We introduce a novel learning-based approach to synthesize safe and robust controllers for autonomous Cyber-Physical Systems and, at the same time, to generate challenging tests. This procedure combines formal methods for model verification with Generative Adversarial Networks. The method learns two Neural Networks: the first one aims at generating troubling scenarios for the controller, while the second one aims at enforcing the safety constraints. We test the proposed method on a variety of case studies.

Adversarial Learning of Robust and Safe Controllers for Cyber-Physical Systems

Luca Bortolussi;Francesca Cairoli;Ginevra Carbone
;
Enrico Regolin
2021

Abstract

We introduce a novel learning-based approach to synthesize safe and robust controllers for autonomous Cyber-Physical Systems and, at the same time, to generate challenging tests. This procedure combines formal methods for model verification with Generative Adversarial Networks. The method learns two Neural Networks: the first one aims at generating troubling scenarios for the controller, while the second one aims at enforcing the safety constraints. We test the proposed method on a variety of case studies.
https://www.sciencedirect.com/science/article/pii/S2405896321012775
File in questo prodotto:
File Dimensione Formato  
S2405896321012775.pdf

accesso aperto

Tipologia: Documento in Versione Editoriale
Licenza: Creative commons
Dimensione 1.32 MB
Formato Adobe PDF
1.32 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11368/2990608
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact