I am a PhD Student at the Robotics and Perception Group,
advised by Prof. Davide Scaramuzza, and an associated doctoral student at the ETH AI Center.
Previously, I studied at TU Graz and the University of Waterloo, and did my Master's thesis with
Prof. Roland Siegwart at the Autonomous Systems Lab, ETH Zurich.
Research Interests: Robot Learning, (Multi-Agent) Reinforcement Learning, Sim-to-Real, World Models, Computer Vision
Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning
preprint, 2026
ICRA Workshop Outstanding Paper Award
Learning Real-World Acrobatic Flight from Human Preferences
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026
Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flight
IEEE International Conference on Robotics and Automation (ICRA), 2026
GAFAR revisited—Exploring the limits of point cloud registration on sparse subsets
Robotics and Autonomous Systems (RAS), 2025
Multi-Task Reinforcement Learning for Quadrotors
IEEE Robotics and Automation Letters (RA‑L), 2024
Demonstrating Agile Flight from Pixels without State Estimation
Robotics: Science and Systems (RSS), 2024
Best Demo Paper Award
Learning to Open Doors with Physically Interacting Aerial Manipulators
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023
European Conference on Mobile Robots (ECMR), 2023
Coursework and thesis projects from my studies.
Reinforcement Learning for Aerial Manipulation of Articulated Objects
Master's Thesis at the Autonomous Systems Lab (ASL), ETH Zurich · Supervisors: Eugenio Cuniato, Dr. Olov Andersson, Dr. Weixuan Zhang, Dr. Marco Tognon, Prof. Daniel Watzenig, Prof. Roland Siegwart
Point Cloud Registration with Graph Attention Networks
Semester Project at the Institute for Computer Graphics and Vision (ICG), TU Graz · Supervised by Prof. Friedrich Fraundorfer
Final project in the Advanced Image Processing course at the University of Waterloo.
Submission for the Machine Learning Reproducibility Challenge 2021, reproducing results from the paper Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging.
Deep Reinforcement Learning with Hindsight Experience Replay
Bachelor's thesis supervised by Prof. Daniel Watzenig
Literature review on Reinforcement Learning in general and re-implementing Hindsight Experience Replay in Pytorch and OpenAI Gym robotic arm environments.