Patrick Hart is a research scientist at fortiss and a Ph.D. student at the Technical University of Munich and fortiss. His main research interest is how agents can learn complex behaviors in uncertain environments using reinforcement learning. 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 Ph.D.. At fortiss, he gained valuable insights in the field of autonomous driving working on autonomous valet parking, on 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.
For more information have a look at my personal website .
Informatik 6 - Lehrstuhl für Robotik, Künstliche Intelligenz und Echtzeitsysteme (Prof. Knoll)
- Tel.: work +49 89 3603522 562
- Homepage: https://www.in.tum.de/i06/people/patrick-hart-msc/
- BARK: Open Behavior Benchmarking in Multi-Agent Environments. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020 mehr…
- Counterfactual Policy Evaluation for Decision-Making in Autonomous Driving. IROS 2020 Workshop Perception, Learning, and Control for Autonomous Agile Vehicles, 2020 mehr…
- Graph Neural Networks and Reinforcement Learning for Behavior Generation in Semantic Environments. Intelligent Vehicles Symposium, 2020 mehr…
- Lane-Merging Using Policy-based Reinforcement Learning and Post-Optimization. 2019 IEEE Intelligent Transportation Systems Conference (ITSC), IEEE, 2019 mehr…
- Bridging the Gap between Open Source Software and Vehicle Hardware for Autonomous Driving. 2019 IEEE Intelligent Vehicles Symposium (IV), IEEE, 2019 mehr…
|0000005307||Masterpraktikum - Planning Robust Behavior for Autonomous Driving (IN2106, IN4251)|