WO2023045029A1 - Method and system for ship route planning in pirate region, electronic device and storage medium - Google Patents

Method and system for ship route planning in pirate region, electronic device and storage medium Download PDF

Info

Publication number
WO2023045029A1
WO2023045029A1 PCT/CN2021/127996 CN2021127996W WO2023045029A1 WO 2023045029 A1 WO2023045029 A1 WO 2023045029A1 CN 2021127996 W CN2021127996 W CN 2021127996W WO 2023045029 A1 WO2023045029 A1 WO 2023045029A1
Authority
WO
WIPO (PCT)
Prior art keywords
path
nodes
route
node
pirate
Prior art date
Application number
PCT/CN2021/127996
Other languages
French (fr)
Chinese (zh)
Inventor
马勇
刘成立
Original Assignee
武汉理工大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 武汉理工大学 filed Critical 武汉理工大学
Publication of WO2023045029A1 publication Critical patent/WO2023045029A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/0206—Control of position or course in two dimensions specially adapted to water vehicles

Definitions

  • the invention belongs to the technical field of ship route planning, and in particular relates to a ship route planning method, system, electronic equipment and storage medium in a pirate area.
  • the PRM (Probabilistic Roadmap) algorithm is a graph-based search method, which is divided into two steps: the learning phase and the query phase.
  • the traditional PRM algorithm adopts a completely random sampling strategy when constructing a path network graph. When the number of sampling points is fixed, some sampling points The point falls in the obstacle space, resulting in a decrease in the number of sampling points in the free space, which may not be able to complete the path planning, and the path searched in the query phase is not optimal, there are too many path nodes and some node corners are too steep.
  • the present invention provides a ship route planning method, system, electronic equipment and storage medium based on the improved PRM algorithm to solve the problem of low utilization rate of sampling points of the PRM algorithm and excessive path nodes. There are many problems and the corners of some nodes are too steep.
  • the present invention provides a method for planning a ship route in a pirate area, comprising the following steps:
  • step S1 includes:
  • step S2 includes:
  • a new node is generated in the navigable area to replace the node falling in the obstacle area.
  • generating new nodes in the navigable area includes:
  • RandomNode(q, r) For the sampling point q(x q , y q ) falling in the obstacle area, use the random node generation function RandomNode(q, r), where q represents the node position, r represents the radius, and generate a new node to replace the node in the obstacle area ;
  • the new node B satisfies the radius And node B is a node within the navigable area.
  • step S4 uses the D-P algorithm to extract key nodes in the initial path nodes, including:
  • the initial threshold ⁇ is determined according to the distribution of obstacles on the map and the number of initial path nodes. In a complex map with more obstacles, a smaller threshold is selected, and the number of obstacles or In a map with simple obstacle distribution, a larger threshold is selected for path key node extraction.
  • step S5 uses Euler spiral fitting to perform path smoothing, including:
  • s m is the arc length of the m-th Euler spiral
  • ⁇ 0m and k 0m are the tangent angle and curvature at the point (x m , y m ) respectively
  • c m represents the parameter of the sharpness of the curvature
  • ⁇ 0m+1 and k 0m+1 represent the initial tangent angle and initial curvature of the m+1th Euler spiral, respectively, and ⁇ m and k m represent the mth segment of the Euler spiral at (x m+1 , y m+1 ) point tangent angle and curvature;
  • step S54 sequentially perform Euler spiral fitting on the k-1 path, so as to obtain a smooth optimized path.
  • the present invention also provides a shipping route planning system in a pirate area, including:
  • the grid map module is used for cluster analysis of historical pirate activity points, and constructs grid maps of obstacle areas and navigable areas;
  • the path network diagram module is used to randomly scatter points in the grid map, and then connect the nodes through the local planner to form a path network diagram;
  • the initial path module is used to connect the starting point and the ending point of the route with the route map, and search for the initial path from the starting point to the ending point of the route through the A* search algorithm;
  • the path optimization module is used to extract the key nodes in the initial path nodes, and connect the key nodes to form an optimized path containing less inflection points;
  • the path smoothing module is used for smoothing the optimized path containing less inflection points to obtain a smooth optimized path.
  • the present invention also provides an electronic device, including one or more processors and memory;
  • One or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs are configured to execute the above-mentioned pirate area ship route planning method.
  • the present invention also provides a computer-readable storage medium, in which program codes are stored, wherein, when the program codes are running, the above method for planning a ship's route in a pirate area is executed.
  • the present invention has the following advantages and beneficial effects:
  • the invention uses the PRM algorithm to plan the ship's route, generates new nodes in the navigable area to replace the nodes falling in the obstacle area, improves the utilization rate of sampling points, reduces the number of nodes on the original path, shortens the path length, and improves the path length. of smoothness.
  • Fig. 1 is a flow chart of a method for planning a ship route in a pirate area provided by an embodiment of the present invention
  • Fig. 2 is a flow chart of constructing an obstacle grid map provided by an embodiment of the present invention
  • Fig. 3 is a method diagram of a random node generation provided by an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a D-P algorithm for extracting key nodes of a path provided by an embodiment of the present invention
  • FIG. 5 is a flow chart of an improved PRM algorithm planning an initial path provided by an embodiment of the present invention.
  • FIG. 6 is a flow chart of path optimization provided by an embodiment of the present invention.
  • the route planned by the invention has fewer inflection points and smoother route, which is close to actual navigation application, and can provide a reasonable and effective route planning method for ships navigating in pirate activity areas.
  • the embodiment of the present invention provides a method for planning a ship route in a pirate area based on an improved PRM algorithm, as shown in FIG. 1 , comprising the following steps:
  • step S1 Carry out cluster analysis on the historical pirate activity points in the route planning sea area, and construct a grid map of obstacle areas and navigable areas.
  • step S1 includes the following sub-steps:
  • S11 Use the K-means clustering algorithm to perform cluster analysis on historical pirate activity points, and extract the cluster center coordinates of each cluster;
  • S12 Construct the Voronoi diagram according to the center coordinates, and extract the boundary of the pirate activity area of the Voronoi diagram as the obstacle boundary;
  • RandomNode(q, r) for the sampling points falling in the obstacle space, use the random node generation function RandomNode(q, r) to generate new nodes to replace the nodes in the obstacle, where q(x q , y q ) Represents the node position, and r represents the radius.
  • the gray area represents obstacles, with the node A in the obstacle as the center, and according to the obstacles in the environment, use a suitable radius r to make a dotted circle, then each of the dotted circles belongs to free space
  • the nodes in may become the replacement nodes of A, the node B is randomly generated by the random node generation function, and the node B(x B , y B ) satisfies the following conditions: radius Node B is a node within the navigable area.
  • S4 Key node extraction, extracting key nodes in the initial path nodes, and connecting path key nodes to form an optimized path with fewer inflection points. Specifically, use the D-P algorithm to extract the key nodes in the initial path nodes, as shown in Figure 6, including the following sub-steps:
  • the initial path nodes are A 1 -A 8 .
  • set an appropriate threshold ⁇ connect A 1 and A 8 , among the path nodes between A 1 and A 8 , the node farthest from the line segment A 1 A 8 is A 3 , A 3 and A 8
  • the distance between A 1 and A8 is d, which is greater than the preset threshold ⁇ , and A 3 is regarded as a key node.
  • Connect A 1 , A 3 and A 3 , A 8 respectively to form two new reference line segments A 1 A 3 and A 3 A 8 .
  • the initial threshold ⁇ is determined according to the distribution of obstacles on the map and the number of initial path nodes. In a complex map with more obstacles, a smaller threshold is selected. In a map with fewer obstacles or a simple distribution of obstacles , select a larger threshold for path key node extraction.
  • S5 path smoothing, smoothing the optimized path with less inflection points to obtain a smooth optimized path. Specifically, including:
  • s m is the arc length of the m-th Euler spiral
  • ⁇ 0m and k 0m are the tangent angle and curvature at the point (x m , y m ) respectively
  • c m represents the parameter of the sharpness of the curvature
  • ⁇ 0m+1 and k 0m+1 represent the initial tangent angle and initial curvature of the m+1th Euler spiral, respectively, and ⁇ m and k m represent the mth segment of the Euler spiral at (x m+1 , y m+1 ) point tangent angle and curvature;
  • S54 According to the conditions of S52 and S53, sequentially perform Euler spiral fitting on the k-1 segment paths to obtain a smooth optimized path.
  • the present invention also provides an electronic device, including one or more processors and a memory; one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured for Execute the pirate area ship route planning method described above.
  • the present invention also provides a computer-readable storage medium, in which program codes are stored, wherein, when the program codes are running, the above method for planning a ship's route in a pirate area is executed.
  • the present invention uses the K-means clustering algorithm to cluster and analyze historical pirate activity points by constructing an obstacle map, extracts the cluster center coordinates of each cluster, constructs a Voronoi diagram according to the coordinates, and extracts the boundary of the Voronoi diagram as an obstacle Object boundaries, and then construct grid maps of obstacle areas and navigable areas; use PRM algorithm to construct path network diagrams, randomly scatter points in a given grid map, and use random node generation functions to generate new nodes to replace obstacles nodes, improve the utilization rate of sampling points, connect the nodes through the local planner, and form a path network graph; the PRM algorithm finds the initial path, connects the starting point and end point of the given route with the path graph, and finds the route through the A* search algorithm The path from the starting point to the end point; path optimization, key node extraction, using the D-P algorithm to extract the key nodes in the initial path nodes, connecting the key nodes of the path to form an optimized path with fewer inflection points; path smoothing, use for optimized paths with
  • each step/component described in this application can be split into more steps/components, and two or more steps/components or part of the operations of steps/components can also be combined into a new Step/component, to realize the object of the present invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Navigation (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

Disclosed are a method and system for ship route planning in a pirate region, an electronic device and a storage medium, which belong to the technical field of ship route planning. The method comprises the following steps: S1, performing cluster analysis on historical pirate activity points to construct a grid map of an obstacle region and a navigable region; S2, randomly scattering points in the grid map, then connecting nodes by means of a local planner to form a route network graph; S3, connecting the start point and end point of a ship route with a route map, and searching for an initial route from the start point to the end point of the ship route by means of an A* search algorithm; S4, extracting key nodes in initial route nodes, connecting the key nodes to form an optimized route containing fewer inflection points; and S5, performing smoothing on the optimized route containing fewer inflection points to obtain a smoothed optimized route. The present invention uses the PRM algorithm to perform ship route planning, thus increasing the utilization of sampling points, reducing the number of nodes on an original route, reducing route length and increasing the smoothness of a route.

Description

海盗区域船舶航线规划方法、系统、电子设备及存储介质Ship route planning method, system, electronic equipment and storage medium in pirate area 技术领域technical field
本发明属于船舶航线规划技术领域，具体涉及一种海盗区域船舶航线规划方法、系统、电子设备及存储介质。The invention belongs to the technical field of ship route planning, and in particular relates to a ship route planning method, system, electronic equipment and storage medium in a pirate area.
背景技术Background technique
船舶在海上航行时，有时会经过海盗活动高发区域，因此为保证船舶的航行安全，研究海盗活动区域内的航线规划方法具有很深的现实意义和理论意义。When a ship sails at sea, it sometimes passes through areas with high incidence of piracy. Therefore, in order to ensure the safety of ships, it is of great practical and theoretical significance to study the route planning method in the area of piracy.
船舶在海上航行，航线规划是其核心内容，目前，船舶航线规划的常用方法主要有A*算法、遗传算法、模拟退火算法、粒子群算法、蚁群算法、PRM算法等。Ships sail at sea, and route planning is the core content. At present, the common methods of ship route planning mainly include A* algorithm, genetic algorithm, simulated annealing algorithm, particle swarm algorithm, ant colony algorithm, PRM algorithm, etc.
PRM(Probabilistic Roadmap)算法是一种基于图搜索的方法，分为学习阶段，查询阶段两个步骤，传统PRM算法构建路径网络图时采用完全随机的采样策略，当采样点数量一定时，一些采样点落在障碍物空间内，导致自由空间中的采样点数量减少，可能无法完成路径的规划，并且查询阶段搜索的路径并非最优，存在路径节点过多以及部分节点转角过陡的问题。The PRM (Probabilistic Roadmap) algorithm is a graph-based search method, which is divided into two steps: the learning phase and the query phase. The traditional PRM algorithm adopts a completely random sampling strategy when constructing a path network graph. When the number of sampling points is fixed, some sampling points The point falls in the obstacle space, resulting in a decrease in the number of sampling points in the free space, which may not be able to complete the path planning, and the path searched in the query phase is not optimal, there are too many path nodes and some node corners are too steep.
因此，对于PRM算法进行船舶航线规划来说，如何提高采样点的利用率，减少原始路径上节点数目，缩短路径长度，提高路径的平滑度是亟待解决的问题。Therefore, for the PRM algorithm for ship route planning, how to improve the utilization rate of sampling points, reduce the number of nodes on the original path, shorten the path length, and improve the smoothness of the path are urgent problems to be solved.
发明内容Contents of the invention
针对现有技术中存在的问题，本发明提供一种基于改进PRM算法的海盗区域船舶航线规划方法、系统、电子设备及存储介质，用以解决PRM算法采样点的利用率不高、路径节点过多以及部分节点转角过陡的问题。Aiming at the problems existing in the prior art, the present invention provides a ship route planning method, system, electronic equipment and storage medium based on the improved PRM algorithm to solve the problem of low utilization rate of sampling points of the PRM algorithm and excessive path nodes. There are many problems and the corners of some nodes are too steep.
为实现上述目的，本发明提供了一种海盗区域船舶航线规划方法，包括以下步骤：In order to achieve the above object, the present invention provides a method for planning a ship route in a pirate area, comprising the following steps:
S1、对历史海盗活动点进行聚类分析，构建障碍物区域及可航区域的栅格地图；S1. Carry out cluster analysis on historical pirate activity points, and construct grid maps of obstacle areas and navigable areas;
S2、在栅格地图中随机撒点，然后通过局部规划器连接节点，形成路径网络图；S2. Randomly sprinkle points in the grid map, and then connect the nodes through the local planner to form a path network graph;
S3、将航线起点和终点与路径图相连，通过A*搜索算法搜索航线起点到终点的初始路径；S3. Connect the starting point and the ending point of the route with the route map, and search for the initial path from the starting point to the ending point of the route through the A* search algorithm;
S4、提取初始路径节点中的关键节点，连接关键节点形成含有较少拐点的优化路径；S4. Extract key nodes in the initial path nodes, and connect the key nodes to form an optimized path containing less inflection points;
S5、对含有较少拐点的优化路径进行平滑处理，得到平滑优化路径。S5. Perform smoothing processing on the optimized path containing less inflection points to obtain a smooth optimized path.
在一些可选的实施方案中，步骤S1包括：In some optional embodiments, step S1 includes:
S11、使用K均值聚类算法对航线规划海域的历史海盗活动点进行聚类分析，提取每簇的聚类中心坐标；S11, using the K-means clustering algorithm to perform cluster analysis on the historical pirate activity points in the route planning sea area, and extract the cluster center coordinates of each cluster;
S12、根据中心坐标构建Voronoi图，提取Voronoi图中海盗活动区域边界作为障碍物边界；S12. Construct a Voronoi diagram according to the center coordinates, and extract the boundary of the pirate activity area in the Voronoi diagram as the obstacle boundary;
S13、根据障碍物边界构建障碍物区域及可航区域的栅格地图。S13. Construct a grid map of the obstacle area and the navigable area according to the obstacle boundary.
在一些可选的实施方案中，步骤S2包括：In some optional embodiments, step S2 includes:
在栅格地图中随机撒点；Randomly sprinkle points in the grid map;
对落在障碍物区域的采样点，在可航区域生成一个新的节点，以替换落在障碍物区域的节点。For the sampling points falling in the obstacle area, a new node is generated in the navigable area to replace the node falling in the obstacle area.
在一些可选的实施方案中，在可航区域生成新的节点包括：In some optional implementations, generating new nodes in the navigable area includes:
对落在障碍物区域的采样点q(x q，y q)，使用随机节点生成函数RandomNode(q，r)，其中q代表节点位置，r代表半径，生成新的节点替换障碍物区域的节点； For the sampling point q(x q , y q ) falling in the obstacle area, use the random node generation function RandomNode(q, r), where q represents the node position, r represents the radius, and generate a new node to replace the node in the obstacle area ;
新的节点B满足半径
Figure PCTCN2021127996-appb-000001
且节点B为可航区域内的节点。 The new node B satisfies the radius
Figure PCTCN2021127996-appb-000001
And node B is a node within the navigable area.
在一些可选的实施方案中，步骤S4使用D-P算法提取初始路径节点中的关键节点，包括：In some optional embodiments, step S4 uses the D-P algorithm to extract key nodes in the initial path nodes, including:
S41、确定初始阈值φ，连接初始路径节点的初始点和目标点形成一条基准线；S41. Determine the initial threshold φ, and connect the initial point and the target point of the initial path node to form a baseline;
S42、计算初始点和目标点之间所有节点到基准线的距离d，得到距离基准线最远的节点，将最远的节点所对应的最远距离d m与初始阈值φ进行比较； S42. Calculate the distance d from all nodes between the initial point and the target point to the baseline, obtain the node farthest from the baseline, and compare the furthest distance d m corresponding to the furthest node with the initial threshold φ;
S43、若d m＜φ，则该基准线段作为新的路径，该段路径处理完毕； S43. If d m <φ, the reference line segment is used as a new path, and the path processing of this segment is completed;
S44、若d m＞φ，则把此节点纳入关键节点集，该关键节点分别与初始点和目标点相连接形成两条新的基准线，并对这两段基准线重复步骤S42至步骤S44以提取新的关键节点； S44. If d m > φ, include this node into the key node set, and the key nodes are respectively connected with the initial point and the target point to form two new baselines, and repeat steps S42 to S44 for these two baselines to extract new key nodes;
S45、最后得到关键节点集，依次连接关键节点，即可得到含较少节点的优化路径。S45. Finally, the key node set is obtained, and the key nodes are connected in sequence to obtain an optimized path with fewer nodes.
在一些可选的实施方案中，初始阈值φ根据地图障碍物的分布情况以及初始路径节点个数来确定，含有较多障碍物的复杂地图中，选取较小的阈值，含有较少障碍物或障碍物分布简单的地图中，选取较大阈值进行路径关键节点提取。In some optional implementations, the initial threshold φ is determined according to the distribution of obstacles on the map and the number of initial path nodes. In a complex map with more obstacles, a smaller threshold is selected, and the number of obstacles or In a map with simple obstacle distribution, a larger threshold is selected for path key node extraction.
在一些可选的实施方案中，步骤S5使用欧拉螺线拟合进行路径平滑处理，包括：In some optional embodiments, step S5 uses Euler spiral fitting to perform path smoothing, including:
S51、设提取的关键节点坐标为Q(x i，y i)(i＝1，2，…，k)，将含较少节点的优化路径分为k-1段； S51. Assuming that the extracted key node coordinates are Q( xi , y i ) (i=1, 2, ..., k), the optimized path containing fewer nodes is divided into k-1 segments;
52、对其中第m段路径进行欧拉螺线拟合，其两端关键节点坐标为(x m，y m)、 (x m+1，y m+1)，两点满足： 52. Carry out Euler spiral fitting on the path of the mth segment, the coordinates of the key nodes at both ends are (x m , y m ), (x m+1 , y m+1 ), and the two points satisfy:
Figure PCTCN2021127996-appb-000002
Figure PCTCN2021127996-appb-000002
其中，s m为第m段欧拉螺线的弧长，θ 0m与k 0m分别为(x m，y m)点处的切线角及曲率，c m表示曲率锐度的参数； Among them, s m is the arc length of the m-th Euler spiral, θ 0m and k 0m are the tangent angle and curvature at the point (x m , y m ) respectively, and c m represents the parameter of the sharpness of the curvature;
S53、(x m+1，y m+1)为第m段欧拉螺线的终点及第m+1段欧拉螺线的起点，此处各参数应满足： S53, (x m+1 , y m+1 ) is the end point of the mth segment Euler spiral and the starting point of the m+1th segment Euler spiral, where each parameter should satisfy:
Figure PCTCN2021127996-appb-000003
Figure PCTCN2021127996-appb-000003
其中，θ 0m+1与k 0m+1分别表示第m+1段欧拉螺线的初始切线角及初始曲率，θ m与k m分别为第m段欧拉螺线在(x m+1，y m+1)点处的切线角及曲率； Among them, θ 0m+1 and k 0m+1 represent the initial tangent angle and initial curvature of the m+1th Euler spiral, respectively, and θ m and k m represent the mth segment of the Euler spiral at (x m+1 , y m+1 ) point tangent angle and curvature;
S54、按照步骤S52和步骤S53依次对k-1段路径进行欧拉螺线拟合，即可得到平滑优化路径。S54 , according to step S52 and step S53 , sequentially perform Euler spiral fitting on the k-1 path, so as to obtain a smooth optimized path.
本发明还提供一种海盗区域船舶航线规划系统，包括：The present invention also provides a shipping route planning system in a pirate area, including:
栅格地图模块，用于对历史海盗活动点进行聚类分析，构建障碍物区域及可航区域的栅格地图；The grid map module is used for cluster analysis of historical pirate activity points, and constructs grid maps of obstacle areas and navigable areas;
路径网络图模块，用于在栅格地图中随机撒点，然后通过局部规划器连接节点，形成路径网络图；The path network diagram module is used to randomly scatter points in the grid map, and then connect the nodes through the local planner to form a path network diagram;
初始路径模块，用于将航线起点和终点与路径图相连，通过A*搜索算法搜索航线起点到终点的初始路径；The initial path module is used to connect the starting point and the ending point of the route with the route map, and search for the initial path from the starting point to the ending point of the route through the A* search algorithm;
路径优化模块，用于提取初始路径节点中的关键节点，连接关键节点形成含有较少拐点的优化路径；The path optimization module is used to extract the key nodes in the initial path nodes, and connect the key nodes to form an optimized path containing less inflection points;
路径平滑模块，用于对含有较少拐点的优化路径进行平滑处理，得到平滑优化路径。The path smoothing module is used for smoothing the optimized path containing less inflection points to obtain a smooth optimized path.
本发明还提供一种电子设备，包括一个或多个处理器以及存储器；The present invention also provides an electronic device, including one or more processors and memory;
一个或多个程序被存储在存储器中并被配置为由一个或多个处理器执行，一个或多个程序配置用于执行上述的海盗区域船舶航线规划方法。One or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs are configured to execute the above-mentioned pirate area ship route planning method.
本发明还提供一种计算机可读存储介质，计算机可读存储介质中存储有程序代码，其中，在程序代码运行时执行上述的海盗区域船舶航线规划方法。The present invention also provides a computer-readable storage medium, in which program codes are stored, wherein, when the program codes are running, the above method for planning a ship's route in a pirate area is executed.
本发明与现有技术相比，具有以下优点及有益效果：Compared with the prior art, the present invention has the following advantages and beneficial effects:
本发明使用PRM算法进行船舶航线规划，在可航区域生成新的节点替换落在障碍物区域的节点，提高了采样点的利用率，减少了原始路径上节点数目，缩短路径长度，提高了路径的平滑度。The invention uses the PRM algorithm to plan the ship's route, generates new nodes in the navigable area to replace the nodes falling in the obstacle area, improves the utilization rate of sampling points, reduces the number of nodes on the original path, shortens the path length, and improves the path length. of smoothness.
附图说明Description of drawings
图1为本发明实施例提供的一种海盗区域船舶航线规划方法的流程图；Fig. 1 is a flow chart of a method for planning a ship route in a pirate area provided by an embodiment of the present invention;
图2为本发明实施例提供的一种障碍栅格地图构建的流程图；Fig. 2 is a flow chart of constructing an obstacle grid map provided by an embodiment of the present invention;
图3为本发明实施例提供的一种随机节点生成的方法图；Fig. 3 is a method diagram of a random node generation provided by an embodiment of the present invention;
图4为本发明实施例提供的一种D-P算法提取路径关键节点的原理图；4 is a schematic diagram of a D-P algorithm for extracting key nodes of a path provided by an embodiment of the present invention;
图5为本发明实施例提供的一种改进PRM算法规划初始路径的流程图；FIG. 5 is a flow chart of an improved PRM algorithm planning an initial path provided by an embodiment of the present invention;
图6为本发明实施例提供的一种路径优化的流程图。FIG. 6 is a flow chart of path optimization provided by an embodiment of the present invention.
具体实施方式Detailed ways
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。此外，下面所描述的本发明各个实施方式中所涉及到的技术特征只要彼此之间未构成冲突就可以相互组合。In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.
本发明规划的路径拐点较少、路径平滑，贴近实际航海应用，能够为航行于海盗活动区域的船舶提供一种合理有效的航线规划方法。The route planned by the invention has fewer inflection points and smoother route, which is close to actual navigation application, and can provide a reasonable and effective route planning method for ships navigating in pirate activity areas.
本发明实施例提供了一种基于改进PRM算法的海盗区域船舶航线规划方法，如图1所示，包括以下步骤：The embodiment of the present invention provides a method for planning a ship route in a pirate area based on an improved PRM algorithm, as shown in FIG. 1 , comprising the following steps:
S1：对航线规划海域的历史海盗活动点进行聚类分析，构建障碍物区域及可航区域的栅格地图。具体地，步骤S1如图2所示，包括以下子步骤：S1: Carry out cluster analysis on the historical pirate activity points in the route planning sea area, and construct a grid map of obstacle areas and navigable areas. Specifically, step S1, as shown in Figure 2, includes the following sub-steps:
S11：使用K均值聚类算法对历史海盗活动点进行聚类分析，提取每簇的聚类中心坐标；S11: Use the K-means clustering algorithm to perform cluster analysis on historical pirate activity points, and extract the cluster center coordinates of each cluster;
S12：根据中心坐标构建Voronoi图，提取Voronoi图海盗活动区域边界作为障碍物边界；S12: Construct the Voronoi diagram according to the center coordinates, and extract the boundary of the pirate activity area of the Voronoi diagram as the obstacle boundary;
S13：根据障碍物边界构建障碍物区域及可航区域的栅格地图。S13: Construct a grid map of the obstacle area and the navigable area according to the obstacle boundary.
S2：在栅格地图中随机撒点，然后通过局部规划器连接节点，形成路径网络图。S2: Randomly sprinkle points in the grid map, and then connect nodes through a local planner to form a path network graph.
具体地，如图5所示，对于落在障碍空间的采样点，使用随机节点生成函数RandomNode(q，r)，生成新的节点替换障碍物中的节点，其中q(x q，y q)代表节点位置，r代表半径。如图3所示，灰色区域代表障碍物，以障碍物中的节点A为圆心，根据所处环境的 障碍物情况，采用合适的半径r做虚线圆，则该虚线圆上每一个属于自由空间内的节点，都可能成为A的替换节点，节点B由随机节点生成函数随机生成，且节点B(x B，y B)满足以下条件：半径
Figure PCTCN2021127996-appb-000004
节点B为可航区域内的节点。 Specifically, as shown in Figure 5, for the sampling points falling in the obstacle space, use the random node generation function RandomNode(q, r) to generate new nodes to replace the nodes in the obstacle, where q(x q , y q ) Represents the node position, and r represents the radius. As shown in Figure 3, the gray area represents obstacles, with the node A in the obstacle as the center, and according to the obstacles in the environment, use a suitable radius r to make a dotted circle, then each of the dotted circles belongs to free space The nodes in , may become the replacement nodes of A, the node B is randomly generated by the random node generation function, and the node B(x B , y B ) satisfies the following conditions: radius
Figure PCTCN2021127996-appb-000004
Node B is a node within the navigable area.
S3：航线起点和终点与路径图相连接，通过A*搜索算法搜索航线起点到终点的路径，此路径即为初始规划路径。S3: The starting point and the ending point of the route are connected with the path graph, and the path from the starting point to the ending point of the route is searched through the A* search algorithm, and this path is the initial planning path.
S4：关键节点提取，提取初始路径节点中的关键节点，连接路径关键节点形成含有较少拐点的优化路径。具体地，使用D-P算法提取初始路径节点中的关键节点，如图6所示，包括以下子步骤：S4: Key node extraction, extracting key nodes in the initial path nodes, and connecting path key nodes to form an optimized path with fewer inflection points. Specifically, use the D-P algorithm to extract the key nodes in the initial path nodes, as shown in Figure 6, including the following sub-steps:
S41：确定初始阈值φ，连接初始路径节点的初始点和目标点形成一条基准线；S41: Determine the initial threshold φ, and connect the initial point and the target point of the initial path node to form a baseline;
S42：计算初始点和目标点之间所有节点到基准线的距离d，得到距离基准线最远的节点，将最远距离d m与初始阈值φ进行比较； S42: Calculate the distance d from all nodes between the initial point and the target point to the baseline, obtain the node farthest from the baseline, and compare the furthest distance d m with the initial threshold φ;
S43：若d m＜φ，则该基准线段作为新的路径，该段路径处理完毕； S43: If d m <φ, the reference line segment is used as a new path, and the path processing of this segment is completed;
S44：若d m＞φ，把此节点纳入关键节点集，该关键节点分别与初始点和目标点相连接形成两条新的基准线，并对这两段基准线重复步骤S42至S44提取新的关键节点； S44: If d m > φ, include this node into the key node set, the key nodes are respectively connected with the initial point and the target point to form two new baselines, and repeat steps S42 to S44 for these two baselines to extract new key nodes of
S45：最后得到关键节点集，依次连接关键节点，即可得到含较少节点的优化路径。S45: Finally, the key node set is obtained, and the key nodes are connected in turn to obtain an optimized path with fewer nodes.
具体地，如图4所示，初始路径节点为A 1～A 8。由图4(a)，设定一合适阈值φ，连接A 1、A 8，在A 1和A 8之间的路径节点中距离线段A 1A 8最远的节点为A 3，A 3与A 1A8的距离为d，大于预先设定的阈值φ，把A 3视为一个关键节点。分别连接A 1、A 3和A 3、A 8形成两条新的基准线段A 1A 3和A 3A 8。由图4(b)可以看出，在A 1与A 3之间与线段A 1A 3距离最远的路径节点为A 2，在A 3和A 8之间距离线段A 3A 8最远的路径节点为A 5，分别与阈值相比较，找出新的路径关键节点。依次重复下去可以得到路径关键节点集，连接路径关键节点即可得到图4(c)所示的新路径B 1—B 2—B 3—B 4。 Specifically, as shown in FIG. 4 , the initial path nodes are A 1 -A 8 . From Figure 4(a), set an appropriate threshold φ, connect A 1 and A 8 , among the path nodes between A 1 and A 8 , the node farthest from the line segment A 1 A 8 is A 3 , A 3 and A 8 The distance between A 1 and A8 is d, which is greater than the preset threshold φ, and A 3 is regarded as a key node. Connect A 1 , A 3 and A 3 , A 8 respectively to form two new reference line segments A 1 A 3 and A 3 A 8 . From Figure 4(b), it can be seen that the path node between A 1 and A 3 is the farthest from the line segment A 1 A 3 is A 2 , and the path node between A 3 and A 8 is the farthest from the line segment A 3 A 8 The path node of A 5 is compared with the threshold value to find out the new path key node. By repeating in turn, the key node set of the path can be obtained, and the new path B 1 —B 2 —B 3 —B 4 shown in Figure 4(c) can be obtained by connecting the key nodes of the path.
其中，初始阈值φ根据地图障碍物的分布情况以及初始路径节点个数来确定，含有较多障碍物的复杂地图中，选取较小的阈值，含有较少障碍物或障碍物分布简单的地图中，选取较大阈值进行路径关键节点提取。Among them, the initial threshold φ is determined according to the distribution of obstacles on the map and the number of initial path nodes. In a complex map with more obstacles, a smaller threshold is selected. In a map with fewer obstacles or a simple distribution of obstacles , select a larger threshold for path key node extraction.
S5：路径平滑，对含有较少拐点的优化路径进行平滑处理，得到平滑优化路径。具体地，包括：S5: path smoothing, smoothing the optimized path with less inflection points to obtain a smooth optimized path. Specifically, including:
S51：设D-P算法提取的关键节点坐标为Q(x i，y i)(i＝1，2，…，k)，将含较少节点的优化路径分为k-1段； S51: Let the key node coordinates extracted by the DP algorithm be Q( xi , y i ) (i=1, 2, ..., k), and divide the optimization path containing fewer nodes into k-1 segments;
S52：对其中第m段路径进行欧拉螺线拟合，其两端关键节点坐标为(x m，y m)、(x m+1，y m+1)，两点满足： S52: Carry out Euler spiral fitting on the m-th section of the path, the coordinates of the key nodes at both ends are (x m , y m ), (x m+1 , y m+1 ), and the two points satisfy:
Figure PCTCN2021127996-appb-000005
Figure PCTCN2021127996-appb-000005
其中，s m为第m段欧拉螺线的弧长，θ 0m与k 0m分别为(x m，y m)点处的切线角及曲率，c m表示曲率锐度的参数； Among them, s m is the arc length of the m-th Euler spiral, θ 0m and k 0m are the tangent angle and curvature at the point (x m , y m ) respectively, and c m represents the parameter of the sharpness of the curvature;
S53：(x m+1，y m+1)为第m段欧拉螺线的终点及第m+1段欧拉螺线的起点，此处各参数应满足： S53: (x m+1 , y m+1 ) is the end point of the m-th Euler spiral and the starting point of the m+1-th Euler spiral, and the parameters here should satisfy:
Figure PCTCN2021127996-appb-000006
Figure PCTCN2021127996-appb-000006
其中，θ 0m+1与k 0m+1分别表示第m+1段欧拉螺线的初始切线角及初始曲率，θ m与k m分别为第m段欧拉螺线在(x m+1，y m+1)点处的切线角及曲率； Among them, θ 0m+1 and k 0m+1 represent the initial tangent angle and initial curvature of the m+1th Euler spiral, respectively, and θ m and k m represent the mth segment of the Euler spiral at (x m+1 , y m+1 ) point tangent angle and curvature;
S54：按照S52与S53的条件依次对k-1段路径进行欧拉螺线拟合，即可得到平滑优化路径。S54: According to the conditions of S52 and S53, sequentially perform Euler spiral fitting on the k-1 segment paths to obtain a smooth optimized path.
本发明还提供一种电子设备，包括一个或多个处理器以及存储器；一个或多个程序被存储在存储器中并被配置为由一个或多个处理器执行，一个或多个程序配置用于执行上述的海盗区域船舶航线规划方法。The present invention also provides an electronic device, including one or more processors and a memory; one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured for Execute the pirate area ship route planning method described above.
本发明还提供一种计算机可读存储介质，计算机可读存储介质中存储有程序代码，其中，在程序代码运行时执行上述的海盗区域船舶航线规划方法。The present invention also provides a computer-readable storage medium, in which program codes are stored, wherein, when the program codes are running, the above method for planning a ship's route in a pirate area is executed.
综上所述，本发明通过构建障碍地图，利用K均值聚类算法对历史海盗活动点进行聚类分析，提取每簇的聚类中心坐标，根据坐标构建Voronoi图，并提取Voronoi图边界作为障碍物边界，进而构建障碍物区域及可航区域的栅格地图；使用PRM算法构建路径网络图，在给定栅格地图中随机撒点，并使用随机节点生成函数生成新的节点替换障碍物中的节点，提高采样点的利用率，通过局部规划器连接节点，形成路径网络图；PRM算法寻找初始路径，将给定的航线起点和终点与路径图相连接，并通过A*搜索算法找到航线起点到终点的路径；路径优化，关键节点提取，使用D-P算法提取初始路径节点中的关键节点，连接路径关键节点形成含有较少拐点的优化路径；路径平滑，对含有较少拐点的优化路径使用欧拉螺线进行拟合，得到平滑优化路径。本发明在对使用PRM算法进行航线规划来说，提高了采 样点的利用率，减少了原始路径上节点数目，缩短路径长度，提高了路径的平滑度，贴近实际航海应用。In summary, the present invention uses the K-means clustering algorithm to cluster and analyze historical pirate activity points by constructing an obstacle map, extracts the cluster center coordinates of each cluster, constructs a Voronoi diagram according to the coordinates, and extracts the boundary of the Voronoi diagram as an obstacle Object boundaries, and then construct grid maps of obstacle areas and navigable areas; use PRM algorithm to construct path network diagrams, randomly scatter points in a given grid map, and use random node generation functions to generate new nodes to replace obstacles nodes, improve the utilization rate of sampling points, connect the nodes through the local planner, and form a path network graph; the PRM algorithm finds the initial path, connects the starting point and end point of the given route with the path graph, and finds the route through the A* search algorithm The path from the starting point to the end point; path optimization, key node extraction, using the D-P algorithm to extract the key nodes in the initial path nodes, connecting the key nodes of the path to form an optimized path with fewer inflection points; path smoothing, use for optimized paths with fewer inflection points Fit the Euler spiral to obtain a smooth optimal path. For route planning using the PRM algorithm, the present invention improves the utilization rate of sampling points, reduces the number of nodes on the original path, shortens the path length, improves the smoothness of the path, and is close to the actual navigation application.
需要指出，根据实施的需要，可将本申请中描述的各个步骤/部件拆分为更多步骤/部件，也可将两个或多个步骤/部件或者步骤/部件的部分操作组合成新的步骤/部件，以实现本发明的目的。It should be pointed out that according to the needs of implementation, each step/component described in this application can be split into more steps/components, and two or more steps/components or part of the operations of steps/components can also be combined into a new Step/component, to realize the object of the present invention.
本领域的技术人员容易理解，以上仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明的保护范围之内。Those skilled in the art can easily understand that the above are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention should be Included within the protection scope of the present invention.

Claims (10)

  1. 一种海盗区域船舶航线规划方法，其特征在于，包括以下步骤：A pirate area ship route planning method, characterized in that it comprises the following steps:
    S1、对历史海盗活动点进行聚类分析，构建障碍物区域及可航区域的栅格地图；S1. Carry out cluster analysis on historical pirate activity points, and construct grid maps of obstacle areas and navigable areas;
    S2、在栅格地图中随机撒点，然后通过局部规划器连接节点，形成路径网络图；S2. Randomly sprinkle points in the grid map, and then connect the nodes through the local planner to form a path network graph;
    S3、将航线起点和终点与路径图相连，通过A*搜索算法搜索航线起点到终点的初始路径；S3. Connect the starting point and the ending point of the route with the route map, and search for the initial path from the starting point to the ending point of the route through the A* search algorithm;
    S4、提取初始路径节点中的关键节点，连接关键节点形成含有较少拐点的优化路径；S4. Extract key nodes in the initial path nodes, and connect the key nodes to form an optimized path containing less inflection points;
    S5、对含有较少拐点的优化路径进行平滑处理，得到平滑优化路径。S5. Perform smoothing processing on the optimized path containing less inflection points to obtain a smooth optimized path.
  2. 根据权利要求1所述的海盗区域船舶航线规划方法，其特征在于，步骤S1包括：The ship route planning method in the pirate area according to claim 1, wherein step S1 comprises:
    S11、使用K均值聚类算法对航线规划海域的历史海盗活动点进行聚类分析，提取每簇的聚类中心坐标；S11, using the K-means clustering algorithm to perform cluster analysis on the historical pirate activity points in the route planning sea area, and extract the cluster center coordinates of each cluster;
    S12、根据中心坐标构建Voronoi图，提取Voronoi图中海盗活动区域边界作为障碍物边界；S12. Construct a Voronoi diagram according to the center coordinates, and extract the boundary of the pirate activity area in the Voronoi diagram as the obstacle boundary;
    S13、根据障碍物边界构建障碍物区域及可航区域的栅格地图。S13. Construct a grid map of the obstacle area and the navigable area according to the obstacle boundary.
  3. 根据权利要求1所述的海盗区域船舶航线规划方法，其特征在于，步骤S2包括：The route planning method for ships in pirate areas according to claim 1, wherein step S2 comprises:
    在栅格地图中随机撒点；Randomly sprinkle points in the grid map;
    对落在障碍物区域的采样点，在可航区域生成一个新的节点，以替换落在障碍物区域的节点。For the sampling points falling in the obstacle area, a new node is generated in the navigable area to replace the node falling in the obstacle area.
  4. 根据权利要求3所述的海盗区域船舶航线规划方法，其特征在于，在可航区域生成新的节点包括：The ship route planning method in the pirate area according to claim 3, wherein generating new nodes in the navigable area comprises:
    对落在障碍物区域的采样点q(x q，y q)，使用随机节点生成函数RandomNode(q，r)，其中q代表节点位置，r代表半径，生成新的节点替换障碍物区域的节点； For the sampling point q(x q , y q ) falling in the obstacle area, use the random node generation function RandomNode(q, r), where q represents the node position, r represents the radius, and generate a new node to replace the node in the obstacle area ;
    新的节点B满足半径
    Figure PCTCN2021127996-appb-100001
    且节点B为可航区域内的节点。     The new node B satisfies the radius
    Figure PCTCN2021127996-appb-100001
    And node B is a node within the navigable area.
  5. 根据权利要求1所述的海盗区域船舶航线规划方法，其特征在于，步骤S4使用D-P算法提取初始路径节点中的关键节点，包括：The route planning method for ships in pirate areas according to claim 1, wherein step S4 uses the D-P algorithm to extract key nodes in the initial path nodes, including:
    S41、确定初始阈值φ，连接初始路径节点的初始点和目标点形成一条基准线；S41. Determine the initial threshold φ, and connect the initial point and the target point of the initial path node to form a baseline;
    S42、计算初始点和目标点之间所有节点到基准线的距离d，得到距离基准线最远的节点，将最远的节点所对应的最远距离d m与初始阈值φ进行比较； S42. Calculate the distance d from all nodes between the initial point and the target point to the baseline, obtain the node farthest from the baseline, and compare the furthest distance d m corresponding to the furthest node with the initial threshold φ;
    S43、若d m＜φ，则该基准线段作为新的路径，该段路径处理完毕； S43. If d m <φ, the reference line segment is used as a new path, and the path processing of this segment is completed;
    S44、若d m＞φ，则把此节点纳入关键节点集，该关键节点分别与初始点和目标点相连 接形成两条新的基准线，并对这两段基准线重复步骤S42至步骤S44以提取新的关键节点； S44. If d m > φ, include this node into the key node set, and the key nodes are respectively connected with the initial point and the target point to form two new baselines, and repeat steps S42 to S44 for these two baselines to extract new key nodes;
    S45、最后得到关键节点集，依次连接关键节点，即可得到含较少节点的优化路径。S45. Finally, the key node set is obtained, and the key nodes are connected in sequence to obtain an optimized path with fewer nodes.
  6. 根据权利要求5所述的海盗区域船舶航线规划方法，其特征在于，初始阈值φ根据地图障碍物的分布情况以及初始路径节点个数来确定，含有较多障碍物的复杂地图中，选取较小的阈值，含有较少障碍物或障碍物分布简单的地图中，选取较大阈值进行路径关键节点提取。The route planning method for ships in the pirate area according to claim 5, wherein the initial threshold φ is determined according to the distribution of obstacles on the map and the number of initial path nodes, and in complex maps containing more obstacles, a smaller value is selected. In a map with fewer obstacles or a simple distribution of obstacles, a larger threshold is selected for path key node extraction.
  7. 根据权利要求1所述的海盗区域船舶航线规划方法，其特征在于，步骤S5使用欧拉螺线拟合进行路径平滑处理，包括：The route planning method for ships in pirate areas according to claim 1, wherein step S5 uses Euler spiral fitting to perform path smoothing, including:
    S51、设提取的关键节点坐标为Q(x i，y i)(i＝1，2，…，k)，将含较少节点的优化路径分为k-1段； S51. Assuming that the extracted key node coordinates are Q( xi , y i ) (i=1, 2, ..., k), the optimized path containing fewer nodes is divided into k-1 segments;
    S52、对其中第m段路径进行欧拉螺线拟合，其两端关键节点坐标为(x m，y m)、(x m+1，y m+1)，两点满足： S52. Carry out Euler spiral fitting to the m-th section of the path, the coordinates of the key nodes at both ends are (x m , y m ), (x m+1 , y m+1 ), and the two points satisfy:
    Figure PCTCN2021127996-appb-100002
    Figure PCTCN2021127996-appb-100002
    其中，s m为第m段欧拉螺线的弧长，θ 0m与k 0m分别为(x m，y m)点处的切线角及曲率，c m表示曲率锐度的参数； Among them, s m is the arc length of the m-th Euler spiral, θ 0m and k 0m are the tangent angle and curvature at the point (x m , y m ) respectively, and c m represents the parameter of the sharpness of the curvature;
    S53、(x m+1，y m+1)为第m段欧拉螺线的终点及第m+1段欧拉螺线的起点，此处各参数应满足： S53, (x m+1 , y m+1 ) is the end point of the mth segment Euler spiral and the starting point of the m+1th segment Euler spiral, where each parameter should satisfy:
    Figure PCTCN2021127996-appb-100003
    Figure PCTCN2021127996-appb-100003
    其中，θ 0m+1与k 0m+1分别表示第m+1段欧拉螺线的初始切线角及初始曲率，θ m与k m分别为第m段欧拉螺线在(x m+1，y m+1)点处的切线角及曲率； Among them, θ 0m+1 and k 0m+1 represent the initial tangent angle and initial curvature of the m+1th Euler spiral, respectively, and θ m and k m represent the mth segment of the Euler spiral at (x m+1 , y m+1 ) point tangent angle and curvature;
    S54、按照步骤S52和步骤S53依次对k-1段路径进行欧拉螺线拟合，即可得到平滑优化路径。S54 , according to step S52 and step S53 , sequentially perform Euler spiral fitting on the k-1 path, so as to obtain a smooth optimized path.
  8. 一种海盗区域船舶航线规划系统，其特征在于，包括：A shipping route planning system in a pirate area, characterized in that it includes:
    栅格地图模块，用于对历史海盗活动点进行聚类分析，构建障碍物区域及可航区域的栅格地图；The grid map module is used for cluster analysis of historical pirate activity points, and constructs grid maps of obstacle areas and navigable areas;
    路径网络图模块，用于在栅格地图中随机撒点，然后通过局部规划器连接节点，形成路径网络图；The path network diagram module is used to randomly scatter points in the grid map, and then connect the nodes through the local planner to form a path network diagram;
    初始路径模块，用于将航线起点和终点与路径图相连，通过A*搜索算法搜索航线起点到终点的初始路径；The initial path module is used to connect the starting point and the ending point of the route with the route map, and search for the initial path from the starting point to the ending point of the route through the A* search algorithm;
    路径优化模块，用于提取初始路径节点中的关键节点，连接关键节点形成含有较少拐点的优化路径；The path optimization module is used to extract the key nodes in the initial path nodes, and connect the key nodes to form an optimized path containing less inflection points;
    路径平滑模块，用于对含有较少拐点的优化路径进行平滑处理，得到平滑优化路径。The path smoothing module is used for smoothing the optimized path containing less inflection points to obtain a smooth optimized path.
  9. 一种电子设备，其特征在于，包括一个或多个处理器以及存储器；An electronic device, characterized in that it includes one or more processors and memory;
    一个或多个程序被存储在存储器中并被配置为由一个或多个处理器执行，一个或多个程序配置用于执行权利要求1-7中任一项所述的海盗区域船舶航线规划方法。One or more programs are stored in the memory and are configured to be executed by one or more processors, and one or more programs are configured to execute the pirate area ship route planning method according to any one of claims 1-7 .
  10. 一种计算机可读存储介质，其特征在于，计算机可读存储介质中存储有程序代码，其中，在程序代码运行时执行权利要求1-7中任一项所述的海盗区域船舶航线规划方法。A computer-readable storage medium, characterized in that program codes are stored in the computer-readable storage medium, wherein, when the program code is running, the route planning method for a ship in a pirate area according to any one of claims 1-7 is executed.
PCT/CN2021/127996 2021-09-27 2021-11-01 Method and system for ship route planning in pirate region, electronic device and storage medium WO2023045029A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111137498.2 2021-09-27
CN202111137498.2A CN113961004A (en) 2021-09-27 2021-09-27 Pirate area ship route planning method and system, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
WO2023045029A1 true WO2023045029A1 (en) 2023-03-30

Family

ID=79462396

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/127996 WO2023045029A1 (en) 2021-09-27 2021-11-01 Method and system for ship route planning in pirate region, electronic device and storage medium

Country Status (2)

Country Link
CN (1) CN113961004A (en)
WO (1) WO2023045029A1 (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116484798A (en) * 2023-04-27 2023-07-25 北京容汇科技有限公司 PCB wiring acceleration optimization method based on segmentation parallel search
CN116880513A (en) * 2023-09-06 2023-10-13 广州慧洋信息科技有限公司 Underwater robot operation monitoring management system based on data analysis
CN116952251A (en) * 2023-09-19 2023-10-27 北京海兰信数据科技股份有限公司 Path planning method, device, terminal equipment and readable storage medium
CN117433541A (en) * 2023-12-22 2024-01-23 中船（浙江）海洋科技有限公司 Automatic planning method for platform avoidance route
CN117452583A (en) * 2023-12-25 2024-01-26 国网浙江省电力有限公司宁波供电公司 Optical cable line planning method, system, storage medium and computing equipment

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023240577A1 (en) * 2022-06-17 2023-12-21 深圳市正浩创新科技股份有限公司 Path planning method, computer device, and storage medium
CN115983512B (en) * 2022-09-02 2023-10-20 武汉理工大学 Specific area-oriented electronic chart display and application platform
CN116307334B (en) * 2023-05-17 2023-08-15 广州一链通互联网科技有限公司 Dynamic programming method, system and computer equipment for internal trade gathering and transportation route
CN117572894B (en) * 2024-01-16 2024-03-22 中国人民解放军陆军航空兵学院 On-time arrival route planning method in unmanned aerial vehicle designated area

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018120489A1 (en) * 2016-12-29 2018-07-05 珠海市一微半导体有限公司 Route planning method for intelligent robot
CN110220514A (en) * 2019-05-27 2019-09-10 中国电子科技集团公司第二十八研究所 A kind of dynamic lane generation method based on chart data
CN113110507A (en) * 2021-05-13 2021-07-13 北京鼎翰科技有限公司 Path planning method for autonomous obstacle avoidance

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110189547B (en) * 2019-05-30 2020-10-20 广州小鹏汽车科技有限公司 Obstacle detection method and device and vehicle
US11625044B2 (en) * 2019-09-26 2023-04-11 Tata Consultancy Services Limited Method and system for real-time path planning
CN113110464A (en) * 2021-04-22 2021-07-13 集美大学 Intelligent full-electric ship path planning method capable of reducing energy consumption

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018120489A1 (en) * 2016-12-29 2018-07-05 珠海市一微半导体有限公司 Route planning method for intelligent robot
CN110220514A (en) * 2019-05-27 2019-09-10 中国电子科技集团公司第二十八研究所 A kind of dynamic lane generation method based on chart data
CN113110507A (en) * 2021-05-13 2021-07-13 北京鼎翰科技有限公司 Path planning method for autonomous obstacle avoidance

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
LIU YANG, ZHANG WEI-GUO, LI GUANG-WEN: "Study on path planning based on improved PRM method", APPLICATION RESEARCH OF COMPUTERS, CHENGDU, CN, vol. 29, no. 1, 31 January 2012 (2012-01-31), CN , pages 104 - 106, XP009544911, ISSN: 1001-3695, DOI: 10.3969/j.issn.1001-3695.2012.01.029 *
WEI, NIANWEI: "Method of PRM Path Optimization Based on Key Nodes and Smooth Processing", COMPUTER ENGINEERING AND APPLICATIONS, HUABEI JISUAN JISHU YANJIUSUO, CN, vol. 56, no. 16, 1 January 2020 (2020-01-01), CN , pages 118 - 123, XP093055890, ISSN: 1002-8331, DOI: 10.3778/j.issn.1002-8331.1905-0442 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116484798A (en) * 2023-04-27 2023-07-25 北京容汇科技有限公司 PCB wiring acceleration optimization method based on segmentation parallel search
CN116484798B (en) * 2023-04-27 2024-05-03 苏州容汇科技有限公司 PCB wiring acceleration optimization method based on segmentation parallel search
CN116880513A (en) * 2023-09-06 2023-10-13 广州慧洋信息科技有限公司 Underwater robot operation monitoring management system based on data analysis
CN116880513B (en) * 2023-09-06 2023-11-17 广州慧洋信息科技有限公司 Underwater robot operation monitoring management system based on data analysis
CN116952251A (en) * 2023-09-19 2023-10-27 北京海兰信数据科技股份有限公司 Path planning method, device, terminal equipment and readable storage medium
CN116952251B (en) * 2023-09-19 2024-01-12 北京海兰信数据科技股份有限公司 Path planning method, device, terminal equipment and readable storage medium
CN117433541A (en) * 2023-12-22 2024-01-23 中船（浙江）海洋科技有限公司 Automatic planning method for platform avoidance route
CN117433541B (en) * 2023-12-22 2024-04-02 中船（浙江）海洋科技有限公司 Automatic planning method for platform avoidance route
CN117452583A (en) * 2023-12-25 2024-01-26 国网浙江省电力有限公司宁波供电公司 Optical cable line planning method, system, storage medium and computing equipment
CN117452583B (en) * 2023-12-25 2024-04-16 国网浙江省电力有限公司宁波供电公司 Optical cable line planning method, system, storage medium and computing equipment

Also Published As

Publication number Publication date
CN113961004A (en) 2022-01-21

Similar Documents

Publication Publication Date Title
WO2023045029A1 (en) Method and system for ship route planning in pirate region, electronic device and storage medium
Li et al. Autonomous underwater vehicle optimal path planning method for seabed terrain matching navigation
CN108827335B (en) Shortest path planning method based on one-way search model
CN105512769A (en) Unmanned aerial vehicle route planning system and unmanned aerial vehicle route planning method based on genetic programming
CN108489491A (en) A kind of Three-dimensional Track Intelligent planning method of autonomous underwater vehicle
Gu et al. An improved RRT algorithm based on prior AIS information and DP compression for ship path planning
Wang et al. Local path optimization method for unmanned ship based on particle swarm acceleration calculation and dynamic optimal control
CN107121146A (en) Optimum path planning method based on road chain depth
CN109916421A (en) Paths planning method and device
CN108225333A (en) A kind of optimal path generation method for flight course planning
CN108994838A (en) The relationship calculation method and system of robot location and planning path
CN113515111B (en) Vehicle obstacle avoidance path planning method and device
CN112344938A (en) Space environment path generation and planning method based on pointing and potential field parameters
CN116734877A (en) Robot dynamic obstacle avoidance method based on improved A-algorithm and dynamic window method
Liu et al. Application of dijkstra algorithm in path planning for geomagnetic navigation
CN116952251B (en) Path planning method, device, terminal equipment and readable storage medium
CN112197783B (en) Two-stage multi-sampling RRT path planning method considering locomotive direction
Liu et al. Ship route planning in the pirate area via hybrid probabilistic roadmap algorithm within the context of the Maritime Silk Road
CN117873115A (en) Autonomous navigation obstacle avoidance path planning method based on SLAM
CN110749325B (en) Flight path planning method and device
CN115826591B (en) Multi-target point path planning method based on neural network estimation path cost
CN116523158A (en) Multi-unmanned aerial vehicle track planning method, device, equipment and storage medium
CN116772846A (en) Unmanned aerial vehicle track planning method, unmanned aerial vehicle track planning device, unmanned aerial vehicle track planning equipment and unmanned aerial vehicle track planning medium
CN113311843B (en) Unmanned ship path planning method based on safe distance constraint and LOS sight judgment
CN114879675A (en) Numerical optimization method for automatically planning restricted water area airway

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21958142

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE