Harald Bayerlein


Address  

Chair of Cyber-Physical Systems in Production Engineering
School of Engineering and Design, Technical University of Munich
5501.02.107, Boltzmannstraße 15, 85748 Garching b. München

Phone  

+49 (89) 289 - 55175

Email  

h.bayerlein@tum.de

Links  

        

Publications


Journals

H. Bayerlein, M. Theile, M. Caccamo, D. Gesbert,  "Multi-UAV Path Planning for Wireless Data Harvesting with Deep Reinforcement Learning",  in IEEE Open Journal of the Communications Society (2021),  Vol. 2,  May 2021.

Conferences

Jichao Chen, Omid Esrafilian, Harald Bayerlein, David Gesbert, and Marco Caccamo,  "Model-aided Federated Reinforcement Learning for Multi-UAV Trajectory Planning in IoT Networks",  in IEEE Global Communications Conference (GLOBECOM),  Kuala Lumpur, Malaysia,  Dec 2023.

Raphael Trumpp, Harald Bayerlein, David Gesbert,  "Modeling Interactions of Autonomous Vehicles and Pedestrians with Deep Multi-Agent Reinforcement Learning for Collision Avoidance",  in IEEE Intelligent Vehicles Symposium 2022,  Aachen, Germany,  Jun 2022.

M. Theile, H. Bayerlein, R. Nai, D. Gesbert, M. Caccamo,  "UAV Path Planning using Global and Local Map Information with Deep Reinforcement Learning",  in 20th International Conference on Advanced Robotics (ICAR),  Ljubljana, Slovenia,  Dec 2021.

H. Bayerlein, M. Theile, M. Caccamo, and D. Gesbert,  "UAV Path Planning for Wireless Data Harvesting: A Deep Reinforcement Learning Approach",  in Proceedings of IEEE Global Communications Conference (GLOBECOM),  Taipei, Taiwan,  Dec 2020.

M. Theile, H. Bayerlein, R. Nai, D. Gesbert, and M. Caccamo,  "UAV Coverage Path Planning under Varying Power Constraints using Deep Reinforcement Learning",  in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS),  Las Vegas, Nevada, USA,  Oct 2020.

Preprints

Mirco Theile, Harald Bayerlein, Marco Caccamo, and Alberto Sangiovanni-Vincentelli,  "Learning to Recharge: UAV Coverage Path Planning through Deep Reinforcement Learning",  in submitted to IEEE Transactions on Neural Networks and Learning Systems,  .