Combat simulation using continuous time neural networks

Abstract

This paper focuses on modeling the behavior of commanders in a combat simulation. A military mission is often associated with multiple conflicting goals, including task success, completion time, enemies’ elimination, and own forces survival. In this paper, considering defensive and non-defensive scenarios, and using multi-objective optimization, a model is presented in order to minimize own forces loss and to maximize enemies’ elimination. Also, based on the weighting method and the Karush-Kuhn-Tucker optimality conditions, a continuous time feedback neural network model is designed for solving the proposed multi-objective optimization problem. The main idea of the neural network approach for the proposed multi-objective optimization problem is to establish a dynamic system in the form of first order ordinary differential equations. The proposed neural network does not require any adjustable parameter and its structure enables a simple hardware implementation. The proposed method can act as a consultant for the commander who decides for its forces. Finally, the validity and efficiency of the proposed model are demonstrated by an example.

Keywords

• combat simulation
• neural network
• multi-objective optimization