Task-Oriented Hand Motion Retargeting for Dexterous Manipulation Imitation

TL;DR

This paper presents a method for retargeting human hand actions to a dexterous hand model for manipulation tasks, combining pose estimation, inverse kinematics, and imitation learning to improve grasping success.

Contribution

It introduces a task-oriented retargeting approach that integrates inverse kinematics and optimization, enabling effective imitation of complex hand manipulation actions.

Findings

Improved grasping success rate over baseline methods.

Effective demonstration recording for policy learning.

Autonomous grasping in virtual environment achieved.

Abstract

Human hand actions are quite complex, especially when they involve object manipulation, mainly due to the high dimensionality of the hand and the vast action space that entails. Imitating those actions with dexterous hand models involves different important and challenging steps: acquiring human hand information, retargeting it to a hand model, and learning a policy from acquired data. In this work, we capture the hand information by using a state-of-the-art hand pose estimator. We tackle the retargeting problem from the hand pose to a 29 DoF hand model by combining inverse kinematics and PSO with a task objective optimisation. This objective encourages the virtual hand to accomplish the manipulation task, relieving the effect of the estimator's noise and the domain gap. Our approach leads to a better success rate in the grasping task compared to our inverse kinematics baseline, allowing us to record successful human demonstrations. Furthermore, we used these demonstrations to learn a policy network using generative adversarial imitation learning (GAIL) that is able to autonomously grasp an object in the virtual space.