Physics-Informed Neural Networks to Model and Control Robots

A Theoretical and Experimental Investigation

Journal article (2024)

Authors

J. Liu Learning & Autonomous Control - Mechanical, Maritime and Materials Engineering

Pablo Borja Plymouth University

C. Della Santina Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR), Learning & Autonomous Control - Mechanical, Maritime and Materials Engineering

Research Group

Learning & Autonomous Control (Mechanical, Maritime and Materials Engineering) (TU Delft)

Physics-informed neural networks Dissipation Model-based control Port-Hamiltonian systems Hamiltonian neural networks Lagrangian neural networks Euler–Lagrange equations

More Info

expand_more

To reference this document use:

http://resolver.tudelft.nl/uuid:64b92602-8cc0-4ae6-ba59-0f18fc22122e

Published Date

2024

Language

English

Faculty

Mechanical, Maritime and Materials Engineering

Department

Cognitive Robotics

Research Group

Learning & Autonomous Control

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.

Files

Advanced_Intelligent_Systems_-... (.pdf)

(.pdf | 5.26 Mb)