Saved in:
Bibliographic Details
Main Authors: Yang, Tae Hoon, Shi, Haochen, Hu, Jiacheng, Zhang, Zhicong, Jiang, Daniel, Wang, Weizhuo, He, Yao, Wu, Zhen, Chen, Yuming, Hou, Yifan, Kennedy III, Monroe, Song, Shuran, Liu, C. Karen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.03607
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911357726621696
author Yang, Tae Hoon
Shi, Haochen
Hu, Jiacheng
Zhang, Zhicong
Jiang, Daniel
Wang, Weizhuo
He, Yao
Wu, Zhen
Chen, Yuming
Hou, Yifan
Kennedy III, Monroe
Song, Shuran
Liu, C. Karen
author_facet Yang, Tae Hoon
Shi, Haochen
Hu, Jiacheng
Zhang, Zhicong
Jiang, Daniel
Wang, Weizhuo
He, Yao
Wu, Zhen
Chen, Yuming
Hou, Yifan
Kennedy III, Monroe
Song, Shuran
Liu, C. Karen
contents Most locomotion methods for humanoid robots focus on leg-based gaits, yet natural bipeds frequently rely on hands, knees, and elbows to establish additional contacts for stability and support in complex environments. This paper introduces Locomotion Beyond Feet, a comprehensive system for whole-body humanoid locomotion across extremely challenging terrains, including low-clearance spaces under chairs, knee-high walls, knee-high platforms, and steep ascending and descending stairs. Our approach addresses two key challenges: contact-rich motion planning and generalization across diverse terrains. To this end, we combine physics-grounded keyframe animation with reinforcement learning. Keyframes encode human knowledge of motor skills, are embodiment-specific, and can be readily validated in simulation or on hardware, while reinforcement learning transforms these references into robust, physically accurate motions. We further employ a hierarchical framework consisting of terrain-specific motion-tracking policies, failure recovery mechanisms, and a vision-based skill planner. Real-world experiments demonstrate that Locomotion Beyond Feet achieves robust whole-body locomotion and generalizes across obstacle sizes, obstacle instances, and terrain sequences.
format Preprint
id arxiv_https___arxiv_org_abs_2601_03607
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Locomotion Beyond Feet
Yang, Tae Hoon
Shi, Haochen
Hu, Jiacheng
Zhang, Zhicong
Jiang, Daniel
Wang, Weizhuo
He, Yao
Wu, Zhen
Chen, Yuming
Hou, Yifan
Kennedy III, Monroe
Song, Shuran
Liu, C. Karen
Robotics
Most locomotion methods for humanoid robots focus on leg-based gaits, yet natural bipeds frequently rely on hands, knees, and elbows to establish additional contacts for stability and support in complex environments. This paper introduces Locomotion Beyond Feet, a comprehensive system for whole-body humanoid locomotion across extremely challenging terrains, including low-clearance spaces under chairs, knee-high walls, knee-high platforms, and steep ascending and descending stairs. Our approach addresses two key challenges: contact-rich motion planning and generalization across diverse terrains. To this end, we combine physics-grounded keyframe animation with reinforcement learning. Keyframes encode human knowledge of motor skills, are embodiment-specific, and can be readily validated in simulation or on hardware, while reinforcement learning transforms these references into robust, physically accurate motions. We further employ a hierarchical framework consisting of terrain-specific motion-tracking policies, failure recovery mechanisms, and a vision-based skill planner. Real-world experiments demonstrate that Locomotion Beyond Feet achieves robust whole-body locomotion and generalizes across obstacle sizes, obstacle instances, and terrain sequences.
title Locomotion Beyond Feet
topic Robotics
url https://arxiv.org/abs/2601.03607