Sebastian Trimpe
Max Planck Institute for Intelligent Systems, RWTH Aachen University
Papers
30
Total Citations
661
H-Index
10
About
Sebastian Trimpe is a robotics and control systems researcher whose work sits at the intersection of machine learning, autonomous systems, and real-world control engineering. He is best known for developing methods that make robotic systems simultaneously safe, efficient, and adaptive — a notoriously difficult balance to strike in practice. Among his most influential contributions is his work combining robust model predictive control (MPC) with deep neural networks to achieve fast, safety-guaranteed tracking on robot manipulators (221 citations), demonstrating that principled control theory and modern machine learning can be powerfully unified. His research on balancing simulations with physical experiments using Bayesian optimization (111 citations) addresses a critical bottleneck in reinforcement learning deployment, offering a practical framework for data-efficient policy tuning. Trimpe has also advanced wireless control systems for smart manufacturing and cyber-physical applications, exploring how feedback loops can be reliably closed over low-power wireless networks — work that underpins next-generation industrial automation. His contributions extend to soft millirobots for biomedical applications and safe global optimization methods like GoSafeOpt, which enable failure-free exploration of complex dynamical systems. Across these domains, Trimpe's research has accumulated substantial scholarly impact, establishing him as a significant voice in intelligent, learning-enabled control.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Feedback control goes wireless47 citations · 2019
- 5Sliding Mode Control with Gaussian Process Regression for Underwater Robots41 citations · 2020
- 6
- 7
- 8
- 9
- 10