a href="https://arxiv.org/pdf/2208.10851">pdf</a>, <a href="https://arxiv.org/format/2208.10851">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Bayesian Floor Field: Transferring people flow predictions across environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Verdoja%2C+F">Francesco Verdoja</a>, <a href="/search/cs?searchtype=author&query=Kucner%2C+T+P">Tomasz Piotr Kucner</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2208.10851v2-abstract-short" style="display: inline;"> Mapping people dynamics is a crucial skill for robots, because it enables them to coexist in human-inhabited environments. However, learning a model of people dynamics is a time consuming process which requires observation of large amount of people moving in an environment. Moreover, approaches for mapping dynamics are unable to transfer the learned models across environments: each model is only a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.10851v2-abstract-full').style.display = 'inline'; document.getElementById('2208.10851v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.10851v2-abstract-full" style="display: none;"> Mapping people dynamics is a crucial skill for robots, because it enables them to coexist in human-inhabited environments. However, learning a model of people dynamics is a time consuming process which requires observation of large amount of people moving in an environment. Moreover, approaches for mapping dynamics are unable to transfer the learned models across environments: each model is only able to describe the dynamics of the environment it has been built in. However, the impact of architectural geometry on people's movement can be used to anticipate their patterns of dynamics, and recent work has looked into learning maps of dynamics from occupancy. So far however, approaches based on trajectories and those based on geometry have not been combined. In this work we propose a novel Bayesian approach to learn people dynamics able to combine knowledge about the environment geometry with observations from human trajectories. An occupancy-based deep prior is used to build an initial transition model without requiring any observations of pedestrian; the model is then updated when observations become available using Bayesian inference. We demonstrate the ability of our model to increase data efficiency and to generalize across real large-scale environments, which is unprecedented for maps of dynamics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.10851v2-abstract-full').style.display = 'none'; document.getElementById('2208.10851v2-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">Submitted to 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.13958">arXiv:2207.13958</a> <span> [<a href="https://arxiv.org/pdf/2207.13958">pdf</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 Based High-Level Decision Making for Abortable Overtaking in Autonomous Vehicles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Malayjerdi%2C+E">Ehsan Malayjerdi</a>, <a href="/search/cs?searchtype=author&query=Alcan%2C+G">Gokhan Alcan</a>, <a href="/search/cs?searchtype=author&query=Kargar%2C+E">Eshagh Kargar</a>, <a href="/search/cs?searchtype=author&query=Darweesh%2C+H">Hatem Darweesh</a>, <a href="/search/cs?searchtype=author&query=Sell%2C+R">Raivo Sell</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2207.13958v3-abstract-short" style="display: inline;"> Autonomous vehicles are a growing technology that aims to enhance safety, accessibility, efficiency, and convenience through autonomous maneuvers ranging from lane change to overtaking. Overtaking is one of the most challenging maneuvers for autonomous vehicles, and current techniques for autonomous overtaking are limited to simple situations. This paper studies how to increase safety in autonomou… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.13958v3-abstract-full').style.display = 'inline'; document.getElementById('2207.13958v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.13958v3-abstract-full" style="display: none;"> Autonomous vehicles are a growing technology that aims to enhance safety, accessibility, efficiency, and convenience through autonomous maneuvers ranging from lane change to overtaking. Overtaking is one of the most challenging maneuvers for autonomous vehicles, and current techniques for autonomous overtaking are limited to simple situations. This paper studies how to increase safety in autonomous overtaking by allowing the maneuver to be aborted. We propose a decision-making process based on a deep Q-Network to determine if and when the overtaking maneuver needs to be aborted. The proposed algorithm is empirically evaluated in simulation with varying traffic situations, indicating that the proposed method improves safety during overtaking maneuvers. Furthermore, the approach is demonstrated in real-world experiments using the autonomous shuttle iseAuto. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.13958v3-abstract-full').style.display = 'none'; document.getElementById('2207.13958v3-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 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">11 pages, 16 figures. This work has been submitted to the IEEE for possible publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2206.14661">arXiv:2206.14661</a> <span> [<a href="https://arxiv.org/pdf/2206.14661">pdf</a>, <a href="https://arxiv.org/format/2206.14661">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Online vs. Offline Adaptive Domain Randomization Benchmark </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tiboni%2C+G">Gabriele Tiboni</a>, <a href="/search/cs?searchtype=author&query=Arndt%2C+K">Karol Arndt</a>, <a href="/search/cs?searchtype=author&query=Averta%2C+G">Giuseppe Averta</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</a>, <a href="/search/cs?searchtype=author&query=Tommasi%2C+T">Tatiana Tommasi</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="2206.14661v1-abstract-short" style="display: inline;"> Physics simulators have shown great promise for conveniently learning reinforcement learning policies in safe, unconstrained environments. However, transferring the acquired knowledge to the real world can be challenging due to the reality gap. To this end, several methods have been recently proposed to automatically tune simulator parameters with posterior distributions given real data, for use w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.14661v1-abstract-full').style.display = 'inline'; document.getElementById('2206.14661v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2206.14661v1-abstract-full" style="display: none;"> Physics simulators have shown great promise for conveniently learning reinforcement learning policies in safe, unconstrained environments. However, transferring the acquired knowledge to the real world can be challenging due to the reality gap. To this end, several methods have been recently proposed to automatically tune simulator parameters with posterior distributions given real data, for use with domain randomization at training time. These approaches have been shown to work for various robotic tasks under different settings and assumptions. Nevertheless, existing literature lacks a thorough comparison of existing adaptive domain randomization methods with respect to transfer performance and real-data efficiency. In this work, we present an open benchmark for both offline and online methods (SimOpt, BayRn, DROID, DROPO), to shed light on which are most suitable for each setting and task at hand. We found that online methods are limited by the quality of the currently learned policy for the next iteration, while offline methods may sometimes fail when replaying trajectories in simulation with open-loop commands. The code used will be released at https://github.com/gabrieletiboni/adr-benchmark. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.14661v1-abstract-full').style.display = 'none'; document.getElementById('2206.14661v1-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 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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">15 pages, 6 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/2204.08573">arXiv:2204.08573</a> <span> [<a href="https://arxiv.org/pdf/2204.08573">pdf</a>, <a href="https://arxiv.org/format/2204.08573">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="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ghadirzadeh%2C+A">Ali Ghadirzadeh</a>, <a href="/search/cs?searchtype=author&query=Poklukar%2C+P">Petra Poklukar</a>, <a href="/search/cs?searchtype=author&query=Arndt%2C+K">Karol Arndt</a>, <a href="/search/cs?searchtype=author&query=Finn%2C+C">Chelsea Finn</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</a>, <a href="/search/cs?searchtype=author&query=Kragic%2C+D">Danica Kragic</a>, <a href="/search/cs?searchtype=author&query=Bj%C3%B6rkman%2C+M">M氓rten Bj枚rkman</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="2204.08573v1-abstract-short" style="display: inline;"> We present a data-efficient framework for solving sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models. The framework, called GenRL, trains deep policies by introducing an action latent variable such that the feed-forward policy search can be divided into two parts: (i) training a sub-policy that outputs a distribut… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.08573v1-abstract-full').style.display = 'inline'; document.getElementById('2204.08573v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.08573v1-abstract-full" style="display: none;"> We present a data-efficient framework for solving sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models. The framework, called GenRL, trains deep policies by introducing an action latent variable such that the feed-forward policy search can be divided into two parts: (i) training a sub-policy that outputs a distribution over the action latent variable given a state of the system, and (ii) unsupervised training of a generative model that outputs a sequence of motor actions conditioned on the latent action variable. GenRL enables safe exploration and alleviates the data-inefficiency problem as it exploits prior knowledge about valid sequences of motor actions. Moreover, we provide a set of measures for evaluation of generative models such that we are able to predict the performance of the RL policy training prior to the actual training on a physical robot. We experimentally determine the characteristics of generative models that have most influence on the performance of the final policy training on two robotics tasks: shooting a hockey puck and throwing a basketball. Furthermore, we empirically demonstrate that GenRL is the only method which can safely and efficiently solve the robotics tasks compared to two state-of-the-art RL methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.08573v1-abstract-full').style.display = 'none'; document.getElementById('2204.08573v1-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 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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: substantial text overlap with arXiv:2007.13134</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.12420">arXiv:2203.12420</a> <span> [<a href="https://arxiv.org/pdf/2203.12420">pdf</a>, <a href="https://arxiv.org/format/2203.12420">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/IROS47612.2022.9981169">10.1109/IROS47612.2022.9981169 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Novel Simulation-Based Quality Metric for Evaluating Grasps on 3D Deformable Objects </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Le%2C+T+N">Tran Nguyen Le</a>, <a href="/search/cs?searchtype=author&query=Lundell%2C+J">Jens Lundell</a>, <a href="/search/cs?searchtype=author&query=Abu-Dakka%2C+F+J">Fares J. Abu-Dakka</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2203.12420v1-abstract-short" style="display: inline;"> Evaluation of grasps on deformable 3D objects is a little-studied problem, even if the applicability of rigid object grasp quality measures for deformable ones is an open question. A central issue with most quality measures is their dependence on contact points which for deformable objects depend on the deformations. This paper proposes a grasp quality measure for deformable objects that uses info… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.12420v1-abstract-full').style.display = 'inline'; document.getElementById('2203.12420v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.12420v1-abstract-full" style="display: none;"> Evaluation of grasps on deformable 3D objects is a little-studied problem, even if the applicability of rigid object grasp quality measures for deformable ones is an open question. A central issue with most quality measures is their dependence on contact points which for deformable objects depend on the deformations. This paper proposes a grasp quality measure for deformable objects that uses information about object deformation to calculate the grasp quality. Grasps are evaluated by simulating the deformations during grasping and predicting the contacts between the gripper and the grasped object. The contact information is then used as input for a new grasp quality metric to quantify the grasp quality. The approach is benchmarked against two classical rigid-body quality metrics on over 600 grasps in the Isaac gym simulation and over 50 real-world grasps. Experimental results show an average improvement of 18\% in the grasp success rate for deformable objects compared to the classical rigid-body quality metrics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.12420v1-abstract-full').style.display = 'none'; document.getElementById('2203.12420v1-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 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 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">In review for IROS 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.09149">arXiv:2203.09149</a> <span> [<a href="https://arxiv.org/pdf/2203.09149">pdf</a>, <a href="https://arxiv.org/format/2203.09149">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 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.2022.3152975">10.1109/LRA.2022.3152975 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Active Visuo-Haptic Object Shape Completion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rustler%2C+L">Lukas Rustler</a>, <a href="/search/cs?searchtype=author&query=Lundell%2C+J">Jens Lundell</a>, <a href="/search/cs?searchtype=author&query=Behrens%2C+J+K">Jan Kristof Behrens</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</a>, <a href="/search/cs?searchtype=author&query=Hoffmann%2C+M">Matej Hoffmann</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="2203.09149v1-abstract-short" style="display: inline;"> Recent advancements in object shape completion have enabled impressive object reconstructions using only visual input. However, due to self-occlusion, the reconstructions have high uncertainty in the occluded object parts, which negatively impacts the performance of downstream robotic tasks such as grasping. In this work, we propose an active visuo-haptic shape completion method called Act-VH that… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.09149v1-abstract-full').style.display = 'inline'; document.getElementById('2203.09149v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.09149v1-abstract-full" style="display: none;"> Recent advancements in object shape completion have enabled impressive object reconstructions using only visual input. However, due to self-occlusion, the reconstructions have high uncertainty in the occluded object parts, which negatively impacts the performance of downstream robotic tasks such as grasping. In this work, we propose an active visuo-haptic shape completion method called Act-VH that actively computes where to touch the objects based on the reconstruction uncertainty. Act-VH reconstructs objects from point clouds and calculates the reconstruction uncertainty using IGR, a recent state-of-the-art implicit surface deep neural network. We experimentally evaluate the reconstruction accuracy of Act-VH against five baselines in simulation and in the real world. We also propose a new simulation environment for this purpose. The results show that Act-VH outperforms all baselines and that an uncertainty-driven haptic exploration policy leads to higher reconstruction accuracy than a random policy and a policy driven by Gaussian Process Implicit Surfaces. As a final experiment, we evaluate Act-VH and the best reconstruction baseline on grasping 10 novel objects. The results show that Act-VH reaches a significantly higher grasp success rate than the baseline on all objects. Together, this work opens up the door for using active visuo-haptic shape completion in more complex cluttered scenes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.09149v1-abstract-full').style.display = 'none'; document.getElementById('2203.09149v1-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> 17 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 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">8 pages, 7 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE Robotics and Automation Letters 7 (2) 2022, 5254-5261 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.03374">arXiv:2203.03374</a> <span> [<a href="https://arxiv.org/pdf/2203.03374">pdf</a>, <a href="https://arxiv.org/format/2203.03374">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"> A Unified Formulation of Geometry-aware Dynamic Movement Primitives </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Abu-Dakka%2C+F+J">Fares J. Abu-Dakka</a>, <a href="/search/cs?searchtype=author&query=Saveriano%2C+M">Matteo Saveriano</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2203.03374v3-abstract-short" style="display: inline;"> Learning from demonstration (LfD) is considered as an efficient way to transfer skills from humans to robots. Traditionally, LfD has been used to transfer Cartesian and joint positions and forces from human demonstrations. The traditional approach works well for some robotic tasks, but for many tasks of interest, it is necessary to learn skills such as orientation, impedance, and/or manipulability… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.03374v3-abstract-full').style.display = 'inline'; document.getElementById('2203.03374v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.03374v3-abstract-full" style="display: none;"> Learning from demonstration (LfD) is considered as an efficient way to transfer skills from humans to robots. Traditionally, LfD has been used to transfer Cartesian and joint positions and forces from human demonstrations. The traditional approach works well for some robotic tasks, but for many tasks of interest, it is necessary to learn skills such as orientation, impedance, and/or manipulability that have specific geometric characteristics. An effective encoding of such skills can be only achieved if the underlying geometric structure of the skill manifold is considered and the constrains arising from this structure are fulfilled during both learning and execution. However, typical learned skill models such as dynamic movement primitives (DMPs) are limited to Euclidean data and fail in correctly embedding quantities with geometric constraints. In this paper, we propose a novel and mathematically principled framework that uses concepts from Riemannian geometry to allow DMPs to properly embed geometric constrains. The resulting DMP formulation can deal with data sampled from any Riemannian manifold including, but not limited to, unit quaternions and symmetric and positive definite matrices. The proposed approach has been extensively evaluated both on simulated data and real robot experiments. The performed evaluation demonstrates that beneficial properties of DMPs, such as convergence to a given goal and the possibility to change the goal during operation, apply also to the proposed formulation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.03374v3-abstract-full').style.display = 'none'; document.getElementById('2203.03374v3-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 7 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 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">18 pages, 12 figures, journal</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.13248">arXiv:2201.13248</a> <span> [<a href="https://arxiv.org/pdf/2201.13248">pdf</a>, <a href="https://arxiv.org/format/2201.13248">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="Artificial Intelligence">cs.AI</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="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kaushik%2C+R">Rituraj Kaushik</a>, <a href="/search/cs?searchtype=author&query=Arndt%2C+K">Karol Arndt</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2201.13248v1-abstract-short" style="display: inline;"> The framework of Simulation-to-real learning, i.e, learning policies in simulation and transferring those policies to the real world is one of the most promising approaches towards data-efficient learning in robotics. However, due to the inevitable reality gap between the simulation and the real world, a policy learned in the simulation may not always generate a safe behaviour on the real robot. A… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.13248v1-abstract-full').style.display = 'inline'; document.getElementById('2201.13248v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.13248v1-abstract-full" style="display: none;"> The framework of Simulation-to-real learning, i.e, learning policies in simulation and transferring those policies to the real world is one of the most promising approaches towards data-efficient learning in robotics. However, due to the inevitable reality gap between the simulation and the real world, a policy learned in the simulation may not always generate a safe behaviour on the real robot. As a result, during adaptation of the policy in the real world, the robot may damage itself or cause harm to its surroundings. In this work, we introduce a novel learning algorithm called SafeAPT that leverages a diverse repertoire of policies evolved in the simulation and transfers the most promising safe policy to the real robot through episodic interaction. To achieve this, SafeAPT iteratively learns a probabilistic reward model as well as a safety model using real-world observations combined with simulated experiences as priors. Then, it performs Bayesian optimization on the repertoire with the reward model while maintaining the specified safety constraint using the safety model. SafeAPT allows a robot to adapt to a wide range of goals safely with the same repertoire of policies evolved in the simulation. We compare SafeAPT with several baselines, both in simulated and real robotic experiments and show that SafeAPT finds high-performance policies within a few minutes in the real world while minimizing safety violations during the interactions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.13248v1-abstract-full').style.display = 'none'; document.getElementById('2201.13248v1-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 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">Under review. For video of the paper http://tiny.cc/safeAPT</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.12819">arXiv:2201.12819</a> <span> [<a href="https://arxiv.org/pdf/2201.12819">pdf</a>, <a href="https://arxiv.org/format/2201.12819">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</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> <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"> A Safety-Critical Decision Making and Control Framework Combining Machine Learning and Rule-based Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Aksjonov%2C+A">Andrei Aksjonov</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2201.12819v1-abstract-short" style="display: inline;"> While artificial-intelligence-based methods suffer from lack of transparency, rule-based methods dominate in safety-critical systems. Yet, the latter cannot compete with the first ones in robustness to multiple requirements, for instance, simultaneously addressing safety, comfort, and efficiency. Hence, to benefit from both methods they must be joined in a single system. This paper proposes a deci… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.12819v1-abstract-full').style.display = 'inline'; document.getElementById('2201.12819v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.12819v1-abstract-full" style="display: none;"> While artificial-intelligence-based methods suffer from lack of transparency, rule-based methods dominate in safety-critical systems. Yet, the latter cannot compete with the first ones in robustness to multiple requirements, for instance, simultaneously addressing safety, comfort, and efficiency. Hence, to benefit from both methods they must be joined in a single system. This paper proposes a decision making and control framework, which profits from advantages of both the rule- and machine-learning-based techniques while compensating for their disadvantages. The proposed method embodies two controllers operating in parallel, called Safety and Learned. A rule-based switching logic selects one of the actions transmitted from both controllers. The Safety controller is prioritized every time, when the Learned one does not meet the safety constraint, and also directly participates in the safe Learned controller training. Decision making and control in autonomous driving is chosen as the system case study, where an autonomous vehicle learns a multi-task policy to safely cross an unprotected intersection. Multiple requirements (i.e., safety, efficiency, and comfort) are set for vehicle operation. A numerical simulation is performed for the proposed framework validation, where its ability to satisfy the requirements and robustness to changing environment is successfully demonstrated. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.12819v1-abstract-full').style.display = 'none'; document.getElementById('2201.12819v1-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 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">11 pages, 9 figures, 2 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/2201.08434">arXiv:2201.08434</a> <span> [<a href="https://arxiv.org/pdf/2201.08434">pdf</a>, <a href="https://arxiv.org/format/2201.08434">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> DROPO: Sim-to-Real Transfer with Offline Domain Randomization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tiboni%2C+G">Gabriele Tiboni</a>, <a href="/search/cs?searchtype=author&query=Arndt%2C+K">Karol Arndt</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2201.08434v2-abstract-short" style="display: inline;"> In recent years, domain randomization over dynamics parameters has gained a lot of traction as a method for sim-to-real transfer of reinforcement learning policies in robotic manipulation; however, finding optimal randomization distributions can be difficult. In this paper, we introduce DROPO, a novel method for estimating domain randomization distributions for safe sim-to-real transfer. Unlike pr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.08434v2-abstract-full').style.display = 'inline'; document.getElementById('2201.08434v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.08434v2-abstract-full" style="display: none;"> In recent years, domain randomization over dynamics parameters has gained a lot of traction as a method for sim-to-real transfer of reinforcement learning policies in robotic manipulation; however, finding optimal randomization distributions can be difficult. In this paper, we introduce DROPO, a novel method for estimating domain randomization distributions for safe sim-to-real transfer. Unlike prior work, DROPO only requires a limited, precollected offline dataset of trajectories, and explicitly models parameter uncertainty to match real data using a likelihood-based approach. We demonstrate that DROPO is capable of recovering dynamic parameter distributions in simulation and finding a distribution capable of compensating for an unmodeled phenomenon. We also evaluate the method in two zero-shot sim-to-real transfer scenarios, showing successful domain transfer and improved performance over prior methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.08434v2-abstract-full').style.display = 'none'; document.getElementById('2201.08434v2-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 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">16 pages, 21 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/2112.01942">arXiv:2112.01942</a> <span> [<a href="https://arxiv.org/pdf/2112.01942">pdf</a>, <a href="https://arxiv.org/format/2112.01942">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/10.1016/j.robot.2022.104224">10.1016/j.robot.2022.104224 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Survey of Robot Manipulation in Contact </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Suomalainen%2C+M">Markku Suomalainen</a>, <a href="/search/cs?searchtype=author&query=Karayiannidis%2C+Y">Yiannis Karayiannidis</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2112.01942v3-abstract-short" style="display: inline;"> In this survey, we present the current status on robots performing manipulation tasks that require varying contact with the environment, such that the robot must either implicitly or explicitly control the contact force with the environment to complete the task. Robots can perform more and more manipulation tasks that are still done by humans, and there is a growing number of publications on the t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.01942v3-abstract-full').style.display = 'inline'; document.getElementById('2112.01942v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.01942v3-abstract-full" style="display: none;"> In this survey, we present the current status on robots performing manipulation tasks that require varying contact with the environment, such that the robot must either implicitly or explicitly control the contact force with the environment to complete the task. Robots can perform more and more manipulation tasks that are still done by humans, and there is a growing number of publications on the topics of 1) performing tasks that always require contact and 2) mitigating uncertainty by leveraging the environment in tasks that, under perfect information, could be performed without contact. The recent trends have seen robots perform tasks earlier left for humans, such as massage, and in the classical tasks, such as peg-in-hole, there is a more efficient generalization to other similar tasks, better error tolerance, and faster planning or learning of the tasks. Thus, in this survey we cover the current stage of robots performing such tasks, starting from surveying all the different in-contact tasks robots can perform, observing how these tasks are controlled and represented, and finally presenting the learning and planning of the skills required to complete these tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.01942v3-abstract-full').style.display = 'none'; document.getElementById('2112.01942v3-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 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </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 in Robotics and Autonomous Systems</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Robotics and Autonomous Systems, Volume 156, 2022, 104224, ISSN 0921-8890, </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.02274">arXiv:2111.02274</a> <span> [<a href="https://arxiv.org/pdf/2111.02274">pdf</a>, <a href="https://arxiv.org/format/2111.02274">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="Machine Learning">cs.LG</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.2022.3158382">10.1109/LRA.2022.3158382 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Manipulation of Granular Materials by Learning Particle Interactions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tuomainen%2C+N">Neea Tuomainen</a>, <a href="/search/cs?searchtype=author&query=Blanco-Mulero%2C+D">David Blanco-Mulero</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2111.02274v3-abstract-short" style="display: inline;"> Manipulation of granular materials such as sand or rice remains an unsolved problem due to challenges such as the difficulty of defining their configuration or modeling the materials and their particles interactions. Current approaches tend to simplify the material dynamics and omit the interactions between the particles. In this paper, we propose to use a graph-based representation to model the i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.02274v3-abstract-full').style.display = 'inline'; document.getElementById('2111.02274v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.02274v3-abstract-full" style="display: none;"> Manipulation of granular materials such as sand or rice remains an unsolved problem due to challenges such as the difficulty of defining their configuration or modeling the materials and their particles interactions. Current approaches tend to simplify the material dynamics and omit the interactions between the particles. In this paper, we propose to use a graph-based representation to model the interaction dynamics of the material and rigid bodies manipulating it. This allows the planning of manipulation trajectories to reach a desired configuration of the material. We use a graph neural network (GNN) to model the particle interactions via message-passing. To plan manipulation trajectories, we propose to minimise the Wasserstein distance between a predicted distribution of granular particles and their desired configuration. We demonstrate that the proposed method is able to pour granular materials into the desired configuration both in simulated and real scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.02274v3-abstract-full').style.display = 'none'; document.getElementById('2111.02274v3-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 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </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, 5 figures. 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/2110.01967">arXiv:2110.01967</a> <span> [<a href="https://arxiv.org/pdf/2110.01967">pdf</a>, <a href="https://arxiv.org/format/2110.01967">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.2022.3191038">10.1109/LRA.2022.3191038 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Season-invariant GNSS-denied visual localization for UAVs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kinnari%2C+J">Jouko Kinnari</a>, <a href="/search/cs?searchtype=author&query=Verdoja%2C+F">Francesco Verdoja</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2110.01967v2-abstract-short" style="display: inline;"> Localization without Global Navigation Satellite Systems (GNSS) is a critical functionality in autonomous operations of unmanned aerial vehicles (UAVs). Vision-based localization on a known map can be an effective solution, but it is burdened by two main problems: places have different appearance depending on weather and season, and the perspective discrepancy between the UAV camera image and the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.01967v2-abstract-full').style.display = 'inline'; document.getElementById('2110.01967v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.01967v2-abstract-full" style="display: none;"> Localization without Global Navigation Satellite Systems (GNSS) is a critical functionality in autonomous operations of unmanned aerial vehicles (UAVs). Vision-based localization on a known map can be an effective solution, but it is burdened by two main problems: places have different appearance depending on weather and season, and the perspective discrepancy between the UAV camera image and the map make matching hard. In this work, we propose a localization solution relying on matching of UAV camera images to georeferenced orthophotos with a trained convolutional neural network model that is invariant to significant seasonal appearance difference (winter-summer) between the camera image and map. We compare the convergence speed and localization accuracy of our solution to six reference methods. The results show major improvements with respect to reference methods, especially under high seasonal variation. We finally demonstrate the ability of the method to successfully localize a real UAV, showing that the proposed method is robust to perspective changes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.01967v2-abstract-full').style.display = 'none'; document.getElementById('2110.01967v2-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 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2021. </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">Published in IEEE Robotics and Automation Letters (Volume: 7, Issue: 4, October 2022)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.06514">arXiv:2109.06514</a> <span> [<a href="https://arxiv.org/pdf/2109.06514">pdf</a>, <a href="https://arxiv.org/format/2109.06514">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="Multiagent Systems">cs.MA</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"> Vision Transformer for Learning Driving Policies in Complex Multi-Agent Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kargar%2C+E">Eshagh Kargar</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2109.06514v1-abstract-short" style="display: inline;"> Driving in a complex urban environment is a difficult task that requires a complex decision policy. In order to make informed decisions, one needs to gain an understanding of the long-range context and the importance of other vehicles. In this work, we propose to use Vision Transformer (ViT) to learn a driving policy in urban settings with birds-eye-view (BEV) input images. The ViT network learns… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.06514v1-abstract-full').style.display = 'inline'; document.getElementById('2109.06514v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.06514v1-abstract-full" style="display: none;"> Driving in a complex urban environment is a difficult task that requires a complex decision policy. In order to make informed decisions, one needs to gain an understanding of the long-range context and the importance of other vehicles. In this work, we propose to use Vision Transformer (ViT) to learn a driving policy in urban settings with birds-eye-view (BEV) input images. The ViT network learns the global context of the scene more effectively than with earlier proposed Convolutional Neural Networks (ConvNets). Furthermore, ViT's attention mechanism helps to learn an attention map for the scene which allows the ego car to determine which surrounding cars are important to its next decision. We demonstrate that a DQN agent with a ViT backbone outperforms baseline algorithms with ConvNet backbones pre-trained in various ways. In particular, the proposed method helps reinforcement learning algorithms to learn faster, with increased performance and less data than baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.06514v1-abstract-full').style.display = 'none'; document.getElementById('2109.06514v1-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 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.05320">arXiv:2109.05320</a> <span> [<a href="https://arxiv.org/pdf/2109.05320">pdf</a>, <a href="https://arxiv.org/format/2109.05320">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.2022.3146551">10.1109/LRA.2022.3146551 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Deformation-Aware Data-Driven Grasp Synthesis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Le%2C+T+N">Tran Nguyen Le</a>, <a href="/search/cs?searchtype=author&query=Lundell%2C+J">Jens Lundell</a>, <a href="/search/cs?searchtype=author&query=Abu-Dakka%2C+F+J">Fares J. Abu-Dakka</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2109.05320v1-abstract-short" style="display: inline;"> Grasp synthesis for 3D deformable objects remains a little-explored topic, most works aiming to minimize deformations. However, deformations are not necessarily harmful -- humans are, for example, able to exploit deformations to generate new potential grasps. How to achieve that on a robot is though an open question. This paper proposes an approach that uses object stiffness information in additio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.05320v1-abstract-full').style.display = 'inline'; document.getElementById('2109.05320v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.05320v1-abstract-full" style="display: none;"> Grasp synthesis for 3D deformable objects remains a little-explored topic, most works aiming to minimize deformations. However, deformations are not necessarily harmful -- humans are, for example, able to exploit deformations to generate new potential grasps. How to achieve that on a robot is though an open question. This paper proposes an approach that uses object stiffness information in addition to depth images for synthesizing high-quality grasps. We achieve this by incorporating object stiffness as an additional input to a state-of-the-art deep grasp planning network. We also curate a new synthetic dataset of grasps on objects of varying stiffness using the Isaac Gym simulator for training the network. We experimentally validate and compare our proposed approach against the case where we do not incorporate object stiffness on a total of 2800 grasps in simulation and 420 grasps on a real Franka Emika Panda. The experimental results show significant improvement in grasp success rate using the proposed approach on a wide range of objects with varying shapes, sizes, and stiffness. Furthermore, we demonstrate that the approach can generate different grasping strategies for different stiffness values, such as pinching for soft objects and caging for hard objects. Together, the results clearly show the value of incorporating stiffness information when grasping objects of varying stiffness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.05320v1-abstract-full').style.display = 'none'; document.getElementById('2109.05320v1-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 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </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">In review for RA-L and ICRA 2022. 8 pages, 10 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/2109.04771">arXiv:2109.04771</a> <span> [<a href="https://arxiv.org/pdf/2109.04771">pdf</a>, <a href="https://arxiv.org/format/2109.04771">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/IROS47612.2022.9981376">10.1109/IROS47612.2022.9981376 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Learning Visual Feedback Control for Dynamic Cloth Folding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hietala%2C+J">Julius Hietala</a>, <a href="/search/cs?searchtype=author&query=Blanco-Mulero%2C+D">David Blanco-Mulero</a>, <a href="/search/cs?searchtype=author&query=Alcan%2C+G">Gokhan Alcan</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2109.04771v3-abstract-short" style="display: inline;"> Robotic manipulation of cloth is a challenging task due to the high dimensionality of the configuration space and the complexity of dynamics affected by various material properties. The effect of complex dynamics is even more pronounced in dynamic folding, for example, when a square piece of fabric is folded in two by a single manipulator. To account for the complexity and uncertainties, feedback… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.04771v3-abstract-full').style.display = 'inline'; document.getElementById('2109.04771v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.04771v3-abstract-full" style="display: none;"> Robotic manipulation of cloth is a challenging task due to the high dimensionality of the configuration space and the complexity of dynamics affected by various material properties. The effect of complex dynamics is even more pronounced in dynamic folding, for example, when a square piece of fabric is folded in two by a single manipulator. To account for the complexity and uncertainties, feedback of the cloth state using e.g. vision is typically needed. However, construction of visual feedback policies for dynamic cloth folding is an open problem. In this paper, we present a solution that learns policies in simulation using Reinforcement Learning (RL) and transfers the learned policies directly to the real world. In addition, to learn a single policy that manipulates multiple materials, we randomize the material properties in simulation. We evaluate the contributions of visual feedback and material randomization in real-world experiments. The experimental results demonstrate that the proposed solution can fold successfully different fabric types using dynamic manipulation in the real world. Code, data, and videos are available at https://sites.google.com/view/dynamic-cloth-folding <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.04771v3-abstract-full').style.display = 'none'; document.getElementById('2109.04771v3-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> 7 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </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, 7 figures. IROS 2022, accepted version. See https://sites.google.com/view/dynamic-cloth-folding for supplementary material</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.00882">arXiv:2109.00882</a> <span> [<a href="https://arxiv.org/pdf/2109.00882">pdf</a>, <a href="https://arxiv.org/format/2109.00882">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="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</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"> MACRPO: Multi-Agent Cooperative Recurrent Policy Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kargar%2C+E">Eshagh Kargar</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2109.00882v1-abstract-short" style="display: inline;"> This work considers the problem of learning cooperative policies in multi-agent settings with partially observable and non-stationary environments without a communication channel. We focus on improving information sharing between agents and propose a new multi-agent actor-critic method called \textit{Multi-Agent Cooperative Recurrent Proximal Policy Optimization} (MACRPO). We propose two novel way… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.00882v1-abstract-full').style.display = 'inline'; document.getElementById('2109.00882v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.00882v1-abstract-full" style="display: none;"> This work considers the problem of learning cooperative policies in multi-agent settings with partially observable and non-stationary environments without a communication channel. We focus on improving information sharing between agents and propose a new multi-agent actor-critic method called \textit{Multi-Agent Cooperative Recurrent Proximal Policy Optimization} (MACRPO). We propose two novel ways of integrating information across agents and time in MACRPO: First, we use a recurrent layer in critic's network architecture and propose a new framework to use a meta-trajectory to train the recurrent layer. This allows the network to learn the cooperation and dynamics of interactions between agents, and also handle partial observability. Second, we propose a new advantage function that incorporates other agents' rewards and value functions. We evaluate our algorithm on three challenging multi-agent environments with continuous and discrete action spaces, Deepdrive-Zero, Multi-Walker, and Particle environment. We compare the results with several ablations and state-of-the-art multi-agent algorithms such as QMIX and MADDPG and also single-agent methods with shared parameters between agents such as IMPALA and APEX. The results show superior performance against other algorithms. The code is available online at https://github.com/kargarisaac/macrpo. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.00882v1-abstract-full').style.display = 'none'; document.getElementById('2109.00882v1-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 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2107.08898">arXiv:2107.08898</a> <span> [<a href="https://arxiv.org/pdf/2107.08898">pdf</a>, <a href="https://arxiv.org/format/2107.08898">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"> Towards synthesizing grasps for 3D deformable objects with physics-based simulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Le%2C+T+N">Tran Nguyen Le</a>, <a href="/search/cs?searchtype=author&query=Lundell%2C+J">Jens Lundell</a>, <a href="/search/cs?searchtype=author&query=Abu-Dakka%2C+F+J">Fares J. Abu-Dakka</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2107.08898v1-abstract-short" style="display: inline;"> Grasping deformable objects is not well researched due to the complexity in modelling and simulating the dynamic behavior of such objects. However, with the rapid development of physics-based simulators that support soft bodies, the research gap between rigid and deformable objects is getting smaller. To leverage the capability of such simulators and to challenge the assumption that has guided rob… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.08898v1-abstract-full').style.display = 'inline'; document.getElementById('2107.08898v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2107.08898v1-abstract-full" style="display: none;"> Grasping deformable objects is not well researched due to the complexity in modelling and simulating the dynamic behavior of such objects. However, with the rapid development of physics-based simulators that support soft bodies, the research gap between rigid and deformable objects is getting smaller. To leverage the capability of such simulators and to challenge the assumption that has guided robotic grasping research so far, i.e., object rigidity, we proposed a deep-learning based approach that generates stiffness-dependent grasps. Our network is trained on purely synthetic data generated from a physics-based simulator. The same simulator is also used to evaluate the trained network. The results show improvement in terms of grasp ranking and grasp success rate. Furthermore, our network can adapt the grasps based on the stiffness. We are currently validating the proposed approach on a larger test dataset in simulation and on a physical robot. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.08898v1-abstract-full').style.display = 'none'; document.getElementById('2107.08898v1-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 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2021. </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">4 pages, 5 figures. Published at Robotics: Science and Systems (RSS) 2021 Workshop on Deformable Object Simulation (DO-Sim)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.15127">arXiv:2106.15127</a> <span> [<a href="https://arxiv.org/pdf/2106.15127">pdf</a>, <a href="https://arxiv.org/format/2106.15127">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="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Other Statistics">stat.OT</span> </div> </div> <p class="title is-5 mathjax"> Evolving-Graph Gaussian Processes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Blanco-Mulero%2C+D">David Blanco-Mulero</a>, <a href="/search/cs?searchtype=author&query=Heinonen%2C+M">Markus Heinonen</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2106.15127v2-abstract-short" style="display: inline;"> Graph Gaussian Processes (GGPs) provide a data-efficient solution on graph structured domains. Existing approaches have focused on static structures, whereas many real graph data represent a dynamic structure, limiting the applications of GGPs. To overcome this we propose evolving-Graph Gaussian Processes (e-GGPs). The proposed method is capable of learning the transition function of graph vertice… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.15127v2-abstract-full').style.display = 'inline'; document.getElementById('2106.15127v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.15127v2-abstract-full" style="display: none;"> Graph Gaussian Processes (GGPs) provide a data-efficient solution on graph structured domains. Existing approaches have focused on static structures, whereas many real graph data represent a dynamic structure, limiting the applications of GGPs. To overcome this we propose evolving-Graph Gaussian Processes (e-GGPs). The proposed method is capable of learning the transition function of graph vertices over time with a neighbourhood kernel to model the connectivity and interaction changes between vertices. We assess the performance of our method on time-series regression problems where graphs evolve over time. We demonstrate the benefits of e-GGPs over static graph Gaussian Process approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.15127v2-abstract-full').style.display = 'none'; document.getElementById('2106.15127v2-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 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </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, 5 figures. Accepted for publication at ICML 2021 Time Series Workshop (TSW)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2105.11739">arXiv:2105.11739</a> <span> [<a href="https://arxiv.org/pdf/2105.11739">pdf</a>, <a href="https://arxiv.org/format/2105.11739">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Affine Transport for Sim-to-Real Domain Adaptation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mallasto%2C+A">Anton Mallasto</a>, <a href="/search/cs?searchtype=author&query=Arndt%2C+K">Karol Arndt</a>, <a href="/search/cs?searchtype=author&query=Heinonen%2C+M">Markus Heinonen</a>, <a href="/search/cs?searchtype=author&query=Kaski%2C+S">Samuel Kaski</a>, <a href="/search/cs?searchtype=author&query=Kyrki%2C+V">Ville Kyrki</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="2105.11739v1-abstract-short" style="display: inline;"> Sample-efficient domain adaptation is an open problem in robotics. In this paper, we present affine transport -- a variant of optimal transport, which models the mapping between state transition distributions between the source and target domains with an affine transformation. First, we derive the affine transport framework; then, we extend the basic framework with Procrustes alignment to model ar… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.11739v1-abstract-full').style.display = 'inline'; document.getElementById('2105.11739v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2105.11739v1-abstract-full" style="display: none;"> Sample-efficient domain adaptation is an open problem in robotics. In this paper, we present affine transport -- a variant of optimal transport, which models the mapping between state transition distributions between the source and target domains with an affine transformation. First, we derive the affine transport framework; then, we extend the basic framework with Procrustes alignment to model arbitrary affine transformations. We evaluate the method in a number of OpenAI Gym sim-to-sim experiments with simulation environments, as well as on a sim-to-real domain adaptation task of a robot hitting a hockeypuck such that it slides and stops at a target position. In each experiment, we evaluate the results when transferring between each pair of dynamics domains. The results show that affine transport can significantly reduce the model adaptation error in comparison to using the original, non-adapted dynamics model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.11739v1-abstract-full').style.display = 'none'; document.getElementById('2105.11739v1-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2021. </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=Kyrki%2C+V&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Kyrki%2C+V&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Kyrki%2C+V&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </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