Moral Testing of Autonomous Driving Systems

TL;DR

This paper introduces a novel framework for testing the moral decision-making of autonomous driving systems by formalizing moral principles as metamorphic relations and applying metamorphic testing to identify ethical violations.

Contribution

It proposes a systematic approach to evaluate ADS morality using moral meta-principles and metamorphic testing, addressing the challenge of testing non-functional moral aspects.

Findings

Developed a set of moral meta-principles from social science theories

Formalized these principles as quantitative metamorphic relations

Demonstrated the framework with violations cases in a driving simulator

Abstract

Autonomous Driving System (ADS) testing plays a crucial role in their development, with the current focus primarily on functional and safety testing. However, evaluating the non-functional morality of ADSs, particularly their decision-making capabilities in unavoidable collision scenarios, is equally important to ensure the systems' trustworthiness and public acceptance. Unfortunately, testing ADS morality is nearly impossible due to the absence of universal moral principles. To address this challenge, this paper first extracts a set of moral meta-principles derived from existing moral experiments and well-established social science theories, aiming to capture widely recognized and common-sense moral values for ADSs. These meta-principles are then formalized as quantitative moral metamorphic relations, which act as the test oracle. Furthermore, we propose a metamorphic testing framework to systematically identify potential moral issues. Finally, we illustrate the implementation of the framework and present typical violation cases using the VIRES VTD simulator and its built-in ADS.