四足机器人运动的快速具身自适应
文章背景与核心概要
在机器人技术中，当硬件属性发生变化（如老化、损伤或负载变化）时，基于学习的机器人策略往往会失效，而人类则能够随着身体的变化轻松调整运动方式。为了解决这一痛点，本文介绍了一种针对四足机器人运动的在线具身自适应框架，该框架能够通过短暂的交互历史推断具身参数，并将控制条件绑定到推断出的硬件状态上。
该方法将一个在具身随机化（embodiment randomization）下训练的通用策略，与一个能够在半秒内识别物理变化的轻量级自适应模块相结合。在真实宇树（Unitree Go2）机器人上的实验表明，该系统在面对严重硬件变化（如完全锁定的腿和 5 公斤负载）时仍能保持稳定的运动，而非自适应方法则会失效。这项研究验证了显式在线具身辨识在快速适应关节极限和负载质量变化方面的实用性，并为处理更广泛的不确定、退化或变化的机器人硬件迈出了坚实的一步。
Overview
- arXiv ID: 2608.01506 [cs.RO]
- Subjects: Robotics (
cs.RO), Artificial Intelligence (cs.AI), Machine Learning (cs.LG) - Authors: Dichen Li, Bo Ai, Nico Bohlinger, Jan Peters, Hao Su, Henrik I. Christensen
- Submission Date: August 2, 2026 (Last revised August 5, 2026)
- Links: View PDF | DOI
Overview
- arXiv ID: 2608.01506 [cs.RO]
- Subjects: Robotics (
cs.RO), Artificial Intelligence (cs.AI), Machine Learning (cs.LG)- Authors: Dichen Li, Bo Ai, Nico Bohlinger, Jan Peters, Hao Su, Henrik I. Christensen
- Submission Date: August 2, 2026 (Last revised August 5, 2026)
- Links: View PDF | DOI
Abstract
人类随着年龄增长、受伤或负重而改变身体时，能够轻而易举地调整自己的动作，然而基于学习的机器人策略在硬件属性发生变化时往往会失效。我们为四足机器人运动引入了一种在线具身自适应框架，该框架通过简短的交互历史推断具身参数，并基于推断出的硬件状态来调节控制策略。
Humans readily adapt their movements as their bodies change through aging, injury, or load carrying, but learning-based robot policies often break when hardware properties shift. We introduce an online embodiment adaptation framework for quadrupedal locomotion that infers embodiment parameters from short interaction histories and conditions control on the inferred hardware state.
我们的方法将一个在具身随机化（embodiment randomization）下训练的通用策略，与一个能够在半秒内识别物理变化的轻量级自适应模块结合起来。我们评估了两种具有代表性的具身变化形式： 1. 关节行程约束（对应于关节级别的运动学退化） 2. 躯干质量变化（对应于机体级别的动力学变化）
Our method pairs a generalist policy trained under embodiment randomization with a lightweight adaptation module that identifies physical changes within half a second. We evaluate two representative forms of embodiment variation: 1. Joint-range constraints (corresponding to joint-level kinematic degradation) 2. Trunk-mass changes (corresponding to body-level dynamic variation)
在仿真中，该模块能够准确估计这些变化，并实现闭环控制，其性能显著优于直接根据交互历史进行条件约束的策略。在真实的宇树 Go2（Unitree Go2）机器人上，我们的系统在面对所评估的严重变化实例（包括完全锁定的腿和 5 公斤的负载）时仍能维持稳定的运动，而非自适应方法则会失效。这些结果证明了显式在线具身辨识在快速适应关节极限和负载质量变化方面的实用性，并为处理更广泛、不确定、退化或变化的机器人硬件提供了一个切入点。
In simulation, the module accurately estimates these changes and enables closed-loop control that substantially outperforms policies conditioned directly on interaction history. On a real Unitree Go2 robot, our system maintains stable locomotion under severe instances of the evaluated changes, including a fully locked leg and a 5 kg payload, where non-adaptive methods fail. These results demonstrate the practicality of explicit online embodiment identification for rapid adaptation to joint-limit and payload-mass changes, and provide a step toward handling broader forms of uncertain, degraded, or changing robot hardware.