Kai Ploeger
Research Interests
Robotics, Motor Skill Learning, Reinforcement Learning, Control
Affiliation
TU Darmstadt, Intelligent Autonomous Systems, Computer Science Department
Contact
kai.ploeger@tu-darmstadt.de
kai@robot-learning.de
Room E226, Building S2|02, TU Darmstadt, FG-IAS, Hochschulstr. 10, 64289 Darmstadt
+49-6151-16-20074
Kai joined the Intelligent Autonomous Systems Group at TU Darmstadt as a Ph.D. researcher in January 2021. Previously, he received his bachelor‘s degree in Electrical Engineering and Information Technology from TU Dortmund, as well as his master’s degree in Autonomous Systems from TU Darmstadt.
Since then, Kai has fallen down the rabbit hole of robot juggling, which is a more serious research topic than it sounds — though only slightly. Juggling is a surprisingly rich testbed for studying the role of feedback in motor skill learning, both in the sense of a control signal and a learning signal. It combines throwing, which offers no meaningful feedback to react to, and catching, which depends entirely on it. It also scales from trivially easy to absurdly hard with a single change to the pattern, so there is always a harder version to fail at. The official goal of the PhD is to understand all of this. His personal goal is to make the robot juggle better than him, a bar that gets easier to clear every year.
Publications
Juggling
- Ploeger, K.; Peters, J. (submitted). Task-Error Residual Learning for Real-Robot Five-Ball Juggling, Submitted to International Symposium on Robotics Research.
- Chowdhury, A.; Maurer, H.; Kshirsagar, A.; Ploeger, K.; Peters, J.; Müller, H.; Maurer, L.K. (in press). The Earlier You Know, the Smoother You Act: The Earlier You Know, the Smoother You Act: Anticipatory Control in Solo and Dyadic Juggling, Experimental Brain Research.
- Lippert, J.R.; Ploeger, K.; Chowdhury, A.; Müller, H.; Peters, J.; Kshirsagar, A. (2026). Catch, Throw, Repeat: Planning for Human–Robot Partner Juggling, Proceedings of the IEEE International Conference on Intelligent Systems and Robots (IROS).
- Gomez Andreu, M.A.; Ploeger, K.; Peters, J. (2024). Beyond the Cascade: Juggling Vanilla Siteswap Patterns, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
- Ploeger, K.; Peters, J. (2022). Controlling the Cascade: Kinematic Planning for N-ball Toss Juggling, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
- Ploeger, K.; Lutter, M.; Peters, J. (2020). High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards, Conference on Robot Learning (CoRL).
Other
- Klink, P.; Wolf, F.; Ploeger, K.; Peters, J.; Pajarinen, J. (submitted). Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning, Submitted to the IEEE Transactions on Robotics (T-Ro).
- Tanneberg, D.; Ploeger, K.; Rueckert, E.; Peters, J. (2021). SKID RAW: Skill Discovery from Raw Trajectories, IEEE Robotics and Automation Letters (RA-L).
- Lakatos, D.; Ploeger, K.; Loeffl, F.; Seidel, D.; Schmidt, F.; Gumpert, T.; John, F.; Bertram, T.; Albu-Schäffer, A. (2018). Dynamic locomotion gaits of a compliantly actuated quadruped with slip-like articulated legs embodied in the mechanical design, IEEE Robotics and Automation Letters (RA-L).