发表机构
Zhejiang University; National University of Singapore; MirrorMe Technology Co., Ltd.（浙江大学; 新加坡国立大学; MirrorMe科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PGMT提出一种感知式通用运动跟踪流程，通过地形感知与跟踪松弛，使人形机器人在复杂地形上实现自适应运动与全身行为，并支持远程操作与跌倒恢复。
AI 中文摘要
人形运动跟踪器能够复现多样的全身运动，但在复杂地形上，其性能会下降，因为与地形无关的参考运动在物理上变得不可行。我们提出了PGMT，一种用于人形机器人的感知式通用运动跟踪流程，它从独立选择的运动参考和地形中学习地形适应。PGMT首先学习一个通用的跟踪和恢复先验，然后通过运动条件的地形瞥见来整合地形感知，这些瞥见选择性地编码与当前运动相关的区域。地形感知的跟踪松弛允许在保持运动意图的同时，对参考进行必要的偏离。在Unitree G1上的零样本部署展示了鲁棒的地形自适应运动和全身运动执行，能够穿越高达37厘米障碍物的真实地形，同时支持远程操作、动态运动跟踪和跌倒恢复。PGMT将通用人形运动跟踪扩展到平坦地面之外，提供了一个统一的策略，用于在复杂环境中进行地形自适应运动、多样的全身行为和远程操作。
英文摘要
Humanoid motion trackers can reproduce diverse whole-body motions, but their performance degrades on complex terrain where terrain-agnostic references become physically infeasible. We present PGMT, a Perceptive General Motion Tracking pipeline for humanoid robots that learns terrain adaptation from independently selected motion references and terrains. PGMT first learns a general tracking and recovery prior, then incorporates terrain perception through motion-conditioned terrain glimpses that selectively encode regions relevant to the current motion. Terrain-aware tracking relaxation allows necessary deviations from the reference while preserving its motion intent. Zero-shot deployment on a Unitree G1 demonstrates robust terrain-adaptive locomotion and whole-body motion execution over real-world terrain with obstacles up to 37 cm high, while supporting teleoperation, dynamic motion tracking, and fall recovery. PGMT extends general humanoid motion tracking beyond flat ground, providing a unified policy for terrain-adaptive locomotion, diverse whole-body behaviors, and teleoperation in complex environments. Project homepage: https://luyili.github.io/pgmt/
