| CARVIEW |
ImDy: Human Inverse Dynamics from Imitated Observations
ICLR 2025
*Corresponding authors.
Abstract
Inverse dynamics (ID), which aims at reproducing the driven torques from human kinematic observations, has been a critical tool for gait analysis. However, it is hindered from wider application to general motion due to its limited scalability. Conventional optimization-based ID requires expensive laboratory setups, restricting its availability. To alleviate this problem, we propose to exploit the recently progressive human motion imitation algorithms to learn human inverse dynamics in a data-driven manner. The key insight is that the human ID knowledge is implicitly possessed by motion imitators, though not directly applicable. In light of this, we devise an efficient data collection pipeline with state-of-the-art motion imitation algorithms and physics simulators, resulting in a large-scale human inverse dynamics benchmark as Imitated Dynamics (ImDy). ImDy contains over 150 hours of motion with joint torque and full-body ground reaction force data. With ImDy, we train a data-driven human inverse dynamics solver ImDyS(olver) in a fully supervised manner, which conducts ID and ground reaction force estimation simultaneously. Experiments on ImDy and real-world data demonstrate the impressive competency of ImDyS in human inverse dynamics and ground reaction force estimation. Moreover, the potential of ImDy(-S) as a fundamental motion analysis tool is exhibited with downstream applications.
ImDy pairs diverse SMPL motion data with dynamics including full-body torques and ground reaction forces (GRF) like the right knee GRF for kneeling, which could be hard to achieve under conventional laboratory setups.
ImDy construction. We first train a motion imitation policy following Luo et al. (2023). Then, the policy is adopted to imitate arbitrary motions, with the imitated states recorded as ImDy.
ImDy compared to related human dynamics datasets. Zell et al. (2020) recorded full-body data but simplified the upper body with a single torso segment. All previous efforts contain only GRF for feet (indicated with *), while we include full body GRF.
ImDyS overview. Taking a motion transition, ImDyS predicts the internal dynamics and ground reaction forces. Moreover, a prior discriminator is trained with the feature from ImDyS. A two-stage sim2real training curriculum is further designed.
Results
Paper
BibTeX
@inproceedings{
liu2025imdy,
title={ImDy: Human Inverse Dynamics from Imitated Observations},
author={Xinpeng Liu and Junxuan Liang and Zili Lin and Haowen Hou and Yong-Lu Li and Cewu Lu},
booktitle={The Thirteenth International Conference on Learning Representations},
year={2025},
url={https://openreview.net/forum?id=br8YB7KMug}
}