Fuzzy logic based air-to-air combat algorithm for unmanned air vehicles

Unmanned combat air vehicles (UCAV) are finding increasing use in military applications due to their autonomy, processing capabilities and low cost with respect to manned flights. In order to use the UCAVs in the air to air combat, required algorithms must be carefully designed to enhance them with aerial combat competence. There are challanges for the design of this kind of an algorithm such as real-time operability and the case with inadequate number of sensors on the UAVs. In this paper a novel attack algorithm is introduced for UCAVs, with the assumption that in order to launch an effective attack the pursuer aircraft must be able to follow the target aircraft from behind with a predetermined distance. The attack algorithm consists of navigation and reference velocity calculation steps. In navigation part the reference values for bank, heading and flight path angles are computed. In velocity generation part, a PID based method and a fuzzy inference based method are employed to compute the reference velocity of the pursuer and the results obtained with these two approaches are compared. The performance of this algorithm is assessed with simulations performed in three different scenarios with different initial conditions for the pursuer and the target. Simulation results show that the effectiveness of the proposed fuzzy inference based air to air attack algorithm is better in action with respect to PID based algorithm since various effects that cause the change in velocity, can be incorporated into the fuzzy inference mechanism.