School of Mechanical and Electronic Information,China University of Geosciences,Wuhan 430074,China. Corresponding author: HE Hong-liang,E-mail: hehongliang@cug. edu. cn
An improved artificial fish swarm algorithm tailored for aircraft route planning was proposed to address the limitations of the traditional artificial fish swarm algorithm. Initially, an improved Sine chaotic mapping was employed for population initialization. On the basis of schooling behavior, an update mechanism based on particle swarm optimization algorithm improved by simulated annealing was incorporated. Furthermore, the following behavior was optimized by adopting multiple adaptive movement step length strategies derived from the wolf pack algorithm. Additionally, the random behavior was replaced with a sine-cosine algorithm, and several adaptive parameters were designed to enhance the search process flexibility. To validate the performance of the proposed algorithm, a three-dimensional mountainous test map was constructed, and analyses were conducted regarding several aspects such as convergence performance, route morphology, and complexity. The results demonstrate that, compared with the traditional algorithm, the improved artificial fish swarm algorithm achieves significant enhancements in indicators such as convergence speed and optimization performance.
仿真部分对比7种算法的性能,为了便于描述,此处采用英文缩写的方式表示各算法:①PSO为基本粒子群算法;②AFSA为传统人工鱼群算法;③AFSA-SCA为正余弦算法替换人工鱼群的随机行为;④AFSA-WCA为利用狼群算法中多种固定步长的方式对人工鱼群的追尾行为进行优化;⑤AFSA-PSO为传统粒子群算法优化人工鱼群的聚群行为;⑥A-P-W-S表示将③,④,⑤的改进方法整合到人工鱼群算法中,是AFSA,PSO,WCA和SCA这4种算法的简单融合;⑦IAFSA(improved artificial fish swarm algorithm,IAFSA)是本文提出的改进算法,IAFSA在A-P-W-S的基础上,应用了基于模拟退火的改进粒子群算法,并加入了自适应鱼群视野和自适应追尾行为步长操作.
LiB W, ZhangH H, ZhangL D, et al. Research on path planning and evaluation method of urban logistics UAV[C]//2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST). Guangzhou, 2021: 1465-1470.
[2]
YangX J, DuZ J, ZhangD Y, et al. Research on dynamic path planning algorithm of UAV[C]//2021 IEEE 4th International Conference on Electronics Technology (ICET). Chengdu, 2021: 946-950.
[3]
LiG Q, LiangD W, ZhaoQ Y, et al. Improved artificial fish swarm algorithm approach to robot path planning problems[C]//2020 5th International Conference on Automation, Control and Robotics Engineering (CACRE). Dalian, 2020: 71-75.
HuKun, ZhangLiang. Penalty function convex optimization iterative algorithm and its application in UAV path planning[J]. Application Research of Computers, 2021, 38(3): 725-728.
[6]
RochaG, BradshawJ. Nonlinear optimal control for autonomous UAV flight planning[C]// 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Vancouver :IEEE,2017:6617-6622.
GuQiu-yi, LiDa-peng. Unmanned aerial vehicle path planning based on improved RRT algorithm[J]. Radio Communications Technology, 2024, 50(6): 1184-1191.
[11]
ZhouZ W, XingX J, LiY, et al. Multi-UAV path planning based on potential field dense reward in unknown environments with static and dynamic obstacles[C]//2023 China Automation Congress (CAC). Chongqing, 2023: 1289-1294.
ZhouWen-juan, ZhangChao-qun, TangWei-dong, et al. A novel modified search and rescue optimization algorithm based on reinforcement learning for UAV path planning[J]. Control and Decision, 2024, 39(4): 1203-1211.
[14]
GeF W, LiK, XuW S, et al. Path planning of UAV for oilfield inspection based on improved grey wolf optimization algorithm[C]//2019 Chinese Control and Decision Conference (CCDC). Nanchang, 2019: 3666-3671.
[15]
LiangQ, YangZ Y, ZhangJ J, et al. An improved sparrow search path planning algorithm for UAV[C]//2023 19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD). Harbin, 2023: 1-6.
[16]
LiuY Z. Improved artificial fish swarm algorithm for UAV path planning in complex environments[J]. International Journal of Advanced Robotic Systems, 2015,12(6):1-10.
[17]
WangG G. A hybrid artificial fish swarm algorithm for solving large-scale reliability-redundancy allocation problems[J]. Applied Soft Computing, 2013,13(5):2517-2532.
[18]
ChenJ L. A multi-objective artificial fish swarm algorithm for UAV path planning[J]. IEEE Transactions on Aerospace and Electronic Systems, 2018,54(3):1235-1247.
[19]
YangX Z. A parallel artificial fish swarm algorithm for UAV path planning in dynamic environments[J]. Journal of Intelligent & Robotic Systems, 2020,98(3/4):1-15.
[20]
YanS K, PanF, XuJ H, et al. Research on UAV path planning based on improved artificial potential field method[C]//2022 2nd International Conference on Computer, Control and Robotics (ICCCR). Shanghai, 2022: 1-5.
[21]
ZhangX, XinB, ChenJ. Differential evolution based path planning for UAVs surveillance in wind[C]//Proceedings of the 32nd Chinese Control Conference. Xi’an, 2013: 4220-4225.
[22]
QiB L, XiongL Y, WangL J, et al. A weights and improved adaptive artificial fish swarm algorithm for path planning[C]//2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC). Chongqing, 2019: 1698-1702.
[23]
HuangY Q, WangP P, YuanM R, et al. Path planning of mobile robots based on logarithmic function adaptive artificial fish swarm algorithm[C]//2017 36th Chinese Control Conference (CCC). Dalian, 2017: 4819-4823.
[24]
HuangS, LiF Y, CaoX, et al. UUV path planning based on GA-AFSA algorithm[C]//2022 5th Asia Conference on Machine Learning and Computing (ACMLC). Bangkok, 2022: 117-121.
[25]
LeiY M, FengZ B. The optimization of fuzzy neural network based on artificial fish swarm algorithm[C]//2013 IEEE 9th International Conference on Mobile Ad-Hoc and Sensor Networks. Dalian, 2013: 469-473.
[26]
LiG Q, LiuQ, YangY W, et al. An improved differential evolution based artificial fish swarm algorithm and its application to AGV path planning problems[C]//2017 36th Chinese Control Conference (CCC). Dalian, 2017: 2556-2561.