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

TL;DR

This paper presents a novel adversarial learning framework that synthesizes safe, robust controllers for cyber-physical systems and generates challenging test scenarios by combining formal verification with GANs.

Contribution

It introduces a new method that jointly trains neural networks for controller safety enforcement and scenario generation, enhancing robustness and safety verification.

Findings

Successfully applied to multiple case studies

Generated challenging scenarios for safety testing

Improved controller robustness through adversarial training

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.