Problem
Research questions and friction points this paper is trying to address.
Dexterous Manipulation
Retargeting
Embodiment Gap
Force-aware
Human-to-Robot Transfer
ReForce: Learning Force-aware Retargeting for Dexterous Manipulation
🤖 AI Summary
This study addresses force interaction misalignment caused by embodiment discrepancies in dexterous manipulation retargeting by proposing a force-aware retargeting framework. The method integrates force feedback into motion transfer, reproducing human contact forces through kinematic residual prediction and leveraging large-scale simulation to train a universal force tracker that supports both online teleoperation and offline data conversion. Experimental results demonstrate that this framework effectively bridges the human-robot embodiment gap, significantly reducing force tracking errors in both simulated and real-world contact-rich tasks. Consequently, it achieves precise force control and robust multi-finger contact, thereby enhancing transfer performance for complex manipulation tasks.
📝 Abstract
Human demonstrations offer a scalable data source for dexterous manipulation, but transferring them to robot actions remains challenging due to the embodiment gap. Today's retargeting is mostly kinematic, yet manipulation is decided by force, which governs how the hand interacts with the object and how the object moves. In this paper, we present ReForce, a Force-aware Retargeting method that turns human motion and forces into robot actions that reproduce the intended contact. ReForce predicts a residual on the kinematically retargeted action to reach the desired force, using a general force tracker trained on large-scale simulation interactions. It supports both online force-aware teleoperation and offline data translation. In simulation and on real hardware, ReForce achieves lower force-tracking error and stronger multi-finger contact engagement on contact-rich tasks such as paper-cup grasping and tongs manipulation.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Force-aware Retargeting
Residual Force Prediction
General Force Tracker
Dexterous Manipulation
Embodiment Gap
🔎 Similar Papers
No similar papers found.
