Genetic Algorithm for Cooperative UAV Task Assignment and Path Optimization
Eugene Edison, Tal Y. Shima · AIAA Guidance, Navigation, and Control Conference and Exhibit · 2008
The problem of assigning a group of uninhabited aerial vehicles to cooperatively perform tasks on multiple stationary ground targets is addressed. A specific set of consecutive tasks needs be performed on each target. A Dubins’ car model is used for motion planning, enabling taking into account each vehicle’s specific constraint of minimum turn radius. By discretizing the possible heading angle of a vehicle while flying over a target we pose the coupled problem of task assignment and path optimization in the form of a graph. This allows obtaining suboptimal trajectory assignments that improve the finer the resolution of the visitation heading angle is. Due to the computational complexity of this coupled problem, we propose a centralized genetic algorithm for the stochastic search of the space of solutions. Results show that the algorithm quickly provides good feasible solutions and converges toward the optimal one. The performance of the genetic algorithm is demonstrated through a Monte Carlo simulation study.