Urban Fasel
Papers
2
Total Citations
9
H-Index
2
About
Urban Fasel is a researcher at the forefront of merging machine learning with control theory, with a focus on aerial robotics and parametric systems. His work centers on developing robust, computationally efficient control strategies for challenging domains, particularly insect-scale Micro Aerial Vehicles (MAVs) and parametric partial differential equations (PDEs). A key contribution is his 2023 paper on deep-learned tube Model Predictive Control (MPC), which enables accurate, high-rate trajectory tracking on sub-gram soft-actuated aerial robots despite severe model uncertainties and fast dynamics. This work, already garnering 7 citations, addresses a critical bottleneck in miniaturized robotics. In 2024, Fasel advanced the field of parametric PDE control by introducing a novel framework that combines deep reinforcement learning with L₀ sparse polynomial policies, achieving optimal control for complex systems across engineering and science. His research not only pushes the boundaries of what is possible with tiny, agile robots but also provides scalable solutions for high-dimensional control problems. Fasel’s achievements highlight his ability to integrate deep learning and control theory, making him a rising figure in the intersection of robotics and scientific machine learning.
Research Focus
Key Achievements
Top Papers
- 1
- 2