status: available from March 2027 · NL work-eligible
Robotics engineer building machine learning that holds up with small data and real, variable humans.
MSc Robotics at TU Delft, with a thesis on data-efficient ML for touchscreen haptics. Background in legged robots, model predictive control and motion planning. Currently also helping to get an AI rescue drone into the field.
research2026
Predicting finger–touchscreen friction under electrostatic actuation from small, highly user-dependent data. The work compares six model families, tests cross-participant generalisation, and identifies a real-time-feasible feature set.
engineering · BEng thesis2021
A pair of robotic legs that walks with its wearer and carries the load. I built the IMU-based gait perception and the phase-synchronised gait control. They were tested in Simulink and then on a 15 kg prototype during 10-minute walking trials.
engineering · Team project2022
A linear model predictive controller on linearised quadrotor dynamics, with a DARE-based terminal cost to guarantee stability and recursive feasibility. Validated in 3D simulation across different horizons and constraint sets.
engineering · Team project2022
A ROS planner built from scratch: occupancy mapping, k-PRM with a KD-tree, A* search, and minimum-snap and corridor-based trajectory optimisation (solved with OSQP). Benchmarked against RRT variants in forest and maze environments.
engineering · Solo2026
A solo entry in a national challenge run by Team Epoch and TNO: an ensemble classifier for bird species from radar tracks, plus a system design that turns calibrated predictions into targeted wind-turbine curtailment.
side project2026
In the base game, AI rulers build almost nothing but castles. This mod rewrites their holding-building logic so that castles, cities and temples are chosen by terrain, culture, government type and ruler personality. It's a small, focused behaviour change, and players adopted it widely: #14 in the Workshop's most-popular list for the past year and #10 for the past six months (Sep 2026), five months after its April release.
for engineering teams
for PhD committees
Data about humans is expensive to collect and varies strongly between people. I work on models that learn from a few calibration samples and still generalise across users, using physics as a prior. My current application is haptics, and I'm equally interested in HRI, wearables and AI for games. I also have an IEEE ICARM publication and a patent from earlier work on wearable robots.
