{"id":2162,"date":"2025-09-23T22:59:08","date_gmt":"2025-09-23T14:59:08","guid":{"rendered":"https:\/\/bionicdl.ancorasir.com\/?p=2162"},"modified":"2025-09-24T00:12:18","modified_gmt":"2025-09-23T16:12:18","slug":"magiclaw-a-dual-use-vision-based-soft-gripper-for-bridging-the-human-demonstration-to-robotic-deployment-gap","status":"publish","type":"post","link":"https:\/\/bionicdl.ancorasir.com\/?p=2162","title":{"rendered":"MagiClaw: A Dual-Use, Vision-Based Soft Gripper for Bridging the Human Demonstration to Robotic Deployment Gap"},"content":{"rendered":"\n<figure class=\"wp-block-image size-large is-resized\"><img data-recalc-dims=\"1\" decoding=\"async\" src=\"https:\/\/i0.wp.com\/bionicdl.ancorasir.com\/wp-content\/uploads\/2025\/09\/2025-W-CoRL-MagiClaw-S2.gif?ssl=1\" alt=\"\" style=\"width:1100px;height:auto\"\/><\/figure>\n\n\n\n<ul class=\"wp-block-list\">\n<li class=\"\"><strong>Full Documentation @ <a href=\"https:\/\/magiclaw.gitbook.io\/magiclaw-docs\/documentation\">THIS LINK<\/a><\/strong><\/li>\n\n\n\n<li class=\"\"><strong>iOS App Available for Free Download @ <a href=\"https:\/\/apps.apple.com\/cn\/app\/magiclaw\/id6661033548\">THIS LINK<\/a><\/strong><\/li>\n\n\n\n<li class=\"\"><strong>Feel Free to Contact Us if You&#8217;re Interested in Acquiring a Full Set of the MagiClaw Toolkit.<\/strong><\/li>\n<\/ul>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><img data-recalc-dims=\"1\" decoding=\"async\" src=\"https:\/\/i0.wp.com\/bionicdl.ancorasir.com\/wp-content\/uploads\/2025\/09\/2025-W-CoRL-MagiClaw-SummaryFigure-scaled.png?ssl=1\" alt=\"\"\/><\/figure>\n<\/div>\n\n\n<hr class=\"\\&quot;\\\\\\\\\\\\&quot;wp-block-separator wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n<div class=\"tp_single_publication\"><span class=\"tp_single_author\">Tianyu Wu, Xudong Han, Haoran Sun, Zishang Zhang, Bangchao Huang, Chaoyang Song, Fang Wan: <\/span> <span class=\"tp_single_title\">MagiClaw: A Dual-Use, Vision-Based Soft Gripper for Bridging the Human Demonstration to Robotic Deployment Gap<\/span>. <span class=\"tp_single_additional\"><span class=\"tp_pub_additional_year\">2025<\/span><span class=\"tp_pub_additional_note\">, (Short Paper accepted to CoRL 2025 Data Workshop on Making Sense of Data in Robotics: Composition, Curation, and Interpretability at Scale &amp; Demo Presentation at CoRL 2025)<\/span>.<\/span><\/div>\n\n\n\n<hr class=\"\\&quot;\\\\\\\\\\\\&quot;wp-block-separator wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<figure class=\"wp-block-video aligncenter\"><video autoplay controls loop muted src=\"https:\/\/bionicdl.ancorasir.com\/wp-content\/uploads\/2025\/09\/2025-W-CoRL-MagiClaw.mp4\"><\/video><\/figure>\n\n\n<h2 class=\"tp_abstract\">Abstract<\/h2><p class=\"tp_abstract\">The transfer of manipulation skills from human demonstration to robotic execution is often hindered by a &quot;domain gap&quot; in sensing and morphology. This paper introduces MagiClaw, a versatile two-finger end-effector designed to bridge this gap. MagiClaw functions interchangeably as both a handheld tool for intuitive data collection and a robotic end-effector for policy deployment, ensuring hardware consistency and reliability. Each finger incorporates a Soft Polyhedral Network (SPN) with an embedded camera, enabling vision-based estimation of 6-DoF forces and contact deformation. This proprioceptive data is fused with exteroceptive environmental sensing from an integrated iPhone, which provides 6D pose, RGB video, and LiDAR-based depth maps. Through a custom iOS application, MagiClaw streams synchronized, multi-modal data for real-time teleoperation, offline policy learning, and immersive control via mixed-reality interfaces. We demonstrate how this unified system architecture lowers the barrier to collecting high-fidelity, contact-rich datasets and accelerates the development of generalizable manipulation policies. Please refer to the iOS app at https:\/\/apps.apple.com\/cn\/app\/magiclaw\/id6661033548 for further details.<\/p>\n\n\n<h2 class=\"tp_links\">Links<\/h2><p class=\"tp_abstract\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-doi\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/dx.doi.org\/10.48550\/arXiv.2509.19169\" title=\"Follow DOI:10.48550\/arXiv.2509.19169\" target=\"_blank\">doi:10.48550\/arXiv.2509.19169<\/a><\/li><\/ul><\/p>\n\n\n<h2 class=\"tp_bibtex\">BibTeX (<a href=\"https:\/\/bionicdl.ancorasir.com?feed=tp_pub_bibtex&amp;key=Wu2025MagiClaw\">Download<\/a>)<\/h2><pre class=\"tp_bibtex\">@workshop{Wu2025MagiClaw,\r\ntitle = {MagiClaw: A Dual-Use, Vision-Based Soft Gripper for Bridging the Human Demonstration to Robotic Deployment Gap},\r\nauthor = {Tianyu Wu and Xudong Han and Haoran Sun and Zishang Zhang and Bangchao Huang and Chaoyang Song and Fang Wan},\r\ndoi = {10.48550\/arXiv.2509.19169},\r\nyear  = {2025},\r\ndate = {2025-09-28},\r\nurldate = {2025-09-28},\r\nabstract = {The transfer of manipulation skills from human demonstration to robotic execution is often hindered by a \"domain gap\" in sensing and morphology. This paper introduces MagiClaw, a versatile two-finger end-effector designed to bridge this gap. MagiClaw functions interchangeably as both a handheld tool for intuitive data collection and a robotic end-effector for policy deployment, ensuring hardware consistency and reliability. Each finger incorporates a Soft Polyhedral Network (SPN) with an embedded camera, enabling vision-based estimation of 6-DoF forces and contact deformation. This proprioceptive data is fused with exteroceptive environmental sensing from an integrated iPhone, which provides 6D pose, RGB video, and LiDAR-based depth maps. Through a custom iOS application, MagiClaw streams synchronized, multi-modal data for real-time teleoperation, offline policy learning, and immersive control via mixed-reality interfaces. We demonstrate how this unified system architecture lowers the barrier to collecting high-fidelity, contact-rich datasets and accelerates the development of generalizable manipulation policies. Please refer to the iOS app at https:\/\/apps.apple.com\/cn\/app\/magiclaw\/id6661033548 for further details.},\r\nnote = {Short Paper accepted to CoRL 2025 Data Workshop on Making Sense of Data in Robotics: Composition, Curation, and Interpretability at Scale & Demo Presentation at CoRL 2025},\r\nkeywords = {Abstract - Extended Abstract, Authorship - Co-Author, Conf - CoRL, Special - Workshop},\r\npubstate = {published},\r\ntppubtype = {workshop}\r\n}\r\n<\/pre>\n\n\n\n<div class=\"wp-block-embedpress-embedpress-pdf aligncenter\"><div class=\"embedpress-document-embed ep-doc-embedpress-pdf-1758642364559   ep-percentage-width\" style=\"width:600%;max-width:100%\" id=\"ep-doc-c2797022-2cd1-42d6-85b6-515cc8aedc91\" data-source-id=\"source-c2797022-2cd1-42d6-85b6-515cc8aedc91\" data-embed-type=\"PDF\"><div class=\"ep-embed-content-wraper\"><div class=\"position-right-wraper gutenberg-pdf-wraper\"><div class=\"main-content-wraper\"><iframe title=\"\" style=\"height:1000px;width:100%\" class=\"embedpress-embed-document-pdf embedpress-pdf-1758642364559\" data-emid=\"embedpress-pdf-1758642364559\" src=\"https:\/\/bionicdl.ancorasir.com\/wp-admin\/admin-ajax.php?action=get_viewer&amp;scrolling=0&amp;selection_tool=0&amp;spreads=0&amp;file=https%3A%2F%2Fbionicdl.ancorasir.com%2Fwp-content%2Fuploads%2F2025%2F09%2F2025-W-CoRL-MagiClaw-ArXivVersion.pdf#key=dGhlbWVNb2RlPWRlZmF1bHQmcHJlc2VudGF0aW9uPXRydWUmbGF6eUxvYWQ9ZmFsc2UmcG9zaXRpb249dG9wJmZsaXBib29rX3Rvb2xiYXJfcG9zaXRpb249Ym90dG9tJmRvd25sb2FkPXRydWUmdG9vbGJhcj10cnVlJmNvcHlfdGV4dD10cnVlJmFkZF90ZXh0PXRydWUmZHJhdz10cnVlJmRvY19kZXRhaWxzPWZhbHNlJmRvY19yb3RhdGlvbj10cnVlJmFkZF9pbWFnZT10cnVlJnpvb21faW49dHJ1ZSZ6b29tX291dD10cnVlJmZpdF92aWV3PXRydWUmYm9va21hcms9dHJ1ZSZzZWxlY3Rpb25fdG9vbD0wJnNjcm9sbGluZz0wJnNwcmVhZHM9MA==\"><\/iframe><\/div><\/div><\/div><\/div><\/div>\n\n\n\n<p class=\"\"><\/p>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"nf_dc_page":"","_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[10],"tags":[27,99],"post_folder":[],"class_list":["post-2162","post","type-post","status-publish","format-standard","hentry","category-publications","tag-co-author","tag-workshop"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/bionicdl.ancorasir.com\/index.php?rest_route=\/wp\/v2\/posts\/2162","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/bionicdl.ancorasir.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/bionicdl.ancorasir.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/bionicdl.ancorasir.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/bionicdl.ancorasir.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2162"}],"version-history":[{"count":5,"href":"https:\/\/bionicdl.ancorasir.com\/index.php?rest_route=\/wp\/v2\/posts\/2162\/revisions"}],"predecessor-version":[{"id":2172,"href":"https:\/\/bionicdl.ancorasir.com\/index.php?rest_route=\/wp\/v2\/posts\/2162\/revisions\/2172"}],"wp:attachment":[{"href":"https:\/\/bionicdl.ancorasir.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2162"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/bionicdl.ancorasir.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2162"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/bionicdl.ancorasir.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2162"},{"taxonomy":"post_folder","embeddable":true,"href":"https:\/\/bionicdl.ancorasir.com\/index.php?rest_route=%2Fwp%2Fv2%2Fpost_folder&post=2162"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}