Saved in:
Bibliographic Details
Main Authors: Zhang, Jianguo, Xu, Wentai, Ye, Shusheng, He, Yuxiang, Qi, Weimin, Sun, Qinbo, Ding, Ning, Zhou, Liguang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.09944
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911670311321600
author Zhang, Jianguo
Xu, Wentai
Ye, Shusheng
He, Yuxiang
Qi, Weimin
Sun, Qinbo
Ding, Ning
Zhou, Liguang
author_facet Zhang, Jianguo
Xu, Wentai
Ye, Shusheng
He, Yuxiang
Qi, Weimin
Sun, Qinbo
Ding, Ning
Zhou, Liguang
contents Robust humanoid stair climbing remains challenging due to geometric discontinuities, sensitivity to step height variations, and perception uncertainty in real-world environments. Existing learning-based locomotion policies often rely on implicit terrain representations or blind proprioceptive feedback, limiting their ability to generalize across varying stair geometries and to anticipate required gait adjustments. This paper proposes an explicit stair geometry conditioning framework for robust humanoid stair climbing. Instead of encoding terrain as high-dimensional latent features, we extract a compact set of interpretable geometric parameters, including step height, step depth, and current yaw angle relative to the robot heading. These explicit stair parameters directly condition a Proximal Policy Optimization (PPO)-based locomotion policy, enabling proactive modulation of swing-foot clearance and stride characteristics according to stair structure. Simulation experiments demonstrate improved generalization across unseen stair heights beyond the training distribution. Real-world experiments on the Unitree G1 humanoid validate reliable indoor and outdoor stair traversal. In challenging outdoor scenarios, the robot successfully ascends 33 consecutive steps without failure, demonstrating robustness and practical deployability.
format Preprint
id arxiv_https___arxiv_org_abs_2605_09944
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Explicit Stair Geometry Conditioning for Robust Humanoid Locomotion
Zhang, Jianguo
Xu, Wentai
Ye, Shusheng
He, Yuxiang
Qi, Weimin
Sun, Qinbo
Ding, Ning
Zhou, Liguang
Robotics
Robust humanoid stair climbing remains challenging due to geometric discontinuities, sensitivity to step height variations, and perception uncertainty in real-world environments. Existing learning-based locomotion policies often rely on implicit terrain representations or blind proprioceptive feedback, limiting their ability to generalize across varying stair geometries and to anticipate required gait adjustments. This paper proposes an explicit stair geometry conditioning framework for robust humanoid stair climbing. Instead of encoding terrain as high-dimensional latent features, we extract a compact set of interpretable geometric parameters, including step height, step depth, and current yaw angle relative to the robot heading. These explicit stair parameters directly condition a Proximal Policy Optimization (PPO)-based locomotion policy, enabling proactive modulation of swing-foot clearance and stride characteristics according to stair structure. Simulation experiments demonstrate improved generalization across unseen stair heights beyond the training distribution. Real-world experiments on the Unitree G1 humanoid validate reliable indoor and outdoor stair traversal. In challenging outdoor scenarios, the robot successfully ascends 33 consecutive steps without failure, demonstrating robustness and practical deployability.
title Explicit Stair Geometry Conditioning for Robust Humanoid Locomotion
topic Robotics
url https://arxiv.org/abs/2605.09944