A physics-informed neural network method to approximate homogeneous Lyapunov functions
Résumé
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.
Domaines
Optimisation et contrôle [math.OC]Origine | Fichiers produits par l'(les) auteur(s) |
---|