Davide Scaramuzza

UAVs can explore longer and more efficiently by explicitly optimizing for energy consumption, as demonstrated by a new frontier exploration framework that reduces energy use without sacrificing speed or map quality.

Train high-speed, event-camera-guided quadrotors without expensive event rendering by decoupling representation learning from policy learning.

Quadrotors can now fly significantly faster and more reliably through complex environments by explicitly optimizing trajectories for both speed and visual perception quality.