مأموریت مشترک برای چندین ناوگان هوایی بر اساس الگوریتم هوشمندانه خود سازمان یافته است

This paper proposes an intelligent self-organized algorithm (ISOA) to solve a cooperative search-attack mission planning problem for multiple unmanned aerial vehicles (multi-UAV). This algorithm adopts the distributed control architecture which divides the global optimization problem into several local optimization problems. Each UAV is able to solve its own local optimization problem, and then make the optimal decision for the multi-UAV system through the information exchange among UAVs. The search-attack mission planning process is divided into two phases, the one is waypoints generation under constraints of UAV's maneuverability, collision avoidance and maximum range, the other is path generation which takes account of the threat avoidance. In the first phase, an improved distributed ant colony optimization (ACO) algorithm is presented to carry out the mission planning and generate waypoints. Considering the range constraint of UAV, a new state transition rule is designed to guide UAV back to its initial point within the maximum flight range. In the second phase, Dubins curve is employed to smoothly connect the waypoints generated by the ACO. As for the unexpected threats during the flight, an online threat avoidance method is proposed to replan the paths. Finally, simulations are carried out to analyze the convergence performance, external responsiveness and internal scalability of the proposed ISOA for the multi-UAV search-attack mission planning problem.