Saved in:
Bibliographic Details
Main Authors: Song, Haolin, Zhu, Hongbo, Yu, Tao, Liu, Yan, Yuan, Mingqi, Zhou, Wengang, Chen, Hua, Li, Houqiang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.07464
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911308031459328
author Song, Haolin
Zhu, Hongbo
Yu, Tao
Liu, Yan
Yuan, Mingqi
Zhou, Wengang
Chen, Hua
Li, Houqiang
author_facet Song, Haolin
Zhu, Hongbo
Yu, Tao
Liu, Yan
Yuan, Mingqi
Zhou, Wengang
Chen, Hua
Li, Houqiang
contents For full-size humanoid robots, even with recent advances in reinforcement learning-based control, achieving reliable locomotion on complex terrains, such as long staircases, remains challenging. In such settings, limited perception, ambiguous terrain cues, and insufficient adaptation of gait timing can cause even a single misplaced or mistimed step to result in rapid loss of balance. We introduce a perceptive locomotion framework that merges terrain sensing, gait regulation, and whole-body control into a single reinforcement learning policy. A downward-facing depth camera mounted under the base observes the support region around the feet, and a compact U-Net reconstructs a dense egocentric height map from each frame in real time, operating at the same frequency as the control loop. The perceptual height map, together with proprioceptive observations, is processed by a unified policy that produces joint commands and a global stepping-phase signal, allowing gait timing and whole-body posture to be adapted jointly to the commanded motion and local terrain geometry. We further adopt a single-stage successive teacher-student training scheme for efficient policy learning and knowledge transfer. Experiments conducted on a 31-DoF, 1.65 m humanoid robot demonstrate robust locomotion in both simulation and real-world settings, including forward and backward stair ascent and descent, as well as crossing a 46 cm gap. Project Page:https://ga-phl.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2512_07464
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction
Song, Haolin
Zhu, Hongbo
Yu, Tao
Liu, Yan
Yuan, Mingqi
Zhou, Wengang
Chen, Hua
Li, Houqiang
Robotics
For full-size humanoid robots, even with recent advances in reinforcement learning-based control, achieving reliable locomotion on complex terrains, such as long staircases, remains challenging. In such settings, limited perception, ambiguous terrain cues, and insufficient adaptation of gait timing can cause even a single misplaced or mistimed step to result in rapid loss of balance. We introduce a perceptive locomotion framework that merges terrain sensing, gait regulation, and whole-body control into a single reinforcement learning policy. A downward-facing depth camera mounted under the base observes the support region around the feet, and a compact U-Net reconstructs a dense egocentric height map from each frame in real time, operating at the same frequency as the control loop. The perceptual height map, together with proprioceptive observations, is processed by a unified policy that produces joint commands and a global stepping-phase signal, allowing gait timing and whole-body posture to be adapted jointly to the commanded motion and local terrain geometry. We further adopt a single-stage successive teacher-student training scheme for efficient policy learning and knowledge transfer. Experiments conducted on a 31-DoF, 1.65 m humanoid robot demonstrate robust locomotion in both simulation and real-world settings, including forward and backward stair ascent and descent, as well as crossing a 46 cm gap. Project Page:https://ga-phl.github.io/
title Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction
topic Robotics
url https://arxiv.org/abs/2512.07464