Jan Ole von Hartz
 |
|
PhD Student | |
| Postal address: |
Albert-Ludwigs-Universität Freiburg |
||
| Office: | 201-01-025 | ||
| 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
Affiliations
- Heterodox Academy
Research Interests
- Policy learning
- Representation learning
- Embodied cognition
Current Research Project
Past Research Projects
Teaching
- 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)
Publications
View all my publications on Google Scholar.
Conference Papers
- 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
- Hannah Dames, Jan Ole von Hartz, Mario Kantz, Nicolas Riesterer, Marco Ragni (2018), “Multinomial Processing Models for Syllogistic Reasoning: A Comparison”, Paper presented at the 40th annual cognitive science society meeting
Workshops
- von Hartz, Jan Ole, and Chisari, Eugenio and Welschehold, Tim Valada, Abhinav. ”Self-Supervised Learning of Multi-Object Keypoints for Robotic Manipulation.” In ICRA 2022 Workshop: Reinforcement Learning for Contact-Rich Manipulation.