首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于改进蚁群算法的山区无人机路径规划方法
引用本文:唐立,郝鹏,张学军.基于改进蚁群算法的山区无人机路径规划方法[J].交通运输系统工程与信息,2019,19(1):158-164.
作者姓名:唐立  郝鹏  张学军
作者单位:1. 西华大学 汽车与交通学院,成都 610039;2. 北航(西部)国际创新港,成都 610000; 3. 北京航空航天大学 电子信息工程学院,北京 100083
基金项目:四川省科技厅项目/Sichuan Provincial Science and Technology Program(17RKX0108);西华大学自然科学重点基金/2015 Natural Science Key Foundation of Xihua University(Z1520315);汽车测控与安全四川省重点实验室开放课题/Open Research Subject of Key Laboratory of Vehicle Measurement, Control and Safety(szjj2016-014).
摘    要:对无人机在山区执行应急物资运输任务时的飞行路径规划问题进行研究.基于对无人机的性能分析与比选,探讨了路径规划的约束条件,提出了一种考虑路径安全度的改进蚁群算法.首先,基于高海拔山峰的位置构造泰森多边形,获取无人机在山区避障飞行条件下的路径可行解;其次,为避开山峰密集区域,建立路径安全度约束,缩小可行解范围;进而,利用蚁群算法搜索最短路径;最后,消除路径中不必要的障碍点以进一步缩短距离,并综合考虑无人机性能参数对拐角进行平滑处理,获得最终可用于实际飞行的最优安全路径.算例分析表明,改进的蚁群算法较传统算法收敛速度更快,且生成的路径更短.

关 键 词:航空运输  路径规划  改进蚁群算法  无人机  应急物资运输  
收稿时间:2018-09-11

An UAV Path Planning Method in Mountainous Area Based on an Improved Ant Colony Algorithm
TANG Li,HAO Peng,ZHANG Xue-jun.An UAV Path Planning Method in Mountainous Area Based on an Improved Ant Colony Algorithm[J].Transportation Systems Engineering and Information,2019,19(1):158-164.
Authors:TANG Li  HAO Peng  ZHANG Xue-jun
Institution:1. School of Automobile and Transportation, Xihua University, Chengdu 610039, China; 2. The Beihang University International Center for Innovation in Western China, Chengdu 610000, China; 3. School of Electricity and Information Engineering, Beihang University, Beijing 100083, China
Abstract:This paper studies the UAV flight route planning problem when carrying out emergency cargo transportation mission in mountainous area. Based on the performance analysis and comparison of UAVs, constraints of path planning is discussed, and an improved ant colony algorithm considering path safety is proposed. Firstly, a Tyson polygon is formulated based on the location of high altitude mountains, and then a feasible UAV path solution under flight condition of obstacle avoidance in mountainous area is obtained. Secondly, in order to avoid dense peaks area, path safety constraints are built. Thirdly, the shortest path is searched by ant colony algorithm. Finally, the unnecessary obstacles in the path are eliminated so as to further shorten the distance, and the corners are smoothed considering the performance parameters of UAVs, generating the optimal safe path which can ultimately be used for an actual flight. The example analysis shows the improved ant colony algorithm converges faster and generates shorter path than traditional one.
Keywords:air transportation  path planning  improved ant colony algorithm  UAV  emergency cargo transportation  
本文献已被 CNKI 等数据库收录!
点击此处可从《交通运输系统工程与信息》浏览原始摘要信息
点击此处可从《交通运输系统工程与信息》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号