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 / Bortolussi, Luca; Cairoli, Francesca; Carbone, Ginevra; Franchina, Francesco; Regolin, Enrico. - ELETTRONICO. - 54/2021:5(2021), pp. 223-228. ( IFAC Conference on Analysis and Design of Hybrid Systems (ADHS) Online 07/07/21-09/07/21) [10.1016/j.ifacol.2021.08.502].
Adversarial Learning of Robust and Safe Controllers for Cyber-Physical Systems
Luca Bortolussi;Francesca Cairoli;Ginevra Carbone
;Enrico Regolin
2021-01-01
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.| 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 |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
