Machine Learning of Social States and Skills for Multi-Party Human-Robot Interaction

We describe several forms of machine learning that are being applied to social interaction in Human-Robot Interaction (HRI), using a robot bartender as our scenario. We first present a data-driven approach to social state recognition based on supervised learning. We then describe an approach to social interaction management based on reinforcement learning, using a data-driven simulation of multiple users to train HRI policies. Finally, we discuss an alternative unsupervised learning framework that combines social state recognition and social skills execution, based on hierarchical Dirichlet processes and an infinite POMDP interaction manager.