用物理约束神经网络提升四足机器人运动控制的准确性与效率
Data-Driven Physics Embedded Dynamics with Predictive Control and Reinforcement Learning for Quadrupeds
- 将拉格朗日神经网络嵌入强化学习与模型预测控制框架
- 长时序误差降低，计算效率提升4倍且任务表现几乎不变
- 适合需要高可靠性和实时性的机器人控制研究者
当前最先进的四足机器人运动控制方法结合了模型预测控制（MPC）与强化学习（RL），实现了复杂运动和地形适应能力。然而，这些方法在长时程中常出现累积误差，且因缺乏物理先验知识而可解释性差。本文通过将拉格朗日神经网络（LNN）引入RL-MPC框架，实现物理一致的动力学学习。部署时，采用逆动力学无限时域MPC方案，避免昂贵的矩阵求逆，计算效率最高提升4倍，任务性能损失极小。通过多组消融实验验证了所提LNN及其变体的有效性：样本效率提升、长时序误差减少、实时规划速度更快。最后，在Unitree Go1机器人上测试，证明了该框架在真实场景中的可行性。
原文摘要 · Abstract (English)
State of the art quadrupedal locomotion approaches integrate Model Predictive Control (MPC) with Reinforcement Learning (RL), enabling complex motion capabilities with planning and terrain adaptive behaviors. However, they often face compounding errors over long horizons and have limited interpretability due to the absence of physical inductive biases. We address these issues by integrating Lagrangian Neural Networks (LNNs) into an RL MPC framework, enabling physically consistent dynamics learning. At deployment, our inverse dynamics infinite horizon MPC scheme avoids costly matrix inversions, improving computational efficiency by up to 4x with minimal loss of task performance. We validate our framework through multiple ablations of the proposed LNN and its variants. We show improved sample efficiency, reduced long-horizon error, and faster real time planning compared to unstructured neural dynamics. Lastly, we also test our framework on the Unitree Go1 robot to show real world viability.
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。