Intelligent optimal control for simultaneous attack problem
Zilun Hu, Yang Jianying · 2017
This paper proposes an online adaptive dynamic programming (ADP) based algorithm to solve the simultaneous attack problem with multiple missiles against a maneuvering target. In contrast to typical cooperative strategy, in this paper we considerate the optimality of the strategy as well as the convergence of the system. To obtain the optimal control, we adopt a new architecture called `cost function-based single network adaptive critic'. This approach is suitable to solve a wide class of nonlinear systems where the optimal control equation can be expressed in terms of the state and cost-related variables. In the present algorithm, a cost function is employed to coordinate the missiles movement. A neural network is designed to approach the optimal cost. Optimal control for each missile is obtained by finding the derivatives of the output of the network with respect to its input and using it in the expression for optimal control.