PAFOT: A Position-Based Approach for Finding Optimal Tests of Autonomous Vehicles

TL;DR

PAFOT is a novel position-based testing framework that uses a genetic algorithm to efficiently generate safety-critical scenarios for autonomous vehicles in simulation, outperforming existing methods.

Contribution

This paper introduces PAFOT, a new position-based testing approach utilizing a genetic algorithm to find safety violations in autonomous vehicle systems.

Findings

PAFOT effectively generates safety-critical scenarios in CARLA.

It finds more safety violations faster than other search-based methods.

PAFOT can identify collisions within short simulation times.

Abstract

Autonomous Vehicles (AVs) are prone to revolutionise the transportation industry. However, they must be thoroughly tested to avoid safety violations. Simulation testing plays a crucial role in finding safety violations of Automated Driving Systems (ADSs). This paper proposes PAFOT, a position-based approach testing framework, which generates adversarial driving scenarios to expose safety violations of ADSs. We introduce a 9-position grid which is virtually drawn around the Ego Vehicle (EV) and modify the driving behaviours of Non-Playable Characters (NPCs) to move within this grid. PAFOT utilises a single-objective genetic algorithm to search for adversarial test scenarios. We demonstrate PAFOT on a well-known high-fidelity simulator, CARLA. The experimental results show that PAFOT can effectively generate safety-critical scenarios to crash ADSs and is able to find collisions in a short simulation time. Furthermore, it outperforms other search-based testing techniques by finding more safety-critical scenarios under the same driving conditions within less effective simulation time.