My research focuses on the ethics of artificial intelligence, more specifically the question whether we can design artifical systems that can make moral decisions. For this, I use a combination of tools from moral philosophy, which studies the nature and scope of right and wrong, and formal theoretical philosophy, which in conjunction with parts of computer science develops formal methods to model different forms of reasoning. My main interest is to what extent these methods can capture the essentials of moral reasoning - and to what extent they remain limited and in need of human supervision.

Besides by research into AI ethics, I am also interested in philosophy of mind and neuroscience and in contemporary political philosophy, especially deliberative democracy.