RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yue, Junpeng, Wang, Zepeng, Wang, Yuxuan, Zeng, Weishuai, Wang, Jiangxing, Xu, Xinrun, Zhang, Yu, Zheng, Sipeng, Ding, Ziluo, Lu, Zongqing
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908408568872960
author Yue, Junpeng
Wang, Zepeng
Wang, Yuxuan
Zeng, Weishuai
Wang, Jiangxing
Xu, Xinrun
Zhang, Yu
Zheng, Sipeng
Ding, Ziluo
Lu, Zongqing
author_facet Yue, Junpeng
Wang, Zepeng
Wang, Yuxuan
Zeng, Weishuai
Wang, Jiangxing
Xu, Xinrun
Zhang, Yu
Zheng, Sipeng
Ding, Ziluo
Lu, Zongqing
contents This paper focuses on a critical challenge in robotics: translating text-driven human motions into executable actions for humanoid robots, enabling efficient and cost-effective learning of new behaviors. While existing text-to-motion generation methods achieve semantic alignment between language and motion, they often produce kinematically or physically infeasible motions unsuitable for real-world deployment. To bridge this sim-to-real gap, we propose Reinforcement Learning from Physical Feedback (RLPF), a novel framework that integrates physics-aware motion evaluation with text-conditioned motion generation. RLPF employs a motion tracking policy to assess feasibility in a physics simulator, generating rewards for fine-tuning the motion generator. Furthermore, RLPF introduces an alignment verification module to preserve semantic fidelity to text instructions. This joint optimization ensures both physical plausibility and instruction alignment. Extensive experiments show that RLPF greatly outperforms baseline methods in generating physically feasible motions while maintaining semantic correspondence with text instruction, enabling successful deployment on real humanoid robots.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12769
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control
Yue, Junpeng
Wang, Zepeng
Wang, Yuxuan
Zeng, Weishuai
Wang, Jiangxing
Xu, Xinrun
Zhang, Yu
Zheng, Sipeng
Ding, Ziluo
Lu, Zongqing
Robotics
Machine Learning
This paper focuses on a critical challenge in robotics: translating text-driven human motions into executable actions for humanoid robots, enabling efficient and cost-effective learning of new behaviors. While existing text-to-motion generation methods achieve semantic alignment between language and motion, they often produce kinematically or physically infeasible motions unsuitable for real-world deployment. To bridge this sim-to-real gap, we propose Reinforcement Learning from Physical Feedback (RLPF), a novel framework that integrates physics-aware motion evaluation with text-conditioned motion generation. RLPF employs a motion tracking policy to assess feasibility in a physics simulator, generating rewards for fine-tuning the motion generator. Furthermore, RLPF introduces an alignment verification module to preserve semantic fidelity to text instructions. This joint optimization ensures both physical plausibility and instruction alignment. Extensive experiments show that RLPF greatly outperforms baseline methods in generating physically feasible motions while maintaining semantic correspondence with text instruction, enabling successful deployment on real humanoid robots.
title RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control
topic Robotics
Machine Learning
url https://arxiv.org/abs/2506.12769