Patrick Hart, M.Sc.

Patrick Hart is a PhD student at the Technical University of Munich and fortiss. His main research interest is how agents can learn complex behaviors in uncertain environments. He obtained his Master's degree from the Karlsruhe Institute of Technology and wrote his master thesis at the FZI Karlsruhe about search-based motion planning for autonomous vehicles in 2016. In 2017, he then joined the autonomous systems group at fortiss and began to pursue his PhD. At fortiss, he gained valuable insights in the field of autonomous driving working on autonomous valet parking, autonomous vehicles, and on simulation. He is the initiator of BARK machine learning (BARK-ML) and one of the initiators and main developers of BARK.

Foto von Patrick Hart

Patrick Hart


Informatik 6 - Lehrstuhl für Robotik, Künstliche Intelligenz und Echtzeitsysteme (Prof. Knoll)

Guerickestraße 25
80805 München


  • Hart, Patrick; Knoll Alois: Kinodynamic Motion Planning Using Multi-Objective Optimization. 2018 IEEE Intelligent Vehicles Symposium, 2018
  • Esterle, Klemens; Hart, Patrick; Bernhard, Julian; Knoll, Alois: Spatiotemporal Motion Planning with Combinatorial Reasoning for Autonomous Driving. IEEE International Conference on ​Intelligent Transportation Systems, 2018
  • Hart, Patrick; Rychly Leonard; Knoll, Alois: Lane-Merging Using Policy-based Reinforcement Learning and Post-Optimization
  • Kessler et al.:Bridging the Gap between Open Source Software and Vehicle Hardware for Autonomous Driving
  • Bernhard, Julian; Esterle, Klemens; Hart, Patrick; Kessler, Tobias: BARK: Open Behavior Benchmarking in Multi-Agent Environments