Stochastic trajectory optimisation for aircraft in air combat

Games Theory is used to model conflict scenarios where two or more players compete to achieve a predefined objective. This paper presents the development of a stochastic modeling technique to optimise the trajectory of two aircraft in an air combat situation. One aircraft will act as an evader and the other as a pursuer. The study considers pilot and aircraft performance limitations and assumes that each aircraft possesses complete knowledge of the states of the opponent. In optimisation routines, a set of the evader's potential trajectories are randomly generated and evaluated. Each trajectory is played for 100 seconds. The end result is the final distance between both players and the best trajectory is the one that gives the longest distance. This trajectory will be used in main simulation for 100 seconds of play. For the next 100 seconds, optimisation routines are called again to find a new optimised trajectory for use in the main simulation. This process is repeated until both aircraft intercept. A proof-of-concept computer program was written and is presented in this paper