Gaussian mixture model and receding horizon control for multiple UAV search in complex environment

In this paper, we present a three-layer distributed control structure with certain centralization mechanism to generate the optimal trajectories of multiple unmanned aerial vehicles (UAVs) for searching target in complex environment, based on the method of Gaussian mixture model (GMM) and receding horizon control (RHC). The goal of cooperative searching problem is to obtain the maximum probability of finding the target during given flight time under various constraints, e.g., obstacle/collision avoidance and simultaneous arrival at the given destination. Hence it is taken as a complicated discrete optimization problem in this paper. First, GMM is utilized to approximate the prior known target probability distribution map, and the searching region is hence decomposed where several subregions representing a cluster of target probability can be extracted. Second, these subregions are prioritized hierarchically by evaluating their Gaussian components obtained from GMM, and then allocated to UAVs aiming to maximize the predicted mission payoff. Third, each UAV visits its allocated subregions sequentially, and the corresponding trajectory is obtained by RHC-based concurrent method. Finally, the proposed method is demonstrated and compared with other methods in the simulated scenario. The simulation results show its high efficiency to solve the cooperative searching problem.