Je. Steck et Sn. Balakrishnan, USE OF HOPFIELD NEURAL NETWORKS IN OPTIMAL GUIDANCE, IEEE transactions on aerospace and electronic systems, 30(1), 1994, pp. 287-293
A Hopfield neural network architecture is developed to solve the optim
al control problem for homing missile guidance. A linear quadratic opt
imal control problem is formulated in the form of an efficient paralle
l computing device known as a Hopfield neural network. Convergence of
the Hopfield network is analyzed from a theoretical perspective, showi
ng that the network, as a dynamical system, approaches a unique fixed
point which is the solution to the optimal control problem at any inst
ant during the missile pursuit. Several target-intercept scenarios are
provided to demonstrate the use of the recurrent feedback neural net
formulation.