Ei_header
Thumb_jan_peters
Jan Peters
Prof. Dr. (USC, USA)
Position: Group Leader
Room no.: 239
Phone: +49 7071 601 585
Fax: +49 7071 601 552

While I remain affliated with MPI, I am now also a full professor at Darmstadt University of Technology (TU Darmstadt).

My research centers around the goal of bringing advanced motor skills to robotics using techniques from machine learning. You can check out my research interests and my publications for further information on my private homepage at private homepage. I have recently completed my Ph.D. at the Department of Computer Science at the University of Southern California in sunny Los Angeles. There, I have been working with Stefan Schaal, Sethu Vijayakumar (now at U. Edinburgh, UK), and Firdaus Udwadia (from the Department of Mechanical Engineering). My fabulous committee also included Chris Atkeson and Gaurav Sukhatme. Before joining USC, I studied computer science (with a focus on artificial intelligence), and electrical engineering (majoring in automation & control) in Germany and Singapore, worked in Germany, Japan, and Singapore. Furthermore, I obtained a Dipl.-Ing. (German MSEE) from Munich University of Technology and a Dipl.-Inform. (German MSCS) from Hagen University. At University of Southern California, I have obtained the obligatory, redundant MS in Computer Science and, recently, completed a Masters in Mechanical Engineering. Check out my curriculum vitae for more information. More information on Jan Peters can be found on his private homepage and on his group's homepage. For a reasonably formatted version of my publications see here.

Jan Peters is a full professor at Darmstadt University of Technology (TU Darmstadt) heading the intelligent systems group while still being affliated with the MPI heading the robot learning lab.

Jan Peters joined the Max-Planck Institute for Biological Cybernetics in April 2007 as a research scientist. Before joining MPI, Jan Peters studied Electrical Engineering, Computer Science and Mechanical Engineering. He graduated from the University of Hagen in 2000 with a Diplom-Informatiker (German M.Sc. in Computer Science) and from Munich University of Technology in 2001 with a Diplom-Ingenieur in Electrical Engineering (German M.Sc. in Electrical Engineering). In 2000-2001, he spent two semesters as visiting student at National University of Singapore. In 2002, he completed a M.Sc. in Computer Science and, in 2005, a M.S. in Mechanical Engineering both from USC. He joined USC's Computer Science Ph.D. program and the CLMC Lab in Fall 2001. Jan Peters has been a visiting research student at the Department of Robotics at the German Aerospace Research Center in Germany, at Siemens Advanced Engineering in Singapore and at the Department of Humanoid Robotics and Computational Neuroscience at the Advanded Telecommunication Research (ATR) Center in Japan. Jan Peters graduated from University of Southern California with a Ph.D. in Computer Science in March 2007. He remains affiliated with the CLMC Lab as an adjunct researcher.

More information on Jan Peters can be found on his private homepage.


Export search results as: [BibTex]

2015
Articles
2014
Books
Articles
  • D. Wierstra, T. Schaul, T. Glasmachers, Y. Sun, J. Peters, J. Schmidhuber (2014). Natural Evolution Strategies Journal of Machine Learning Research, 15, 949-980
  • C. Dann, G. Neumann, J. Peters (2014). Policy Evaluation with Temporal Differences: A Survey and Comparison Journal of Machine Learning Research, 15, 809-883
  • AG. Kupcsik, MP. Deisenroth, J. Peters, L. Ai Poh, V. Vadakkepat, G. Neumann (2014). Model-based Contextual Policy Search for Data-Efficient Generalization of Robot Skills Artificial Intelligence, State: submitted
  • H. Ben Amor, A. Saxena, N. Hudson, J. Peters (2014). Special issue on autonomous grasping and manipulation Autonomous Robots, 36, (1-2), 1-3
Conference Papers
  • R. Lioutikov, A. Paraschos, J. Peters, G. Neumann (2014). Sample-Based Information-Theoretic Stochastic Optimal Control In: Proceedings of 2014 IEEE International Conference on Robotics and Automation, ICRA 2014, State: accepted
  • MP. Deisenroth, P. Englert, J. Peters, D. Fox (2014). Multi-Task Policy Search for Robotics In: Proceedings of 2014 IEEE International Conference on Robotics and Automation, ICRA 2014, State: accepted
  • S. Kamthe, J. Peters, MP. Deisenroth (2014). Multi-modal filtering for non-linear estimation In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014, State: to be published
  • H. Ben Amor, G. Neumann, S. Kamthe, O. Kroemer, J. Peters (2014). Interaction Primitives for Human-Robot Cooperation Tasks In: Proceedings of 2014 IEEE International Conference on Robotics and Automation, IEEE, ICRA 2014, State: accepted
  • S. Manschitz, J. Kober, M. Gienger, J. Peters (2014). Learning to Unscrew a Light Bulb from Demonstrations In: Proceedings of ISR/ROBOTIK 2014, State: accepted
  • R. Calandra, N. Gopalan, A. Seyfarth, J. Peters, MP. Deisenroth (2014). Bayesian Gait Optimization for Bipedal Locomotion In: Proceedings of the 2014 Learning and Intelligent Optimization Conference (LION8), State: to be published
  • O. Kroemer, H. Hoof, G. Neumann, J. Peters (2014). Learning to Predict Phases of Manipulation Tasks as Hidden States In: Proceedings of 2014 IEEE International Conference on Robotics and Automation, ICRA 2014, State: accepted
  • R. Calandra, A. Seyfarth, J. Peters, MP. Deisenroth (2014). An Experimental Comparison of Bayesian Optimization for Bipedal Locomotion In: Proceedings of 2014 IEEE International Conference on Robotics and Automation, ICRA 2014, State: accepted
  • R. Lioutikov, O. Kroemer, J. Peters, GH. Maeda (2014). Learning Manipulation by Sequencing Motor Primitives with a Two-Armed Robot In: Proceedings of the 13th International Conference on Intelligent Autonomous Systems, IAS 2014, State: accepted
2013
Proceedings
  • MP. Deisenroth, C. Szepesvári, J. Peters (2013). Proceedings of the 10th European Workshop on Reinforcement Learning, Volume 24 JMLR, 173 pages, European Workshop On Reinforcement Learning, EWRL 2012
Articles
Conference Papers
  • H. Hoof, O. Krömer, J. Peters (2013). Object Modeling and Segmentation by Robot Interaction with Cluttered Environments In: Proceedings of the IEEE International Conference on Humanoid Robots (HUMANOIDS), IEEE, 13th IEEE-RAS International Conference on Humanoid Robots
  • P. Englert, A. Paraschos, J. Peters, MP. Deisenroth (2013). Model-based Imitation Learning by Probabilistic Trajectory Matching In: Proceedings of 2013 IEEE International Conference on Robotics and Automation (ICRA 2013)
  • H. Ben Amor, D. Vogt, M. Ewerton, E. Berger, B. Jung, J. Peters (2013). Learning Human-Robot Interaction by Imitation IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2013), State: accepted
  • N. Gopalan, MP. Deisenroth, J. Peters (2013). Feedback Error Learning for Rhythmic Motor Primitives In: Proceedings of 2013 IEEE International Conference on Robotics and Automation (ICRA 2013)
  • B. Bocsi, L. Csato, J. Peters (2013). Alignment-based Transfer Learning for Robot Models In: Proceedings of the 2013 International Joint Conference on Neural Networks (IJCNN 2013)
  • C. Daniel, G. Neumann, J. Peters (2013). Autonomous Reinforcement Learning with Hierarchical REPS In: Proceedings of the 2013 International Joint Conference on Neural Networks (IJCNN 2013)
  • E. Sgouritsa, D. Janzing, J. Peters, B. Schölkopf (2013). Identifying Finite Mixtures of Nonparametric Product Distributions and Causal Inference of Confounders In: Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence (UAI), (Ed) A Nicholson and P Smyth, AUAI Press Corvallis, Oregon, USA, 556-565, UAI 2013
  • AG. Kupcsik, MP. Deisenroth, J. Peters, G. Neumann (2013). Data-Efficient Generalization of Robot Skills with Contextual Policy Search In: Proceedings of the 27th National Conference on Artificial Intelligence (AAAI 2013)
  • A. Paraschos, C. Daniel, J. Peters, G. Neumann (2013). Probabilistic Movement Primitives 2616–2624, 27th Annual Conference on Neural Information Processing Systems (NIPS 2013)
  • J. Peters, D. Janzing, B. Schölkopf (2013). Causal Inference on Time Series using Restricted Structural Equation Models In: Advances in Neural Information Processing Systems 26, (Ed) C.J.C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger, 154-162, 27th Annual Conference on Neural Information Processing Systems (NIPS 2013)
  • C. Daniels, G. Neumann, J. Peters (2013). Learning Sequential Motor Tasks In: Proceedings of 2013 IEEE International Conference on Robotics and Automation (ICRA 2013)
  • A. Paraschos, G. Neumann, J. Peters (2013). Robot Trajectory Generation based on Probabilistic Modeling In: Proceedings of the IEEE International Conference on Humanoid Robots (HUMANOIDS), IEEE, 13th IEEE-RAS International Conference on Humanoid Robots
  • G. Neumann, AG. Kupcsik, MP. Deisenroth, J. Peters (2013). Information-Theoretic Motor Skill Learning In: Proceedings of the 27th AAAI 2013, Workshop on Intelligent Robotic Systems (AAAI 2013)
Contributions to books
2012
Articles
  • CH. Lampert, J. Peters (2012). Real-time detection of colored objects in multiple camera streams with off-the-shelf hardware components Journal of Real-Time Image Processing, 7, (1), 31-41
Conference Papers
  • MP. Deisenroth, J. Peters (2012). Solving Nonlinear Continuous State-Action-Observation POMDPs for Mechanical Systems with Gaussian Noise The 10th European Workshop on Reinforcement Learning (EWRL 2012)
  • O. Kroemer, E. Ugur, E. Oztop, J. Peters (2012). A Kernel-based Approach to Direct Action Perception 1-6, IEEE International Conference on Robotics and Automation (ICRA 2012), State: accepted