I am interested in multi-robot systems 'in-the-wild' -- field robotics, that brings robot teams into their real (deployment) environments. This means I get to look at practical solutions to planning, coordination, and learning mutual interactions, while also developing full-stack integrative systems (control, networking, mechanical effectors..). My recent work (with my collaborators) is an effort into making multi-robot teams more realistic. This includes efficiently learning mutual-interaction forces between aerial systems, RL for non-trivial team behaviours, language (LLM) conditioning for navigating robot teams, and classical distributed systems for managing aerial swarms.

During my PhD, I worked on aerial platforms that can perform physical/tactile interactions with other airborne entities (parachutes, cargo, even another multicopter in the air). This capability makes them far more useful agents in bringing them closer to the physical world and maintain long-range autonomy. I've developed systems, mechanisms and algorithms that have allowed two multicopters to transfer a (cargo) payload between them without having to land, intercept free-drifting parachutes, and even dock mid-air.

In my post-doc work and beyond, I am looking at extending many of these ideas to multi-robot settings, where classical control strategies need to mix with data-driven (ML) solutions for the combinatorial problems. I am ultimately interested in how these systems, when brought closer and closer to our physical worlds, create novel opportunities for us to sense the atmosphere, measure properties of air and water, and even explore previously unmodeled phenomena in real time.