REACH：基于 RL 的分层人形机器人爬行框架，实现受限空间自适应穿行
REACH: An RL-based Hierarchical Humanoid Crawling Framework for Adaptable Confined Space Traversal
AI 导读
研究者提出 REACH，一个基于 RL 的分层框架，使 Unitree G1 人形机器人在受限空间中通过变高双足行走与爬行穿行。策略可在双足 1.27–0.50m、爬行 0.50–0.20m 的指令范围内调节身体高度，并借助双向过渡策略衔接两种步态。系统结合基于 LiDAR 的规划器生成无碰撞三维路径，真机实验验证了高度与速度跟踪、步态切换和受限空间穿行能力。
正文 · 原文
Abstract:Humanoid locomotion in confined spaces requires continuous height adaptation across multiple locomotion modes, yet most existing approaches remain limited to height-adjustable bipedal walking. We present REACH, an RL-based hierarchical framework that enables a Unitree G1 humanoid to traverse height-constrained environments through variable-height bipedal walking and crawling. The learned policies regulate body height over complementary command ranges of 1.27--0.50m in bipedal locomotion and 0.50--0.20m in crawling, extending traversal beyond the clearance limits of crouched walking. To address contact-rich crawling dynamics, we employ a history-conditioned latent representation that captures terrain and interaction context from proprioceptive observations. A bidirectional transition policy further connects crouched bipedal locomotion and crawling across large kinematic and contact discontinuities. These skills are integrated with a LiDAR-based planner that converts point clouds into collision-free three-dimensional paths and locomotion commands, including proactive height targets. Real-world experiments demonstrate accurate height and velocity tracking, robust terrain traversal, reliable mode transitions and confined-space traversal with the proposed pipeline. Code and videos are available at this https URL.
| Comments: | To appear at IEEE Humanoids 2026; Project page this https URL |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.36546 [cs.RO] |
| (or arXiv:2610.36546v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36546 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: He Kong Dr. [view email]
[v1]
Tue, 27 Oct 2026 02:59:37 UTC (18,883 KB)
来源：arXiv cs.AI · arxiv.org