Formal Verification of Ethical Properties in Multiagent Systems

The increasing use of autonomous arti cial agents in hospitals or in transport control systems leads to consider whether moral rules shared by many of us are followed by these agents. This is a particularly hard problem because most of these moral rules are often not compatible. In such cases, humans usually follow ethical rules to promote one moral rule or another. Using formal veri cation to ensure that an agent follows a given ethical rule could help in increasing the con dence in arti cial agents. In this article, we show how a set of formal properties can be obtained from an ethical rule ordering con icting moral rules. If the behaviour of an agent entails these properties (which can be proven using our existing proof framework), it means that this agent follows this ethical rule.