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

2020/09/04 by Bortolussi, Luca, Cairoli, Francesca, Carbone, Ginevra +2
#FOS: Electrical engineering #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2009.02019

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.

Related

• Reasoning about Safety of Learning-Enabled Components in Autonomous\n Cyber-physical Systems
• SMC-ES: Automated synthesis of formally verified control policies
• Robustness to Adversarial Attacks in Learning-Enabled Controllers
• Adversarial Training for a Continuous Robustness Control Problem in Power Systems
• Safety Verification of Neural Network Controlled Systems