SMAP: Self-supervised Motion Adaptation for Physically Plausible Humanoid Whole-body Control

TL;DR

This paper introduces SMAP, a framework that uses self-supervised learning and a vector-quantized autoencoder to enable humanoid robots to mimic human motion accurately and stably, improving training efficiency and handling challenging motions.

Contribution

SMAP bridges the gap between human and humanoid action spaces using a vector-quantized autoencoder, enhancing motion mimicry and stability in humanoid control.

Findings

SMAP accelerates training convergence.

SMAP improves stability over state-of-the-art methods.

SMAP demonstrates effective real-world humanoid motion control.

Abstract

This paper presents a novel framework that enables real-world humanoid robots to maintain stability while performing human-like motion. Current methods train a policy which allows humanoid robots to follow human body using the massive retargeted human data via reinforcement learning. However, due to the heterogeneity between human and humanoid robot motion, directly using retargeted human motion reduces training efficiency and stability. To this end, we introduce SMAP, a novel whole-body tracking framework that bridges the gap between human and humanoid action spaces, enabling accurate motion mimicry by humanoid robots. The core idea is to use a vector-quantized periodic autoencoder to capture generic atomic behaviors and adapt human motion into physically plausible humanoid motion. This adaptation accelerates training convergence and improves stability when handling novel or challenging motions. We then employ a privileged teacher to distill precise mimicry skills into the student policy with a proposed decoupled reward. We conduct experiments in simulation and real world to demonstrate the superiority stability and performance of SMAP over SOTA methods, offering practical guidelines for advancing whole-body control in humanoid robots.