Matthias Rolf (PhD with highest honors, MSc) is Senior Lecturer in robotics at Oxford Brookes University, UK since 2016. He previously was Specially Appointed Researcher and Assistant Professor at Osaka University, Japan (2013-2016) and research assistant at Bielefeld University (2008-2013) where he obtained his PhD in 2012.
His research interest spans robotics, machine learning, software engineering, and cognitive science, with a particular focus on developmental robotics. His work on “goal babbling” as an efficient way of sensorimotor learning lead to several research awards and international news coverages. His recent research focuses on machine learning approaches to agents’ autonomous learning of own goals.
What if: robots create novel goals? Ethics based on social value systems
Future personal robots might possess the capability to autonomously generate novel goals that exceed their initial programming as well as their past experience. We discuss the ethical challenges involved in such a scenario, ranging from the construction of ethics into such machines to the standard of ethics we could actually demand from such machines. We argue that we might have to accept those machines committing human-like ethical failures if they should ever reach human-level autonomy and intentionality. We base our discussion on recent ideas that novel goals could be originated from agents’ value system that expresses a subjective goodness of world or internal states. Novel goals could then be generated by extrapolating what future states would be good to achieve. Ethics could be built into such systems not just by simple utilitarian measures but also by constructing a value for the expected social acceptance of the agent’s conduct.