Physics-Informed Neural Networks to Model and Control Robots: A Theoretical and Experimental Investigation

Authors

Jingyue Liu, Delft University of Technology
Pablo Borja, School of Engineering, Computing and Mathematics
Cosimo Della Santina, Delft University of Technology

ORCID

• Pablo Borja: 0000-0001-7744-0846

Abstract

This work concerns the application of physics-informed neural networks to the modeling and control of complex robotic systems. Achieving this goal requires extending physics-informed neural networks to handle nonconservative effects. These learned models are proposed to combine with model-based controllers originally developed with first-principle models in mind. By combining standard and new techniques, precise control performance can be achieved while proving theoretical stability bounds. These validations include real-world experiments of motion prediction with a soft robot and trajectory tracking with a Franka Emika Panda manipulator.

DOI

10.1002/aisy.202300385

Publication Date

2024-02-23

Publication Title

Advanced Intelligent Systems

Volume

6

Issue

5

Keywords

dissipation, Euler–Lagrange equations, Hamiltonian neural networks, Lagrangian neural networks, model-based control, physics-informed neural networks, port-Hamiltonian systems

Recommended Citation

Liu, J., Borja, P., & Della Santina, C. (2024) 'Physics-Informed Neural Networks to Model and Control Robots: A Theoretical and Experimental Investigation', Advanced Intelligent Systems, 6(5). Available at: 10.1002/aisy.202300385