Lennart Röstel

PhD Student @ Technical University of Munich (TUM)

with the TUM Learning AI for Dextrous Robots Lab

LinkedInEmail

Publications

I'm a PhD student researching reinforcement learning, state estimation, and sim2real for robotic applications.
In my research, I develop realistic simulations and train robust manipulation behavior for multi-fingered robotic hands. 

Learning a Shape-Conditioned Agent for Purely Tactile In-Hand Manipulation of Various Objects

Johannes Pitz*, Lennart Röstel*, Leon Sievers and Berthold Bäuml
Accepted at 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 

Estimator-Coupled Reinforcement Learning for Robust
Purely Tactile In-Hand Manipulation

Lennart Röstel, Johannes Pitz, Leon Sievers and Berthold Bäuml
2023 IEEE-RAS International Conference on Humanoid Robots

Dextrous Tactile In-Hand Manipulation Using a Modular Reinforcement Learning Architecture

Johannes Pitz, Lennart Röstel, Leon Sievers and Berthold Bäuml
2023 IEEE International Conference on Robotics and Automation (ICRA)

Learning a State Estimator for Tactile In-Hand Manipulation

Lennart Röstel, Leon Sievers , Johannes Pitz and Berthold Bäuml
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Get in contact: lennart.roestel@tum.de