Robert Gieselmann

I am an AI Researcher at Amazon in Berlin. My work focuses on developing fast, verifiable, and self-improving reasoning agents, primarily leveraging Large Language Models (LLMs). Previously, I completed a PhD in Computer Science at KTH Royal Institute of Technology in Stockholm, supervised by Florian T. Pokorny, and supported by WASP, the Wallenberg AI, Autonomous Systems and Software Program. I completed several research internships, including at Meta and Bosch AI. Before my PhD, I worked as a Research Assistant within machine learning and robotics at the Technical University of Hamburg (TUHH). I received my M.Sc. in Robotics, Cognition, Intelligence from the Technical University of Munich (TUM).


LinkedIn  /  Google Scholar  /  Github


Research



Fast-dRRT*: Efficient Multi-Robot Motion Planning for Automated Industrial Manufacturing
Andrey Solano, Arne Sieverling, Robert Gieselmann, Andreas Orthey
Arxiv , 2024
[Paper]


Expansive Latent Planning for Sparse Reward Offline Reinforcement Learning
Robert Gieselmann, Florian T. Pokorny
Conference on Robot Learning (CORL) , 2023 (oral presentation 6.6%)
Previously RSS 2023 - Workshop on Learning for Task and Motion Planning (spotlight)
[Paper]


Latent Planning via Expansive Space Trees
Robert Gieselmann, Florian T. Pokorny
Neural Information Processing Systems (NeurIPS) , 2022 (acceptance rate 25.6%)
[Paper]


DLO@Scale - A Large-Scale Meta Dataset for Learning Non-Rigid Object Pushing Dynamics
Robert Gieselmann, Alberta Longhini, Alfredo Reichlin, Danica Kragic, Florian T. Pokorny
[Paper][Website]
Workshop on Physical Reasoning and Inductive Biases for the Real World, NeurIPS , 2021


Planning-Augmented Hierarchical Reinforcement Learning
Robert Gieselmann, Florian T. Pokorny
IEEE Robotics and Automation Letters (RA-L), 2021
[Paper]


ReForm: A Robot Learning Sandbox for Deformable Linear Object Manipulation
Rita Laezza*, Robert Gieselmann*, Florian T. Pokorny, Yiannis Karayiannidis
IEEE International Conference on Robotics and Automation (ICRA) , 2021
[Paper]


Standard Deep Generative Models for Density Estimation in Configuration Spaces: A Study of Benefits, Limits and Challenges
Robert Gieselmann, Florian T. Pokorny
IEEE International Conference on Intelligent Robots and Systems (IROS) , 2020
[Paper]


Experience-Based Heuristic Search: Robust Motion Planning with Deep Q-Learning
Julian Bernhard, Robert Gieselmann, Klemens Esterle, Alois Knoll
IEEE International Conference on Intelligent Transportation Systems (ITSC) , 2018
[Paper]