Data-Driven Physics Embedded Dynamics with Predictive Control and Reinforcement Learning for Quadrupeds
This addresses efficiency and reliability issues for robotics researchers and engineers working on legged robots, though it appears incremental as it builds on existing MPC+RL approaches.
The paper tackles compounding errors and limited interpretability in quadrupedal locomotion by integrating Lagrangian Neural Networks into an RL MPC framework, achieving up to 4x computational efficiency improvement with minimal performance loss.
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.