Jan Ole von Hartz
 |
PhD Student | |
| Postal address: |
Albert-Ludwigs-Universität Freiburg |
|
| Office: | 080-01-024 | |
| Email: | hartzj@cs.uni-freiburg.de | |
| Phone: | +49 761 203-8029 | |
About me
- 12/2022 - current: Ph.D. Student in the Robot Learning, and Neurorobotics labs, University of Freiburg
- 05/2020 - 11/2022: M.Sc. in Computer Science with minor in Neuroscience, University of Freiburg
- 09/2019 - 04/2020: Erasmus stay at ESIEE Paris
- 09/2015 - 08/2019: B.Sc. in Computer Science with minor in Cognitive Science, University of Freiburg
Research Interests
- Policy learning
- Representation learning
- Embodied cognition
Current Research Project
Past Research Projects
Teaching
- TA Deep Learning Lab, Summer 25
- TA Deep Learning Lab, Summer 24
- TA Learning with Limited Supervision Seminar, Summer 24
- TA Robot Learning Seminar, Winter 23/24
- TA Deep Learning Lab, Summer 23
Students
- Jonas Fischer: Parametrized GMMs for Robotic Manipulation
- Rafael Andrioli Bauer: Neuro-CEILing: Interactive Learning via EEG
- Sven Pfitzer: Object keypoints for robot skill adaptation
- Peter Koenigstein: Foundation Models for Dense Correspondence
- Lukas Schweizer: Task-Parameterized Conditional Flow Matching
- Yaëlle Gaillard: Task-Parameterized Diffusion Policy
- Abdelrahman Mansour: Latent Skill Learning (w. Nick Heppert)
- Khiem Vu Duy: Grasping and Manipulation with Softhand (w. Eugenio Chisari)
- Jan Gruhnert: Graph Neural Networks for Continual Hierarchical Reinforcement Learning
- Erich Choudhury: PolicyGuide: Inference Time Policy Guidance from Language using Unstructured Data (w. Nick Heppert)
- Lukas Schweizer: In-Context Policy Learning
- Jan Gruhnert: Federated Hierarchical Reinforcement Learning
- Nils Schmidt: Bimanual Few-Shot Policy Learning
- Michael Wernthaler: Probabilistic Guitar Tablature Transcription
Publications
View all my publications on Google Scholar.
Conference and Journal Papers
- Jan Ole von Hartz, Abhinav Valada, Joschka Boedecker. "One Hand Watches The Other: Dynamic Multi-Agent Cooperation for Sample-Efficient Bimanual Manipulation in Dynamic Environments." arXiv:2607.22119 (2026)
- Jan Ole von Hartz, Lukas Schweizer, Joschka Boedecker, Abhinav Valada. "MSG: Multi-Stream Generative Policies for Sample-Efficient Robotic Manipulation." in IEEE Robotics and Automation Letters (2026).
- Jan Ole von Hartz, Adrian Röfer, Joschka Boedecker, Abhinav Valada. "The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning." in IEEE Transactions on Robotics (2026).
- Eugenio Chisari, Jan Ole von Hartz, Fabien Despinoy, Abhinav Valada "Robotic Task Ambiguity Resolution via Natural Language Interaction." in Transactions of the Conference on Intelligent Robots and System 2025.
- Daniel Honerkamp, Harsh Mahesheka, Jan Ole von Hartz, Tim Welschehold, Abhinav Valada , "Whole-body teleoperation for mobile manipulation at zero added cost," in IEEE Robotics and Automation Letters.
- Jan Ole von Hartz, , Tim Welschehold, Abhinav Valada, Joschka Boedecker, "The Art of Imitation: Learning Long-Horizon Manipulation Tasks from Few Demonstrations," in IEEE Robotics and Automation Letters, doi: 10.1109/LRA.2024.3487506.
- Jan Ole von Hartz, Eugenio Chisari, Tim Welschehold, Wolfram Burgard, Joschka Boedecker, Abhinav Valada, "The Treachery of Images: Bayesian Scene Keypoints for Deep Policy Learning in Robotic Manipulation," in IEEE Robotics and Automation Letters, vol. 8, no. 11, pp. 6931-6938, Nov. 2023, doi: 10.1109/LRA.2023.3313917.
- Raghu Rajan, Jessica Lizeth Borja Diaz, Suresh Guttikonda, Fabio Ferreira, André Biedenkapp, Jan Ole von Hartz, Frank Hutter (2023), "MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning", in JAIR
Workshop Papers
- Jan Ole von Hartz, Eugenio Chisari, Tim Welschehold, Abhinav Valada ”Self-Supervised Learning of Multi-Object Keypoints for Robotic Manipulation.” In ICRA 2022 Workshop: Reinforcement Learning for Contact-Rich Manipulation.