Research
* Equal contribution.
Contact-based optimization for collision-free motion planning for a million robots
Extending the mathematics of optimal motion from two robots to entire fleets. By understanding how robots interact through pairwise contacts, we can construct collision-free trajectories without treating every robot as an entirely coupled problem.
arXiv ↗PDF ↗@misc{kamm2026contact, title = {Contact-based optimization for collision-free motion planning for a million robots}, author = {Kamm, Jan and Terpin, Antonio and D'Andrea, Raffaello}, year = {2026}, eprint = {2610.41548}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41548} }A complete analytical characterization of optimal collision-free motion for two robots
Even two robots avoiding each other reveal surprisingly rich mathematical structure. We study how optimal trajectories change as the robots interact, and how this structure can be used to construct solutions systematically.
arXiv ↗PDF ↗@misc{kamm2026analytical, title = {A complete analytical characterization of optimal collision-free motion for two robots}, author = {Kamm, Jan and Terpin, Antonio and D'Andrea, Raffaello}, year = {2026}, eprint = {2610.41558}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41558} }Motion planning for hundreds of floating robots
Planning collision-free motion for hundreds of robots is computationally challenging. We make the problem scalable by identifying smaller groups of interacting robots and planning their motion largely independently.
arXiv ↗PDF ↗Poster ↗Presentation ↗@inproceedings{kamm2026motion, title = {Motion planning for hundreds of floating robots}, author = {Kamm, Jan and Terpin, Antonio and D'Andrea, Raffaello and Ramachandran, Aswin}, booktitle = {2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, publisher = {IEEE}, year = {2026} }Choreographing the Way of Water: A Computational Framework for Aquatic Robotic Art
Turning fleets of autonomous boats into a platform for robotic performances. We developed a system that translates artistic choreography into coordinated motion, bringing together planning, control, and music.
arXiv ↗PDF ↗@inproceedings{ramachandran2026choreographing, title = {Choreographing the Way of Water: A Computational Framework for Aquatic Robotic Art}, author = {Ramachandran, Aswin and Golling, Christopher and Burmester, Sebastian and Sendlhofer, Noa and Kamm, Jan and Jiang, Ruiheng and D'Andrea, Raffaello}, booktitle = {Proceedings of the International Conference on New Interfaces for Musical Expression}, pages = {585--592}, publisher = {Zenodo}, year = {2026} }Scalable Collision-Free Motion Planning for Robot Fleets
How can hundreds of robots plan their motion without getting in each other's way? My thesis explored how identifying local interactions can turn a large, tightly coupled planning problem into smaller, more manageable ones.
@mastersthesis{kamm2026thesis, title = {Scalable Collision-Free Motion Planning for Robot Fleets}, author = {Kamm, Jan}, type = {Bachelor's thesis}, school = {ETH Z{\"u}rich}, year = {2026} }