Teacher Motion Priors: Enhancing Robot Locomotion over Challenging Terrain

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jin, Fangcheng, Wang, Yuqi, Ma, Peixin, Yang, Guodong, Zhao, Pan, Li, En, Zhang, Zhengtao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909659607072768
author Jin, Fangcheng
Wang, Yuqi
Ma, Peixin
Yang, Guodong
Zhao, Pan
Li, En
Zhang, Zhengtao
author_facet Jin, Fangcheng
Wang, Yuqi
Ma, Peixin
Yang, Guodong
Zhao, Pan
Li, En
Zhang, Zhengtao
contents Achieving robust locomotion on complex terrains remains a challenge due to high dimensional control and environmental uncertainties. This paper introduces a teacher prior framework based on the teacher student paradigm, integrating imitation and auxiliary task learning to improve learning efficiency and generalization. Unlike traditional paradigms that strongly rely on encoder-based state embeddings, our framework decouples the network design, simplifying the policy network and deployment. A high performance teacher policy is first trained using privileged information to acquire generalizable motion skills. The teacher's motion distribution is transferred to the student policy, which relies only on noisy proprioceptive data, via a generative adversarial mechanism to mitigate performance degradation caused by distributional shifts. Additionally, auxiliary task learning enhances the student policy's feature representation, speeding up convergence and improving adaptability to varying terrains. The framework is validated on a humanoid robot, showing a great improvement in locomotion stability on dynamic terrains and significant reductions in development costs. This work provides a practical solution for deploying robust locomotion strategies in humanoid robots.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10390
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Teacher Motion Priors: Enhancing Robot Locomotion over Challenging Terrain
Jin, Fangcheng
Wang, Yuqi
Ma, Peixin
Yang, Guodong
Zhao, Pan
Li, En
Zhang, Zhengtao
Robotics
Artificial Intelligence
68T40
Achieving robust locomotion on complex terrains remains a challenge due to high dimensional control and environmental uncertainties. This paper introduces a teacher prior framework based on the teacher student paradigm, integrating imitation and auxiliary task learning to improve learning efficiency and generalization. Unlike traditional paradigms that strongly rely on encoder-based state embeddings, our framework decouples the network design, simplifying the policy network and deployment. A high performance teacher policy is first trained using privileged information to acquire generalizable motion skills. The teacher's motion distribution is transferred to the student policy, which relies only on noisy proprioceptive data, via a generative adversarial mechanism to mitigate performance degradation caused by distributional shifts. Additionally, auxiliary task learning enhances the student policy's feature representation, speeding up convergence and improving adaptability to varying terrains. The framework is validated on a humanoid robot, showing a great improvement in locomotion stability on dynamic terrains and significant reductions in development costs. This work provides a practical solution for deploying robust locomotion strategies in humanoid robots.
title Teacher Motion Priors: Enhancing Robot Locomotion over Challenging Terrain
topic Robotics
Artificial Intelligence
68T40
url https://arxiv.org/abs/2504.10390