让机器人在各种干扰下精准追踪任意动作
Track Any Motions under Any Disturbances
- 分两阶段强化学习框架，实现动作与环境干扰的协同追踪
- 零样本迁移至真实机器人，成功应对多种物理扰动
- 适合需要高鲁棒性的复杂动态任务场景
一个基础的人形运动追踪系统需能跟踪多样、高度动态且接触丰富的动作，并在真实场景中稳定运行，应对地形变化、外力冲击及物理属性改变等多重干扰。为此，我们提出 Any2Track（在任意干扰下追踪任意动作），一种两阶段强化学习框架，可在真实世界中追踪多种动作并应对多类干扰。Any2Track 将动力学适应性作为基础动作执行之外的附加能力，包含两个核心组件：AnyTracker 和 AnyAdapter。AnyTracker 是一个通用运动追踪器，通过一系列精心设计，在单一策略中实现对多种动作的追踪；AnyAdapter 是一个基于历史信息的自适应模块，赋予追踪器在线动力学适应能力，有效弥合仿真到现实的差距并应对多重真实干扰。我们在 Unitree G1 硬件上部署 Any2Track，实现了零样本的仿真到现实迁移，表现出色，在多种真实干扰条件下均能稳定追踪各类动作。
原文摘要 · Abstract (English)
A foundational humanoid motion tracker is expected to be able to track diverse, highly dynamic, and contact-rich motions. More importantly, it needs to operate stably in real-world scenarios against various dynamics disturbances, including terrains, external forces, and physical property changes for general practical use. To achieve this goal, we propose Any2Track (Track Any motions under Any disturbances), a two-stage RL framework to track various motions under multiple disturbances in the real world. Any2Track reformulates dynamics adaptability as an additional capability on top of basic action execution and consists of two key components: AnyTracker and AnyAdapter. AnyTracker is a general motion tracker with a series of careful designs to track various motions within a single policy. AnyAdapter is a history-informed adaptation module that endows the tracker with online dynamics adaptability to overcome the sim2real gap and multiple real-world disturbances. We deploy Any2Track on Unitree G1 hardware and achieve a successful sim2real transfer in a zero-shot manner. Any2Track performs exceptionally well in tracking various motions under multiple real-world disturbances.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。