Implicit Kinodynamic Motion Retargeting for Human-to-humanoid Imitation Learning
This addresses the scalability issue in human-to-humanoid imitation learning for robotics, though it appears incremental as it builds on existing retargeting methods by integrating kinematics and dynamics.
The paper tackles the problem of efficiently converting large-scale human motion into robot-executable trajectories for humanoid imitation learning, proposing Implicit Kinodynamic Motion Retargeting (IKMR) to achieve real-time, physically feasible motion retargeting validated in simulation and on a real robot.
Human-to-humanoid imitation learning aims to learn a humanoid whole-body controller from human motion. Motion retargeting is a crucial step in enabling robots to acquire reference trajectories when exploring locomotion skills. However, current methods focus on motion retargeting frame by frame, which lacks scalability. Could we directly convert large-scale human motion into robot-executable motion through a more efficient approach? To address this issue, we propose Implicit Kinodynamic Motion Retargeting (IKMR), a novel efficient and scalable retargeting framework that considers both kinematics and dynamics. In kinematics, IKMR pretrains motion topology feature representation and a dual encoder-decoder architecture to learn a motion domain mapping. In dynamics, IKMR integrates imitation learning with the motion retargeting network to refine motion into physically feasible trajectories. After fine-tuning using the tracking results, IKMR can achieve large-scale physically feasible motion retargeting in real time, and a whole-body controller could be directly trained and deployed for tracking its retargeted trajectories. We conduct our experiments both in the simulator and the real robot on a full-size humanoid robot. Extensive experiments and evaluation results verify the effectiveness of our proposed framework.