Michael Ziegltrum
Papers
1
Total Citations
1
H-Index
1
About
Michael Ziegltrum is a robotics researcher specializing in safe, real-time motion planning and control for autonomous systems. His work centers on integrating formal safety guarantees into sampling-based model-predictive control, with a particular focus on the Model-Predictive Path-Integral (MPPI) framework. His most-cited contribution, "BC-MPPI: A Probabilistic Constraint Layer for Safe Model-Predictive Path-Integral Control" (2025), introduces a novel method that overlays a probabilistic constraint layer onto MPPI, enabling the controller to handle complex, nonlinear safety constraints without sacrificing computational efficiency. This approach is critical for applications in autonomous driving, drone navigation, and human-robot interaction, where real-time safety is paramount. While early in his career, Ziegltrum’s work has already garnered attention for bridging the gap between theoretical safety guarantees and practical, high-speed control. His research is notable for its rigorous mathematical foundation and its potential to make autonomous systems both safer and more agile, positioning him as an emerging leader in the field of safe robot autonomy.
Research Focus
Key Achievements
Top Papers
- 1