一种面向城市战的无人机路径规划群智能算法

doi:10.12382/bgxb.2023.0869

摘要/Abstract

摘要：

针对传统路径规划算法用于解决无人机战术路径规划问题时存在局部最优、慢收敛等问题,提出一种改进的群智能算法,以改变初始种群的更新方式,提升灰狼算法的全局寻优能力并加快其收敛速度。引入莱维飞行随机策略以及共生生物搜索算法,借助莱维飞行策略更新种群个体,利用共生生物搜索算法偏利共生阶段的交互性避免陷入局部最优问题。威胁建模是UAV路径规划的重要前提,对威胁物进行等效预处理,结合适应度函数检验算法。设计一种虚实映射仿真验证平台,通过以实映虚的手段验证算法的有效性。实验结果表明,改进后的算法改善了传统路径规划算法的局部最优和慢收敛等路径规划问题,对UAV作战能力的提升具有一定参考价值。

关键词: 无人机路径规划, 灰狼算法, 莱维飞行策略, 共生生物搜索算法

Abstract:

For the traditional path planning algorithm used to solve the tactical path planning problem of unmanned aerial vehicle, there are some problems, such as local optimum and slow convergence. In this paper, an improved grey wolf algorithm is proposed, which changes the updating mode of the initial population, improves the global optimization ability of grey wolf algorithm and speeds up its convergence speed. The Lévy flight random strategy and symbiotic search algorithm are introduced. The Lévy flight strategy isused to update the population individuals, and the symbiotic search algorithm is usedto avoid the local optimal problem. Threat modeling is an important prerequisite for UAV path planning, and the equivalent preprocessing of the threats is performed,and the algorithm is verifiedby combining the fitness function. And a simulation verification platform, incorporating virtual-to-real mapping, was designed to validate the algorithm’s effectiveness through a real-to-virtual approach. The experimental results show that the improved algorithm effectively improves the path planning problems such as local optimum and slow convergence of the traditional path planning algorithm, and has a certain reference value for the improvement of UAV combat capability.

Key words: unmanned aerial vehicle path planning, grey wolf algorithm, the Lévy flight random strategy, symbiotic search algorithm

中图分类号:

TP391

卢颖, 庞黎晨, 陈雨思, 宋婉莹, 傅妍芳. 一种面向城市战的无人机路径规划群智能算法[J]. 兵工学报, 2023, 44(S2): 146-156.

LU Ying, PANG Lichen, CHEN Yusi, SONG Wanying, FU Yanfang. A Swarm Intelligence Algorithm for UAV Path Planning in Urban Warfare[J]. Acta Armamentarii, 2023, 44(S2): 146-156.

图/表 21

图1 威胁建模

Fig.1 Threat modelling

图2 UAV路径规划二维示意图

Fig.2 Two-dimensional schematic diagram of UAV path planning

图3 UAV路径规划三维示意图

Fig.3 Three-dimensional schematic diagram of UAV path planning

图4 威胁度量的计算

Fig.4 Calculation of threat measure

图5 三维威胁度量的计算

Fig.5 Calculation of three-dimensional threat measure

图6 AirSim总体框架

Fig.6 AirSim overall framework

图7 仿真平台框架图

Fig.7 Simulation platform frame diagram

表1 威胁区域信息

Table 1 Threat area information

案例	威胁中心/m	威胁半径/m	高度/m
	(350,100)	80	500
	(200,600)	150	800
	(600,150)	100	500
案例1	(450,800)	75	300
	(680,400)	120	500
	(850,600)	70	750
	(150,250)	80	700
	(750,800)	100	1000
	(200,200)	100	1000
	(380,450)	150	1000
	(550,150)	125	650
案例2	(250,750)	150	800
	(750,450)	100	600
	(800,250)	150	850
	(500,700)	150	1000
	(800,850)	100	750

图8 案例1:三维路径规划

Fig.8 Case 1:three-dimensional path planning

图9 案例1:三维路径规划俯视图

Fig.9 Case 1:top view of three-dimensional path planning

图10 案例2:三维路径规划

Fig.10 Case 2:three-dimensional path planning

图11 案例2:二维路径规划俯视图

Fig.11 Case 2:top view of three-dimensional path planning

图12 案例1:收敛曲线

Fig.12 Case 1: convergence curves

图13 案例2:收敛曲线

Fig.13 Case 2: convergence curves

图14 运动轨迹对比

Fig.14 Comparison of motion trajectories

表2 采样的真实、虚拟UAV各轴方向上的运动轨迹误差率平均值

Table 2 Average error rate of motion trajectories of sampled real and virtual UAVs in each axis direction

x轴运动轨迹误差率平均值	y轴运动轨迹误差率平均值	z轴运动轨迹误差率平均值
0.2494	0.2392	0.2420

图15 UE4场景图

Fig.15 UE4 Scenario

表3 任务目标点信息

Table 3 Task target point information

任务目标点	起始点/m	任务目标点/m	移动威胁运动方向/(m·s^-1)
1	(0, 0, 0)	(81, 25, 10)	(0, 1, 0)
2	(0, 0, 0)	(55, 57, 20)	(1, 0, 0)
3	(0, 0, 0)	(85, 70, 4)	(0, 0, 1)

图16 UAV朝向目标点1运动

Fig.16 UAV moving towards target point 1

图17 平均碰撞次数

Fig.17 Mean number of collisions

图18 平均飞行时间

Fig.18 Mean flight time

参考文献 20

[1]	张文昌. 运用与思考[J]. 国防科技工业, 2023(4):47-49.
	ZHANG W C. UAV application and thinking[J]. Defence Science & Technology Industry, 2023(4):47-49. (in Chinese)
[2]	RAGAB M, ALTALBE A, ALGHAMDI A M, et al. A drones optimal path planning based on swarm intelligence algorithms[J]. Computers Materials & Continua, 2022(7):365-380.
[3]	白玉. 四旋翼无人机的应用与发展综述[J]. 广西农业机械化, 2020(2):7,9.
	BAI Y. A review of the application and development of four-rotor UAV[J]. Guangxi Agricultural Mechanization, 2020(2):7,9. (in Chinese)
[4]	刘永琦, 徐丹, 程归, 等. 基于改进A^*算法的无人机快速轨迹规划方法[J]. 飞行力学, 2020, 38(2): 40-46.
	LIU Y Q, XU D, CHEN G, et al. Fast trajectory planning method of UAV based on improved A^* algorithm[J]. Flight Mechanics, 2020, 38(2): 40-46. (in Chinese)
[5]	AGGARWAL S, KUMAR N. Path planning techniques for unmanned aerial vehicles:a review, solutions, and challenges[J]. Computer Communications, 2020, 149:270-299. doi: 10.1016/j.comcom.2019.10.014 URL
[6]	尹依伊, 王晓芳, 周健. 基于Q学习的多协同航迹规划方法[J]. 兵工学报, 2023, 44(2): 484-495. doi: 10.12382/bgxb.2021.0606
	YIN Y Y, WANG X F, ZHOU J. Q-Learning-based Multi-UAV Cooperative Path Planning Method[J]. Acta Armamentarii, 2023, 44(2): 484-495. (in Chinese) doi: 10.12382/bgxb.2021.0606
[7]	ZHOU L T, WU N P, CHEN H. RRT-fuzzy dynamic window approach (RRT-FDWA) for collision-free path planning[J]. Applied Sciences, 2023, 13(9):5234. doi: 10.3390/app13095234 URL
[8]	郭晓静, 杨卓橙. 基于邻域拓展的静态路径规划A^*算法研究[J]. 计算机工程与应用, 2022, 58(8):168-174. doi: 10.3778/j.issn.1002-8331.2010-0222
	GUO X J, YANG Z C. Research on A^* algorithm of static path planning based on neighborhood extension[J]. Computer Engineering and Applications, 2022, 58(8):168-174. (in Chinese)
[9]	陈智康, 刘佳, 王丹丹, 等. 改进Dijkstra机器人路径规划算法研究[J]. 天津职业技术师范大学学报, 2020, 30(3):30-35.
	CHEN Z K, LIU J, WANG D D, et al. Research on improved path planning algorithm of dijkstra robot[J]. Journal of Tianjin University of Technical and Education, 2020, 30(3):30-35. (in Chinese)
[10]	傅亮, 刘峰, 刘书勇, 等. 基于改进D*Lite的二维路径连续动态规划算法[J/OL]. 无线电通信技术, 2023(2023-11-13).[2023-11-30]. http://kns.cnki.net/kcms/detail/13.1099.TN.20231101.1357.002.html.
	FU L, LIU F, LIU S Y, et al. Two-dimensional path continuous dynamic programming algorithm based on improved D*Lite[J/OL]. Radio Communications Technology, 2023(2023-11-13)..[2023-11-30]. http://kns.cnki.net/kcms/detail/13.1099.TN.20231101.1357.002.html. (in Chinese)
[11]	ZHANG H, LI Z M, JIANG X Y, et al. Beetle colony optimization algorithm and its application[J]. IEEE Access, 2020, 8: 128416-128425. doi: 10.1109/Access.6287639 URL
[12]	DEWANGAN R, SHUKLA A, GODFREY W. Three dimensional path planning using grey wolf optimizer for UAVs[J]. Applied Intelligence, 2019, 49(6): 2201-2217. doi: 10.1007/s10489-018-1384-y
[13]	LI Y, LIN X X, LIU J S. An improved grey wolf optimization algorithm to solve engineering problems[J]. Sustainability, 2021, 13(6): 3208. doi: 10.3390/su13063208 URL
[14]	王永琦, 江潇潇. 基于混合灰狼算法的机器人路径规划[J]. 计算机工程与科学, 2020, 42(7): 1294-1301.
	WANG Y Q, JIANG X X. Robot path planning using a hybrid grey wolf optimization algorithm[J]. Computer Engineering & Science, 2020, 42(7): 1294-1301. (in Chinese)
[15]	CHEN Y, YU J, MEI Y, et al. Modifiedcentral force optimization (MCFO) algorithm for 3D UAV path planning[J]. Neurocomputing, 2016, 171:878-888. doi: 10.1016/j.neucom.2015.07.044 URL
[16]	XU C, DUAN H, LIU F. Chaotic artificial bee colony approach to uninhabited combat air vehicle (UCAV) path planning[J]. Aerospaceence & Technology, 2010, 14(8):535-541.
[17]	MIRJALILI S, MIRJALILI S M, LEWIS A D. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69:46-61. doi: 10.1016/j.advengsoft.2013.12.007 URL
[18]	GOLDANLOO, JAVANMARD M, GHAREHCHOPOGH, et al. A hybrid OBL-based firefly algorithm with symbiotic organisms search algorithm for solving continuous optimization problems[J]. The Journal of Supercomputing, 2021, 78:3998-4031. doi: 10.1007/s11227-021-04015-9
[19]	李阳, 李维刚, 赵云涛, 等. 基于莱维飞行和随机游动策略的灰狼算法[J]. 计算机科学, 2020, 47(8): 291-296. doi: 10.11896/jsjkx.190600107
	LI Y, LI W G, ZHAO Y T, et al. Grey wolf algorith-m based on Levy flight and random walk strategy[J]. Computer Science, 2020, 47(8):291-296. (in Chinese)
[20]	GUERRERO M, CASTILLO O, GARCÍA M, Cuckoo search via Lévy flights and acomparison with genetic algorithms[J]. Fuzzy Logic Augmentation of Nature-Inspired Optimization Metaheuristics. Berlin,Germany:Springer, 2015, 574:91-103.