UAV Formation Shape Control via Decentralized Markov Decision Processes

In this paper, we present a decentralized unmanned aerial vehicle (UAV) swarm formation control approach based on decision theoretic approach. Specifically, pose the UAV motion problem as Markov process (Dec-MDP). Here, goal is to drive from an initial geographical region another where must form three-dimensional shape (e.g., surface of sphere). As most decision-theoretic formulations suffer curse dimensionality, adapt existing fast approximate dynamic programming method called nominal belief-state optimization (NBO) approximately solve problem. We perform numerical studies in MATLAB validate performance above algorithms.