无需传感器，让四足机器人自适应复杂地形和负载变化。
CARO: Contact-Agnostic Residual Observation for Zero-Shot Robust Quadruped Locomotion
- 用固定基底动力学模型生成扭矩残差观测信号。
- 在未见过的负载、质心偏移等条件下零样本鲁棒性显著提升。
- 适合希望减少传感器依赖的机器人控制研究者。
我们提出CARO，一种接触无关的残差观测框架，用于策略自适应。CARO将固定基底的欧拉-拉格朗日模型嵌入强化学习控制循环中，构建了无需扭矩传感器、显式接触估计或基于视觉的浮地位置与线速度测量的扭矩级残差观测。干扰观测器提取代表动力学不匹配的结构化信号，策略则学习利用该反馈实现在线自适应。CARO在与基础策略相同的地形、指令和域随机化条件下训练，无需专门的干扰课程或额外适应监督。然而，在模拟及真实场景转移任务中，面对分布外负载、质心偏移、地形几何差异、突发动力学变化和高平台着陆等情况，均实现了显著提升的零样本鲁棒性。
原文摘要 · Abstract (English)
We propose CARO, a contact-agnostic residual observation framework for policy adaptation. CARO embeds a fixed-base Euler--Lagrange model into the reinforcement learning control loop and constructs a torque-level residual observation without requiring torque sensors, explicit contact estimation, or vision-based measurements of the floating-base position and linear velocity. A disturbance observer extracts a structured signal representing dynamics mismatch, while the policy learns to exploit this feedback for online adaptation. CARO is trained under the same terrain, command, and domain-randomization conditions as the nominal policy, without specialized disturbance curricula or additional adaptation supervision. Nevertheless, it achieves substantially improved zero-shot robustness in simulation and sim-to-real transfer tasks involving out-of-distribution payloads, center-of-mass shifts, terrain geometries, abrupt dynamics changes, and elevated-platform landings.
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。