Abstract

As automation in artificial intelligence is increasing, we will need to automate a growing amount of ethical decision making. However, ethical decision- making raises novel challenges for engineers, ethicists and policymakers, who will have to explore new ways to realize this task. The presented work focuses on the development and formalization of models that aim at ensuring a correct ethical behaviour of artificial intelligent agents, in a provable way, extending and implementing a logic-based proving calculus that is based on argumentation reasoning with support and attack arguments. This leads to a formal theoretical framework of ethical competence that could be implemented in artificial intelligent systems in order to best formalize certain parameters of ethical decision-making to ensure safety and justified trust.