Problem
Research questions and friction points this paper is trying to address.
Zero-Shot Robustness
Quadruped Locomotion
Dynamics Mismatch
Online Adaptation
Sim-to-Real Transfer
CARO: Contact-Agnostic Residual Observation for Zero-Shot Robust Quadruped Locomotion
🤖 AI Summary
CARO框架通过在强化学习控制回路中嵌入模型并构建扭矩级残差观察，解决了四足机器人零样本鲁棒运动的问题。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
contact-agnostic
residual observation
disturbance observer
zero-shot robustness
sim-to-real transfer
🔎 Similar Papers
No similar papers found.
