Aerial Shepherds: Coordination among UAVs and Swarms of Robots

We address the problem of deploying groups of tens or hundreds of unmanned ground vehicles (UGVs) in urban environments where a group of aerial vehicles (UAVs) can be used to coordinate the ground vehicles. We envision a hierarchy in which UAVs with aerial cameras can be used to monitor and command a swarm of UGVs, controlling the splitting and merging of the swarm into groups and the shape (distribution) and motion of each group. We call these UAVs Aerial Shepherds. We show a probabilistic approach using the EM algorithm for the initial assignment of shepherds to groups and present behaviors that allow an efficient hierarchical decomposition. We illustrate the framework through simulation examples, with applications to deployment in an urban environment.