让双足机器人在复杂地形上稳定行走，关键在于真实建模关节耦合关系。
Robust RL Control for Bipedal Locomotion with Closed Kinematic Chains
- 直接建模闭链动力学，不简化为串联结构。
- 在自研机器人TopA上实现多地形稳定行走，效果显著优于简化模型方法。
- 通过对称损失、对抗训练提升策略鲁棒性，适合做真实机器人控制研究者参考。
针对具有闭链结构的双足机器人，现有强化学习方法通常将并联机构简化为串联模型进行训练，这会严重损害仿真到现实的迁移能力，因无法捕捉关节耦合、摩擦动力学和电机空间控制特性等关键因素。本文提出一种显式包含闭链动力学的强化学习框架，并在自研机器人TopA上验证。通过对称感知损失函数、对抗训练和定向网络正则化，显著提升了策略鲁棒性。实验表明，该方法在多种地形下均实现稳定行走，性能明显优于基于简化运动学模型的方法。
原文摘要 · Abstract (English)
Developing robust locomotion controllers for bipedal robots with closed kinematic chains presents unique challenges, particularly since most reinforcement learning (RL) approaches simplify these parallel mechanisms into serial models during training. We demonstrate that this simplification significantly impairs sim-to-real transfer by failing to capture essential aspects such as joint coupling, friction dynamics, and motor-space control characteristics. In this work, we present an RL framework that explicitly incorporates closed-chain dynamics and validate it on our custom-built robot TopA. Our approach enhances policy robustness through symmetry-aware loss functions, adversarial training, and targeted network regularization. Experimental results demonstrate that our integrated approach achieves stable locomotion across diverse terrains, significantly outperforming methods based on simplified kinematic models.
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。