AnyDexRT: Calibration-Free Dexterous Hand Retargeting with Few-Shot Human Guidance

• URL: http://arxiv.org/abs/2607.08341v1
• Date: Thu, 09 Jul 2026 10:29:53 GMT
• Title: AnyDexRT: Calibration-Free Dexterous Hand Retargeting with Few-Shot Human Guidance
• Abstract summary: AnyDexRT is a calibration-free method for intuitive dexterous teleoperation across human-like dexterous hands.<n>Experiments show that AnyDexRT improves quality, reduces manual tuning, and provides more intuitive and efficient control than prior methods.
• Score: 52.973947477815614
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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: https://chenxi-wang.github.io/projects/anydexrt

Related papers

• Teleopit: A Full-Embodiment Humanoid Teleoperation System [3.436474641224862]
  We introduce Teleopit, a full-embodiment teleoperation system that maps body, hand, and signals from VR to a humanoid body.<n>A history encoder and failure-aware rewind sampling improve the motion tracker on both motion-capture and live VR references.<n>ACT and GRT N1.7 policies trained on 96 successful demonstrations collected with Teleopit achieve task success rates of 90.0% and 95.0%, respectively.
  arXiv  Detail & Related papers  (2026-08-03T07:45:13Z)
• DexMani: Human-Derived Manipulability Guidance for Dexterous Rotation [7.918622126766639]
  We introduce DexMani, a framework that transfers human demonstrations as contact-conditioned manipulability evolution.<n>We show that DexMani reaches an average success rate of 57.5% on LEAP Hand, outperforming other baselines and producing smoother rotatory motions.
  arXiv  Detail & Related papers  (2026-08-01T09:17:30Z)
• Towards Human-level Dexterous Teleoperation [62.77371751776912]
  Human-level dexterous teleoperation requires precise control of object motion via dynamic hand-object contact.<n>We introduce TeleDexter, a hand-object co-tracking controller that maps operator intent into learned, low-level contact execution.<n>We evaluate TeleDexter on seven challenging dexterous teleoperation tasks spanning object reorientation and long-horizon tool use across two dexterous hands.
  arXiv  Detail & Related papers  (2026-07-13T12:36:47Z)
• Cross-Embodiment Robot Manipulation via a Unified Hand Action Space [5.6990246782356735]
  We propose a sphere-based unified action representation for cross-embodiment dexterous manipulation.<n>Our experiments show that the proposed UHAS representation enables stable dexterous control and cross-embodiment policy transfer across robotic hands.
  arXiv  Detail & Related papers  (2026-07-03T19:19:20Z)
• RealDexUMI: A Wearable Universal Manipulation Interface for Dexterous Robot Learning [21.875676616617838]
  We present RealDexUMI, a wearable universal manipulation interface built around a shared dexterous end-effector module.<n>A palm-side is teleoperation maps human finger inputs to robot-hand commands, enabling real-time, glove-free, intuitive, and precise hand control.
  arXiv  Detail & Related papers  (2026-06-04T11:28:23Z)
• DexImit: Learning Bimanual Dexterous Manipulation from Monocular Human Videos [56.64773686434068]
  We propose DexImit, an automated framework that converts human manipulation videos into physically plausible robot data.<n>DexImit can generate large-scale robot data based on human videos, either from the Internet or video generation models.<n>It is capable of handling diverse manipulation tasks, including tool use, long-horizon tasks, and fine-grained manipulations.
  arXiv  Detail & Related papers  (2026-02-10T18:59:02Z)
• ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning [24.675197489823898]
  We introduce ManipTrans, a novel method for transferring human bimanual skills to dexterous robotic hands in simulation.<n>Experiments show that ManipTrans surpasses state-of-the-art methods in success rate, fidelity, and efficiency.<n>We also create DexManipNet, a large-scale dataset featuring previously unexplored tasks like pen capping and bottle unscrewing.
  arXiv  Detail & Related papers  (2025-03-27T17:50:30Z)
• AnyDexGrasp: General Dexterous Grasping for Different Hands with Human-level Learning Efficiency [49.868970174484204]
  We introduce an efficient approach for learning dexterous grasping with minimal data.<n>Our method achieves high performance with human-level learning efficiency: only hundreds of grasp attempts on 40 training objects.<n>This method demonstrates promising applications for humanoid robots, prosthetics, and other domains requiring robust, versatile robotic manipulation.
  arXiv  Detail & Related papers  (2025-02-23T03:26:06Z)
• Cross-Embodiment Dexterous Grasping with Reinforcement Learning [29.867524903691802]
  Dexterous hands exhibit significant potential for complex real-world grasping tasks. We study the learning of cross-embodiment dexterous grasping policies using reinforcement learning. Our approach demonstrates an 80% success rate in grasping objects from the YCB dataset.
  arXiv  Detail & Related papers  (2024-10-03T13:36:02Z)
• RealDex: Towards Human-like Grasping for Robotic Dexterous Hand [64.33746404551343]
  We introduce RealDex, a pioneering dataset capturing authentic dexterous hand grasping motions infused with human behavioral patterns.<n>RealDex holds immense promise in advancing humanoid robot for automated perception, cognition, and manipulation in real-world scenarios.
  arXiv  Detail & Related papers  (2024-02-21T14:59:46Z)
• DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video [86.49357517864937]
  We propose DexVIP, an approach to learn dexterous robotic grasping from human-object interaction videos. We do this by curating grasp images from human-object interaction videos and imposing a prior over the agent's hand pose. We demonstrate that DexVIP compares favorably to existing approaches that lack a hand pose prior or rely on specialized tele-operation equipment.
  arXiv  Detail & Related papers  (2022-02-01T00:45:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.