State estimation for a class of nonlinear differential games using differential neural networks

This paper deals with the problem of the state estimation for a certain class of nonlinear differential games, where the mathematical model of this class is completely unknown. Being thus, a Luenberger-like differential neural network observer is applied and a new learning law for its synaptic weights is suggested. Furthermore, by means of a Lyapunov stability analysis, the stability conditions for the state estimation error are established and the upper bound of this error is obtained. Finally, a numerical example illustrates the applicability of this approach.