Task-Oriented Hand Motion Retargeting for Dexterous Manipulation Imitation
This work addresses the challenge of imitating complex human hand manipulations for robotics, though it is incremental as it builds on existing retargeting and imitation learning methods.
The paper tackled the problem of retargeting human hand poses to a dexterous hand model for imitation learning, achieving a better success rate in grasping tasks compared to an inverse kinematics baseline, which enabled recording successful human demonstrations and learning an autonomous grasping policy.
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.