EaDex: A Cross-Embodiment Dexterous Manipulation Framework from Low-Cost Demonstrations
2026-06-02 • Robotics
Robotics
AI summaryⓘ
The authors propose EaDex, a method to teach robot hands to perform tricky tasks using cheaper and easier-to-get demonstration data. They capture real human hand movements with a simple camera and convert those into usable training data for robots. Their learning approach gradually shifts from following demonstrations to learning on its own using feedback from contact points during manipulation. Tested on different robot hands and tasks, EaDex showed a noticeable improvement compared to methods without this gradual learning strategy. This shows their approach helps robots learn dexterous tasks more efficiently with fewer costly demonstrations.
dexterous manipulationreinforcement learningimitation learningMANO hand modelRGB-D cameradata normalizationmotion retargetingdemonstration annealingcontact reward
Authors
Qian Zhao, Xin Tong, Chengdong Wu, Yang Yang, Yingtian Li
Abstract
Dexterous manipulation learning has long been hindered by the high costs of data and training, as pure reinforcement learning typically requires large-scale interactive exploration and imitation learning depends on high-quality demonstrations that are expensive to collect. To address this problem, we propose EaDex, a multi-embodiment dexterous manipulation learning framework under low-cost demonstration conditions, which enables rapid generation of demonstration data and consequently reduces training time for efficient dexterous manipulation. At the data level, EaDex captures human hand motions using only a single RGB-D camera and constructs structured demonstration data through MANO-based hand modeling, data normalization, and motion retargeting. At the learning level, we introduce a contact-reward-based dynamic demonstration annealing mechanism, which guides early-stage exploration under demonstration and gradually transitions to autonomous optimization with accumulating contact rewards. Using our custom dataset, we evaluate EaDex on three dexterous hands and three articulated object-opening tasks, covering nine cross-embodiment manipulation settings, achieving a 55.3% relative improvement over the baseline without demonstration annealing. These results validate the effectiveness of the proposed low-cost demonstration pipeline and the dynamic demonstration annealing strategy for dexterous manipulation learning.