About me
I am a third-year PhD student at the Technical University of Munich (TUM) in the Learning Systems and Robotics Lab (LSY), advised by Prof. Angela Schoellig. I develop algorithms for robots to learn to safely perform complex tasks in the real world. For this, I am mostly using generative robot policies, such as vision-language-action models (VLAs). I am particularly interested in uncertainty quantification, continual and reinforcement learning of these models.
Before joining LSY, I obtained a MSc in Electrical and Computer Engineering at TUM in 2023 and a BSc in Mechatronics at FAU Erlangen-Nuremberg in 2020, funded by the German Academic Scholarship Foundation. During my studies, I spent a semester at EPFL and conducted research in machine learning for robotic throwing with Prof. Aude Billard. Previously, I also worked with Prof. Sandra Hirche at TUM and with Prof. Knut Graichen at FAU. In 2021, I did a research internship in optimal control for autonomous driving at Bosch Research in Renningen, Germany.
Student Supervision: I am always open to supervising excellent and ambitious Master and Bachelor students for a semester project or thesis. You can find a non-exhaustive list of potential topics here. If you want to work with me, please send me an email describing your area of interest and attach your CV and up-to-date transcripts.
News
| 07/26 | I gave an invited talk at the RSS Workshop on Trustworthy Embodied Foundation Models. At the Diffusion for Robot Learning Workshop, we received the best paper award! [Impressions] |
| 06/26 | I gave an invited talk at the Robot Learning Lab at the University of Freiburg. [Impressions] |
| 04/26 | Our paper “CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion” has been accepted to the IEEE Robotics and Automation Letters (RA-L). [Website] |
| 04/26 | I have started as a visiting researcher at the [Learning and Adaptive Systems Group] at ETH Zurich, hosted by Prof. [Andreas Krause]. |
| 03/26 | Our paper “CRISP - Compliant ROS2 Controllers for Learning-Based Manipulation Policies and Teleoperation” has been accepted to IEEE Robotics and Automation Practice (RA-P). [Website] |
| 12/25 | I have presented FIPER at NeurIPS in San Diego, California, and summarized my 8 takeaways on the state of embodied AI & robotics research: [Takeaways] |
| 11/25 | I was invited to participated as a tutor at the 1st RIG Bootcamp on Foundational Behavior Models to push collaborative VLA research in Germany! [Impressions] |
| 09/25 | “Failure Prediction at Runtime for Generative Robot Policies” has been accepted at NeurIPS! |
| 06/25 | I have presented DPCC at L4DC at the University of Michigan, Ann Arbor. [Impressions] |
| 03/25 | Our paper “Semantically Safe Robot Manipulation: From Semantic Scene Understanding to Motion Safeguards” has been accepted for the Robotics and Automation Letters (RA-L). [PDF] |
| 02/25 | Our paper “Diffusion Predictive Control with Constraints (DPCC)” has been accepted at the Learning for Dynamics & Control Conference (L4DC). [PDF] |
| 01/25 | Our paper “Flying through Moving Gates without Full State Estimation” has been accepted at the IEEE International Conference on Robotics and Automation (ICRA). [PDF] |
| 09/24 | We are organizing a workshop “Mastering Robot Manipulation in a World of Abundant Data” on November 9 at the Conference on Robot Learning (CoRL) in Munich. [Website] |
| 07/24 | I have presented our paper “Is Data All That Matters? The Role of Control Frequency for Learning-Based Sampled-Data Control of Uncertain Systems” at ACC in Toronto, Canada. [Video] |
| 05/24 | I have presented our RA-L paper and a workshop paper “Safe Offline Reinforcement Learning using Trajectory-level Diffusion Models” at ICRA in Yokohama, Japan. Check out the workshop paper here! |
| 01/24 | Our paper “Is Data All That Matters? The Role of Control Frequency for Learning-Based Sampled-Data Control of Uncertain Systems” has been accepted at the American Control Conference (ACC). [PDF] |
| 12/23 | I have joined the Learning Systems and Robotics Lab at TUM as a PhD student, advised by Prof. Angela Schoellig. |
| 10/23 | Our paper “Vision-Based Uncertainty-Aware Motion Planning Based on Probabilistic Semantic Segmentation” has been published in the Robotics and Automation Letters (RA-L). [PDF] |