Cooperative Unmanned Aerial Vehicles formation via decentralized LBMPC

In this paper, a team of cooperative Unmanned Aerial Vehicles (UAVs) maintains a desired geometrical formation while tracking a reference trajectory using a new control approach. Decentralized Learning Based Model Predictive Control (DLBMPC) is a new control technique that combines statistical learning along with control engineering while providing guarantees on safety, robustness and convergence. The ability of the proposed DLBMPC controller in solving the problem of formation for a team of cooperative UAVs is solved in simulation. The designed controller respects the general formation constraints known as Reynolds rules of flocking. Our main contribution in this paper lays in the stabilization of a group of cooperative UAVs, in a desired formation, while tracking a reference trajectory using DLBMPC in the presence of model uncertainties.