Path determination method and system for field multi-terrain scene

Abstract

The invention provides a path determination method and system for a field multi-terrain scene, and relates to the technical field of path planning. According to the method provided by the invention, a plurality of connection point grids are determined, a path with a minimum cost value between a target connection point grid and a target point is determined as a first path, and a path with a minimum cost value between a starting point and the target connection point grid is determined as a second path; and then combining the first path and the second path to obtain a target path from the starting point to the target point. Therefore, the second path can comprise a plurality of grids of which the categories are road terrains, and compared with an action path determined by an A-star algorithm in the related technology, the path determined by the embodiment of the invention can effectively reduce the passing time from the starting point to the target point through the grids of the plurality of road terrains, and the passing efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of path planning technology, and in particular to a path determination method and system for outdoor multi-terrain scenarios. Background Art

[0002] When performing field exploration or rescue operations, it is usually necessary to perform path planning based on complex multi-terrain field environments to determine the vehicle movement path of technicians so that relevant personnel can quickly reach the target point and improve traffic efficiency.

[0003] Related technologies typically use intelligent search methods based on optimal algorithms for path planning, such as ant colony algorithms, particle swarm algorithms, genetic algorithms, probabilistic roadmaps, and rapid exploration random tree algorithms. Alternatively, path planning methods based on geometric models, such as the Dijkstra algorithm, A* algorithm, D* algorithm, and Field D* algorithm, exist. However, both approaches present challenges. In complex, multi-terrain outdoor environments, related technologies typically use existing road networks or roadless terrain for path planning. The resulting paths require significant time for personnel to travel to the destination, resulting in low path efficiency.

[0004] Therefore, there is an urgent need for a path determination method and system for outdoor multi-terrain scenarios that can determine vehicle movement paths with less time travel and improve traffic efficiency. Summary of the Invention

[0005] The embodiments of the present invention provide a path determination method and system for outdoor multi-terrain scenarios. Compared with the action path determined by the A-star algorithm in the related art, the path determined by the embodiments of the present invention can effectively reduce the travel time from the starting point to the target point, thereby improving travel efficiency.

[0006] To achieve the above objectives, the embodiments of the present invention adopt the following technical solutions:

[0007] In a first aspect, a path determination method for outdoor multi-terrain scenarios is provided, the method comprising: receiving a path planning request, the path planning request being used to request planning of a target path from a starting point to a target point in a target area, the path planning request carrying image data of the target area, the image data comprising high-resolution images, hyperspectral images, and digital elevation model images; determining a grid map of the target area based on the image data of the target area, the grid map comprising a plurality of square grids of the same size, and coordinates, categories, and slope grades corresponding to each grid, the categories comprising obstacle terrain, road terrain, or non-road non-obstacle terrain; establishing a heuristic function and a cost function, wherein the heuristic function is used to characterize the path distance and yaw angle from each first grid to each second grid, and the cost function is used to characterize the path distance and yaw angle from each first grid to each second grid. The cost value of the second grid; the first grid is one of the multiple grids, and the second grid is a grid adjacent to the first grid; a connection point grid among the multiple grids is determined according to the category of each grid, wherein a grid of the road terrain category exists among the multiple grids adjacent to the connection point grid; based on the A-star algorithm, a target path is determined according to a heuristic function and a cost function, the target path includes a first path and a second path, the first path is the path with the smallest cost value among the multiple paths between the multiple connection point grids and the target point, the second path is the path with the smallest cost value among the multiple paths between the starting point and the target connection point grid, the cost value of each path is the sum of the heuristic function value and the cost function value obtained by traversing the multiple grids arranged in order included in each path, and the target connection point grid is the connection point grid corresponding to the starting point of the first path.

[0008] In a possible implementation of the first aspect, the heuristic function includes a first heuristic function and a second heuristic function. When the second grid is adjacent to the first grid in the horizontal or vertical direction, the expression of the first heuristic function is:

[0009] h(n)=d*h d (n)+d*[h s (n)-2h s (n)];

[0010] When the second grid is a grid adjacent to the first grid in the diagonal direction, the expression of the first heuristic function is:

[0011]

[0012] h d (n) = min(|x n -x g |,|y n -y g |);

[0013] hs (n)=(|x n -x g |+|y n -y g |);

[0014] Among them, n is the identifier of the second grid, and the coordinates of the second grid are (x n ,y n ); the coordinates of the target grid g where the target point is located are (x g ,y g ), d is the length of each grid, h d (n) is the number of diagonal movable steps, h s (n) is the number of linear movable steps.

[0015] In a possible implementation of the first aspect, the second heuristic function is expressed as:

[0016]

[0017] Where θ is the yaw angle, is the vector from the first grid to the target grid, is the vector from the first grid to the second grid.

[0018] In a possible implementation of the first aspect, when the category of the second grid is obstacle terrain, the cost function is expressed as:

[0019]

[0020] pass(n-1,n)=α(n))*β(n);

[0021] n-1 is the identifier of the first grid, α(n) is the slope weight coefficient of the second grid, which is determined according to the slope grade of each grid; β(n) is the surface attribute weight coefficient of the second grid, which is determined according to the category of each grid; D is the horizontal distance from the first grid to the second grid, and Δh is the vertical distance from the first grid to the second grid;

[0022] When the second grid is classified as road terrain or non-road obstacle-free terrain, the cost function is expressed as:

[0023] g(n)=k road *[g(n-1)+cost(n,n-1)];

[0024] cost(n,n-1)=d(n,n-1)(1+αS slope +βk road );

[0025] Among them, k road is the traffic coefficient of different types of grids, S slope is the cost coefficient corresponding to different slope levels, and α and β are adjustment coefficients.

[0026] In a possible implementation of the first aspect, based on the A-star algorithm, a target path is determined according to a heuristic function and a cost function, including: based on the A-star algorithm, determining the path with the smallest cost value among multiple paths between multiple connection point grids and the target point as a first path; determining the connection point grid corresponding to the starting point of the first path as the target connection point grid; based on the A-star algorithm, determining the path with the smallest cost value between the starting point and the target connection point grid as a second path; and merging the first path and the second path to obtain the target path.

[0027] In a possible implementation of the first aspect, based on the A-star algorithm, the path with the smallest cost value among multiple paths between multiple connection point grids and a target point is determined as the first path, including: taking each connection point grid as the starting point, determining the center point of the grid with the smallest cost value and a yaw angle less than a preset angle among multiple grids adjacent to each connection point grid as the path point, wherein the yaw angle is determined based on a second heuristic function; based on each path point, determining the center point of the grid with the smallest cost value among multiple grids adjacent to the grid corresponding to the path point as the next path point corresponding to each path point; determining multiple path points in sequence, and when the path point is located in the grid where the target point is located, obtaining the path corresponding to each connection point grid, the path being a line connecting multiple path points arranged in order with each connection point grid as the starting point; and determining the path with the smallest cost value among the paths corresponding to each connection point grid as the first path.

[0028] In a possible implementation of the first aspect, based on the A-star algorithm, a path with the smallest cost value among multiple paths between multiple connection point grids and a target point is determined as a first path, including: merging multiple grids of the same category arranged in a preset shape in a grid map to obtain a grid group corresponding to the multiple grids, where the preset shape is a square; taking each connection point grid as a starting point, determining the center point of the grid or grid group with the smallest cost value and a yaw angle less than a preset angle among multiple grids or grid groups adjacent to each connection point grid as a path point, wherein the yaw angle is based on a second heuristic function. The cost value of the grid group is the maximum value among the cost values ​​of the multiple grids included in the grid group; based on each path point, the grid or the center point of the grid group with the smallest cost value among the multiple grids or grid groups adjacent to the grid corresponding to the path point is determined as the next path point corresponding to each path point; multiple path points are determined in sequence, and when the path point is located in the grid where the target point is located, the path corresponding to each connection point grid is obtained, and the path is a line connecting multiple path points arranged in sequence with each connection point grid as the starting point; the path with the smallest cost value among the paths corresponding to each connection point grid is determined as the first path.

[0029] The beneficial effects of the present invention are as follows: the method provided by the present invention determines multiple connection point grids, determines the path with the minimum cost between the target connection point grid and the target point as a first path, and determines the path with the minimum cost between the starting point and the target connection point grid as a second path, and then merges the first path and the second path to obtain a target path from the starting point to the target point. In this way, the second path can include multiple grids classified as road terrain. Compared to the action path determined by the A-star algorithm in the related art, the path determined by the embodiment of the present invention, by passing through multiple road terrain grids, can effectively reduce the travel time from the starting point to the target point and improve travel efficiency.

[0030] In a second aspect, an embodiment of the present invention provides a path determination system for outdoor multi-terrain scenarios, the system comprising: a request receiving unit for receiving a path planning request, the path planning request being used to request planning of a target path from a starting point to a target point in a target area, the path planning request carrying image data of the target area, the image data comprising high-resolution images, hyperspectral images and digital elevation model images; an image processing unit for determining a grid map of the target area based on the image data of the target area, the grid map comprising a plurality of square grids of the same size, and coordinates, categories and slope grades corresponding to each grid, the categories comprising obstacle terrain, road terrain or non-road non-obstacle terrain; a function construction unit for establishing a heuristic function and a cost function, wherein the heuristic function is used to characterize the path distance and yaw angle from each first grid to each second grid, and the cost function is used to characterize the path distance and yaw angle from each first grid to each second grid, The cost value from the first grid to each second grid; the first grid is one of the multiple grids, and the second grid is a grid adjacent to the first grid; a grid determination unit is used to determine a connection point grid among the multiple grids according to the category of each grid, wherein there is a grid of the road terrain category among the multiple grids adjacent to the connection point grid; a path determination unit is used to determine a target path based on the A-star algorithm according to a heuristic function and a cost function, the target path including a first path and a second path, the first path being the path with the smallest cost value among the multiple paths between the multiple connection point grids and the target point, the second path being the path with the smallest cost value among the multiple paths between the starting point and the target connection point grid, the cost value of each path being the sum of the heuristic function value and the cost function value obtained by traversing the multiple grids arranged in order included in each path, and the target connection point grid being the connection point grid corresponding to the starting point of the first path.

[0031] In a third aspect, an electronic device is provided, comprising a memory and one or more processors; the memory is coupled to the processor; wherein computer program code is stored in the memory, and the computer program code comprises computer instructions, and when the computer instructions are executed by the processor, the electronic device executes a path determination method for outdoor multi-terrain scenarios as in any implementation of the first aspect.

[0032] In a fourth aspect, a computer-readable storage medium is provided, comprising computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes a path determination method for outdoor multi-terrain scenarios as described in any implementation of the first aspect.

[0033] In a fifth aspect, a computer program product is provided. When the computer program product is run on a computer, the computer is caused to execute the path determination method for outdoor multi-terrain scenarios in any implementation of the first aspect.

[0034] It can be understood that the beneficial effects that can be achieved by the path determination system for outdoor multi-terrain scenarios of the second aspect provided above, the electronic device of the third aspect, the computer-readable storage medium of the fourth aspect, and the computer program product of the fifth aspect can be referred to the beneficial effects of the first aspect and any possible design method thereof, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention is shown;

[0036] Figure 2 A flow chart of a path determination method for outdoor multi-terrain scenarios provided by an embodiment of the present invention;

[0037] Figure 3 A schematic diagram of a grid map provided by an embodiment of the present invention;

[0038] Figure 4 This is a flow chart of another method for determining a path in a field multi-terrain scenario according to an embodiment of the present invention;

[0039] Figure 5 A schematic diagram of another grid map according to an embodiment of the present invention;

[0040] Figure 6 A schematic diagram of the hardware structure of a determination system provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present invention will be described below in conjunction with the accompanying drawings in the embodiments of the present invention. In the description of the present invention, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship. For example, A / B can represent A or B. The "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, in the description of the present invention, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0042] In addition, to facilitate a clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that the words "first" and "second" do not limit the quantity or execution order, and the words "first" and "second" do not necessarily mean different.

[0043] In the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner to facilitate understanding.

[0044] When performing field exploration or rescue operations, it is usually necessary to perform path planning based on complex multi-terrain field environments to determine the vehicle movement path of technicians so that relevant personnel can quickly reach the target point and improve traffic efficiency.

[0045] Related technologies typically use intelligent search methods based on optimal algorithms for path planning, such as ant colony algorithms, particle swarm algorithms, genetic algorithms, probabilistic roadmaps, and rapid exploration random tree algorithms. Alternatively, path planning methods based on geometric models, such as the Dijkstra algorithm, A* algorithm, D* algorithm, and Field D* algorithm, exist. However, both approaches present challenges. In complex, multi-terrain outdoor environments, related technologies typically use existing road networks or roadless terrain for path planning. The resulting paths require significant time for personnel to travel to the destination, resulting in low path efficiency.

[0046] Therefore, there is an urgent need for a path determination method and system for outdoor multi-terrain scenarios that can determine vehicle movement paths with less time travel and improve traffic efficiency.

[0047] In view of this, an embodiment of the present invention provides a path determination method for outdoor multi-terrain scenarios, the method comprising: receiving a path planning request, the path planning request being used to request planning of a target path from a starting point to a target point in a target area, the path planning request carrying image data of the target area, the image data comprising high-resolution images, hyperspectral images and digital elevation model images; determining a grid map of the target area based on the image data of the target area, the grid map comprising a plurality of square grids of the same size, and coordinates, categories and slope grades corresponding to each grid, the categories comprising obstacle terrain, road terrain or non-road non-obstructive terrain; establishing a heuristic function and a cost function, wherein the heuristic function is used to characterize the path distance and yaw angle from each first grid to each second grid, and the cost function is used to characterize the path distance and yaw angle from each first grid to each second grid. The cost value of each second grid; the first grid is one of the multiple grids, and the second grid is a grid adjacent to the first grid; the connection point grid among the multiple grids is determined according to the category of each grid, wherein there is a grid of the road terrain category among the multiple grids adjacent to the connection point grid; based on the A-star algorithm, the target path is determined according to the heuristic function and the cost function, the target path includes a first path and a second path, the first path is the path with the smallest cost value among the multiple paths between the multiple connection point grids and the target point, the second path is the path with the smallest cost value among the multiple paths between the starting point and the target connection point grid, the cost value of each path is the sum of the heuristic function value and the cost function value obtained by traversing the multiple grids arranged in order included in each path, and the target connection point grid is the connection point grid corresponding to the starting point of the first path.

[0048] The method provided by an embodiment of the present invention determines multiple connection point grids, identifies the path with the lowest cost between the target connection point grid and the target point as a first path, and identifies the path with the lowest cost between the starting point and the target connection point grid as a second path. The first and second paths are then merged to obtain a target path from the starting point to the target point. This second path can include multiple grids classified as road terrain. Compared to the action path determined by the A-star algorithm in related technologies, the path determined by the embodiment of the present invention, by traversing multiple road terrain grids, can effectively reduce travel time from the starting point to the target point, thereby improving travel efficiency.

[0049] In some embodiments, the path determination method for outdoor multi-terrain scenarios provided by embodiments of the present invention can be executed by a path determination system 100 for outdoor multi-terrain scenarios (hereinafter referred to as determination system 100). By way of example, determination system 100 can be any electronic device 200 with data processing capabilities, such as a general-purpose computer, personal computer, laptop computer, switch, or tablet computer. The specific implementation of determination system 100 is not limited herein.

[0050] Figure 1 The electronic device 200 includes a processor 210 , a memory 220 , and a communication interface 230 .

[0051] The processor 210 may include one or more processing cores. The processor 210 uses various interfaces and lines to connect various parts of the electronic device 200, and executes various functions and processes data of the electronic device 200 by running or executing instructions, programs, code sets or instruction sets stored in the memory 220, and calling data stored in the memory 220. Optionally, the processor 210 can be implemented in the form of at least one hardware of a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA).

[0052] The memory 220 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 220 includes a non-transitory computer-readable storage medium. The memory 220 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 220 may include a program storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a request receiving function, a path confirmation function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.

[0053] The communication interface 230 is used to communicate with other devices, equipment or communication networks, such as data storage devices, image processing equipment or Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0054] In physical implementation, the aforementioned components (e.g., processor 210, memory 220, and communication interface 230) may be components within the same device (e.g., a laptop). Alternatively, at least two of the components may be provided within the same device, i.e., as different components within a single device, similar to the deployment of devices or components in a distributed system.

[0055] It should be understood that the structure illustrated in this embodiment does not constitute a specific limitation on the electronic device 200. In other embodiments of the present invention, the electronic device 200 may include more or fewer components than shown, or may combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0056] The following describes a path determination method for outdoor multi-terrain scenarios provided by an embodiment of the present invention in conjunction with the accompanying drawings.

[0057] Figure 2 A flow chart of a method for determining a path in a field multi-terrain scenario provided by an embodiment of the present invention. Optionally, the method may be executed by the determination system 100. The method may include the following steps:

[0058] S1. Receive a path planning request, where the path planning request is used to request planning of a target path from a starting point to a target point in a target area.

[0059] Specifically, the path planning request carries image data of the target area, and the image data includes high-resolution images, hyperspectral images, and digital elevation model images.

[0060] Among them, high-resolution images are high-resolution satellite images, which refer to images of the earth's surface taken by high-resolution cameras carried on satellites.

[0061] Hyperspectral imaging is an imaging technology that combines the advantages of imaging technology and spectral technology and can obtain continuous, narrow-band image data of actual scenes.

[0062] A Digital Elevation Model (DEM) is a geographic information model that mathematically represents the elevation of each point on the Earth's surface. Rather than presenting it directly as an image, it constructs a three-dimensional representation of the Earth's surface using a series of digital data. This data is typically stored as a raster or point cloud, and includes the elevation value of each point or grid cell.

[0063] S2. Determine a grid map of the target area based on the image data of the target area. The grid map includes a plurality of square grids of the same size, and coordinates, categories, and slope levels corresponding to each grid.

[0064] Specifically, the categories include obstacle terrain, road terrain, or non-road non-obstacle terrain. Obstacle terrain includes impassable terrain such as rivers, forests, or lakes. Road terrain refers to terrain where vehicles can quickly pass through roads. Non-road non-obstacle terrain refers to terrain where vehicles can slowly pass through without roads, such as sand or grass.

[0065] For example, see Figure 3 , Figure 3 This is a schematic diagram of a grid map provided by an embodiment of the present invention. The image data of the target area is divided into nine grids, grids 1-9. Grids 1, 2, and 3 are classified as obstacle terrain (rivers); grids 4, 5, and 6 are classified as road terrain (mountain roads); and grids 7, 8, and 9 are classified as non-road, non-obstructive terrain (grassland). Grid 1 has coordinates (1, 1) in the grid map, and grid 9 has coordinates (3, 3) in the grid map.

[0066] The slope grade determines the slope of the area corresponding to the grid based on the elevation data in the area corresponding to the grid, and different slopes correspond to different slope grades. Different slope grades correspond to different slope weight coefficients.

[0067] For example, when the slope is between 0° and 5°, the slope level is 0. When the slope is between 5° and 10°, the slope level is 1. When the slope is between 10° and 15°, the slope level is 2. When the slope is between 15° and 20°, the slope level is 3. When the slope is between 20° and 25°, the slope level is 4. When the slope is between 25° and 30°, the slope level is 5. When the slope is greater than 31°, the slope level is 6. The slope weight coefficient corresponding to the slope level 0 is 1. The slope weight coefficient corresponding to the slope level 1 is 0.8. The slope weight coefficient corresponding to the slope level 2 is 0.6. The slope weight coefficient corresponding to the slope level 3 is 0.4. The slope weight coefficient corresponding to the slope level 4 is 0.2. The slope weight coefficient corresponding to the slope level 5 is 0.1. The slope weight coefficient corresponding to the slope level 6 is 0.

[0068] S3. Establish a heuristic function and a cost function, wherein the heuristic function is used to characterize the path distance and yaw angle from each first grid to each second grid, and the cost function is used to characterize the cost value from each first grid to each second grid.

[0069] Specifically, the first grid is one of the multiple grids, and the second grid is the grid adjacent to the first grid. Alternatively, when the path is from grid 1 to grid 2, the heuristic function is used to represent the path distance and yaw angle from grid 1 to grid 2, and the cost function is used to represent the cost of moving from grid 1 to grid 2.

[0070] It should be understood that adjacent grids refer to the four grids that share a common edge with the first grid, as well as the four grids that share a common vertex with the first grid. In other words, these are the eight grids in eight directions around the first grid. The angle between the line connecting the center point of the first grid and the target point and the line connecting the center point of the first grid and the center point of the second grid is the yaw angle.

[0071] In a possible implementation, the heuristic function includes a first heuristic function and a second heuristic function.

[0072] The first heuristic function is used to characterize the path distance from each first grid to each second grid, and the second heuristic function is used to characterize the yaw angle from each first grid to each second grid.

[0073] Furthermore, when the second grid is adjacent to the first grid in the horizontal or vertical direction, the expression of the first heuristic function is:

[0074] h(n)=d*h d (n)+d*[h s (n)-2h s (n)];

[0075] When the second grid is a grid adjacent to the first grid in the diagonal direction, the expression of the first heuristic function is:

[0076]

[0077] h d (n)=min((|x n -x g |,|y n -y g |);

[0078] h s (n)=(|x n -x g |+|y n -y g |);

[0079] Among them, n is the identifier of the second grid, and the coordinates of the second grid are (x n ,y n ); the coordinates of the target grid g where the target point is located are (x g ,y g ), d is the length of each grid, h d (n) is the number of diagonal movable steps, h s (n) is the number of linear movable steps.

[0080] In another possible implementation, the expression of the second heuristic function is:

[0081]

[0082] Where θ is the yaw angle, is the vector from the first grid to the grid where the target point is located, is the vector from the first grid to the second grid.

[0083] In another possible implementation, when the category of the second grid is obstacle terrain, the cost function is expressed as:

[0084]

[0085] pass(n-1,n)=α(n)*β(n);

[0086] n-1 is the identifier of the first grid, α(n) is the slope weight coefficient of the second grid, and the slope weight coefficient is determined according to the slope grade of each grid; β(n) is the surface attribute weight coefficient of the second grid, and the surface attribute weight coefficient is determined according to the category of each grid; D is the horizontal distance from the first grid to the second grid, and Δh is the vertical distance from the first grid to the second grid.

[0087] The closer the slope weight coefficient α(n) and surface attribute weight coefficient β(n) of the second grid are to 1, the better the accessibility of the second grid is. The lower the slope weight coefficient α(n) and surface attribute weight coefficient β(n) of the second grid are, the higher the access risk of the second grid is.

[0088] Construction of weight matrix: In a three-dimensional grid map, each grid is assigned a weight value between 0 and 1. The weight matrix is ​​constructed by each slope weight coefficient α(n) and surface attribute weight coefficient β(n).

[0089] In one example, the surface attribute weight coefficient of a raster with a road terrain category is 1. The surface attribute weight coefficient of a raster with an obstacle terrain category is 0. The surface attribute weight coefficient of a raster with a non-road obstacle terrain category is 0.5.

[0090] In a possible implementation, the determination system 100 performs a finer-grained classification of roadless, obstacle-free terrain, including saline-alkali terrain, grassland terrain, gravel terrain, and sandy terrain. The surface attribute weight coefficient for saline-alkali terrain is 0.8, the surface attribute weight coefficient for grassland terrain is 0.7, the surface attribute weight coefficient for gravel terrain is 0.4, and the surface attribute weight coefficient for sandy terrain is 0.2.

[0091] When the second grid is classified as road terrain or non-road obstacle-free terrain, the cost function is expressed as:

[0092] g(n)=k road *[g(n-1)+cost(n,n-1)];

[0093] cost(n,n-1)=d(n,n-1)(1+αS slope +βk road );

[0094] Among them, k road is the traffic coefficient of different types of grids, S slope is the cost coefficient corresponding to different slope levels, and α and β are adjustment coefficients.

[0095] S4. Determine a connection point grid among the plurality of grids according to the category of each grid, wherein a grid of the category of road terrain exists among the plurality of grids adjacent to the connection point grid.

[0096] For example, combined Figure 3 ,Since the category of grid 4, grid 5 and grid 6 is road terrain (mountain road), grid 1, grid 2, grid 3, grid 7, grid 8 and grid 9 are adjacent to the road grid, so grid 1, grid 2, grid 3, grid 7, grid 8 and grid 9 are connection point grids.

[0097] In one possible implementation, the process of determining the connection point grid by the determination system 100 may be implemented by the following algorithm.

[0098] Specifically, the determination system 100 initializes an empty list "connection_points" for storing all connection point grids; traverses each row and column of the grid in the road map; if the category of the current grid (x, y) is road terrain, then further check all adjacent grids of this grid (8 grids in 8 directions); for each direction (d x ,d y ), calculate the new grid coordinates (n x ,n y ); check the grid coordinates (n x ,n y) is a road terrain. If not, the grid is a connection point grid. Then the connection point grid is added to the "connection_points" table, and the checking of other directions around the current grid (x, y) is stopped. When all grids included in the grid map are checked, the "connection_points" list is returned, which contains the coordinates of all connection point grids, and the system 100 determines the connection point grid among the multiple grids.

[0099] S5. Based on the A-star algorithm, the target path is determined according to the heuristic function and the cost function. The target path includes a first path and a second path. The first path is the path with the smallest cost value among multiple paths between multiple connection point grids and the target point. The second path is the path with the smallest cost value among multiple paths between the starting point and the target connection point grid.

[0100] Specifically, the cost value of each path is the sum of the heuristic function value and the cost function value obtained by traversing multiple grids arranged in sequence included in each path, and the target connection point grid is the connection point grid corresponding to the starting point of the first path.

[0101] It should be understood that the A-star algorithm, also known as the A algorithm, is a heuristic search algorithm that combines the features of the best-first search and the Dijkstra algorithm to find the shortest path from a starting point to a target point in a graph.

[0102] In some embodiments, see Figure 4 The above S5 specifically includes the following steps:

[0103] S51, determining a path with the smallest cost value among multiple paths between multiple connection point grids and a target point as a first path;

[0104] In one possible implementation, the above S51 specifically includes the following steps: based on the A-star algorithm, taking each connection point grid as the starting point, determining the center point of the grid with the smallest cost value and a yaw angle less than a preset angle among multiple grids adjacent to each connection point grid as a path point, wherein the yaw angle is determined based on the second heuristic function; based on each path point, determining the center point of the grid with the smallest cost value among multiple grids adjacent to the grid corresponding to the path point as the next path point corresponding to each path point; determining multiple path points in sequence, and when the path point is located in the grid where the target point is located, obtaining the path corresponding to each connection point grid, the path being a line connecting multiple path points arranged in order with each connection point grid as the starting point; determining the path with the smallest cost value among the paths corresponding to each connection point grid as the first path.

[0105] In one example, the preset angle is 90°.

[0106] In another possible implementation, the above S51 specifically includes the following steps: merging multiple grids of the same category arranged in a preset shape in the grid map to obtain a grid group corresponding to the multiple grids, wherein the preset shape is a square; based on the A-star algorithm, taking each connection point grid as a starting point, determining the center point of the grid or grid group with the smallest cost value and a yaw angle less than a preset angle among the multiple grids or grid groups adjacent to each connection point grid as a path point, wherein the yaw angle is determined based on the second heuristic function, wherein the cost value of the grid group is is the maximum value among the cost values ​​of the multiple grids included in the grid group; based on each path point, the grid or the center point of the grid group with the smallest cost value among the multiple grids or grid groups adjacent to the grid corresponding to the path point is determined as the next path point corresponding to each path point; multiple path points are determined in sequence, and when the path point is located in the grid where the target point is located, the path corresponding to each connection point grid is obtained, and the path is a line connecting multiple path points arranged in sequence with each connection point grid as the starting point; the path with the smallest cost value among the paths corresponding to each connection point grid is determined as the first path.

[0107] For example, Figure 5 This is a schematic diagram of another grid map according to an embodiment of the present invention. The grid map includes grids A, B, C, and D, each of which is classified as roadless and obstacle-free terrain. Grids A, B, C, and D are arranged in a preset shape. Grids A, B, C, and D are combined into grid group 1. When grid E is a path point, the cost value from grid E to grid A, B, C, or D is determined. The cost value from grid E to grid A, B, C, or D with the smallest cost value is determined as the cost value from grid E to grid group 1. The cost value from grid E to each grid F is then determined. If the cost value from grid E to grid group 1 is smaller than the cost value from grid E to each adjacent grid, the center point of grid group 1 is determined as the next path point.

[0108] S52: Determine the connection point grid corresponding to the starting point of the first path as the target connection point grid.

[0109] S53: Determine the path with the minimum cost between the starting point and the target connection point grid as the second path.

[0110] It should be understood that the process of determining the second path with the starting point as the starting point is the same as the above-mentioned method of determining multiple paths with the connection point grid as the starting point. Both of them are to sequentially determine the center point of the grid with the smallest cost value and a yaw angle less than the preset angle among the multiple adjacent grids as the next path point until the path point and the end point are located in the same grid. No further details will be given here.

[0111] S54: Merge the first path and the second path to obtain a target path.

[0112] Specifically, the starting point of the first path is the target connection point grid, and the end point is the target point. The starting point of the second path is the initial point, and the end point is the target connection point grid. Therefore, the first path and the second path are connected through the target connection point grid to obtain a target path with the starting point as the starting point and the end point as the target point.

[0113] In one example, based on the A-star algorithm, the process of determining the target path according to the heuristic function and the cost function can be implemented by the following algorithm.

[0114] Specifically, the "is_diagonal_move" function is constructed to determine the diagonal move from the first grid (x n-1 ,y n-1 ) to the second grid (x n ,y n ) is a diagonal move; set the slope weight coefficient α(n) and surface attribute weight coefficient β(n) of the second grid, and set the special weight coefficient ω of the connection point connect , create two direction lists "directions" and "extended_directions", "directions" contains the regular eight directions (up, down, left, right and their diagonal directions), and "extended_directions" includes four long-distance directions (two grids away in each direction); determine the category of the current location based on the "slope_mape", "terrain_map" and "road_map" information of the current location; determine whether the category of the current second grid is road terrain or roadless terrain, and add "extended_directions" to "directions"; for each direction in "directions", calculate the coordinates of each second grid and check whether each second grid is within the legal range of the map (that is, it does not exceed the map boundary); for each potential next waypoint, the category of each second grid is again determined based on the grid's elevation information; if there is a second grid with the category of obstacle terrain, then skip the second grid with the category of obstacle terrain according to actual needs and do not add this second grid to the neighbor list.

[0115] As can be seen from S1-S5 above, the method provided by the embodiment of the present invention determines multiple connection point grids, determines the path with the lowest cost between the target connection point grid and the target point as the first path, and determines the path with the lowest cost between the starting point and the target connection point grid as the second path, then merges the first and second paths to obtain the target path from the starting point to the target point. In this way, the second path can include multiple grids classified as road terrain. Compared to the action path determined by the A-star algorithm in the related art, the path determined by the embodiment of the present invention, by passing through multiple road terrain grids, can effectively reduce the travel time from the starting point to the target point and improve travel efficiency.

[0116] The above mainly introduces the solution of the embodiment of the present invention from the perspective of method. It can be understood that in order to realize the above functions, the determination system 100 includes at least one of the hardware structure and software modules corresponding to the execution of each function. It should be easy for those skilled in the art to realize that, in combination with the units and algorithm steps of each example described in the embodiment disclosed herein, the embodiment of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiment of the present invention.

[0117] In an embodiment of the present invention, the determination system 100 may be divided into functional units according to the above-described method example. For example, the determination system 100 may be divided into functional units corresponding to respective functions, or two or more functions may be integrated into a single processing unit. The above-described integrated units may be implemented in the form of hardware or software functional units. It should be noted that the division of units in the embodiment of the present invention is illustrative and is merely a logical functional division. In actual implementation, other division methods may be used.

[0118] For example, Figure 6The hardware structure diagram of a determination system 100 provided by an embodiment of the present invention is shown. The determination system 100 includes: a request receiving unit 610, for receiving a path planning request, the path planning request is used to request planning of a target path from a starting point to a target point in a target area, and the path planning request carries image data of the target area, and the image data includes high-resolution images, hyperspectral images, and digital elevation model images; an image processing unit 620, for determining a grid map of the target area based on the image data of the target area, the grid map includes a plurality of square grids of the same size, and coordinates, categories, and slope grades corresponding to each grid, and the categories include obstacle terrain, road terrain, or non-road non-obstructive terrain; a function construction unit 630, for establishing a heuristic function and a cost function, wherein the heuristic function is used to characterize the path distance and yaw angle from each first grid to each second grid, and the cost function is used to characterize the cost from each first grid to each second grid. value; the first grid is one of the multiple grids, and the second grid is a grid adjacent to the first grid; a grid determination unit 640 is used to determine the connection point grid in the multiple grids according to the category of each grid, wherein there is a grid of the road terrain category in the multiple grids adjacent to the connection point grid; a path determination unit 650 is used to determine the target path based on the A-star algorithm according to the heuristic function and the cost function, the target path includes a first path and a second path, the first path is the path with the minimum cost value among the multiple paths between the multiple connection point grids and the target point, the second path is the path with the minimum cost value among the multiple paths between the starting point and the target connection point grid, the cost value of each path is the sum of the heuristic function value and the cost function value obtained by traversing the multiple grids arranged in order included in each path, and the target connection point grid is the connection point grid corresponding to the starting point of the first path.

[0119] It should be understood that the specific description of the above optional methods can refer to the above method embodiments, which will not be repeated here. In addition, the explanation of any of the above-provided determination systems 100 and the description of the beneficial effects can refer to the above corresponding method embodiments, which will not be repeated here.

[0120] An embodiment of the present invention further provides a computer-readable storage medium storing at least one computer instruction, which is loaded and executed by a processor to implement the methods of each of the above embodiments. For explanations of the relevant contents and descriptions of the beneficial effects of any of the above-mentioned computer-readable storage media, reference can be made to the corresponding embodiments described above and will not be repeated here.

[0121] The embodiment of the present invention further provides a chip. The chip integrates a control circuit and one or more ports for implementing the functions of the above-mentioned determination system 100. Optionally, the functions supported by the chip can be referred to above and will not be repeated here.

[0122] Those skilled in the art will appreciate that all or part of the steps of the above-described embodiments can be implemented by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium. The aforementioned storage medium can be a read-only memory, a random access memory, etc. The aforementioned processing unit or processor can be a central processing unit, a general-purpose processor, an application-specific integrated circuit (ASIC), a microprocessor (digital signal processor, DSP), a field programmable gate array (FPGA) or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof.

[0123] An embodiment of the present invention further provides a computer program product comprising instructions that, when executed on a computer, cause the computer to perform any of the methods described in the above embodiments. The computer program product comprises one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present invention are fully or partially generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium accessible by a computer or a data storage device such as a server or data center that includes one or more available media. Available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives).

[0124] It should be noted that the above-mentioned devices for storing computer instructions or computer programs provided in the embodiments of the present invention, such as but not limited to the above-mentioned memories, computer-readable storage media and communication chips, etc., all have non-transitory properties. Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present invention can be implemented using hardware, software, firmware or any combination thereof. When implemented using software, these functions can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0125] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A path determination method for outdoor multi-terrain scenes, characterized in that: The method comprises: receiving a path planning request, the path planning request being used to request planning of a target path from a starting point to a target point in a target area, the path planning request carrying image data of the target area, the image data including high-resolution imagery, hyperspectral imagery, and digital elevation model imagery; Determining a grid map of the target area based on the image data of the target area, the grid map including a plurality of square grids of the same size, and coordinates, categories, and slope levels corresponding to each grid, the categories including obstacle terrain, road terrain, or non-road obstacle terrain; Establishing a heuristic function and a cost function, wherein the heuristic function is used to characterize the path distance and yaw angle from each first grid to each second grid, and the cost function is used to characterize the cost value from each first grid to each second grid; the first grid is one of a plurality of grids, and the second grid is a grid adjacent to the first grid; Determining a connection point grid among the plurality of grids according to the category of each grid, wherein a grid of the category of road terrain exists among the plurality of grids adjacent to the connection point grid; Based on the A-star algorithm, the target path is determined according to the heuristic function and the cost function, the target path includes a first path and a second path, the first path is the path with the smallest cost value among multiple paths between multiple connection point grids and the target point, the second path is the path with the smallest cost value among multiple paths between the starting point and the target connection point grid, the cost value of each path is the sum of the heuristic function value and the cost function value obtained by traversing the multiple grids arranged in order included in each path, and the target connection point grid is the connection point grid corresponding to the starting point of the first path.

2. The method according to claim 1, characterized in that The heuristic function includes a first heuristic function and a second heuristic function. When the second grid is a grid adjacent to the first grid in the horizontal or vertical direction, the expression of the first heuristic function is: h(n)=d*h d (n)+d*[h s (n)-2h s (n)]; When the second grid is a grid adjacent to the first grid in a diagonal direction, the expression of the first heuristic function is: h d (n)=min(|x n -x g |,|y n -y g |); h s (n)=(|x n -x g |+|y n -y g |); Among them, n is the identifier of the second grid, and the coordinates of the second grid are (x n ,y n ); the coordinates of the target grid g where the target point is located are (x g ,y g ), d is the length of each grid, h d (n) is the number of diagonal movable steps, h s (n) is the number of linear movable steps.

3. The method according to claim 2, characterized in that The expression of the second heuristic function is: Where θ is the yaw angle, is the vector from the first grid to the target grid, is the vector from the first grid to the second grid.

4. The method according to claim 3, characterized in that When the category of the second grid is obstacle terrain, the expression of the cost function is: pass(n-1,n)=a(n)*β(n); n-1 is the identifier of the first grid, α(n) is the slope weight coefficient of the second grid, which is determined according to the slope grade of each grid; β(n) is the surface attribute weight coefficient of the second grid, which is determined according to the category of each grid; D is the horizontal distance from the first grid to the second grid, and Δh is the vertical distance from the first grid to the second grid; When the second grid is classified as road terrain or non-road obstacle-free terrain, the cost function is expressed as follows: g(n)=k road *[g(n-1)+cost(n,n-1)]; cost(n,n-1)=d(n,n-1)(1+αS slope +βk road ); Among them, k road is the traffic coefficient of different types of grids, S slope is the cost coefficient corresponding to different slope levels, and α and β are adjustment coefficients.

5. The method according to claim 4, characterized in that The determining the target path based on the A-star algorithm and the heuristic function and the cost function includes: Based on the A-star algorithm, determining a path with the smallest cost value among multiple paths between multiple connection point grids and the target point as the first path; Determine the connection point grid corresponding to the starting point of the first path as the target connection point grid; Based on the A-star algorithm, determining the path with the minimum cost between the starting point and the target connection point grid as the second path; The first path and the second path are merged to obtain the target path.

6. The method according to claim 5, characterized in that The step of determining, based on the A-star algorithm, a path with the smallest cost value among multiple paths between the multiple connection point grids and the target point as the first path includes: Taking each connection point grid as a starting point, determining the center point of a grid with the smallest cost value and a yaw angle less than a preset angle among multiple grids adjacent to each connection point grid as a path point, wherein the yaw angle is determined based on a second heuristic function; Based on each of the path points, determining the center point of a grid with the smallest cost value among a plurality of grids adjacent to the grid corresponding to the path point as the next path point corresponding to each of the path points; Determine a plurality of the path points in sequence, and when the path points are located in the grid where the target point is located, obtain a path corresponding to each connection point grid, wherein the path is a line connecting the plurality of path points arranged in sequence starting from each connection point grid; The path with the smallest cost value among the paths corresponding to each connection point grid is determined as the first path.

7. The method according to claim 6, characterized in that The step of determining, based on the A-star algorithm, a path with the smallest cost value among multiple paths between the multiple connection point grids and the target point as the first path includes: Merging multiple grids of the same category that are arranged in a preset shape in the grid map to obtain a grid group corresponding to the multiple grids, wherein the preset shape is a square; Taking each connection point grid as a starting point, determining the center point of a grid or grid group with the smallest cost value and a yaw angle less than a preset angle among multiple grids or grid groups adjacent to each connection point grid as a path point, wherein the yaw angle is determined based on the second heuristic function, and wherein the cost value of the grid group is the maximum value among the cost values ​​of the multiple grids included in the grid group; Based on each of the path points, determining the center point of a grid or grid group with the smallest cost value among a plurality of grids or grid groups adjacent to the grid corresponding to the path point as the next path point corresponding to each of the path points; Determine a plurality of the path points in sequence, and when the path points are located in the grid where the target point is located, obtain a path corresponding to each connection point grid, wherein the path is a line connecting the plurality of path points arranged in sequence starting from each connection point grid; The path with the smallest cost value among the paths corresponding to each connection point grid is determined as the first path.

8. A path determination system for outdoor multi-terrain scenes, characterized in that: The system comprises: a request receiving unit, configured to receive a path planning request, wherein the path planning request is used to request planning of a target path from a starting point to a target point in a target area, wherein the path planning request carries image data of the target area, wherein the image data includes high-resolution imagery, hyperspectral imagery, and digital elevation model imagery; an image processing unit, configured to determine a grid map of the target area based on the image data of the target area, the grid map comprising a plurality of square grids of equal size, and coordinates, a category, and a slope grade corresponding to each grid, the category comprising obstacle terrain, road terrain, or non-road obstacle-free terrain; a function construction unit, configured to establish a heuristic function and a cost function, wherein the heuristic function is configured to characterize a path distance and a yaw angle from each first grid to each second grid, and the cost function is configured to characterize a cost value from each first grid to each second grid; the first grid is one of a plurality of grids, and the second grid is a grid adjacent to the first grid; a grid determining unit, configured to determine a connection point grid among the plurality of grids according to the category of each grid, wherein a grid of the category of road terrain exists among the plurality of grids adjacent to the connection point grid; A path determination unit is configured to determine the target path based on the A-star algorithm according to the heuristic function and the cost function, wherein the target path includes a first path and a second path, the first path being the path with the smallest cost value among multiple paths between multiple connection point grids and the target point, and the second path being the path with the smallest cost value among multiple paths between the starting point and the target connection point grid, the cost value of each path being the sum of the heuristic function value and the cost function value obtained by traversing the multiple grids arranged in order included in each path, and the target connection point grid being the connection point grid corresponding to the starting point of the first path.

9. An electronic device, characterized in that: include: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A computer-readable medium, characterized in that Computer program instructions are stored, which can be executed by a processor to implement the method according to any one of claims 1 to 7.

Images