南京航空航天大学学报2025，Vol.57Issue(3)：475-486,12.DOI:10.16356/j.1005-2615.2025.03.009
基于多策略改进蜣螂算法的三维无人机路径规划
3D Path Planning of UAV Based on Multi-strategy Improved Dung Beetle Algorithm
摘要
Abstract
Aiming at the problems of low accuracy,slow convergence and local optimality of traditional dung beetle algorithm in 3D unmanned aerial vehicle(UAV)path planning,a multi-strategy improved dung beetle optimizer(MSIDBO)is proposed.Firstly,spatial pyramid matching(SPM)chaotic mapping and reverse learning strategy are used to initialize the population to improve the diversity and quality of the initial population.Secondly,an improved boundary convergence factor is introduced to achieve the balance between global exploration and local search.Then,the attack mechanism of gull optimization algorithm is integrated to improve the convergence speed and solving accuracy.Finally,the t-distribution differential variation strategy is used to improve the ability of the algorithm to jump out of the local optimal solution.The improved Dung Beetle algorithm is compared with other heuristic algorithms and related improved algorithms by benchmark function test.Compared with other heuristic algorithms and improved algorithms,MSIDBO algorithm has outstanding performance in convergence speed and accuracy.In addition,the improved Dung Beetle algorithm is applied to 3D UAV path planning simulation.Experimental simulation results show that the path cost function generated by MSIDBO algorithm is smaller,the path quality is higher,and the stability is better under different scenarios.关键词
蜣螂算法/空间金字塔匹配混沌映射/反向学习/海鸥优化算法/t-distribution差分变异Key words
dung beetle algorithm/spatial pyramid matching(SPM)chaotic mapping/reverse learning/seagull optimization algorithm/t-distributed difference variation分类
信息技术与安全科学引用本文复制引用
王紫益,王雷,徐浩然,张桐彬,夏强强..基于多策略改进蜣螂算法的三维无人机路径规划[J].南京航空航天大学学报,2025,57(3):475-486,12.基金项目
安徽省高校优秀拔尖人才培育项目(gxbjZD2022023) （gxbjZD2022023）
安徽省机器视觉检测与感知重点实验室开放基金(KLMVI-2024-HIT-15). （KLMVI-2024-HIT-15）
