arXiv 2512.074642025-12-08cs.RO

具有实时底层地形重建的感知人体机器人运动

Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction

Department of Electronic Engineering and Information Science (EEIS), University of Science and Technology of China（电子工程与信息科学系，中国科学技术大学）；LimX Dynamics（LimX动力学）；Hong Kong University of Science and Technology（香港科技大学）；School of Mechanics Engineering, Harbin Institute of Technology (HIT)（机械工程学院，哈尔滨工业大学）；Department of Computing, The Hong Kong Polytechnic University（计算学院，香港理工大学）；Zhejiang University-University of Illinois Urbana-Champaign Institute (ZJUI)（浙江大学-伊利诺伊大学厄巴纳-香槟分校联合研究所）

Haolin Song, Hongbo Zhu, Tao Yu, Yan Liu, Mingqi Yuan, Wengang Zhou, Hua Chen, Houqiang Li

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

该研究提出了一种结合地形感知、步态调节和全身控制的强化学习框架，通过实时底层地形重建实现稳健的人形机器人运动。

摘要：

对于全尺寸人形机器人，即使在最近的基于强化学习的控制技术取得进展的情况下，实现复杂地形上的可靠运动，如长台阶，仍然具有挑战性。在这样的情况下，有限的感知能力、模糊的地形线索以及步态时机的不足，可能导致单个错误的步子或时机错误迅速导致平衡丧失。我们介绍了一个感知运动框架，将地形感知、步态调节和全身控制合并到一个强化学习策略中。安装在基底下方的向下深度相机观察脚部周围的支撑区域，一个紧凑的U-Net从每个帧中实时重建密集的以自身为中心的高度图，以与控制回路相同的频率运行。感知高度图与本体感觉观察一起，由统一的策略处理，生成关节命令和全局步态阶段信号，使步态时机和全身姿势能够共同适应所命令的运动和局部地形几何形状。我们进一步采用单阶段连续教师-学生训练方案，以实现高效的策略学习和知识转移。在31自由度、1.65米的人形机器人上进行的实验表明，在仿真和现实环境中均表现出稳健的运动能力，包括向前和向后台阶攀爬和下降，以及跨越46厘米的间隙。项目页面：https://ga-phl.github.io/

英文摘要：

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/

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。