Research theme
Agile, dense aerial swarms
Dense, agile swarm flight with downwash control, cooperative docking, scalable kinodynamic planning, and outdoor deployment.
We build the algorithms and platforms for flying dense robot swarms in tight indoor and outdoor spaces. Our work spans scalable kinodynamic planning that respects the full continuous dynamics of each vehicle, aerodynamic-aware control that accounts for downwash coupling between neighbors, and cooperative docking maneuvers. Recent results include concrete multi-agent path planning that guarantees collision-free, dynamically feasible trajectories for dozens of drones, and dynamics-aware diffusion methods for generating smooth multi-robot flight plans.
Recent papers
- Concrete multi-agent path planning enabling kinodynamically aggressive maneuvers npj Robotics · 2026
- CoViS-Net: A Cooperative Visual Spatial Foundation Model for Multi-Robot Applications CoRL 2024 · 2024
- D4orm: Multi-Robot Trajectories with Dynamics-aware Diffusion Denoised Deformations IROS 2025 · 2025
- DVM-SLAM: Decentralized Visual Monocular Simultaneous Localization and Mapping for Multi-Agent Systems ICRA 2025 · 2025
People
- Amanda Prorok
- Jennifer Gielis
- Lorenzo Magnino
- Maxence Boels
- Michael Amir
- Peter Woo
- Rishabh Jain
- Sridhar Sola