Trinh, Minh (Laboratory for Machine Tools and Production Engineering), Geist, Andreas René (Max Planck Institute for Intelligent Systems), Josefine, Monnet (Laboratory of Machine Tools and Production Engineering), Stefan, Vilceanu (Laboratory for Machine Tools and Production Engineering), Trimpe, Sebastian (RWTH Aachen University), Brecher, Christian (Laboratory for Machine Tools and Production Engineering (WZL) of)

Newtonian and Lagrangian Neural Networks: A Comparison towards Efficient Inverse Dynamics Identification

Scheduled for presentation during the Regular Session "AI-based Robot Control I" (WeAT2), Wednesday, July 16, 2025, 11:40−12:00, Room 106

Joint 10th IFAC Symposium on Mechatronic Systems and 14th Symposium on Robotics, July 15-18, 2025, Paris, France

This information is tentative and subject to change. Compiled on July 16, 2025

Abstract

Accurate inverse dynamics models are essential tools for controlling industrial robot arms. Recent research combines neural network regression with inverse dynamics formulations of the Newton-Euler and the Euler-Lagrange equations of motion, resulting in so-called Newtonian neural networks and Lagrangian neural networks, respectively. These physics-informed models seek to identify unknowns in the analytical equations from data. Despite their potential, current literature lacks guidance on choosing between Lagrangian and Newtonian networks. In this study, we show that when motor torques are estimated instead of directly measuring joint torques, Lagrangian networks prove less effective compared to Newtonian networks as they do not explicitly model dissipative torques. The performance of these models is compared to neural network regression on data of a MABI MAX 100 industrial robot arm.