I am now a Robotics Research Engineer at Ocado Technology. You can still reach me via marco@robot-learning.de.

Marco Ewerton

Research Interests

Artificial Intelligence, Machine Learning, Robotics, Imitation Learning, Human-Robot Interaction, Motor Skill Learning

More Information

Curriculum Vitae Google Citations ResearchGate Loop DBLP Academia.edu ORCID Publons GitHub

Contact Information

Mail. Marco Ewerton
marco@robot-learning.de

Marco Ewerton is a Ph.D. student at the IAS under the supervision of Guilherme Maeda and Jan Peters since January 2015. He works on the BIMROB project, which investigates how humans and robots can improve their movements by interacting with each other.

He obtained his master's degree in Electrical and Information Engineering from the TU Darmstadt in 2014. His master's thesis work focused on modeling human-robot interaction with probabilistic movement representations (video here).

From April 2012 to December 2013, he was a research assistant at the IAS under the supervision of Heni Ben Amor. During that time, the main topics of Marco's work were "3D reconstruction from multiple Kinect cameras" and "Human-Robot Interaction".

Research Interests

Artificial Intelligence, Machine Learning, Robotics, Imitation Learning, Human-Robot Interaction, Motor Skill Learning

Key References

    •     Bib
      Ewerton, M.; Neumann, G.; Lioutikov, R.; Ben Amor, H.; Peters, J.; Maeda, G. (2015). Learning Multiple Collaborative Tasks with a Mixture of Interaction Primitives, Proceedings of the International Conference on Robotics and Automation (ICRA), pp.1535--1542.
    . Best Paper Award Finalist, Best Student Paper Award Finalist and Best Service Robotics Paper Award Finalist
    •     Bib
      Ewerton, M.; Maeda, G.J.; Peters, J.; Neumann, G. (2015). Learning Motor Skills from Partially Observed Movements Executed at Different Speeds, Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), pp.456--463.
    •     Bib
      Ewerton, M.; Maeda, G.; Neumann, G.; Kisner, V.; Kollegger, G.; Wiemeyer, J.; Peters, J. (2016). Movement Primitives with Multiple Phase Parameters, Proceedings of the International Conference on Robotics and Automation (ICRA), pp.201--206.
    •     Bib
      Ewerton, M.; Maeda, G.J.; Kollegger, G.; Wiemeyer, J.; Peters, J. (2016). Incremental Imitation Learning of Context-Dependent Motor Skills, Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), pp.351--358.
    •     Bib
      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.
    •       Bib
      Ewerton, M.; Arenz, O.; Maeda, G.; Koert, D.; Kolev, Z.; Takahashi, M.; Peters, J. (2019). Learning Trajectory Distributions for Assisted Teleoperation and Path Planning, Frontiers in Robotics and AI.

Code

MATLAB code on Learning Motor Skills from Partially Observed Movements Executed at Different Speeds: code related to the work "Learning Motor Skills from Partially Observed Movements Executed at Different Speeds", IROS 2015.

MATLAB code on Pointing Out Mistakes in Japanese Characters: code related to Section 3 (Processing Demonstrations and Assessing the Correctness of Observed Trajectories) of the paper "Assisting Movement Training and Execution with Visual and Haptic Feedback", Frontiers in neurorobotics, 2018.

MATLAB code on Relevance Weighted Policy Optimization: code related to Section 5 (Relevance Weighted Policy Optimization) of the paper "Assisting Movement Training and Execution with Visual and Haptic Feedback", Frontiers in neurorobotics, 2018.

Python code on PRO + GP Regression: code related to the papers "Learning Trajectory Distributions for Assisted Teleoperation and Path Planning", Frontiers in Robotics and AI, 2019 and "Reinforcement Learning of Trajectory Distributions: Applications in Assisted Teleoperation and Motion Planning", IROS 2019.

Videos

Semi-Autonomous Robots at TU Darmstadt: Learning Multiple Collaborative Tasks (ICRA 2015)

Quick explanation of "Mixture of Interaction Primitives" recorded by Robohub at ICRA 2015

Estimating the phase of the execution of the human movement for human-robot interaction (IROS 2015)

Incremental Imitation Learning of Context-Dependent Motor Skills (HUMANOIDS 2016)