Papers
4
Total Citations
18
H-Index
3
About
Maarten Schoukens is a leading researcher in nonlinear system identification, with a particular focus on developing methods that bridge the gap between high-dimensional, real-world data and robust mathematical models. His work addresses the critical challenge of identifying systems with complex, high-dimensional inputs and outputs—such as those captured by video streams—with direct applications in robotics, autonomous vehicles, and medical imaging. Schoukens has pioneered novel nonlinear state-space identification methods that leverage deep encoders to process video data, enabling more accurate modeling of dynamic systems. He also explores the integration of physics-based models with learning-based augmentation, as demonstrated in his work on industrial robot arms for Model Predictive Control (MPC). Additionally, his contributions to filter-based regularization for impulse response estimation have advanced the theoretical foundations of the field, offering a reformulation of Bayesian kernel-based approaches. With over 18 citations across his most-cited works, Schoukens’ research is shaping the future of data-driven modeling and control, making him a key figure for students and researchers interested in the intersection of machine learning, control theory, and system identification.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4