基于改进神经网络的多AUV全覆盖路径规划

doi:10.16182/j.issn1004731x.joss.19-0012

系统仿真学报 ›› 2020, Vol. 32 ›› Issue (8): 1505-1514.doi: 10.16182/j.issn1004731x.joss.19-0012

• 仿真支撑平台/系统技术 • 上一篇下一篇

基于改进神经网络的多AUV全覆盖路径规划

朱大奇, 朱婷婷, 颜明重

上海海事大学上海智能海事搜救与水下机器人工程技术研究中心,上海 201306

收稿日期:2019-01-07 修回日期:2019-03-07 出版日期:2020-08-18 发布日期:2020-08-13
作者简介:朱大奇(1964-), 男, 安徽安庆, 博士, 教授,博导, 研究方向为水下机器人故障诊断与路径规划。
基金资助:
国家自然科学基金(U1706224,91748117),上海市科委创新行动计划(18JC1413000, 18DZ2253100, 17ZR1412400)

Multi-AUV Complete Coverage Path Planning Based on Improved Neural Network

Zhu Daqi, Zhu Tingting, Yan Mingzhong

Engineering Technology Research Center of MIntelligent maritime search and rescue and underwater vehicle, Shanghai Maritime Univ., Shanghai 201306, China

Received:2019-01-07 Revised:2019-03-07 Online:2020-08-18 Published:2020-08-13

摘要/Abstract

摘要： 针对三维环境下的多自主水下机器人(Autonomous Underwater Vehicle,AUV)全覆盖路径规划问题,提出一种基于改进神经网络—Glasius生物启发神经网络（Glasius Bio-inspired Neural Network,GBNN）的全覆盖路径规划算法。对AUV的水下工作环境构建离散的三维栅格地图;根据栅格地图,建立相对应的三维GBNN模型;根据GBNN活性值的动态变化,AUV规划各自的搜索路径,对水下任务区域进行全覆盖搜索。仿真结果表示,多AUV可以协同完成覆盖搜索任务,能够自动避开各类静态和动态的障碍物,自动逃离路径的死锁区。

关键词: 多AUV, 三维环境, 全覆盖路径规划, Glasius生物启发神经网络

Abstract: Aiming at the working space search task of multiple AUVs (Autonomous Underwater Vehicle) in 3-dimensional underwater environments, a complete coverage path planning algorithm based on an improved neural network-Glasius Bio-inspired Neural Network (GBNN) is presented in this paper. A discrete 3-D grid map of the underwater environment is constructed. A 3-D GBNN model is established topologically according to the map. Based on the dynamic activities of GBNN model, each AUV plans its own coverage path independently, and covers the whole working space collaboratively. The simulation results show that the multiple AUVs can collaboratively cover the working space completely, automatically avoid the obstacle and escape from the deadlock in the path.

Key words: multi-AUV, 3-D environment, complete coverage path planning, Glasius Bio-inspired Neural Network

中图分类号:

TP273

朱大奇, 朱婷婷, 颜明重. 基于改进神经网络的多AUV全覆盖路径规划[J]. 系统仿真学报, 2020, 32(8): 1505-1514.

Zhu Daqi, Zhu Tingting, Yan Mingzhong. Multi-AUV Complete Coverage Path Planning Based on Improved Neural Network[J]. Journal of System Simulation, 2020, 32(8): 1505-1514.

参考文献 24

[1]	余明刚, 张旭, 陈宗恒. 自治水下机器人技术综述[J]. 机电工程技术, 2017, 46(8): 155-157.Yu Minggang, Zhang Xu, Chen Zongheng.Summary of Autonomous Underwater Vehicle Technology[J]. Mechanical & Electrical Technology, 2017, 46(8): 155-157.
[2]	Hsu P, Lin C, Yang M.On the complete coverage path planning for mobile robots[J]. Journal of Intelligent & Robotic Systems (S0921-0296), 2014, 74(3): 945-963.
[3]	徐博, 徐旻, 陈立平, 等. 智能机械全覆盖路径规划算法综述[J]. 计算机测量与控制, 2016, 24(10): 1-5.Xu Bo, Xu Min, Chen Liping, et al.Overview of intelligent mechanical complete coverage path planning algorithm[J]. Computer Measurement and Control, 2016, 24(10): 1-5.
[4]	李一平, 李硕, 张艾群. 自主/遥控水下机器人研究现状[J]. 工程研究-跨学科视野中的工程, 2016, 8(2): 217-222.Li Yiping, Li Shuo, Zhang Aiqun.Research Status of Autonomous/Remote Control Underwater Vehicles[J]. Science and Technology Innovation and Productivity, 2016, 8(2): 217-222.
[5]	简毅, 张月. 移动机器人全覆盖路径规划算法研究进展与展望[J]. 计算机应用, 2014, 34(10): 2844-2849.Jian Yi, Zhang Yue.Research progress and prospects of mobile robot complete coverage path planning algorithm[J]. Journal of Computer Applications, 2014, 34(10): 2844-2849.
[6]	朱宝艳. 移动机器人全覆盖路径规划算法研究[D]. 淄博: 山东理工大学, 2017.Zhu Baoyan.Research on Complete Coverage Planning Algorithm for Mobile Robots [D]. Zibo: Shandong University of Technology, 2017.
[7]	Maxim A B, Gaurav S S.Spreading out: a local approach to multi-robot coverage[M]. Japan: Springer Japan, 2002.
[8]	Parlaktuna O, Sipahioglu A, Kirlik G.Multi-robot sensor-based coverage path planning using capacitated arc routing approach[C]. Proceedings of the 2009 IEEE Conference on Control Applications. Russia: IEEE, 2009: 1146-1151.
[9]	Sipahioglu A, Kirlik G, Parlaktuna O.Energy constrained multi-robot sensor-based coverage path planning using capacitated arc routing approach[J]. Robotics and Autonomous System (S0921-8890), 2014, 74(3): 945-963.
[10]	Janchiv A, Batsaikhan D, Kim G H.Complete cover-age path planning for multi-robots based on[C]. Proceedings of the 2011 11th International Conference on Control, Automation and Systems. Korea (South): Robot World, 2011: 824-827.
[11]	Kapanoglu M, Alikalfa M, Ozkan M.A pattern-based genetic algorithm for multi-robot coverage path planning minimizing completion time[J]. Journal of Intelligent Manufacturing (S0956-5515), 2012, 23(4): 1035-1045.
[12]	Li J H, Yang J G, Tian X J, et al.An improved ant colony algorithm for robot path planning[J]. Soft Computing (S1432-7643), 2017, 21(10): 5829-5839.
[13]	Luo C M, Yang S M.A real-time cooperative sweeping strategy for multiple cleaning robots[C]. Proceedings of the 2002 IEEE International Symposium on Intelligent Control. Canada: IEEE, 2002: 660-665.
[14]	Glasius R, Komoda A, Gielen S.A biologically inspired neural net for trajectory formation and obstacle avoidance[J]. Biol. Cybern (S0340-1200), 1996, 6(84): 511-520.
[15]	Yan M Z.A novel 3-D bio-inspired neural network model for the path planning of an AUV in underwater environment[J]. Intelligent Automation and Soft Computing (S1079-8587), 2013, 19(4): 555-566.
[16]	朱大奇, 张光磊, 李蓉. 生物启发AUV三维轨迹跟踪控制算法[J]. 智能系统学报, 2014, 9(2): 180-185.Zhu Daqi, Zhang Guanglei, Li Rong.Biological inspired three-dimensional tracking control algorithm for autonomous underwater vehicles[J]. CAAI Transactions on Intelligent Systems, 2014, 9(2): 180-185.
[17]	朱大奇, 孙兵, 李利. 基于生物启发模型的AUV三维自主路径规划与安全避障算法[J]. 控制与决策, 2015, 30(5): 798-806.Zhu Daqi, Sun Bing, Li Li.An AUV’s 3-D autonomous path planning and secure obstacles avoidance algorithm based on biological heuristic model[J]. Control and Decisions, 2015, 30(5): 798-806.
[18]	武雅杰, 杨晶东. 基于A算法的机器人路径规划[J]. 电子科技, 2017, 30(6): 124-127.Wu Yajie, Yang Jingdong.Robot Path Planning Based on A Algorithm[J]. Electronic Science & Technology, 2017, 30(6): 124-127.
[19]	余翀, 邱其文. 基于栅格地图的分层式机器人路径规划算法[J]. 中国科学院大学学报, 2013, 30(4): 528-538, 546.Yu Chong, Qiu Qiwen.A hierarchical robot path planning algorithm based on raster map[J]. Journal of the Chinese Academy of Sciences, 2013, 30(4): 528-538, 546.
[20]	赵蕾. 未知环境下全覆盖路径规划问题的研究[D]. 南昌: 南昌大学, 2016.Zhao Lei.Research on complete coverage path planning in unknown environment [D]. Nanchang: Nanchang University, 2016.
[21]	王琦斐, 杨军. 基于内螺旋覆盖算法的多AUV协作反水雷路径规划研究[J]. 计算机测量与控制, 2012, 20(1): 144-146, 160.Wang Qifei, Yang Jun.Research on multi-AUV collaborative anti-mine path planning based on inner spiral coverage algorithm[J]. Journal of Computer Measurement and Control, 2012, 20(1): 144-146, 160.
[22]	Luo C M, Yang S M, Stacey D A, et al.A solution to Vicinity problem of Obstacles in complete coverage path planning[C]. Proc. IEEE Int. Conf. Robotics and Automation. USA: IEEE, 2002: 612-617.
[23]	颜明重. 生物启发神经动力学模型及其在AUV路径规划中的应用[D]. 上海: 上海海事大学, 2012.Yan Mingzhong.Biologically inspired neurons dynamic model and its application in AUV path planning [D]. Shanghai: Shanghai Maritime University, 2012.
[24]	朱宝艳, 李彩虹, 王小宇, 等. 基于栅格的移动机器人区域分解遍历算法[J]. 山东理工大学学报(自然科学版), 2017, 31(4): 13-18.Zhu Baoyan, Li Caihong, Wang Xiaoyu, et al.A grid-based domain decomposition traversal algorithm for mobile robots[J]. Journal of Shandong University of Technology (Natural Science), 2017, 31(4): 13-18.

基于改进神经网络的多AUV全覆盖路径规划

Multi-AUV Complete Coverage Path Planning Based on Improved Neural Network

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 24

相关文章 1

编辑推荐

Metrics

本文评价