基于智能算法的无人机航迹规划

doi:10.16180/j.cnki.issn1007-7820.2019.02.003

摘要/Abstract

摘要：

文中针对多无人机在复杂约束条件下编队协同、巡航范围内覆盖率高的问题,基于K-means算法和Hop-field神经网络算法实现了一种无人机整体航迹规划方法。对任务要求的禁飞区域、目标区域建立任务区域的数字地图模型,进行模型分解合理的将有效区域分解为多个子目标点。随后采用K-means算法对无人机巡航的目标点进行聚类,并结合Hop-field神经网络算法对同类子目标点进行无人机航迹规划。以无人机在抗震救灾中的真实数据为实例,通过仿真实现了巡航区域90%的覆盖率,验证了文中方法的鲁棒性和有效性。

关键词: 无人机, 编队协同, 航迹规划, 模型区域分解技术, K-means算法, Hop-field神经网络算法, 覆盖率

Abstract:

This paper proposed a new method for UAV route planning based on K-means algorithm and Hop-field neural network algorithm, which dealt with the formation of multi UAVs under complex constraints and high coverage cruise. A digital map model of the task area was established for the no-fly zone, the target zone and the valid zone required by the mission and the model decomposition was performed to reasonably decompose the effective area into multiple sub-target points. Then the K-means algorithm was used to cluster the target points of UAV cruise, and the Hop-field neural network algorithm was used to carry out UAV trajectory planning for similar sub-target points. Taking the real data of UAV in earthquake relief as an example, the coverage ratio of 90% of the cruise area was simulated, which proved the robustness and effectiveness of the proposed method.

Key words: UAV, formation teamwork, path planning, model area decomposition technique, K means algorithm, Hop field neural network algorithm, coverage ratio

中图分类号:

TP29

岳秀,张伟. 基于智能算法的无人机航迹规划[J]. 电子科技, 2019, 32(2): 9-13.

YUE Xiu,ZHANG Wei. UAV Path Planning Based on Intelligent Algorithm[J]. Electronic Science and Technology, 2019, 32(2): 9-13.

图/表 2

参考文献 17

[1]	王海波, 林久辉, 李永涛 . 军用无人机的应用与发展趋势[J]. 科技视界, 2014 ( 15):112-113. doi: 10.3969/j.issn.2095-2457.2014.15.080
	Wang Haibo, Lin Jiuhui, Li Yongtao . The application and development trend of military UAV[J]. Science and Technology of Horizon, 2014 ( 15):112-113. doi: 10.3969/j.issn.2095-2457.2014.15.080
[2]	McLain T, Chandler P, Pachter M. A decompositionstrategy for optimal coordination of un-manned air vehicles [C].Chicago:The Proceeding of American Control Conference, 2000.
[3]	Gokham Inalham, Stipanovic Dusan M, Tomlin Claire J. Decen-tralized optimization with application to multiple aircraft coordination [C].Las Vegas:Proceeding of the 41st IEEE Conference on Decision and Control, 2002.
[4]	Tom S, Jonathan H, Eric F. Decentralized cooperative trajectory planning of multiple aircraft with hard safety guarantees [C].Rhode Island:AIAA Guidance Navigation and Control Conference and Exhibit, 2004.
[5]	谢明 . 多架无人机协同攻击多目标任务规划研究[D]. 西安:空军工程大学, 2007.
	Xie Ming . Multi objective cooperative multi-mission UAV mission planning[D]. Xi’an:Air Force Engineering University, 2007.
[6]	Robert B, Kavraki L E. Path planning using lazy PRM [C].San Francisco:Proceeding of the IEEE International Conference on Robotics and Automation, 2000
[7]	郭静, 罗华, 张涛 . 机器视觉与应用[J]. 电子科技, 2014,27(7):185-188.
	Guo Jing, Luo Hua, Zhang Tao . Machine vision and its application[J]. Electronic Science and Technology, 2014,27(7):185-188.
[8]	黄炳强, 曹广益 . 基于模糊人工势场的移动机器人路径规划[J].上海理工大学学报,2006(4):347-350. doi: 10.3969/j.issn.1007-6735.2006.04.010
	Huang Bingqiang, Cao Guangyi . Path planning of mobile robot based on fuzzy artifical potential field[J].Journal of University of Shanghai for Science and Technology,2006(4):347-350. doi: 10.3969/j.issn.1007-6735.2006.04.010
[9]	王新增, 慈林林, 李俊山 , 等. 基于改进粒子群优化算法的无人机实时航迹规划[J]. 微电子学与计算机, 2011,28(4):87-90.
	Wang Xinzeng, Lin Lin, Li Junshan , et al. Real time trajectory planning of UAV based on improved particle swarm optimization[J]. Microelectronics and Computers, 2011,28(4):87-90.
[10]	丁明跃, 郑昌文, 周成平 , 等. 无人飞行器航迹规划[M]. 北京: 电子工业出版社, 2009.
	Ding Mingyue, Zheng Changwen, Zhou Chengping , et al. UAV flight path planning[M]. Beijing: Publishing House of Electronics Industry, 2009.
[11]	Brand M, Oliver N, Pentland A. Coupled hidden Markov models for complex action recognition [C].The United States:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2002. 1997:994-999.
[12]	冯波, 郝文宁, 陈刚 , 等. K-means算法初始聚类中心选择的优化[J]. 计算机工程与应用, 2013,49(14):182-185. doi: 10.3778/j.issn.1002-8331.1111-0289
	Feng Bo, Hao Wenning, Chen Gang , et al. Optimization of initial clustering center selection based on K-means algorithm[J]. Computer Engineering and Applications, 2013,49(14):182-185. doi: 10.3778/j.issn.1002-8331.1111-0289
[13]	赵莉, 候兴哲, 胡君 , 等. 基于改进k-means算法的海量智能用电数据分析[J]. 电网技术, 2014,38(10):2715-2720. doi: 10.13335/j.1000-3673.pst.2014.10.015
	Zhao Li, Hou Xingzhe, HU Jun , et al. Data analysis of massive intelligent electricity using improved k-means algorithm[J]. Power System Technology, 2014,38(10):2715-2720. doi: 10.13335/j.1000-3673.pst.2014.10.015
[14]	靳蕃 . 神经计算智能基础[M]. 成都: 西南交通大学出版社, 2000.
	Jin Fan. Neural computing intelligent foundation[M]. Chengdu: Southwest Jiao Tong University Press, 2000.
[15]	黎明, 杨小芹, 周琳霞 . 基于局部进化的Hopfield神经网络的优化计算方法[J].中国图象图形学报,2004(2):82-88. doi: 10.3969/j.issn.1006-8961.2004.02.015
	Li Ming, Yang Xiaoqin, Zhou Linxia . Optimization calculation of hopfield neural network based on local evolution[J].Journal of Image and Graphics,2004(2):82-88. doi: 10.3969/j.issn.1006-8961.2004.02.015
[16]	杨秀梅, 陈洪亮, 董得义 , 等. 利用Hopfield神经网络求解旅行商问题研究[J]. 微型电脑应用, 2006,22(11):1-3. doi: 10.3969/j.issn.1007-757X.2006.11.001
	Yang Xiumei, Chen Hongliang, Dong Deyi , et al. Study on traveling salesman problem using Hopfield neural network[J]. Microcomputer Applications, 2006,22(11):1-3. doi: 10.3969/j.issn.1007-757X.2006.11.001
[17]	陈文宇, 吴跃 . Hopfield神经网络参数设置[J].计算机工程与应用,2006(31):34-36. doi: 10.3321/j.issn:1002-8331.2006.31.012
	Chen Wenyu, Wu Yue . Hopfield neural network parameter setting[J]. Computer Engineering and Applications, 2006 ( 31):34-36. doi: 10.3321/j.issn:1002-8331.2006.31.012