Today’s robots have motor abilities and sensors that exceed those of humans in many ways: They move more accurately and faster; their sensors see more and at a higher precision and in contrast to humans they can accurately measure even the smallest forces and torques. Robot hands with three, four, or five fingers are commercially available, and, so are advanced dexterous arms. Indeed, modern motion-planning methods have rendered grasp trajectory generation a largely solved problem. Still, no robot to date matches the manipulation skills of industrial assembly workers despite that manipulation of mechanical objects remains essential for the industrial assembly of complex products. So, why are current robots still so bad at manipulation and humans so good?
Neurophysiology has a clear answer to this question: During manipulation, humans make substantial use of the sensory information from tactile sensors. However, robust tactile sensors are just starting to be available to robots and have not yet been integrated into their control. What is lacking at this stage is not the availability of tactile sensing, but the intelligent use of the information provided by such sensors.
We address the intelligent use of tactile sensing as a learning problem – focusing on the control of objects in-hand, as well as the perception problems encountered by a robot exploring its environment with tactile sensors. To accomplish this goal, we focus on the five core questions in tactile manipulation: (i) What can we learn to recognize from tactile interaction? (ii) How can we efficiently explore through touch? (iii) How can we learn to control slip from touch? (iv) Can we obtain modular grip control from single finger slip control? (v) How can we self-improve manipulation? We address each of these questions separately, but facilitate quick scaling from straightforward, well-captured scenarios employing a single finger to complex multi-fingered manipulation throughout the chain of answers.
Biography: 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, IEEE Robotics & Automation Society's Early Career Award and 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.