Photo by Simone Parisi

Eventually, our society will depend on robots as general-purpose helpers that will accompany us throughout our entire lives. This vision requires robots capable of learning motor commands by themselves to manipulate and interact with the world in a way that is useful for us. My work involves the investigation and proposition of learning control algorithms, particularly the representation and transferring of human demonstrations into learned robot policies, and the implementation and validation using real robots.

News and activities

  • November 2018. I am giving an invited talk at Preferred Networks on machine learning perspectives in robot control.
  • September 2018. I am serving as Associate Editor for ICRA 2019 (as such, I am not reviewing papers submitted to ICRA 2019).
  • August 2018. Our paper “Reinforcement Learning of Phase Oscillators for Fast Adaptation to Moving Targets” was accepted to CoRL 2018! Check the paper and the video.


  • May 2018. I am presenting our latest work at the Okinawa Institute of Science and Technology as part of the “AI and Brain Science” and “Adaptive Circuit Shift” Joint Area Meeting in May.
  • May 2018. New Frontiers journal paper
    • Ewerton, M.; Rother, D.; Weimar, J.; Kollegger, G.; Wiemeyer, J.; Peters, J.; Maeda, G. (2018). Assisting Movement Training and Execution with Visual and Haptic Feedback, Frontiers in Neurorobotics.[pdf][BibTeX]
  • April 2018. New RAS journal paper
    • Koc, O., Maeda, G., Peters, J.  (2018). Online optimal trajectory generation for robot table tennis. Robotics and Autonomous Systems (RAS), vol. 105, pp. 121-137.[pdf][BibTeX]
  • I will be serving as Area Chair for CoRL 2018.
  • I am Associate Editor for IROS 2018.
  • Two papers accepted at ICRA 2018.
  • Presenting our work on active learning at CoRL 2017.
  • I am transitioning from TU Darmstadt to ATR.