Marcel Menner
Papers
5
Total Citations
45
H-Index
4
About
Marcel Menner is a roboticist whose work sits at the intersection of machine learning, control theory, and human-robot interaction. His research focuses on developing algorithms that enable robots to adapt their behavior—whether through human feedback or autonomous online learning. Menner’s most cited work, "Using Human Ratings for Feedback Control," introduces a supervised learning approach to tailor controllers based on subjective human ratings, with a compelling application to gait rehabilitation robots that learn to walk patients physiologically. He has also made significant contributions to legged locomotion, proposing an auto-tuning framework using an Unscented Kalman Filter (UKF) to simultaneously adapt feedback controllers and online trajectory planners for robust robot walking. His work on simultaneous state estimation and contact detection models legged robot movement as a switched system, advancing real-time perception. With over 45 citations across his top papers, Menner’s research is shaping how robots learn from sparse data and uncertain environments, as seen in his work on residual error prediction and constrained Gaussian-process models for magnetic-field SLAM. His achievements demonstrate a clear trajectory toward more intelligent, adaptive, and clinically relevant robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2Auto-Tuning of Controller and Online Trajectory Planner for Legged Robots16 citations · 2022
- 3
- 4
- 5