引用本文:刘晨霞,朱大奇,周蓓,顾伟.海流环境下多AUV多目标生物启发任务分配与路径规划算法[J].控制理论与应用,2022,39(11):2100~2107.[点击复制]
LIU Chen-xia,ZHU Da-qi,ZHOU Bei,GU Wei.A novel algorithm of multi-AUVs task assignment and path planning based on biologically inspired neural network for ocean current environment[J].Control Theory and Technology,2022,39(11):2100~2107.[点击复制]
海流环境下多AUV多目标生物启发任务分配与路径规划算法
A novel algorithm of multi-AUVs task assignment and path planning based on biologically inspired neural network for ocean current environment
摘要点击 1026  全文点击 276  投稿时间：2021-10-25  修订日期：2022-09-16
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/CTA.2022.11019
  2022,39(11):2100-2107
中文关键词  生物启发神经网络(BINN)模型  任务分配  路径规划  海流环境  安全避障
英文关键词  biologically inspired neural network (BINN)  task assignment  path planning  ocean current environment  obstacle avoidance
基金项目  国家自然科学基金项目(62033009, U1706224), 上海市科技创新行动计划项目(20510712300)资助.
作者单位E-mail
刘晨霞 上海海事大学 物流工程学院 liuchenxia@shmtu.edu.cn 
朱大奇* 上海海事大学 物流工程学院 zdq367@aliyun.com 
周蓓 上海海事大学 物流工程学院  
顾伟 上海海事大学 物流工程学院  
中文摘要
      针对多障碍物海流环境下多自治水下机器人(AUV)目标任务分配与路径规划问题, 本文在栅格地图构建的 基础上给出了一种基于生物启发神经网络(BINN)模型的新型自主任务分配与路径规划算法, 并考虑海流对路径规 划的影响. 首先建立BINN模型, 利用此模型表示AUV的工作环境, 神经网络中的每一个神经元与栅格地图中的位 置单元一一对应; 接着, 比较每个目标物在BINN地图中所有AUV的活性值, 并选取活性值最大的AUV作为它的获 胜AUV, 实现多AUV任务分配; 最后, 考虑常值海流影响, 根据矢量合成算法确定AUV实际的航行方向, 实现AUV路 径规划与安全避障. 海流环境下仿真实验结果表明了生物启发模型在多AUV水下任务分配与路径规划中的有效性.
英文摘要
      Aiming at the multi-AUVs task assignment and path planning in the ocean current underwater environment with multi-obstacles, a novel autonomous task assignment and path planning algorithm is presented based on the biological inspired neural network model and grid map, and the impact of ocean current on path planning is considered. Firstly, the biologically inspired neural network model is established, and which is used to represent the working environment of the AUV. Each neuron in the neural network corresponds to the position unit in the grid map. Then, activity values of all AUVs of each target in the BINN map are compared, and the AUV with the largest active value is selected as its winning AUV for a certain target. The task assignment of multi-AUVs is realized. Finally, the actual direction of AUV navigation for ocean current environment is determined according to the vector synthesis algorithm. The simulation results show the effectiveness of the proposed multi-AUVs task assignment and path planning for the underwater environment with obstacles and ocean current.