发表机构
The University of Hong Kong; Beijing Institute of Technology; The University of Tokyo（香港大学; 北京理工大学; 东京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出MILD地形建模方法，结合物理离散元接触求解器与深度强化学习训练地形感知双足运动控制器，可提升机器人在可变形表面的运动适应性。
AI 中文摘要
让机器人在可变形地面行走对灾难响应、行星探测等应用至关重要。尽管双足机器人潜力巨大，但其在可变形表面的运动能力仍有限，因为当前模拟器无法捕捉这类可变形基底的时空异质性。本文提出MILD，它包含基于物理的离散元接触求解器，能准确模拟空间变化的足-地交互。作为该模型的补充，我们通过带潜在调制和本体感觉估计的深度强化学习训练地形感知运动控制器。与最先进方法的定量对比显示，我们的方法在训练期间生成更多样、更真实的接触场景，从而得到在真实可变形表面表现出自然适应性的控制器。通过硬件实验，我们证明该系统具备在线地形识别能力，且能在多种表面刚度下实现适应。
英文摘要
Enabling robots to walk on yielding terrain is vital for applications ranging from disaster response to planetary exploration. While bipedal robots hold immense potential, their locomotion on deformable surfaces remains limited as current simulators fail to capture the spatiotemporal heterogeneity of such yielding substrates. We present MILD, featuring a physics-grounded discrete-element contact solver that accurately simulates spatially varying foot-terrain interactions. Complementing this model, we train a terrain-aware locomotion controller via deep reinforcement learning with latent modulation and proprioceptive estimation. Quantitative comparisons against state-of-the-art methods show our approach generates more diverse and realistic contact scenarios during training, resulting in controllers that exhibit natural adaptation on real deformable surfaces. Through hardware experiments, we demonstrate the system's capability for online terrain identification and adaptation across a wide range of surface stiffness.
Comments8 pages, 9 figures
Journal refIEEE Robotics and Automation Letters (2025)
