Reachability Analysis of Linear Parameter-Varying Systems with Neural Network Controllers - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Reachability Analysis of Linear Parameter-Varying Systems with Neural Network Controllers

Résumé

A method is presented to obtain outerapproximations of forward reachable sets for Linear Parameter-Varying (LPV) systems controlled by neural networks for safety verification. The method relies on abstracting the activation functions by optimization-based sector constraints. The forward reachable sets are obtained in terms of solutions to a set of Linear Matrix Inequalities (LMIs). A numerical example is provided to demonstrate the applicability of the proposed method. A comparison with some available methods is also included.
Fichier principal
Vignette du fichier
CCTA2022.pdf (488.99 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04412111 , version 1 (23-01-2024)

Identifiants

Citer

Arash Sadeghzadeh, Pierre-Loïc Garoche. Reachability Analysis of Linear Parameter-Varying Systems with Neural Network Controllers. 2022 IEEE Conference on Control Technology and Applications (CCTA), Aug 2022, Trieste, France. pp.1372-1377, ⟨10.1109/CCTA49430.2022.9966104⟩. ⟨hal-04412111⟩

Collections

ENAC LII ANR
4 Consultations
6 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More