Specification-Based Autonomous Driving System Testing

Yuan Zhou

doi:10.1109/TSE.2023.3254142

Specification-Based Autonomous Driving System Testing

2023-01-01

11

OA

AI

Christopher M. Poskitt

DOI：10.1109/TSE.2023.3254142

Original

Original request for help

Save

Abstract

En 中文

Autonomous vehicle (AV) systems must be comprehensively tested and evaluated before they can be deployed. Highfidelity simulators such as CARLA or LGSVL allow this to be done safely in very realistic and highly customizable environments. Existing testing approaches, however, fail to test simulated AVs systematically, as they focus on specific scenarios and oracles (e.g., lane following scenario with the no collision requirement) and lack any coverage criteria measures. In this paper, we propose AVUnit, a framework for systematically testing AV systems against customizable correctness specifications. Designed modularly to support different simulators, AVUnit consists of two new languages for specifying dynamic properties of scenes (e.g., changing pedestrian behaviour after waypoints) and fine-grained assertions about the AV's journey. AVUnit further supports multiple fuzzing algorithms that automatically search for test cases that violate these assertions, using robustness and coverage measures as fitness metrics. We evaluated the implementation of AVUnit for the LGSVL+Apollo simulation environment, finding 19 kinds of issues in Apollo, which indicate that the open-source Apollo does not perform well in complex intersections and lane-changing related scenarios.

Keywords:

Testing

Fuzzing

Planning

Roads

Vehicle dynamics

Sun

Sensors

Autonomous driving system

coverage criteria

fuzzing

specification languages

testing

Specification-Based Autonomous Driving System Testing

Abstract

Journal

Organization