Moral Testing of Autonomous Driving Systems
Wenbing Tang, Mingfei Cheng, Yuan Zhou, Yang Liu
TL;DR
This work tackles the challenge of evaluating ADS morality in unavoidable collision scenarios, where universal ethical principles are absent. It introduces Moral Meta-Principles sourced from diverse ethical frameworks and formalizes them as Moral Metamorphic Relations (MMRs) to serve as test oracles within a metamorphic testing framework. A SCENEST-derived Moral Testing Language enables structured, mutation-driven scenario modeling, and the framework is instantiated in the VIRES VTD simulator to uncover immoral-revealing test cases (IRTCs). The methodology advances trustworthy ADS decision-making by enabling systematic, simulation-based detection of ethical issues, with flexibility to extend to other simulators and evolving moral considerations.
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.