基于蚁群算法的无人机协同任务规划研究
Research on UAV Collaborative Task Planning Based on Ant Colony Algorithm
马一凡1
作者信息
- 1. 中国人民解放军战略支援部队信息工程大学,河南郑州 450004
- 折叠
摘要
无人机搜寻具有机动性强、定位精度高的优势.本文结合实际情况,模拟红蓝两方的无人机协同海域规划问题.一是协同搜索问题,利用BFS算法先将热力图可视化,根据蚁群算法将红方无人机最优搜索路线规划出来,再利用K-means聚类算法将多架无人机分配到多个区域,实现无人机协同搜索.二是全区域覆盖问题,通过计算区域圆度是否大于0.86判断是用螺旋法还是割草法搜寻方式,实现全区域覆盖.根据不同的搜寻模式对热点区域进行分割处理,建立蓝方搜寻船的机动模型.
Abstract
Drone search has the advantages of strong maneuverability and high positioning accuracy.Based on the actual situation,simulate the coordinated sea area planning problem of unmanned aerial vehicles from the red and blue sides,and solve two problems:One is the problem of collaborative search.Using the BFS algorithm to first visualize the heat map,and based on the ant colony algorithm to plan the optimal search route for the red drone,then using the K-means clustering algorithm to allocate multiple drones to multiple areas,can achieve collaborative search of drones.The second issue is the issue of full regional coverage.Calculate whether the roundness of the area is greater than 0.86 to determine whether to use the spiral method or the mowing method,which search method to achieve full area coverage.Finally,the hot spot area was segmented according to different search modes,and a maneuvering model of the blue search ship was established.
关键词
线性规划/BFS算法/K-means聚类算法/蚁群算法/几何分析法Key words
linear programming/BFS algorithm/K-means clustering algorithm/ant colony algorithm/geometric analysis method引用本文复制引用
出版年
2024
NETL
NSTL
万方数据