摘要
针对目前路径规划容易陷入局部最优和搜索时间较长的问题,提出基于拓扑位置关系的无人艇路径搜索方法。分析空间物体的拓扑位置关系,构建基于拓扑位置关系的地图表达。在地图要素表达、拓扑关系谓词和拓扑路径可达的基础上建立拓扑地图,避免大量网格化的路径搜索造成时间复杂度提升,同时避免搜索陷入局部最小值。采用Dijkstra算法对建立的拓扑地图进行最优路径选择。试验结果表明:在障碍物不变、搜索范围变大的情况下,该方法相比栅格化的A*算法能以较低的搜索时间实现更优路径的搜索。
The path search method for USV (unmanned surface vehicle) based on topological position relationship is proposed to improve the search speed and escape from local optimum. The topological positional relationship of spatial objects is analyzed, and the map representation based on topological positional relationship is constructed. The topological map is established on the basis of map feature expression, topological relationship, topological relationship predication and topological path reachability. The map helps to avoid the time complexity caused by a large number of path searches, and to avoid falling into local minimum. The Dijkstra algorithm is used to optimize the path selection on the established topological map. The experimental results show that the method can achieve the optimal path search with lower search time than the A* algorithm of the grid method.
作者
顾尚定
周春辉
文元桥
肖长诗
杜哲
黄亮
GU Shangding;ZHOU Chunhui;WEN Yuanqiao;XIAO Changshi;DU Zhe;HUANG Liang(School of Navigation,Wuhan University of Technology,Wuhan 430063,China;Hubei Key Laboratory of Inland Shipping Technology,Wuhan 430063,China;National Engineering Research Center for Water Transport Safety,Wuhan 430063,China;Intelligent Transport Systems Center,Wuhan University of Technology,Wuhan 430063,China)
出处
《中国航海》
CSCD
北大核心
2019年第2期52-58,共7页
Navigation of China
基金
国家重点研发计划(2018YFC1407405
2018YFC0213904
2018YFC0213900)
国家自然科学基金(51679180
51579204
41801375
51709218)
武汉大学测绘遥感信息工程国家重点实验室开放基金(17I03)
武汉理工大学双一流项目
武汉理工大学研究生优秀学位论文培育项目(2017-YS-070)
