Jan de Priester

Short Bio

Jan de Priester received his B.S. and M.S. degrees in Mechanical Engineering from the Eindhoven University of Technology, The Netherlands, in 2018 and 2020, respectively. During his bachelor's degree, he enrolled in the Honors Academy: a 2-year extra-curricular program on Big Data focused on machine learning. In 2018 he was part of the winning student team for the Business Process Intelligence Challenge (BPIC) and the Shell Energy Challenge (bachelor's thesis). During his master's degree, he was part of the Dynamics & Control research group. In 2019 he held a visiting research scholar position at UCSC at the Hybrid Systems Laboratory. His master's thesis was on stop-band optimization and structural-aeroacoustic characterization of acoustic micro-slitted resonant metamaterials (results published in the Journal of Applied Acoustics). He held a remote student researcher position at UCSC at the Hybrid Systems Laboratory from May 2021 to September 2022. He is currently pursuing his Ph.D. in the ECE department at the Hybrid Systems Laboratory and received the Chancellor's Fellowship upon admission.

His research interests include safe and high-performance learning-based control for robotic applications by combining/extending ideas from hybrid control and machine learning [1][2]. 

References

  1. [316] MultiHyRL: Robust Hybrid RL for Obstacle Avoidance against Adversarial Attacks on the Observation Space, de Priester, J., Bell Z., Ganesh P., and Sanfelice R. G. , Reinforcement Learning Journal, August, Volume 1, Number 1, (2024)
  2. [265] Hysteresis-Based RL: Robustifying Reinforcement Learning-Based Control Policies Via Hybrid Control, de Priester, J., Sanfelice R. G., and Wouw N. V. D. , Proceedings of the American Control Conference, June, p.2663-2668, (2022)