AnyDexRT: Calibration-Efficient Dexterous Hand Retargeting with Few-Shot Human Guidance
AnyDexRT: Calibration-Efficient Dexterous Hand Retargeting with Few-Shot Human Guidance
This research presents AnyDexRT, a novel approach for calibrating dexterous robotic hands that leverages self-supervised learning and minimal human guidance to map operator motions to robot actions. By focusing on task-relevant regions and refining pinch poses via a contact classifier, the method aims to enhance teleoperation intuitiveness and efficiency across diverse hand models without extensive manual tuning.
The paper introduces AnyDexRT, a method that combines self-supervised fingertip correspondence learning with few-shot human guidance to improve kinematic retargeting for dexterous robotic hands, reducing reliance on precise calibration and global shape matching.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- TeleoperatedOpen source S2
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2607.08341v2 Announce Type: replace 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
Open source S2
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-efficient 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
Open source S3
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
Open source S4
AnyDexRT: Calibration-Efficient Dexterous Hand Retargeting with Few-Shot Human Guidance
Open source S1
Source：arXiv Robotics — research abstracts · arxiv.org