Bachelor studies in mechanical engineering at RWTH Aachen University with a semester abroad at the University of California in Davis (USA), graduation in 2022. Internship with Siemens AG in Munich on multi-agent reinforcement learning algorithms for machine occupancy scheduling. Subsequent master studies in automation engineering with a semester abroad at Seoul National University (South Korea). Master's thesis at Robert Bosch GmbH in Renningen and the Institute for Data Science in Mechanical Engineering (DSME) on data-driven controller design for hydraulic excavators.

Research associate at the IRS since July 2024.

Automated Parametrization of Motion Planning and Control of Driver Assistance Systems

The motion planning and control of modern driver assistance systems requires a variety of parameters. This includes, for example, the cost function of the optimization problem to determine the vehicle trajectory. These parameters are usually tuned manually to achieve the desired driving behavior. With the growing complexity of these systems, for instance due to extended operating conditions, this approach increasingly reaches its limits. Machine learning methods, on the other hand, allow for a data-driven approach. Goal of the research is to investigate how motion planning and control of driver assistance systems can be parametrized automatically to cover a broad range of vehicle types and scenarios.