Investigating Lagrangian Neural Networks for Infinite Horizon Planning in Quadrupedal Locomotion

TL;DR

This paper evaluates Lagrangian Neural Networks for long-term planning in quadrupedal robots, showing they improve prediction accuracy, sample efficiency, and real-time control capabilities by leveraging physical laws.

Contribution

The study demonstrates the effectiveness of LNNs in quadrupedal locomotion, introducing diagonalized and reduced-order models that enhance efficiency and interpretability for real-time control.

Findings

LNNs improve sample efficiency by 10x.

Prediction accuracy increases by 2-10x over baselines.

Diagonalization reduces computational complexity for real-time control.

Abstract

Lagrangian Neural Networks (LNNs) present a principled and interpretable framework for learning the system dynamics by utilizing inductive biases. While traditional dynamics models struggle with compounding errors over long horizons, LNNs intrinsically preserve the physical laws governing any system, enabling accurate and stable predictions essential for sustainable locomotion. This work evaluates LNNs for infinite horizon planning in quadrupedal robots through four dynamics models: (1) full-order forward dynamics (FD) training and inference, (2) diagonalized representation of Mass Matrix in full order FD, (3) full-order inverse dynamics (ID) training with FD inference, (4) reduced-order modeling via torso centre-of-mass (CoM) dynamics. Experiments demonstrate that LNNs bring improvements in sample efficiency (10x) and superior prediction accuracy (up to 2-10x) compared to baseline methods. Notably, the diagonalization approach of LNNs reduces computational complexity while retaining some interpretability, enabling real-time receding horizon control. These findings highlight the advantages of LNNs in capturing the underlying structure of system dynamics in quadrupeds, leading to improved performance and efficiency in locomotion planning and control. Additionally, our approach achieves a higher control frequency than previous LNN methods, demonstrating its potential for real-world deployment on quadrupeds.