Papers
5
Total Citations
79
H-Index
4
About
Kai Ploeger is a robotics researcher whose work lies at the intersection of dynamic locomotion, skill acquisition, and real-world reinforcement learning. His key research areas include compliantly actuated quadrupedal robots, skill discovery from raw trajectory data, and high-acceleration manipulation tasks like juggling. Ploeger’s major contributions include demonstrating how the spring-loaded inverted pendulum (SLIP) model can be embodied in the mechanical design of articulated legs for dynamic locomotion gaits, as detailed in his most-cited 2018 paper (44 citations). He has also pioneered methods for enabling robots to learn complex tasks in the physical world, such as juggling with binary rewards under high-acceleration constraints (2020, 13 citations), pushing the limits of actuation and learning. Notably, his work on skill discovery from raw trajectories (2022, 14 citations) offers a natural, intuitive approach for teaching robots sequences of skills without manual segmentation. Ploeger’s research is impactful for its focus on bridging low-order template models with high-dimensional robotic systems, advancing both theoretical understanding and practical deployment of dynamic, learning-enabled robots.
Research Focus
Key Achievements
Top Papers
- 1
- 2SKID RAW: Skill Discovery From Raw Trajectories14 citations · 2022
- 3
- 4High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards5 citations · 2020
- 5Controlling the Cascade: Kinematic Planning for N-ball Toss Juggling3 citations · 2022