Special Seminar with Giuseppe Loianno

Autonomous mobile robots will play a critical role in addressing diverse time-sensitive and hazardous tasks, including logistics, reconnaissance, search and rescue missions, indoor and outdoor monitoring, transportation, and construction. Future smart cities will need to reconsider their current transportation and delivery systems. Small-scale aerial and ground robots will navigate in dense urban environments to deliver in a timely manner various items, ranging from medical supplies to fresh groceries. To handle these challenges effectively, robots must be Super Autonomous or USARC: Unmanned, Small, Agile, Resilient, and Collaborative in complex, cluttered, unknown, and dynamic environments.

In this talk, I will discuss recent research results on developing super autonomous robots. Achieving this goal requires reimagining the existing perception-action paradigm governing robot autonomy. This entails shifting the existing autonomy system from a sequential to a concurrent approach through a principled combination of physics-based and data-driven techniques across modeling, perception, learning, and control while accounting for the interplay between perception and action. This transition will produce more accurate models and representations of the world and potentially unify perception and action representations. Consequently, this will boost agility, resilience, and improve both individual and collaborative decision-making processes for small-scale robots.