Towards a framework to deal with ethical conflicts in autonomous agents and multi - agent systems

International audienceAutonomy is a central property in robotic systems, human-machine interfaces, e-business, ambient intelligence and assisted living applicatio ns. As the complexity of the situations the autonomous agents may encounter in such contexts is increasing, the decisions those agents make must deal with new issues, e.g. decision s involving contextual ethical considerations. Consequently contributions have prop osed recommendations, advice or hard-wired ethical principles for autonomous agents. However, socio-technical systems are more and more open and decentralized, and involve a utonomous artificial agents interacting with other agents, human operators or use rs. For such systems, novel and original methods are needed to address contextual et hical decision-making, as decisions are likely to interfere with one another. This paper a ims at presenting the ETHICAA project (Ethics and Autonomous Agents) whose objective is to define what should be an autonomous entity that could manage ethical conflicts . As a first proposal, we present various practical case studies of ethical conflicts and highlight what their main contextual and decision features are