A physics-informed neural network method to approximate homogeneous Lyapunov functions - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2024

A physics-informed neural network method to approximate homogeneous Lyapunov functions

Abstract

This paper applies the physics-informed neural network approach to approximate globally-defined Lyapunov functions and stabilizing controls for homogeneous dynamical systems. The advantage of this class of systems is that all analysis and design can be made locally on a suitably defined unit sphere, which corresponds perfectly to the applicability conditions of neural networks.
Fichier principal
Vignette du fichier
LUE-ECC24-final.pdf (277.38 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04541506 , version 1 (10-04-2024)

Licence

Attribution

Identifiers

  • HAL Id : hal-04541506 , version 1

Cite

Danilo R Lima, Rosane Ushirobira, Denis Efimov. A physics-informed neural network method to approximate homogeneous Lyapunov functions. European Control Conference (ECC24), European Control Association, Jun 2024, Stockholm, Sweden. ⟨hal-04541506⟩
14 View
49 Download

Share

Gmail Facebook X LinkedIn More