Joint Dept. MEMS/CS Colloquium
Prof. Marc Toussaint, Head of the Machine Learning and Robotics Lab, University of Stuttgart, Germany
Title: A United Machine Learning and Modern AI Approach to Robotics: Learning and Reasoning in Logic, Geometric and Uncertain Domains
Hosts: Aaron Dollar and Brian Scassellati
Refreshments at 3:45 p.m.
Abstract: There recently is, again, substantial optimism about AI. While I welcome and share the general enthusiasm I believe that the great advances in machine learning and data-driven methods alone cannot solve some fundamental problems in real-world robotic AI. Instead, a united machine learning, modern, probabilistic AI and robotics research approach is necessary. In this talk I will review core research threads of mine, such as the Planning-as-Inference framework, model-based relational Reinforcement Learning, and the Logic Geometric Programming framework, and explain how this fundamental research is aimed at tackling real-world robotics problems. This research generally aims at capturing essential structure of real-world decision making and manipulation problems, and thereby provide the foundation for learning on top of such representations. I will also discuss three concrete target scenarios that dominated our applied robotics work and which define our mid-term goals: Robots that autonomously explore the environment to learn what is manipulable and how; robots that (learn to) solve geometric/kinematic manipulation puzzles; and robots that learn sequential manipulation and cooperative assembly from demonstration. All three raise fundamental challenges and thereby guide us in what we think are interesting theoretical questions to work on and to progress the field towards robotic AI.
Bio: Marc Toussaint is full professor for Machine Learning and Robotics at the University of Stuttgart since 2012. Before he was assistant professor at the Free University Berlin, leading an Emmy Noether research group at TU Berlin, and spent two years as a post-doc at the University of Edinburgh. His research focuses on the combination of decision theory and machine learning, motivated by fundamental research questions in robotics. Reoccurring themes in his research are appropriate representations (symbols, temporal abstractions, relational representations) to enable efficient learning and manipulation in real world environments, and how to achieve jointly geometric, logic and probabilistic learning and reasoning. He currently is coordinator of the German research priority programme on Autonomous Learning, member of the editorial board of the Journal of AI Research (JAIR), reviewer for the German Research Foundation, and programme committee member of several top conferences in the field (UAI, R:SS, ICRA, IROS, AIStats, ICML). His work was awarded best paper at R:SS’12, ICMLA’07 and runner up at UAI’08.