Bi-Level Motion Imitation for Humanoid Robots

TL;DR

This paper introduces a bi-level optimization framework for humanoid robot imitation learning that refines human motion data to be physically feasible, improving robot policy performance.

Contribution

It proposes a novel bi-level optimization approach combined with a self-consistent auto-encoder to generate physically consistent reference motions for humanoid robots.

Findings

Enhanced robot policy performance in simulations

Generated reference motions are physically feasible

Improved imitation accuracy

Abstract

Imitation learning from human motion capture (MoCap) data provides a promising way to train humanoid robots. However, due to differences in morphology, such as varying degrees of joint freedom and force limits, exact replication of human behaviors may not be feasible for humanoid robots. Consequently, incorporating physically infeasible MoCap data in training datasets can adversely affect the performance of the robot policy. To address this issue, we propose a bi-level optimization-based imitation learning framework that alternates between optimizing both the robot policy and the target MoCap data. Specifically, we first develop a generative latent dynamics model using a novel self-consistent auto-encoder, which learns sparse and structured motion representations while capturing desired motion patterns in the dataset. The dynamics model is then utilized to generate reference motions while the latent representation regularizes the bi-level motion imitation process. Simulations conducted with a realistic model of a humanoid robot demonstrate that our method enhances the robot policy by modifying reference motions to be physically consistent.