Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration

Zhu, Xinghao, Liu, Zixi, Jain, Shalin, Li, Chenran, Noori, Milad, Lin, Michael Andres, Zhao, Huihua, Welsh, John, Verghese, Mrinal, Liu, Wei, Wang, Tingwu, Da, Xingye, Luo, Zhengyi, Kulkarni, Vishal, Bhatti, Naema, Zhu, Yuke, Fan, Linxi, Wen, Bowen, Xu, Danfei, Pouya, Soha, Chang, Yan · N/A · 2026

Summary

Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging.

Abstract Summary

Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging. We present Contact Wrench Guidance from Human Demonstration in Robotic Dexterous Manipulation (CHORD), a framework for long-horizon manipulation of rigid and articulated objects with reinforcement learning. The key idea is object-centric contact wrench space guidance: we represent human and robot motions by the forces and torques they can induce on the object, enabling similarity to be measured by the induced instantaneous motions. This guidance makes reinforcement learning more scalable for contact-rich dexterous manipulation. We further introduce a large-scale simulation benchmark with 4,739 bimanual dexterous manipulation tasks, constructed from motion-capture datasets and reconstructed in-house videos. Evaluated on 1,831 benchmark tasks, CHORD achieves an average success rate of 82.12%, demonstrating strong scalability. CHORD also generalizes to whole-body manipulation from hand-only and third-person demonstrations, achieving a 90.77% success rate, and the learned policies transfer to the real world in both open-loop and closed-loop settings.

Key Points

Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging.
We present Contact Wrench Guidance from Human Demonstration in Robotic Dexterous Manipulation (CHORD), a framework for long-horizon manipulation of rigid and articulated objects with reinforcement learning.
The key idea is object-centric contact wrench space guidance: we represent human and robot motions by the forces and torques they can induce on the object, enabling similarity to be measured by the induced instantaneous motions.
This guidance makes reinforcement learning more scalable for contact-rich dexterous manipulation
We further introduce a large-scale simulation benchmark with 4,739 bimanual dexterous manipulation tasks, constructed from motion-capture datasets and reconstructed in-house videos.

Method

Our goal is to learn long-horizon manipulation of rigid and articulated objects from human demonstrations. We consider objects with $K$ rigid bodies, either as $K$ separate rigid objects or as an articulated object with $K$ parts.

Experiments

We conduct experiments to evaluate the scalability of CHORD on large-scale tasks and compare it against baseline methods ( Section 4.1 ). We then analyze the proposed contact-wrench reward, showing its advantages over prior objectives ( Section 4.2 ), its correlation with manipulation success ( Section 4.3 ), and its utility in learning long-horizon dexterous tasks ( Section 4.4 ).

Next, we demonstrate the generalizability of CHORD to whole-body manipulation ( Section 4.5 ) and real-world deployment ( Section 4.6 ).

Experiments — Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration — Figure from the paper. Source: Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration.

Sources and Demonstrations

Figures are reproduced from Zhu et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.