跳到主要导航 跳到搜索 跳到主要内容

TerAdapt: Proprioceptive Terrain-Adaptive Locomotion via Codebook Aligned Representation Learning

  • Yubiao Ma
  • , Han Yu
  • , Kai Guo*
  • , Chongming Chen
  • , Wuwei Huang
  • , Boyang Xing
  • , Xuemei Ren
  • , Dongdong Zheng*
  • *此作品的通讯作者
  • Beijing Institute of Technology
  • Humanoid Robotics (Shanghai) Company Ltd.
  • Shandong University

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

Humanoid robots aim to achieve human-like locomotion in unstructured environments. However, designing a controller for such robots is highly challenging due to their inherent instability and the requirement to adapt to diverse terrains. To address this problem, we present TerAdapt, a proprioceptive terrain-adaptive locomotion framework that learns semantically meaningful terrain representations and delivers terrain-aware gait modulation directly from onboard proprioception. TerAdapt achieves this through Terrain Codebook Alignment (TCA), which discretizes elevation maps into a compact terrain codebook and aligns these semantic terrain tokens with a latent representation inferred purely from proprioceptive history. This alignment enables the policy to infer terrain categories and generate adaptive gaits solely from onboard proprioception. Extensive experiments in simulation and on the Unitree G1 humanoid robot demonstrate that TerAdapt achieves state-of-the-art performance among proprioceptive methods, delivering robust and adaptive locomotion across challenging terrains without any exteroceptive sensing.

源语言英语
页(从-至)6831-6838
页数8
期刊IEEE Robotics and Automation Letters
卷11
期6
DOI
出版状态已出版 - 1 6月 2026
已对外发布是

学术指纹

探究 'TerAdapt: Proprioceptive Terrain-Adaptive Locomotion via Codebook Aligned Representation Learning' 的科研主题。它们共同构成独一无二的学术指纹。

引用此