I'm a Doctoral Fellow at the ETH AI Center and ETH Zürich, supervised by Prof. Marc Pollefeys and Prof. Stefan Leutenegger. I work on robots that understand scenes by interacting with them: mobile manipulation, force-grounded perception and scene understanding.
Most robots map a room by looking at it. I'm interested in what they learn by interacting with it: pressing a light switch to find out which lamp it controls, or opening drawers and cabinets to recover how they move and what is inside.
Two doors can look the same and still need very different effort. I record and model the forces of real interactions, from a dataset of people opening things with force and touch sensing to digital twins that capture friction, springs and door closers, and use them to control robots.
Hoi!-A Multimodal Dataset for Force-Grounded, Cross-View Articulated ManipulationForceTwin
Robots share spaces with people and their devices. I have worked on localizing legged robots, phones and headsets in the same map, on a mixed-reality interface for directing several robots at once, and on learning where a robot should look from human egocentric video.
ForceTwin: Physics-informed Digital Twins for Robotic Manipulation from Instrumented Human Interaction→
Tim Engelbracht, René Zurbrügg, Mayank Mittal, Marco Hutter, Marc Pollefeys, Hermann Blum, Zuria Bauer · arXiv 2026 preprint
@article{engelbracht2026forcetwin,
title = {{ForceTwin}: Physics-informed Digital Twins for Robotic Manipulation from Instrumented Human Interaction},
author = {Tim Engelbracht and René Zurbrügg and Mayank Mittal and Marco Hutter and Marc Pollefeys and Hermann Blum and Zuria Bauer},
journal = {arXiv preprint arXiv:2609.21751},
year = {2026},
eprint = {2609.21751},
archivePrefix = {arXiv}
}LIME: Learning Intent-aware Camera Motion from Egocentric Video→
Boyang Sun, Jiajie Li, Yung-Hsu Yang, Chenyangguang Zhang, Tim Engelbracht, Sunghwan Hong, Cesar Cadena, Marc Pollefeys, Hermann Blum · arXiv 2026 preprint
@article{sun2026lime,
title = {{LIME}: Learning Intent-aware Camera Motion from Egocentric Video},
author = {Boyang Sun and Jiajie Li and Yung-Hsu Yang and Chenyangguang Zhang and Tim Engelbracht and Sunghwan Hong and Cesar Cadena and Marc Pollefeys and Hermann Blum},
journal = {arXiv preprint arXiv:2607.02417},
year = {2026},
eprint = {2607.02417},
archivePrefix = {arXiv}
}Articulated 3d scene graphs for open-world mobile manipulation→
Martin Büchner, Adrian Röfer, Tim Engelbracht, Tim Welschehold, Zuria Bauer, Hermann Blum, Marc Pollefeys, Abhinav Valada · arXiv 2026 preprint
@article{buchner2026articulated,
title = {Articulated 3d scene graphs for open-world mobile manipulation},
author = {Martin Büchner and Adrian Röfer and Tim Engelbracht and Tim Welschehold and Zuria Bauer and Hermann Blum and Marc Pollefeys and Abhinav Valada},
journal = {arXiv preprint arXiv:2602.16356},
year = {2026},
eprint = {2602.16356},
archivePrefix = {arXiv}
}Hoi!-A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation→
CVPR 2026Tim Engelbracht, René Zurbrügg, Matteo Wohlrapp, Martin Büchner, Abhinav Valada, Marc Pollefeys, Hermann Blum, Zuria Bauer
@inproceedings{engelbracht2026hoi,
title = {{Hoi}!-A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation},
author = {Tim Engelbracht and René Zurbrügg and Matteo Wohlrapp and Martin Büchner and Abhinav Valada and Marc Pollefeys and Hermann Blum and Zuria Bauer},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2026},
eprint = {2512.04884},
archivePrefix = {arXiv}
}Spotlight: Robotic scene understanding through interaction and affordance detection→
Humanoids 2025Tim Engelbracht, René Zurbrügg, Marc Pollefeys, Hermann Blum, Zuria Bauer
project pagearXivpapercodevideo
@inproceedings{engelbracht2025spotlight,
title = {{Spotlight}: Robotic scene understanding through interaction and affordance detection},
author = {Tim Engelbracht and René Zurbrügg and Marc Pollefeys and Hermann Blum and Zuria Bauer},
booktitle = {IEEE-RAS International Conference on Humanoid Robots (Humanoids)},
year = {2025},
doi = {10.1109/Humanoids65713.2025.11203097},
eprint = {2409.11870},
archivePrefix = {arXiv}
}Crocodl: Cross-device collaborative dataset for localization→
CVPR 2025Hermann Blum, Alessandro Mercurio, Joshua O'Reilly, Tim Engelbracht, Mihai Dusmanu, Marc Pollefeys, Zuria Bauer
@inproceedings{blum2025crocodl,
title = {{Crocodl}: Cross-device collaborative dataset for localization},
author = {Hermann Blum and Alessandro Mercurio and Joshua O'Reilly and Tim Engelbracht and Mihai Dusmanu and Marc Pollefeys and Zuria Bauer},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2025},
doi = {10.1109/CVPR52734.2025.02554}
}Spot-On: A Mixed Reality Interface for Multi-Robot Cooperation→
CVPR Workshop 2025Tim Engelbracht, Petar Lukovic, Tjark Behrens, Kai Lascheit, René Zurbrügg, Marc Pollefeys, Hermann Blum, Zuria Bauer
@inproceedings{engelbracht2025spot,
title = {{Spot-On}: A Mixed Reality Interface for Multi-Robot Cooperation},
author = {Tim Engelbracht and Petar Lukovic and Tjark Behrens and Kai Lascheit and René Zurbrügg and Marc Pollefeys and Hermann Blum and Zuria Bauer},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
year = {2025},
eprint = {2505.22539},
archivePrefix = {arXiv}
}Cool people, fun to work with ;)
Working on something related, or just curious about what I do? I'd love to hear from you. Drop me a few lines about what you have in mind. And if it's something unrelated, I'm always happy to see if I can help ;)