Wasserstein Generative Adversarial Networks for Online Test Generation for Cyber Physical Systems

TL;DR

This paper introduces WOGAN, an online test generation method using Wasserstein GANs, applicable to cyber-physical systems, demonstrated by generating challenging road scenarios for lane assistance systems.

Contribution

The paper presents a novel black-box test generation algorithm based on Wasserstein GANs, applicable to various systems with a fitness function.

Findings

WOGAN performs competitively compared to existing algorithms.

WOGAN successfully generates test scenarios causing system failures.

The method is general-purpose and applicable to different cyber-physical systems.

Abstract

We propose a novel online test generation algorithm WOGAN based on Wasserstein Generative Adversarial Networks. WOGAN is a general-purpose black-box test generator applicable to any system under test having a fitness function for determining failing tests. As a proof of concept, we evaluate WOGAN by generating roads such that a lane assistance system of a car fails to stay on the designated lane. We find that our algorithm has a competitive performance respect to previously published algorithms.