Pr. Jan Peters
Pr. Jan Peters


Intelligent Autonomous Systems Institute, Computer Science Department of the Technische Universitat, Darmstadt & Robot Learning Lab Empirical Inference and Autonomous Motions, Depts of the Max Planck Institute for Intelligent Systems, Tübingen

Plenary Session: Learning Algorithms to Teach Robots New Tricks


Autonomous robots that can assist humans in situations of daily life have been  a long standing vision of robotics, artificial intelligence, and cognitive  sciences. A first step towards this goal is to endow robots with learning algorithms that can acquire a wide range of tasks triggered by environmental context or higher level instruction. However, learning methods have yet to live up to this promise as only few methods manage to scale to high-dimensional manipulator or humanoid robots. In this  talk, we investigate the key ingredients for learning motor skills in  robotics based on a representation of motor skills by  parameterized motor primitive policies acting as building blocks of movement  generation, and a learned task execution module that transforms these movements  into motor commands. We discuss learning on three different levels of  abstraction, i.e., learning for accurate control is needed to execute, learning  of motor primitives is needed to acquire simple movements, and learning of the  task-dependent "hyperparameters" of these motor primitives allows learning complex tasks. We discuss task-appropriate learning approaches for imitation  learning, model learning and reinforcement learning for robots with many  degrees of freedom. Empirical evaluations on a several robot systems illustrate  the effectiveness and applicability to learning control on an anthropomorphic  robot arm. These robot motor skills range from toy examples (e.g., paddling a  ball, ball-in-a-cup) to playing robot table tennis against a human being and 


Jan Peters is a full professor (W3) for Intelligent Autonomous Systems at the Computer Science Department of the Technische Universitaet Darmstadt and at the same time a senior research scientist and group leader at the Max-Planck  Institute for Intelligent Systems, where he heads the interdepartmental Robot Learning Group. Jan Peters has received the Dick Volz Best 2007 US PhD Thesis Runner-Up Award, the Robotics: Science & Systems - Early Career Spotlight, the  INNS Young Investigator Award, and the IEEE Robotics & Automation Society's Early Career Award. In 2015, he received an ERC Starting Grant.

Jan Peters has studied Computer Science, Electrical, Mechanical and Control Engineering at TU Munich and FernUni Hagen in Germany, at the National University of Singapore (NUS) and the University of Southern California (USC). He has received four Master's degrees in these disciplines as well as a Computer Science PhD from USC. Jan Peters has performed research in Germany at DLR, TU Munich and the Max Planck Institute for Biological Cybernetics (in addition to the institutions above), in Japan at the Advanced Telecommunication Research Center (ATR), at USC and at both NUS and Siemens Advanced Engineering in Singapore.