Neural network approach for solving UAV team cooperative control

One of the key algorithm research areas for unpiloted aerial vehicles team cooperative control is solution of network optimization models. Computational speed is an important success criterion as much of the cooperative work is done in real time. The linear programming (LP) class of approaches has been shown to be the fastest technique according to AFRL's work. In this paper a neural network (NN) approach to solving the constrained LP problem will be introduced and compared to a typical public domain LP solver. Computational time will be used as a comparison and it will be shown that significant time savings results from the NN approach.