Marcello Chiaberge

A novel control architecture reduces steady-state attitude error in underactuated spacecraft by integrating model predictive control with a physics-informed neural network and a Lyapunov safety layer.

Navigating caves is hard, so here's a new multimodal dataset with ground truth motion capture to help robots see in the dark.

Ditch the features: VinePT-Map uses vine trunks and poles as persistent landmarks, enabling robust robot localization across seasons in challenging vineyard environments.