Intelligent Autonomous Systems Lab

Welcome to the Intelligent Autonomous Systems Group of the Computer Science Department of the Technische Universitaet Darmstadt. Our research centers around the goal of bringing advanced motor skills to robotics using techniques from machine learning and control. Please check out our research or contact any of our lab members. As we originated out of the RObot Learning Lab in the Department for Empirical Inference and Machine Learning at the Max-Planck Institute of Intelligent Systems, we also have a few members in Tuebingen.

Our agenda: Creating autonomous robots that can learn to assist humans in situations of daily life is a fascinating challenge for machine learning. While this aim has been a long-standing vision of artificial intelligence and the cognitive sciences, we have yet to achieve the first step of creating robots that can learn to accomplish many different tasks triggered by environmental context or higher-level instruction. The goal of our robot learning laboratory is the investigation of the ingredients for such a general approach to motor skill learning, to get closer towards human-like performance in robotics. We thus focus on the solution of basic problems in robotics while developing domain- appropriate machine-learning methods.

For doing so, we develop methods for learning models and control policy in real time, see e.g., learning models for control and learning operational space control. We are particularly interested in reinforcement learning where we try push the state-of-the-art further on and received a tremendous support by the RL community. Much of our research relies upon learning motor primitives that can be used to learn both elementary tasks as well as complex applications such as grasping or sports.

In case that you are searching for our address or for directions on how to get to our lab, look at our contact information.

We always have thesis opportunities for enthusiastic and driven Masters/Bachelors students (please contact Jan Peters, Marc Deisenroth, Gerhard Neumann or Heni Ben Amor). Check out the currently offered theses (Abschlussarbeiten) or suggest one yourself, drop us a line by email or simply drop by! We also have open Ph.D. or Post-Doc positions please apply.

Some more information on us fore the general public can be found in an article in the Max Planck Research magazine and on the IEEE Blog on Robotics.

News

• Duy Nguyen-Tuong got his last Ph.D. thesis chapter accepted as journal paper: Nguyen-Tuong, D.; Peters, J. (accepted). Online Kernel-based Learning for Task-Space Tracking Robot Control, IEEE Transactions on Neural Networks and Learning Systems
• Heni Ben Amor received a very competitive grant from the Daimler-Benz (Stipendium für Postdoktoranden und Juniorprofessoren) where out of 800 post-docs and junior professors only 10 were funded. See for more information.
• Heni Ben Amor, Oliver Kroemer, Ashutosh Saxena and Jan Peters will organize the IROS 2012 Workshop: Beyond Robot Grasping - Modern Approaches for Dynamic Manipulation.
• Zhikun Wang has a new R:SS paper Wang, Z.;Deisenroth, M; Ben Amor, H.; Vogt, D.; Schoelkopf, B.; Peters, J. (2012). Probabilistic Modeling of Human Dynamics for Intention Inference, Proceedings of Robotics: Science and Systems (R:SS)
• Jens Kober has gotten an Autonomous Robots journal paper accepted: Kober, J.; Wilhelm, A.; Oztop, E.; Peters, J. (2012). Reinforcement Learning to Adjust Parametrized Motor Primitives to New Situations, Autonomous Robots, Springer - Online First  download [PDF]
• Marc Deisenroth, Csaba Szepezvari and Jan Peters organize the 10th European Workshop on Reinforcement Learning (EWRL 2012) as an ICML workshop dedicated to Reinforcement Learning.
• Christian Daniel has gotten an AIStats paper accepted on Daniel, C.; Neumann, G.; Peters, J. (2012). Hierarchical Relative Entropy Policy Search, Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS 2012)  download [PDF] Daniel, C. (2012). Hierarchical Relative Entropy Policy Search, Masters Thesis
• Jan Peters and Pieter Abeel will hold a Tutorial on Reinforcement Learning at the International Conference on Robotics and Automation (ICRA 2012).
• We had two ICRA 2012 papers accepted: (i) Bocsi, B.; Hennig, P.; Csato, L.; Peters, J. (2012). Learning Tracking Control with Forward Models, Proceedings of the International Conference on Robotics and Automation (ICRA)  download [PDF] and (ii) Kroemer, O. ; Ugur, E.; Oztop, E. ; Peters, J. (2012). A Kernel-based Approach to Direct Action Perception, Proceedings of the International Conference on Robotics and Automation (ICRA)  download [PDF]
• Oliver Kroemer has a full NIPS-2011 plenary presentation (~1% acceptance rate) on Kroemer, O.; Peters, J. (2011). A Non-Parametric Approach to Dynamic Programming, Advances in Neural Information Processing Systems 25 (NIPS 2011), Cambridge, MA: MIT Press.  download [PDF]