[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85079-en":3,"doc-seo-85079-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85079,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","AnyDexRT Calibration-Free Dexterous Hand Retargeting with Few-Shot Human Guidance","Teleoperation enables dexterous robotic hands to collect demonstrations for imitation learning, but its performance depends on kinematic retargeting that maps operator motions to feasible, intuitive robot motions. Prior approaches often require hand-crafted objectives, precise calibration, or global shape matching, limiting reliability across different robot hands. AnyDexRT introduces a calibration-free retargeting method using self-supervised fingertip correspondence learning, few-shot human guidance for task-relevant anchoring, and a contact classifier to refine pinch poses, improving quality and reducing tuning.","AnyDexRT: Calibration-Free Dexterous Hand Retargeting with Few-Shot Human Guidance  \nChenxi Wang∗, 1 Ying Feng∗,2,3 Hongjie Fang2,† Shangning Xia 1 Lixin Yang2 Chuan Wen2 Cewu Lu 1,2,3,†  \n1Noematrix 2 Shanghai Jiao Tong University 3 Shanghai Innovation Institute  \n∗ Equal Contribution †Corresponding Authors  \narXiv :2607 .0834 1v 1 [ cs .RO] 9 Jul 2026  \n…  \n+  \nRobot Retargeted  \nSpace Space  \nFew-Shot Human Guidance  \nFor Any Human-Like Hands  \n6 DoF   \n16 DoF  \n7 DoF 11 DoF   \n20 DoF   \n……  \n……  \nAnyDexRT  \nHigh-Quality Retargeting  \nFigure 1: AnyDexRT System. AnyDexRT is a calibration-free dexterous hand retargeting system. With fewshot human guidance, our system achieves high-quality retargeting across diverse human-like hands.  \nAbstract: Teleoperation is a key interface for controlling dexterous robotic hands and collecting demonstrations for imitation learning. Its effectiveness largely depends on kinematic retargeting, which maps operator hand motions to feasible and intuitive robot hand motions. Existing methods often require hand-crafted objectives, precise calibration, or global shape matching between human and robot hand spaces, making them sensitive to hand-specific tuning and less reliable across different dexterous hands. We propose AnyDexRT, a calibration-free retargeting method for intuitive dexterous teleoperation across human-like dexterous hands. AnyDexRT combines self-supervised fingertip correspondence learning with few-shot human guidance to anchor the mapping in task-relevant regions, and further refines pinch-related poses using a contact classifier. Experiments on diverse dexterous hands and real-world teleoperation tasks show that AnyDexRT improves retargeting quality, reduces manual tuning, and provides more intuitive and efficient control than prior retargeting methods. Project website:  \n[https://chenxi-wang.github.io/projects/anydexrt](https://chenxi-wang.github.io/projects/anydexrt).  \nKeywords: Dexterous Hand Retargeting, Teleoperation, Dexterous Manipulation  \n1 Introduction  \nDexterous manipulation is a key capability for general-purpose robots, enabling rich and adaptive physical interactions with objects and environments [2, 14, 30] . Compared with grippers, dexterous hands provide greater kinematic expressiveness and contact versatility, supporting diverse grasping [13, 53], in-hand object reorientation [5, 6], and contact-rich behaviors [22, 44] in unstructured environments. However, the same expressiveness that makes dexterous hands powerful also makes them difficult to control. Their high-dimensional action spaces, joint couplings, and contact dynamics make it challenging to manually design effective hand motions. Teleoperation provides a natural interface for accessing human dexterity, where an operator controls a robotic hand through their own  \nhand motions while observing the robot’s response in real time [33, 43, 55] . In this process, retargeting translates operator hand kinematics into feasible and intuitive robot hand motions. The resulting teleoperated interactions can further serve as high-quality demonstrations for imitation learning [21, 48, 57], making retargeting important for both real-time control and data-driven robot learning.  \nAs this interface, retargeting should not be reduced to direct pose matching between human and robot hands. Because the operator and robot hands may differ in scale, motion range, joint coupling, and feasible configurations [29, 51], a natural operator motion may not directly correspond to a natural robot motion. A practical retargeting algorithm should therefore satisfy three requirements:  \n(R1) Intuitiveness. It should preserve the operator’s motion intent and produce feasible, predictable robot motions that are easy to control.  \n(R2) Calibration Efficiency. It should reduce dependence on precise calibration or manually tuned hyperparameters such as scale factors, offsets, and task weights.  \n(R3) Generality. The same operator hand space ","cbCaiovBAEs9pNsX","https://ap.wps.com/l/cbCaiovBAEs9pNsX","pdf",12564570,3,1,14,"English","en",105,"# Introduction\n# Related Works\n## Kinematic Retargeting for Dexterous Hands","[{\"question\":\"What problem does AnyDexRT address in dexterous hand teleoperation?\",\"answer\":\"It addresses the challenge of mapping operator hand motions to feasible and intuitive robot hand motions without heavy calibration or hand-specific tuning.\"},{\"question\":\"How does AnyDexRT achieve calibration-free retargeting?\",\"answer\":\"It learns fingertip-level correspondence with self-supervised shape matching, uses few-shot human guidance to anchor mappings in task-relevant regions, and refines pinch-related poses with a contact classifier.\"},{\"question\":\"What benefits does AnyDexRT show over previous retargeting methods?\",\"answer\":\"Experiments report improved retargeting quality, reduced manual tuning effort, and more intuitive and efficient control across diverse dexterous hands and real-world teleoperation tasks.\"}]",1784200912,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"anydexrt-calibration-free-dexterous-hand-retargeting-with-few-shot-human-guidance","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/anydexrt-calibration-free-dexterous-hand-retargeting-with-few-shot-human-guidance/85079/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does AnyDexRT address in dexterous hand teleoperation?","Question",{"text":75,"@type":76},"It addresses the challenge of mapping operator hand motions to feasible and intuitive robot hand motions without heavy calibration or hand-specific tuning.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does AnyDexRT achieve calibration-free retargeting?",{"text":80,"@type":76},"It learns fingertip-level correspondence with self-supervised shape matching, uses few-shot human guidance to anchor mappings in task-relevant regions, and refines pinch-related poses with a contact classifier.",{"name":82,"@type":73,"acceptedAnswer":83},"What benefits does AnyDexRT show over previous retargeting methods?",{"text":84,"@type":76},"Experiments report improved retargeting quality, reduced manual tuning effort, and more intuitive and efficient control across diverse dexterous hands and real-world teleoperation tasks.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]