Genetic Algorithm for Dynamic Task Allocation of Multiautonomous Unmanned Air Vehicles (Dept.C)

Abstract

Uninanned aerial vehicles (UAVs) have useful military applications, including reconnaissance, search and destroy, search and rescue missions in hazardous environments such as battlefields or disaster areas. Recently, there has been considerable interest in the possibility of using large teams of UAVs functioning cooperatively to accomplish a large number of tasks e.g. attacking targets However, this requires the assignment of multiple spatially distributed tasks lo each UAV along with a feasible path thai minimizes eflori and avoids threats. Task Allocation (TA) is one of the core steps 10 effectively exploit the capabilities of cooperative control of multiple UAV teams. It is an NP-complete problem non-deterministic polynomial time“. So the computation can't be implemented in real time, no chance for cooperation among the team members, and no autonomy for these vehicles. The reported papers in this field consider the problem in static condition using different techniques (e.g. auction based, scheduling, linear programming). In this paper, a nerve dynamic task allocation algorithm is presented that is based on the principles of genetic algorithm GA). It discusses the adaptation and implementation of the GA search strategy to the task allocation problem in the cooperative control of multiple UAVs. Simulation results indicate that the GA strategy is a feasible approach for the task allocation problem, and the resulted task assignment is near optimal. This means that the total cost of the team is minimized. A major advantage sits low computation cost