Mathijs Schuurmans
Postdoctoral Researcher | Optimization, Control & Machine Learning
About
I am a postdoctoral working at the intersection of optimization, control theory, and machine learning. I completed my PhD at the department of Electrical Engineering at KU Leuven under the supervision of Panos Patrinos.
I have since been awarded an FWO postdoctoral fellowship for the development of new methods that close the gap between theory and practice for safety guarantees in learning-enabled control systems.
News
2025-11
Submitted a new paper to ECC
2025-10
Officially started my FWO postdoctoral fellowship
Publications
For a more complete and up-to-date list of my publications, see my
Google Scholar
page.
Risk-Sensitive Model Predictive Control for Interaction-Aware Planning–A Sequential Convexification Algorithm
IEEE Control Systems Letters, 9:1916-1921, 2025
Optimal intraday power trading for single-price balancing markets: An adaptive risk-averse strategy using mixture models
Applied Energy, 389:125754, 2025
Probabilistic Safety under Arbitrary Disturbance Distributions using Piecewise-Affine Control Barrier Functions
arXiv preprint arXiv:2512.04194, 2025
EM++: A parameter learning framework for stochastic switching systems
arXiv preprint arXiv:2407.16359, 2024
A general framework for learning-based distributionally robust MPC of Markov jump systems
IEEE Transactions on Automatic Control, 68(5):2950--2965, 2023
Safe, learning-based MPC for highway driving under lane-change uncertainty: A distributionally robust approach
Artificial Intelligence, 320:103920, 2023
Interaction-aware model predictive control for autonomous driving
2023 European Control Conference (ECC), 2023
SPOCK: A proximal method for multistage risk-averse optimal control problems
IFAC World Congress on Automatic Control, 2023
Distributionally robust optimization using cost-aware ambiguity sets
IEEE Control Systems Letters, 7:1855--1860, 2023
Teaching
Model Predictive Control
Teaching Assistant, 2019-2025
EAGLE
Technical Expert, 2019-2021