Biography

Justus Piater is a professor of computer science at the University of Innsbruck, Austria, where he leads the Intelligent and Interactive Systems group. He holds a M.Sc. degree from the University of Magdeburg, Germany, and M.Sc. and Ph.D. degrees from the University of Massachusetts Amherst, USA, all in computer science.  Before joining the University of Innsbruck in 2010, he was a visiting researcher at the Max Planck Institute for Biological Cybernetics in Tübingen, Germany, a professor of computer science at the University of Liège, Belgium, and a Marie-Curie research fellow at GRAVIR-IMAG, INRIA Rhône-Alpes, France.  His research interests focus on visual perception, learning and inference in sensorimotor systems.  He has published more than 160 papers in international journals and conferences, several of which have received best-paper awards, and currently serves as Associate Editor of the IEEE Transactions on Robotics.

Abstract

Open-Ended Robot Learning: First Steps and Next Challenges

Current robot learning, and machine learning in general requires carefully-engineered setups (environments, objective functions, training data, etc.) for learning to succeed.  Perception and action spaces are specially crafted to meet the requirements of the learning objective, which is specified in advance.  How can we construct robot learning systems that can learn in an open-ended fashion, acquire skills not foreseen by its designers, and scale up to virtually unlimited levels of complexity?  I argue that this is exremely hard even for humans, and that exploratory learning must be complemented by several additional mechanisms to allow open-ended learning.