Unmanned ship global path planning method and system based on electronic fence
By using a path planning method based on electronic fences, and optimizing the path search of unmanned surface vessels (USVs) by utilizing water flow direction information and obstacle avoidance, the problem of low path planning efficiency for USVs in large river basins is solved, and efficient and safe navigation is achieved.
Patent Information
- Application Number
- CN202410980459.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-08
AI Technical Summary
Existing unmanned vessels involve large computational loads in path planning across large river basins and fail to effectively utilize river direction information, resulting in low path search efficiency and poor environmental adaptability.
A path planning method based on electronic fences is adopted. The navigation area of the unmanned vessel is divided into closed fenced areas. Path search is carried out by using water flow direction information. Obstacle avoidance is taken into account in the path planning. Path search is optimized by using river direction information.
It improves the efficiency and environmental adaptability of path planning, reduces the amount of computation, and ensures that unmanned ships can navigate safely and efficiently in complex environments.
Smart Images

Figure CN118913284A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of unmanned ships and path planning, and in particular to a global path planning method and system for an unmanned ship based on an electronic fence. Background Art
[0002] An unmanned boat is a fully automatic surface robot that can navigate on the water according to preset tasks without remote control, relying on precise satellite positioning and its own sensors. At present, unmanned boats are mostly used for surveying and mapping, hydrology and water quality monitoring. The automatic navigation and sampling of unmanned boats can greatly save human resources and improve work efficiency.
[0003] The key technology to realize the automatic navigation of unmanned ships lies in path planning. When the existing unmanned ships do global path planning, they must first obtain the grid map covering the navigation area, select the starting point and the target point on the grid map, and then use the search algorithm to finally calculate the navigation path that is short and meets the requirements of safety and comfort. In this process, small-scale planning can quickly obtain the navigation path, but the actual application scenario may involve a large area of river basins, and a lot of calculations are required to obtain the navigation path; in addition, considering the seasonal changes in water levels and tidal changes, the grid map used for path planning must also be updated accordingly, which will lead to an increase in the workload and difficulty of unmanned ship path planning. At the same time, the path search does not use the direction information of the river, and the winding of the river will reduce the efficiency of the search calculation. Summary of the invention
[0004] In response to the above technical problems, the present application provides a global path planning method and system for an unmanned ship based on an electronic fence to improve the efficiency and environmental adaptability of the unmanned ship path planning.
[0005] In a first aspect, the present application provides a global path planning method for an unmanned ship based on an electronic fence, comprising:
[0006] Obtain the current position, navigation destination and electronic fence area of the unmanned ship, wherein the electronic fence area is obtained by dividing the navigation area of the unmanned ship into several closed fence areas through the intersection of several cross-sectional segments perpendicular to the water flow direction and the shoreline, and each of the cross-sectional segments has a corresponding navigation path point;
[0007] According to the navigation path points, based on a preset search algorithm, a plurality of routes from the current position to the navigation destination are searched and obtained, wherein the routes are formed by connecting lines between the navigation path points, and each navigation path point appears at most once in each route;
[0008] The various routes are evaluated according to preset evaluation indicators, and the route with the highest score is used as the final planned navigation route of the unmanned ship.
[0009] The embodiment of the present application provides a global path planning method for an unmanned ship based on an electronic fence, by obtaining the current position of the unmanned ship, the navigation end point and the electronic fence area, and planning the navigation path of the unmanned ship based on the electronic fence. Among them, there is only one corresponding navigation path point on each cross-sectional line segment of the electronic fence, and each navigation path point appears at most once in the route. Through the setting of the electronic fence, it is not necessary to search in all directions based on the position of the unmanned ship or to focus on the straight line direction of the target point in a heuristic way during the path search process, but only to search for the navigation path points near the unmanned ship. And because each cross-sectional line segment is perpendicular to the flow direction of the water, the route formed by the connection of the navigation path points on each cross-sectional line segment must be downstream or upstream, so that the direction information of the river can be effectively used in the path search process, further reducing the amount of calculation in the path search process and the number of invalid paths generated, and improving the efficiency of path planning. Finally, this application not only uses distance as an evaluation indicator for the route, but also evaluates each generated route based on preset indicators. Therefore, in practical applications, the evaluation indicators can be preset according to the local environment, climate and the tasks performed by the unmanned ship, and then the optimal route can be obtained from each route, thereby improving the environmental adaptability of the path planning.
[0010] In a possible implementation, the electronic fence area is obtained by dividing the navigation area of the unmanned ship into a plurality of closed fence areas by intersecting the shoreline with a plurality of cross-sectional line segments perpendicular to the water flow direction, including:
[0011] Determining the current shoreline of the navigation area of the unmanned vessel;
[0012] Determining the location of obstacles in the navigation area of the unmanned ship;
[0013] Generating a plurality of first cross-sectional line segments perpendicular to the water flow direction and intersecting with the water shoreline according to a preset interval distance;
[0014] Generating corresponding second cross-sectional line segments perpendicular to the flow direction of the water flow from the positions of the respective obstacles to intersect with the shoreline;
[0015] Generating first navigation path points on each of the first cross-sectional line segments according to a first preset value, wherein the first preset value is a ratio of the distances from each of the first navigation path points to the shorelines on both sides;
[0016] The second navigation path points on each of the second cross-sectional line segments are generated according to a second preset value, wherein the second preset value is the minimum distance from each of the second navigation path points to the corresponding obstacle.
[0017] The embodiment of the present application provides a method for generating an electronic fence area, which mainly involves the division of cross-sectional segments and the determination of navigation path points. When all cross-sectional segments are divided, the electronic fence area is naturally formed. The cross-sectional segments include a first cross-sectional segment and a second cross-sectional segment, wherein the first cross-sectional segment is generated based on the waterfront, the flow direction of the water flow, and the preset interval distance, which is equivalent to constructing an initial electronic fence area. The present application further considers the problem of obstacles in path planning. In the existing unmanned ship navigation technology, obstacles are generally handled by automatically avoiding obstacles through the detection radar of the unmanned ship body. However, if the obstacle is large, it will cause the unmanned ship to deviate significantly from the original planned path, and even fail to reach the target location. Therefore, the present application considers the avoidance of obstacles in advance in path planning, generates the corresponding second cross-sectional segments from each obstacle position, and sets the navigation path points away from the obstacles on the second cross-sectional segments to achieve early avoidance of fixed obstacles, thereby improving the environmental adaptability of path planning and the navigation safety of the unmanned ship.
[0018] In a possible implementation, searching for a plurality of routes from the current position to the navigation destination based on the respective navigation path points and a preset search algorithm includes:
[0019] Taking the navigation path point closest to the current position as the search starting point;
[0020] Taking the navigation path point closest to the navigation end point as the search end point;
[0021] Determine the upstream neighboring point set and the downstream neighboring point set corresponding to each navigation path point according to the electronic fence area, wherein the upstream neighboring point set of any third navigation path point is a number of navigation path points located upstream of the third navigation path point and adjacent to the third navigation path point, and the downstream neighboring point set of the third navigation path point is a number of navigation path points located downstream of the third navigation path point and adjacent to the third navigation path point;
[0022] Starting from the search starting point, a plurality of search paths that can reach the search end point are obtained through a plurality of searches based on a preset search algorithm, wherein each search selects a navigation path point from an upstream neighbor point set or a downstream neighbor point set of the current search point as the next search point;
[0023] The search starting point of each search path is connected to the current position, and the search end point of each search path is connected to the navigation end point to obtain the plurality of routes.
[0024] The embodiment of the present application provides a route generation method. Since the path planning is based on each navigation path point, it is necessary to first determine the search starting point and the search end point. The subsequent path planning only needs to search multiple paths from the search starting point through several navigation path points to the search end point to obtain multiple corresponding routes. Then, in order to effectively use the river information for path planning, the upstream neighbor point set and the downstream neighbor point set corresponding to each navigation path point are determined in the path planning process, so that each subsequent search only needs to select a navigation path point from the upstream neighbor point set or the downstream neighbor point set of the current search point as the next search point, further narrowing the path search range and improving the efficiency of path planning.
[0025] Furthermore, starting from the search starting point, obtaining a plurality of search paths that can reach the search end point through a plurality of searches based on a preset search algorithm includes:
[0026] In each search, the navigation path points in the upstream neighbor point set and the downstream neighbor point set of the current search point that do not appear in the current search path are used as the neighbor point set to be searched, and search path branches with the same number as the navigation path points in the neighbor point set to be searched are created, and the current search path is deleted, wherein each of the search path branches inherits the navigation path points in the current search path, and each of the search path branches selects different navigation path points from the neighbor point set to be searched to form multiple different search paths and each performs the next search;
[0027] When a first search path does not reach the search end point and cannot be further expanded, deleting the first search path;
[0028] When a second search path reaches the search end point, the second search path is saved.
[0029] An embodiment of the present application provides a path search method, in which a corresponding search path branch is generated based on the number of neighboring point sets to be searched in each search, and each search path branch inherits the current search path. Each search path branch continues the next search until the search end point is reached, ensuring that all non-repeated paths that can reach the end point from the starting point are found, thereby realizing global planning of the unmanned ship path.
[0030] In a possible implementation, the unmanned ship global path planning method further includes:
[0031] When the water level of the river in the navigation area of the unmanned boat changes, the electronic fence area will automatically adjust the area range according to the change of the water level of the river;
[0032] During navigation, the unmanned boat continuously detects whether the unmanned boat exceeds the electronic fence area according to a preset time interval.
[0033] In the embodiment of the present application, the electronic fence area will automatically adjust the area range according to the change of the river water level, so that when facing environmental changes, the present application can handle the impact of water level changes on path planning without modifying the map data in large quantities, thereby improving the environmental adaptability of path planning. In addition, during the navigation of the unmanned boat, the unmanned boat is continuously detected according to the preset time interval to see whether it exceeds the electronic fence area, ensuring that the unmanned boat can correctly execute the planned route, thereby improving the navigation efficiency and navigation safety of the unmanned boat.
[0034] In a second aspect, accordingly, the present application provides an unmanned ship global path planning system based on electronic fence, including an acquisition module, a search module and an evaluation module;
[0035] The acquisition module is used to acquire the current position, navigation destination and electronic fence area of the unmanned ship, wherein the electronic fence area is obtained by dividing the navigation area of the unmanned ship into several closed fence areas through the intersection of several cross-sectional segments perpendicular to the water flow direction and the shoreline, and each of the cross-sectional segments has a corresponding navigation path point;
[0036] The search module is used to search and obtain a plurality of routes from the current position to the navigation destination according to the navigation path points based on a preset search algorithm, wherein the routes are formed by connecting lines between the navigation path points, and each navigation path point appears at most once in each route;
[0037] The evaluation module is used to evaluate the various routes according to preset evaluation indicators, and use the route with the highest score as the final planned navigation route of the unmanned ship.
[0038] In a possible implementation, the unmanned ship global path planning system further includes an electronic fence generation module, which is used to obtain the electronic fence area after dividing the navigation area of the unmanned ship into a plurality of closed fence areas through a plurality of cross-sectional segments perpendicular to the water flow direction intersecting with the shoreline, and includes a shoreline determination unit, an obstacle determination unit, a first cross-sectional segment generation unit, a second cross-sectional segment generation unit, a first navigation path point generation unit, and a second navigation path point generation unit;
[0039] Wherein, the water shoreline determination unit is used to determine the current water shoreline of the navigation area of the unmanned ship;
[0040] The obstacle determination unit is used to determine the position of obstacles in the navigation area of the unmanned ship;
[0041] The first cross-sectional line segment generating unit is used to generate a plurality of first cross-sectional line segments perpendicular to the water flow direction and intersecting with the water shoreline according to a preset interval distance;
[0042] The second cross-sectional line segment generating unit is used to generate corresponding second cross-sectional line segments perpendicular to the water flow direction from the positions of the obstacles to intersect with the shoreline;
[0043] The first navigation path point generating unit is used to generate the first navigation path points on each of the first cross-sectional line segments according to a first preset value, wherein the first preset value is a ratio of the distances from each of the first navigation path points to the waterfronts on both sides;
[0044] The second navigation path point generating unit is used to generate the second navigation path points on each second cross-sectional line segment according to a second preset value, wherein the second preset value is the minimum distance from each second navigation path point to the corresponding obstacle.
[0045] In a possible implementation, the search module includes a search starting point determination unit, a search end point determination unit, a neighbor point set determination unit, a search unit, and a route generation unit;
[0046] Wherein, the search starting point determination unit is used to take the navigation path point closest to the current position as the search starting point;
[0047] The search end point determination unit is used to take the navigation path point closest to the navigation end point as the search end point;
[0048] Determine the upstream neighboring point set and the downstream neighboring point set corresponding to each navigation path point according to the electronic fence area, wherein the upstream neighboring point set of any third navigation path point is a number of navigation path points located upstream of the third navigation path point and adjacent to the third navigation path point, and the downstream neighboring point set of the third navigation path point is a number of navigation path points located downstream of the third navigation path point and adjacent to the third navigation path point;
[0049] The search unit is used to obtain a plurality of search paths that can reach the search end point through a plurality of searches starting from the search starting point based on a preset search algorithm, wherein each search selects a navigation path point from an upstream neighbor point set or a downstream neighbor point set of a current search point as a next search point;
[0050] The route generating unit is used to connect the search starting point of each search path with the current position, and connect the search end point of each search path with the navigation end point, so as to obtain the plurality of routes.
[0051] Further, the search unit starts from the search starting point and obtains a plurality of search paths that can reach the search end point through a plurality of searches based on a preset search algorithm, including:
[0052] In each search, the navigation path points in the upstream neighbor point set and the downstream neighbor point set of the current search point that do not appear in the current search path are used as the neighbor point set to be searched, and search path branches with the same number as the navigation path points in the neighbor point set to be searched are created, and the current search path is deleted, wherein each of the search path branches inherits the navigation path points in the current search path, and each of the search path branches selects different navigation path points from the neighbor point set to be searched to form multiple different search paths and each performs the next search;
[0053] When a first search path does not reach the search end point and cannot be further expanded, deleting the first search path;
[0054] When a second search path reaches the search end point, the second search path is saved.
[0055] In a possible implementation, the unmanned ship global path planning system further includes an electronic fence adjustment module and a navigation detection module;
[0056] Wherein, the electronic fence adjustment module is used for automatically adjusting the area range of the electronic fence area according to the change of the river water level when the river water level of the navigation area of the unmanned ship changes;
[0057] The navigation detection module is used for continuously detecting whether the unmanned ship exceeds the electronic fence area according to a preset time interval during the navigation of the unmanned ship. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] Figure 1 :A flow chart of a global path planning method for an unmanned ship based on an electronic fence provided in an embodiment of the present application.
[0059] Figure 2 : A schematic diagram of the electronic fence area of an unmanned ship global path planning method based on electronic fence provided in an embodiment of the present application.
[0060] Figure 3 : A schematic diagram of the process of constructing an electronic fence area in a global path planning method for an unmanned ship based on an electronic fence provided in an embodiment of the present application.
[0061] Figure 4 : A schematic diagram of a portion of the second cross-sectional line segment and the corresponding second navigation path point of a global path planning method for an unmanned ship based on an electronic fence provided in an embodiment of the present application.
[0062] Figure 5 : A schematic diagram of the process of generating several routes in a global path planning method for an unmanned ship based on an electronic fence provided in an embodiment of the present application.
[0063] Figure 6 : A schematic diagram of the electronic fence area range adjustment of an unmanned ship global path planning method based on electronic fence provided in an embodiment of the present application.
[0064] Figure 7 : A structural diagram of a global path planning system for an unmanned ship based on an electronic fence provided in an embodiment of the present application.
[0065] Figure 8 : A structural schematic diagram of an electronic fence generation module of an unmanned ship global path planning system based on electronic fence provided in an embodiment of the present application.
[0066] Fig. 9 : A structural diagram of a search module of an unmanned ship global path planning system based on electronic fence provided in an embodiment of the present application. DETAILED DESCRIPTION
[0067] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0068] It should be noted that the step numbers in the text are only for the convenience of explanation of the specific embodiments and do not serve to limit the order in which the steps are executed. In the description of this application, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.
[0069] Embodiment 1:
[0070] like Figure 1 As shown, embodiment 1 provides a global path planning method for an unmanned ship based on an electronic fence, including steps S1-S3:
[0071] Step S1, obtaining the current position, navigation destination and electronic fence area of the unmanned ship, wherein the electronic fence area is obtained by dividing the navigation area of the unmanned ship into several closed fence areas through the intersection of several cross-sectional segments perpendicular to the water flow direction and the shoreline, and each of the cross-sectional segments has a corresponding navigation path point;
[0072] Step S2, searching and obtaining a plurality of routes from the current position to the navigation destination based on the preset search algorithm according to the respective navigation path points, wherein the routes are formed by connecting lines between the respective navigation path points, and the respective navigation path points appear at most once in each of the routes;
[0073] Step S3: Evaluate each route according to preset evaluation indicators, and use the route with the highest score as the final planned navigation route of the unmanned ship.
[0074] In a preferred embodiment, the schematic diagram of the electronic fence area in step S1 is as follows: Figure 2 As shown, it is obtained by adding the aforementioned several cross-sectional line segments to a map with location information (such as longitude and latitude). Specifically: draw a cross-sectional line segment perpendicular to the direction of water flow in the river channel, and the two ends of the cross-sectional line segment intersect with the waterfront on both sides respectively, and the cross-sectional line segments are represented by numbers f1, f2, ..., f16 in sequence. For any line segment fn, the intersection point of fn with the waterfront on the left side of the water flow direction is point Fnl, and the intersection point of fn with the waterfront on the right side of the water flow direction is point Fnr. Each cross-sectional line segment is uniquely determined by the left and right endpoint sets (Fnl, Fnr), that is, each pair (Fnl, Fnr) represents a cross-sectional line segment. The closed area formed by connecting all Fnl points and Fnr points along the waterfront is the electronic fence area (such as Figure 2 The route planning range of the unmanned ship during navigation does not exceed the range of the electronic fence area. Take a point M on each cross-sectional line segment (such as Figure 2 In M1, M2, ..., M16), point M can be the midpoint or a point offset to the left or right according to a certain proportion. These points will be used as the navigation path points of the unmanned ship. The process of the unmanned ship moving from the current cross-section segment to the adjacent cross-section segment can be simplified to the process from the navigation path point on the current cross-section segment to the navigation path point on the adjacent cross-section segment. The planned path generated by the embodiment of the present application generally exists in the form of a straight line path between adjacent navigation path points.
[0075] The embodiment of the present application provides a global path planning method for an unmanned ship based on an electronic fence, by obtaining the current position of the unmanned ship, the navigation end point and the electronic fence area, and planning the navigation path of the unmanned ship based on the electronic fence. Among them, there is only one corresponding navigation path point on each cross-sectional line segment of the electronic fence, and each navigation path point appears at most once in the route. Through the setting of the electronic fence, it is not necessary to search in all directions based on the position of the unmanned ship or to focus on the straight line direction of the target point in a heuristic way during the path search process, but only to search for the navigation path points near the unmanned ship. And because each cross-sectional line segment is perpendicular to the flow direction of the water, the route formed by the connection of the navigation path points on each cross-sectional line segment must be downstream or upstream, so that the direction information of the river can be effectively used in the path search process, further reducing the amount of calculation in the path search process and the number of invalid paths generated, and improving the efficiency of path planning. Finally, this application not only uses distance as an evaluation indicator for the route, but also evaluates each generated route based on preset indicators. Therefore, in practical applications, the evaluation indicators can be preset according to the local environment, climate and the tasks performed by the unmanned ship, and then the optimal route can be obtained from each route, thereby improving the environmental adaptability of the path planning.
[0076] In a possible implementation, in step S1, the navigation area of the unmanned ship is divided into several closed fence areas by intersecting the water shoreline with several cross-sectional line segments perpendicular to the water flow direction, and then the electronic fence area is obtained, such as Figure 3 As shown, steps S101-S106 are included:
[0077] Step S101, determining the current shoreline of the navigation area of the unmanned ship;
[0078] Step S102: determining the location of obstacles in the navigation area of the unmanned ship;
[0079] Step S103, generating a plurality of first cross-sectional line segments perpendicular to the water flow direction and intersecting with the shoreline according to a preset interval distance;
[0080] Step S104, generating corresponding second cross-sectional line segments perpendicular to the water flow direction from the positions of the respective obstacles to intersect with the shoreline;
[0081] Step S105, generating first navigation path points on each of the first cross-sectional line segments according to a first preset value, wherein the first preset value is a ratio of the distances from each of the first navigation path points to the shorelines on both sides;
[0082] Step S106: Generate second navigation path points on each second cross-sectional line segment according to a second preset value, wherein the second preset value is the minimum distance from each second navigation path point to the corresponding obstacle.
[0083] In a preferred embodiment, a schematic diagram of part of the second cross-sectional line segments and the corresponding second navigation path points is as follows: Figure 4 As shown. Figure 4 In the figure, line segment f2 is the second cross-sectional line segment. If there is an obstacle O on the second cross-sectional line segment, a corresponding second navigation path point is generated at a second preset distance from the obstacle O to avoid the obstacle. Regarding the setting of the second preset value, the radius information of each obstacle can be obtained when the position of each obstacle is determined in step S102, and then a suitable second preset value is generated according to the radius information. Furthermore, the second navigation path point can be set to be generated on the longer cross-sectional line segment of the two cross-sectional line segments divided by the obstacle, for example, Figure 4 In the figure, the cross-section segment is divided into f2l-O segment and O-f2r segment by obstacles. Since the O-f2r segment is longer, the corresponding navigation path point M2 is generated on the O-f2r segment, so that when the unmanned ship passes through the navigation path point M2, there is a wider water surface on the left and right sides of the unmanned ship, which improves the safety of the unmanned ship's passage.
[0084] The embodiment of the present application provides a method for generating an electronic fence area, which mainly involves the division of cross-sectional segments and the determination of navigation path points. When all cross-sectional segments are divided, the electronic fence area is naturally formed. The cross-sectional segments include a first cross-sectional segment and a second cross-sectional segment, wherein the first cross-sectional segment is generated based on the waterfront, the flow direction of the water flow, and the preset interval distance, which is equivalent to constructing an initial electronic fence area. The present application further considers the problem of obstacles in path planning. In the existing unmanned ship navigation technology, obstacles are generally handled by automatically avoiding obstacles through the detection radar of the unmanned ship body. However, if the obstacle is large, it will cause the unmanned ship to deviate significantly from the original planned path, and even fail to reach the target location. Therefore, the present application considers the avoidance of obstacles in advance in path planning, generates the corresponding second cross-sectional segments from each obstacle position, and sets the navigation path points away from the obstacles on the second cross-sectional segments to achieve early avoidance of fixed obstacles, thereby improving the environmental adaptability of path planning and the navigation safety of the unmanned ship.
[0085] In a possible implementation, in step S2, the plurality of routes from the current position to the navigation destination are searched and obtained based on the various navigation path points and a preset search algorithm, such as Figure 5 As shown, steps S201-S205 are included:
[0086] Step S201, taking the navigation path point closest to the current position as the search starting point;
[0087] Step S202, taking the navigation path point closest to the navigation end point as the search end point;
[0088] Step S203: determining an upstream neighboring point set and a downstream neighboring point set corresponding to each navigation path point according to the electronic fence area, wherein the upstream neighboring point set of any third navigation path point is a plurality of navigation path points located upstream of the third navigation path point and adjacent to the third navigation path point, and the downstream neighboring point set of the third navigation path point is a plurality of navigation path points located downstream of the third navigation path point and adjacent to the third navigation path point;
[0089] Step S204, starting from the search starting point, obtaining a plurality of search paths that can reach the search end point through a plurality of searches based on a preset search algorithm, wherein each search selects a navigation path point from an upstream neighbor point set or a downstream neighbor point set of the current search point as the next search point;
[0090] Step S205: Connect the search starting point of each search path with the current position, and connect the search end point of each search path with the navigation end point to obtain the plurality of routes.
[0091] The embodiment of the present application provides a route generation method. Since the path planning is based on each navigation path point, it is necessary to first determine the search starting point and the search end point. The subsequent path planning only needs to search multiple paths from the search starting point through several navigation path points to the search end point to obtain multiple corresponding routes. Then, in order to effectively use the river information for path planning, the upstream neighbor point set and the downstream neighbor point set corresponding to each navigation path point are determined in the path planning process, so that each subsequent search only needs to select a navigation path point from the upstream neighbor point set or the downstream neighbor point set of the current search point as the next search point, further narrowing the path search range and improving the efficiency of path planning.
[0092] Furthermore, in step S204, starting from the search starting point, a plurality of search paths that can reach the search end point are obtained through a plurality of searches based on a preset search algorithm, including:
[0093] In each search, the navigation path points in the upstream neighbor point set and the downstream neighbor point set of the current search point that do not appear in the current search path are used as the neighbor point set to be searched, and search path branches with the same number as the navigation path points in the neighbor point set to be searched are created, and the current search path is deleted, wherein each of the search path branches inherits the navigation path points in the current search path, and each of the search path branches selects different navigation path points from the neighbor point set to be searched to form multiple different search paths and each performs the next search;
[0094] When a first search path does not reach the search end point and cannot be further expanded, deleting the first search path;
[0095] When a second search path reaches the search end point, the second search path is saved.
[0096] In a preferred embodiment, Figure 2 The path search method proposed in this application is described by way of example: When the search starting point is M16 and the search end point is M1, it is necessary to search for all routes from M16 to M1 to generate an initial search path S, where S=(M16).
[0097] First, it is found that the downstream neighbor point set of M16 is empty, and the upstream neighbor point set is {M9, M15}, so the neighbor point set to be searched is {M9, M15}, so two search path branches S1 and S2 are created to start the search. Each of the search path branches inherits the navigation path points in the current search path, that is, both path branches inherit point M16. Among them, the search path branch S1 selects the path point M9, at this time S1 = (M16, M9); the search path branch S2 selects the path point M15, at this time S2 = (M16, M15). Delete the search path S, and S1 and S2 are different search paths and each performs the next search.
[0098] For the search path S1, the current search point is M9, and the downstream neighbor point set of M9 {M16} already exists in the search path S1, so M16 is not considered. The upstream neighbor point set of M9 {M8} is a navigation path point that does not appear in S1, so the corresponding neighbor point set to be searched is {M8}. A search path branch S11 is created and inherits the current search path S1, then S11 = (M16, M9), and the search path S1 is deleted. Then S11 selects the navigation path point M8 in the neighbor point set to be searched to continue the next search, and S11 = (M16, M9, M8). Finally, a path to M1 can be obtained (M16, M9, M8, M7, M6, M5, M4, M3, M2, M1).
[0099] For the search path S2, the current search point is M15, and the downstream point set of M15 is {M16}, and the upstream point set is {M14}. M16 already exists in the search path S2, so the corresponding neighboring point set to be searched is {M14}. A search path branch S21 is generated and inherits the current search path S2, then S12 = (M16, M15), and the search path S1 is deleted. Then S21 selects the navigation path point M14 in the neighboring point set to be searched to continue the next search, and S21 = (M16, M15, M14). When the route searches to M10, the path (M16, M15, M14, M13, M12, M11, M10) is obtained. The path can no longer be expanded, and M10 is not the end point of the search, so the path is deleted.
[0100] When the search is finished, only one path remains (M16, M9, M8, M7, M6, M5, M4, M3, M2, M1). M16 is connected to the current position of the unmanned ship, and M1 is connected to the navigation destination of the unmanned ship to obtain a complete route.
[0101] The embodiment of the present application provides a path search method, in which a corresponding search path branch is generated based on the number of neighboring point sets to be searched in each search, and each search path branch inherits the current search path. Each search path branch continues the next search until the search end point is found, ensuring that all non-repeated paths that can reach the end point from the starting point are found. Finally, based on the evaluation index, the optimal route is selected from each route path, thereby realizing the global planning of the unmanned ship path.
[0102] In a possible implementation, the unmanned ship global path planning method further includes:
[0103] When the water level of the river in the navigation area of the unmanned boat changes, the electronic fence area will automatically adjust the area range according to the change of the water level of the river;
[0104] During navigation, the unmanned boat continuously detects whether the unmanned boat exceeds the electronic fence area according to a preset time interval.
[0105] In a preferred embodiment, Figure 6As shown in the figure, when the water level of the river changes, the shoreline retreats from the solid line position to the dotted line position. At this time, you only need to indent the end point of the cross section inward by a specified distance to the new point Fnl-new / Fnr-new on the old electronic fence, and then regenerate the fence area and the position of point M with these new points. The upstream and downstream neighboring point sets of point M do not need to be changed. When the shoreline rises, you only need to extend the end point of the cross section outward by a specified distance to a new point, and then regenerate the fence area and the position of point M. When a section of the river is relatively uniform and the waterline on both sides of the upstream and downstream changes in the same distance when the water rises and falls, a pair of unified change distances on both sides (left change distance, right change distance) can be given to update the positions of each end point of the cross section segment. Furthermore, the current shoreline data of the river can be estimated based on the historical shoreline change data of the river, and then the positions of each end point of the cross section segment can be updated.
[0106] In the embodiment of the present application, the electronic fence area will automatically adjust the area range according to the change of the river water level, so that when facing environmental changes, the present application can handle the impact of water level changes on path planning without modifying the map data in large quantities, thereby improving the environmental adaptability of path planning. In addition, during the navigation of the unmanned boat, the unmanned boat is continuously detected according to the preset time interval to see whether it exceeds the electronic fence area, ensuring that the unmanned boat can correctly execute the planned route, thereby improving the navigation efficiency and navigation safety of the unmanned boat.
[0107] Embodiment 2:
[0108] like Figure 7 As shown, the second embodiment provides an unmanned ship global path planning system based on electronic fence, including an acquisition module 10, a search module 20 and an evaluation module 30;
[0109] The acquisition module 10 is used to acquire the current position, navigation destination and electronic fence area of the unmanned ship, wherein the electronic fence area is obtained by dividing the navigation area of the unmanned ship into several closed fence areas through the intersection of several cross-sectional segments perpendicular to the water flow direction and the shoreline, and each of the cross-sectional segments has a corresponding navigation path point;
[0110] The search module 20 is used to search for a plurality of routes from the current position to the navigation destination according to the navigation path points based on a preset search algorithm, wherein the routes are formed by connecting lines between the navigation path points, and each navigation path point appears at most once in each route;
[0111] The evaluation module 30 is used to evaluate the various routes according to preset evaluation indicators, and use the route with the highest score as the final planned navigation route of the unmanned ship.
[0112] In one possible implementation, Figure 8 As shown, the unmanned ship global path planning system also includes an electronic fence generation module 40, which is used to obtain the electronic fence area after dividing the navigation area of the unmanned ship into a plurality of closed fence areas through a plurality of cross-sectional segments perpendicular to the water flow direction and intersecting the water shoreline, and includes a water shoreline determination unit 401, an obstacle determination unit 402, a first cross-sectional segment generation unit 403, a second cross-sectional segment generation unit 404, a first navigation path point generation unit 405, and a second navigation path point generation unit 406;
[0113] The waterfront determination unit 401 is used to determine the current waterfront of the navigation area of the unmanned ship;
[0114] The obstacle determination unit 402 is used to determine the position of obstacles in the navigation area of the unmanned ship;
[0115] The first cross-sectional line segment generating unit 403 is used to generate a plurality of first cross-sectional line segments perpendicular to the water flow direction and intersecting with the shoreline according to a preset interval distance;
[0116] The second cross-sectional line segment generating unit 404 is used to generate corresponding second cross-sectional line segments perpendicular to the water flow direction from the positions of the obstacles to intersect with the shoreline;
[0117] The first navigation path point generating unit 405 is used to generate the first navigation path points on each of the first transverse line segments according to a first preset value, wherein the first preset value is a ratio of the distances from each of the first navigation path points to the shorelines on both sides;
[0118] The second navigation path point generating unit 406 is used to generate the second navigation path points on each second cross-sectional line segment according to a second preset value, wherein the second preset value is the minimum distance from each second navigation path point to the corresponding obstacle.
[0119] In one possible implementation, Fig. 9 As shown, the search module 20 includes a search starting point determination unit 201, a search end point determination unit 202, a neighbor point set determination unit 203, a search unit 204 and a route generation unit 205;
[0120] The search starting point determination unit 201 is used to take the navigation path point closest to the current position as the search starting point;
[0121] The search end point determination unit 202 is used to take the navigation path point closest to the navigation end point as the search end point;
[0122] The neighbor point set determination unit 203 is used to determine the upstream neighbor point set and the downstream neighbor point set corresponding to each navigation path point according to the electronic fence area, wherein the upstream neighbor point set of any third navigation path point is a plurality of navigation path points located upstream of the third navigation path point and adjacent to the third navigation path point, and the downstream neighbor point set of the third navigation path point is a plurality of navigation path points located downstream of the third navigation path point and adjacent to the third navigation path point;
[0123] The search unit 204 is used to obtain a plurality of search paths that can reach the search end point through a plurality of searches starting from the search starting point based on a preset search algorithm, wherein each search selects a navigation path point from an upstream neighbor point set or a downstream neighbor point set of a current search point as a next search point;
[0124] The route generating unit 205 is used to connect the search starting point of each search path with the current position, and connect the search end point of each search path with the navigation end point, so as to obtain the plurality of routes.
[0125] Further, the search unit 204 starts from the search starting point and obtains several search paths that can reach the search end point through several searches based on a preset search algorithm, including:
[0126] In each search, the navigation path points in the upstream neighbor point set and the downstream neighbor point set of the current search point that do not appear in the current search path are used as the neighbor point set to be searched, and search path branches with the same number as the navigation path points in the neighbor point set to be searched are created, and the current search path is deleted, wherein each of the search path branches inherits the navigation path points in the current search path, and each of the search path branches selects different navigation path points from the neighbor point set to be searched to form multiple different search paths and each performs the next search;
[0127] When a first search path does not reach the search end point and cannot be further expanded, deleting the first search path;
[0128] When a second search path reaches the search end point, the second search path is saved.
[0129] In a possible implementation, the unmanned ship global path planning system further includes an electronic fence adjustment module and a navigation detection module;
[0130] Wherein, the electronic fence adjustment module is used for automatically adjusting the area range of the electronic fence area according to the change of the river water level when the river water level of the navigation area of the unmanned ship changes;
[0131] The navigation detection module is used for continuously detecting whether the unmanned ship exceeds the electronic fence area according to a preset time interval during the navigation of the unmanned ship.
[0132] The more detailed working principle and step flow of this embodiment can refer to, but are not limited to, the relevant records of Embodiment 1.
[0133] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the scope of protection of the present application. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims
1. A global path planning method for an unmanned ship based on an electronic fence, characterized in that: include: Obtain the current position, navigation destination and electronic fence area of the unmanned ship, wherein the electronic fence area is obtained by dividing the navigation area of the unmanned ship into several closed fence areas through the intersection of several cross-sectional segments perpendicular to the water flow direction and the shoreline, and each of the cross-sectional segments has a corresponding navigation path point; According to the navigation path points, based on a preset search algorithm, a plurality of routes from the current position to the navigation destination are searched and obtained, wherein the routes are formed by connecting lines between the navigation path points, and each navigation path point appears at most once in each route; The various routes are evaluated according to preset evaluation indicators, and the route with the highest score is used as the final planned navigation route of the unmanned ship.
2. A global path planning method for an unmanned ship based on an electronic fence as claimed in claim 1, characterized in that: The electronic fence area is obtained by dividing the navigation area of the unmanned ship into a plurality of closed fence areas by intersecting the water shoreline with a plurality of cross-sectional line segments perpendicular to the water flow direction, including: Determining the current shoreline of the navigation area of the unmanned vessel; Determining the location of obstacles in the navigation area of the unmanned ship; Generating a plurality of first cross-sectional line segments perpendicular to the water flow direction and intersecting with the water shoreline according to a preset interval distance; Generating corresponding second cross-sectional line segments perpendicular to the flow direction of the water flow from the positions of the respective obstacles to intersect with the shoreline; Generating first navigation path points on each of the first cross-sectional line segments according to a first preset value, wherein the first preset value is a ratio of the distances from each of the first navigation path points to the shorelines on both sides; The second navigation path points on each of the second cross-sectional line segments are generated according to a second preset value, wherein the second preset value is the minimum distance from each of the second navigation path points to the corresponding obstacle.
3. The global path planning method for an unmanned ship based on an electronic fence as claimed in claim 1, characterized in that: The searching and obtaining, based on the various navigation path points and based on a preset search algorithm, a plurality of routes from the current position to the navigation destination includes: Taking the navigation path point closest to the current position as the search starting point; Taking the navigation path point closest to the navigation end point as the search end point; Determine the upstream neighboring point set and the downstream neighboring point set corresponding to each navigation path point according to the electronic fence area, wherein the upstream neighboring point set of any third navigation path point is a number of navigation path points located upstream of the third navigation path point and adjacent to the third navigation path point, and the downstream neighboring point set of the third navigation path point is a number of navigation path points located downstream of the third navigation path point and adjacent to the third navigation path point; Starting from the search starting point, a plurality of search paths that can reach the search end point are obtained through a plurality of searches based on a preset search algorithm, wherein each search selects a navigation path point from an upstream neighbor point set or a downstream neighbor point set of the current search point as the next search point; The search starting point of each search path is connected to the current position, and the search end point of each search path is connected to the navigation end point to obtain the plurality of routes.
4. A global path planning method for an unmanned ship based on an electronic fence as claimed in claim 3, characterized in that: Starting from the search starting point, a plurality of search paths that can reach the search end point are obtained through a plurality of searches based on a preset search algorithm, including: In each search, the navigation path points in the upstream neighbor point set and the downstream neighbor point set of the current search point that do not appear in the current search path are used as the neighbor point set to be searched, and search path branches with the same number as the navigation path points in the neighbor point set to be searched are created, and the current search path is deleted, wherein each of the search path branches inherits the navigation path points in the current search path, and each of the search path branches selects different navigation path points from the neighbor point set to be searched to form multiple different search paths and each performs the next search; When a first search path does not reach the search end point and cannot be further expanded, deleting the first search path; When a second search path reaches the search end point, the second search path is saved.
5. The global path planning method for an unmanned ship based on an electronic fence as claimed in claim 1, characterized in that: The unmanned ship global path planning method also includes: When the water level of the river in the navigation area of the unmanned boat changes, the electronic fence area will automatically adjust the area range according to the change of the water level of the river; During navigation, the unmanned boat continuously detects whether the unmanned boat exceeds the electronic fence area according to a preset time interval.
6. A global path planning system for unmanned ships based on electronic fences, characterized in that: It includes acquisition module, search module and evaluation module; The acquisition module is used to acquire the current position, navigation destination and electronic fence area of the unmanned ship, wherein the electronic fence area is obtained by dividing the navigation area of the unmanned ship into several closed fence areas through the intersection of several cross-sectional segments perpendicular to the water flow direction and the shoreline, and each of the cross-sectional segments has a corresponding navigation path point; The search module is used to search and obtain a plurality of routes from the current position to the navigation destination according to the navigation path points based on a preset search algorithm, wherein the routes are formed by connecting lines between the navigation path points, and each navigation path point appears at most once in each route; The evaluation module is used to evaluate the various routes according to preset evaluation indicators, and use the route with the highest score as the final planned navigation route of the unmanned ship.
7. The global path planning system for an unmanned ship based on an electronic fence as claimed in claim 6, characterized in that: The unmanned ship global path planning system also includes an electronic fence generation module, which is used to obtain the electronic fence area after dividing the navigation area of the unmanned ship into a plurality of closed fence areas through a plurality of cross-sectional segments perpendicular to the water flow direction intersecting with the shoreline, and includes a shoreline determination unit, an obstacle determination unit, a first cross-sectional segment generation unit, a second cross-sectional segment generation unit, a first navigation path point generation unit, and a second navigation path point generation unit; Wherein, the water shoreline determination unit is used to determine the current water shoreline of the navigation area of the unmanned ship; The obstacle determination unit is used to determine the position of obstacles in the navigation area of the unmanned ship; The first cross-sectional line segment generating unit is used to generate a plurality of first cross-sectional line segments perpendicular to the water flow direction and intersecting with the water shoreline according to a preset interval distance; The second cross-sectional line segment generating unit is used to generate corresponding second cross-sectional line segments perpendicular to the water flow direction from the positions of the obstacles to intersect with the shoreline; The first navigation path point generating unit is used to generate the first navigation path points on each of the first cross-sectional line segments according to a first preset value, wherein the first preset value is a ratio of the distances from each of the first navigation path points to the waterfronts on both sides; The second navigation path point generating unit is used to generate the second navigation path points on each second cross-sectional line segment according to a second preset value, wherein the second preset value is the minimum distance from each second navigation path point to the corresponding obstacle.
8. The global path planning system for an unmanned ship based on an electronic fence as claimed in claim 6, characterized in that: The search module includes a search starting point determination unit, a search end point determination unit, a neighbor point set determination unit, a search unit, and a route generation unit; Wherein, the search starting point determination unit is used to take the navigation path point closest to the current position as the search starting point; The search end point determination unit is used to take the navigation path point closest to the navigation end point as the search end point; Determine the upstream neighboring point set and the downstream neighboring point set corresponding to each navigation path point according to the electronic fence area, wherein the upstream neighboring point set of any third navigation path point is a number of navigation path points located upstream of the third navigation path point and adjacent to the third navigation path point, and the downstream neighboring point set of the third navigation path point is a number of navigation path points located downstream of the third navigation path point and adjacent to the third navigation path point; The search unit is used to obtain a plurality of search paths that can reach the search end point through a plurality of searches starting from the search starting point based on a preset search algorithm, wherein each search selects a navigation path point from an upstream neighbor point set or a downstream neighbor point set of a current search point as a next search point; The route generating unit is used to connect the search starting point of each search path with the current position, and connect the search end point of each search path with the navigation end point, so as to obtain the plurality of routes.
9. The global path planning system for an unmanned ship based on an electronic fence as claimed in claim 8, characterized in that: The search unit starts from the search starting point and obtains a plurality of search paths that can reach the search end point through a plurality of searches based on a preset search algorithm, including: In each search, the navigation path points in the upstream neighbor point set and the downstream neighbor point set of the current search point that do not appear in the current search path are used as the neighbor point set to be searched, and search path branches with the same number as the navigation path points in the neighbor point set to be searched are created, and the current search path is deleted, wherein each of the search path branches inherits the navigation path points in the current search path, and each of the search path branches selects different navigation path points from the neighbor point set to be searched to form multiple different search paths and each performs the next search; When a first search path does not reach the search end point and cannot be further expanded, deleting the first search path; When a second search path reaches the search end point, the second search path is saved.
10. The global path planning system for an unmanned ship based on an electronic fence as claimed in claim 6, characterized in that: The unmanned ship global path planning system also includes an electronic fence adjustment module and a navigation detection module; Wherein, the electronic fence adjustment module is used for automatically adjusting the area range of the electronic fence area according to the change of the river water level when the river water level of the navigation area of the unmanned ship changes; The navigation detection module is used for continuously detecting whether the unmanned ship exceeds the electronic fence area according to a preset time interval during the navigation of the unmanned ship.
Citation Information
Cited By
Air route drawing method and device based on flow field data
CN119379852A
