Foto von Jakob Thumm

Jakob Thumm, M.Sc.

Technische Universität München

Dienstort

Informatik 6 - Professur für Cyber Physical Systems (Prof. Althoff)

Work:
Boltzmannstr. 3(5607)/III
85748 Garching b. München

LinkedIn: https://www.linkedin.com/in/jakobthumm/ Homepage: https://jakob-thumm.com/ House Mail: Boltzmannstr. 3

Curriculum Vitae

Jakob Thumm joined the Cyber Physical Systems Group as a PhD candidate under the supervision of Prof. Dr.-Ing. Matthias Althoff in February 2021. He received his bachelor's and master's degree in Mechatronics and Information Technology from the Karlsruher Institute of Technology (KIT).

His research focuses on safe motion planning for robots using deep reinforcement learning and formal methods techniques.

Offered Thesis Topics

I am always looking for self-motivated students to solve interesting problems arising in my research areas. If you are interested in one of the currently available topics, or in my research in general and want to write a thesis in this field, send me a mail with a brief statement of motivation and your transcript of records.

Currently Available

Teaching

Practical Course 

Publications

2024

  • Thumm, Jakob; Trost, Felix; Althoff, Matthias: Human-Robot Gym: Benchmarking Reinforcement Learning in Human-Robot Collaboration. Proc. of the IEEE Int. Conf. on Robotics and Automation (ICRA), 2024 mehr…
  • Thumm, Jakob; Trost, Felix; Althoff, Matthias: Human-Robot Gym: Benchmarking Reinforcement Learning in Human-Robot Collaboration. Proc. of the IEEE Int. Conf. on Robotics and Automation (ICRA), 2024 mehr…

2023

  • Hanna Krasowski; Jakob Thumm; Marlon Müller; Lukas Schäfer; Xiao Wang; Matthias Althoff: Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking. Transactions on Machine Learning Research, 2023 mehr…
  • Thumm, Jakob; Pelat, Guillaume; Althoff, Matthias: Reducing Safety Interventions in Provably Safe Reinforcement Learning. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023 mehr…

2022

  • Schepp, Sven R.; Thumm, Jakob; Liu, Stefan B.; Althoff, Matthias: SaRA: A Tool for Safe Human-Robot Coexistence and Collaboration through Reachability Analysis. Proc. of the IEEE International Conference on Robotics and Automation, 2022 mehr…
  • Thumm, Jakob; Althoff, Matthias: Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environments. 2022 International Conference on Robotics and Automation (ICRA), IEEE, 2022 mehr…