一种基于群体智能的无人空战系统

An unmanned air combat system based on swarm intelligence

无人机通常是指由无线电遥控或者由自主控制算法控制的不载人飞行器.相比于有人机,无人机在执行危险任务等方面有着很大的优势,但是目前还没有能够应对高强度空战的无人机系统.此外,在执行空战任务时,单一无人机的鲁棒性往往得不到保证,而多无人机系统不仅能保证鲁棒性,还能通过饱和攻击的方式提高任务的成功率.因此,本文对基于群体智能的多无人机空战系统进行了研究.针对多无人机协同飞抵空战场并完成作战任务的问题,本文对飞机的空气动力学模型和飞机路径上的威胁区域进行了建模,并利用蚁群算法完成了无人机飞抵空战场的航迹规划.在单无人机有限状态机控制算法的基础上,结合多无人机协同,提出了一种多无人机自主控制算法以提高无人机集群在空战中的成功率.本文还搭建了一套仿真平台,对所设计算法的有效性进行了相关测试.

Unmanned aerial vehicles(UAVs) are usually controlled by radio or by autonomous control algorithms. Compared with manned aerial vehicles, they have great advantages in performing dangerous tasks but,presently, no UAV system can cope with high-intensity air combat. In addition, the robustness of a single UAV cannot be guaranteed in air combat missions;on the other hand, a multi-UAV system not only ensures this robustness but also improves the mission success rate by using saturation attacks. Therefore, this paper presents a multi-UAV air combat system based on swarm intelligence. Considering the problem of multi-UAV cooperative arrival at the air battlefield and the accomplishment of combat tasks, the aerodynamic model of the aircrafts and the threat area on the path to the battlefield are modeled;the path planning is completed through an ant colony algorithm. Based on the control algorithm of single-UAV finite-state machine and the cooperation of multiple UAVs, an autonomous control algorithm for multi-UAV systems is proposed to improve the success rate of UAV clusters in air combat. The effectiveness of the proposed algorithm is tested with a simulation platform.