A multi-terrain integrated path planning method incorporating road factors
By constructing a grid map and combining terrain features with an improved neighborhood search algorithm, the problem of path deviation in unstructured environments in traditional path planning is solved, achieving more efficient path selection and improving traffic efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHONGKE ZHIKONG TIANDI TECHNOLOGY (HANGZHOU) CO LTD
- Filing Date
- 2025-05-23
- Publication Date
- 2026-05-26
AI Technical Summary
Traditional path planning methods are prone to deviations in unstructured environments, resulting in low traffic efficiency and failing to effectively consider the path traversability in unstructured environments.
By constructing a grid map, combining terrain features such as slope, type, and vehicle speed, and using an improved neighborhood search algorithm, a cost function and penalty coefficient are set to optimize path selection and integrate path planning for both structured and unstructured environments.
It improves the efficiency of route planning, enabling the finding of the optimal route with lower time costs and enhancing users' travel efficiency.
Smart Images
Figure CN120702466B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of route planning technology, and in particular to a multi-terrain integrated route planning method that incorporates road factors. Background Technology
[0002] Path planning is one of the key technologies for autonomous driving and is the foundation for the safe and stable operation of autonomous vehicles. The purpose of path planning is to plan the optimal driving route (the shortest time, the shortest distance, or the most reasonable route) according to certain rules given a starting point and destination, so as to ensure that the user can reach the destination smoothly.
[0003] Due to the complex terrain and irregular travel areas in unstructured environments, such as mountain roads, gravel roads, and grasslands, traditional path planning methods (e.g., ant colony optimization, particle swarm optimization) often ignore paths in unstructured environments and only consider paths in structured environments (e.g., wilderness paths formed by multiple vehicle traffic, highways, urban main roads). Since some paths in unstructured environments may also be passable, the travel paths obtained using traditional path planning methods are prone to deviate from the actual optimal travel paths, reducing user travel efficiency. Summary of the Invention
[0004] The technical problem this invention aims to solve is to provide a multi-terrain integrated route planning method that incorporates road factors, comprehensively considering the traversability of paths in both structured and unstructured environments. This allows for route planning that improves user travel efficiency.
[0005] The technical solution of the present invention to solve the above-mentioned technical problems is as follows:
[0006] Firstly, this invention provides a multi-terrain integrated path planning method that integrates road factors. Based on image information of a target area, it determines at least one terrain feature included in the target area. Based on the at least one terrain feature, a grid map corresponding to the target area is constructed. The grid map includes at least one grid, and the terrain features included in the same grid are of the same type. In response to an input path search instruction, at least one path is determined in the grid map. The path search instruction instructs the search for a driving path between a start point and an end point in the target area, where the start point of the path is the position corresponding to the start point in the grid map, and the end point of the path is the position corresponding to the end point in the grid map. For any path among the at least one path, the sum of the cost function values corresponding to each grid passed through by that path in the grid map is obtained. The cost function is associated with the slope value of the terrain feature included in the corresponding grid, the type of terrain feature, a preset vehicle speed passing through the terrain feature included in the corresponding grid, and the Euclidean distance between the start point and the end point. The path corresponding to the minimum sum among the at least one path is determined as the target path. The path corresponding to the target path in the target area is determined as the driving path.
[0007] Based on the above technical solution, the present invention can be further improved as follows.
[0008] Furthermore, the image information is preprocessed. This preprocessing includes at least one of noise removal, edge enhancement, and image smoothing. At least one terrain feature is extracted from the preprocessed image information based on a pre-defined extraction algorithm. This pre-defined extraction algorithm is used for supervised classification of the corresponding image information.
[0009] Furthermore, based on at least one terrain feature, an area dominance method is used to construct a raster map corresponding to the target area.
[0010] Furthermore, the cost function includes:
[0011] A = Cost + H(node, goal);
[0012] Wherein, Cost is the first cost function, which is associated with the slope value and type of terrain features included in the corresponding grid. H(node,goal) is the second cost function, which is associated with the preset speed of the vehicle passing through the terrain features included in the corresponding grid and the Euclidean distance between the starting point and the ending point.
[0013] Furthermore, for any grid cell traversed by any path in the raster map, the elevation data of the terrain features included in that grid cell are obtained. Based on the elevation data of the terrain features included in that grid cell, the slope level of the terrain features included in that grid cell is determined. Based on the slope level of the terrain features included in that grid cell, and the type of terrain features included in that grid cell, the value of the first cost function corresponding to that grid cell is determined.
[0014] Furthermore, the first cost function includes:
[0015] Cost = D + Cost terrain +Cost slope ;
[0016] Where D represents the Euclidean distance between the starting point and the ending point, and Cost terrain Cost represents the terrain cost of the terrain features included in the corresponding grid when a vehicle passes through a preset area. slope This represents the slope cost of the terrain features passed through the corresponding grid by the preset vehicle. The terrain cost is associated with the type of terrain feature passed through the corresponding grid by the preset vehicle. The type of terrain feature includes at least one of saline-alkali land, grassland, gravel land, and sandy land. The slope cost is associated with the slope grade of the terrain feature passed through the corresponding grid by the preset vehicle.
[0017] Furthermore, based on the elevation data of the terrain features included in any grid, the slope value of the terrain features included in any grid is determined. Based on a first preset relationship and the slope value of the terrain features included in any grid, the slope grade of the terrain features included in any grid is determined. The first preset relationship includes the correspondence between slope values and slope grades.
[0018] Furthermore, the raster map includes road rasters and non-road rasters. The terrain features included in road rasters correspond to a structured environment in the target area, while the terrain features included in non-road rasters correspond to an unstructured environment in the target area. The value of the second cost function corresponding to any given raster is determined. The second cost function includes:
[0019]
[0020] Where α is the first penalty coefficient, which is related to the number of road grids traversed by any path in the grid map. β is the second penalty coefficient, which is related to the number of non-road grids traversed by any path in the grid map. α + β = 1. v represents the preset speed of the vehicle passing through the terrain features included in the corresponding grid, and α(terrain) represents the preset speed attenuation rate of the vehicle passing through the terrain features included in the corresponding grid, which is related to the type of terrain features included in the corresponding grid.
[0021] Furthermore, based on a preset neighborhood search algorithm, at least one path is determined in the grid map.
[0022] Furthermore, the image information includes at least one of high-resolution image information, hyperspectral image information, and elevation image information.
[0023] The beneficial effects of this invention are as follows: This invention considers the slope and type of terrain features, and replaces the influence of soil softness and terrain friction on the passage of the preset vehicle by taking into account the speed attenuation problem of the preset vehicle on various terrain features. This invention considers that paths in structured environments have better passability for the preset vehicle. By setting a grid penalty coefficient, it guides the search for paths more favorable to structured environments based on a preset neighborhood search algorithm. Through the setting of multiple cost functions, the path selection is made more reasonable. Simulation results show that the method provided by this invention has high path planning efficiency. Numerical experimental results show that the preset neighborhood search algorithm provided in this invention, compared with the traditional A* algorithm, can plan the optimal path at a lower time cost, thereby improving the user's travel efficiency.
[0024] In a second aspect, the present invention provides a multi-terrain integrated path planning system that integrates road factors, for performing a multi-terrain integrated path planning method that integrates road factors as described in any of the first aspects above.
[0025] Thirdly, the present invention provides an electronic device, comprising: a memory and one or more processors; the memory and the processors are coupled; wherein the memory stores computer program code, the computer program code including computer instructions, and when the computer instructions are executed by the processor, the electronic device performs the multi-terrain integrated path planning method that integrates road factors as described in any of the first aspects above.
[0026] Fourthly, a computer-readable storage medium is provided, including computer instructions that, when executed on an electronic device, cause the electronic device to perform a multi-terrain integrated path planning method that integrates road factors as described in any of the first aspects above.
[0027] Fifthly, a computer program product is provided, which, when run on a computer, causes the computer to execute the multi-terrain integrated path planning method that integrates road factors as described in any of the first aspects above.
[0028] It is understood that the beneficial effects achieved by the system of the second aspect, 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 of its possible design embodiments, which will not be repeated here. Attached Figure Description
[0029] Figure 1 A flowchart illustrating a multi-terrain integrated path planning method that incorporates road factors, provided as an embodiment of this application;
[0030] Figure 2 A partially enlarged schematic diagram of a raster map provided in an embodiment of this application;
[0031] Figure 3 A macroscopic schematic diagram of a grid map provided in an embodiment of this application;
[0032] Figure 4 This is another enlarged schematic diagram of a raster map provided in an embodiment of this application. Detailed Implementation
[0033] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. In the description of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. "And / or" in this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Furthermore, in the description of this application, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single 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, and c can be single or multiple. Furthermore, to facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that "first" and "second" are not necessarily different. Meanwhile, in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate that something is being used as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes.
[0034] Off-road autonomous ground vehicles (AGVs) have received widespread attention in fields such as field exploration, disaster relief, and military operations. Especially in emergency rescue missions, off-road AGVs are widely used in field rescue operations due to their excellent off-road mobility and ability to quickly reach the target point.
[0035] Off-road environments are characterized by undulating terrain and complex surface types, which introduces numerous delays and obstacles to the passage of off-road AGVs, posing a significant challenge to their emergency rescue missions. In addition to various complex surface types, the wilderness environment also contains unpaved roads with high traversability formed by long-term vehicle traffic. However, existing AGV off-road path planning algorithms often overlook the fact that these existing unpaved roads have higher traversability compared to the off-road environment.
[0036] Therefore, establishing a path planning method that considers both the risks of off-road scenarios and integrates existing roads in the wild under simulation is of great significance for completing rescue or exploration tasks in off-road scenarios.
[0037] See Figure 1 This invention provides a multi-terrain integrated path planning method that incorporates road factors, comprising the following steps S101-S106:
[0038] S101: Based on the image information of the target area, determine at least one terrain feature included in the target area.
[0039] In some embodiments, the image information may include at least one of high-resolution image information, hyperspectral image information, and elevation image information.
[0040] In some embodiments, the image information may be preprocessed. Then, at least one terrain feature is extracted from the preprocessed image information based on a preset extraction algorithm.
[0041] The preprocessing may include at least one of noise removal, edge enhancement, and image smoothing. A pre-defined extraction algorithm is used for supervised classification of the corresponding image information.
[0042] For example, image information refers to the corresponding image. Based on software (or equipment) with "land monitoring and classification functions," a support vector machine-based feature extraction method can be used to process the surface attributes included in the preprocessed image to extract at least one terrain feature from the image.
[0043] In some embodiments, the types of terrain features may include at least one of bare land, sandy land, grassland, saline-alkali land, and bare rocky gravel land.
[0044] S102: Construct a raster map corresponding to the target area based on at least one terrain feature.
[0045] The raster map includes at least one raster, and the same raster contains the same type of terrain features.
[0046] For example, see Figure 2 This is a partially enlarged schematic diagram of a raster map provided by the present invention. In this raster map, the terrain features in raster 201 are all bare land, the terrain features in raster 202 are all grassland, and the terrain features in raster 203 are all bare rock and gravel. That is, each raster includes only one type of terrain feature, and different rasteres may include the same or different terrain features.
[0047] In some embodiments, a raster map corresponding to the target area can be constructed based on at least one terrain feature using the area dominance method.
[0048] In some embodiments, the types of graticles included in the raster map include road graticles and non-road graticles. The terrain features included in the road graticles correspond to a structured environment in the target area. The terrain features included in the non-road graticles correspond to an unstructured environment in the target area.
[0049] The structured environment can include roads formed by long-term vehicle traffic, roads that have been artificially repaired to support vehicle passage, etc. Roads included in the structured environment can also be called field roads. The unstructured environment can include roads that are rarely driven by vehicles. Roads included in the structured environment can also be called non-field roads. In conjunction with the foregoing embodiments, since the types of terrain features can include at least one of bare land, sandy land, grassland, saline-alkali land, and bare rocky gravel land, non-field roads can also include at least one of bare land roads, sandy land roads, grassland roads, saline-alkali land roads, and bare rocky gravel land roads.
[0050] In some embodiments, because existing field roads and surrounding soil have similar spectral characteristics, this similarity makes it more difficult to distinguish field roads from surrounding soil in image processing. Therefore, high-precision image analysis and processing techniques can be used to accurately identify and extract road information. In this embodiment, field roads in the target area can be extracted based on deep learning methods.
[0051] S103: In response to the input path search instruction, determine at least one path in the raster map.
[0052] The route search command is used to instruct the search for a driving route between a start point and an end point in the target area. The start point of the route is the location of the start point on the raster map, and the end point of the route is the location of the end point on the raster map.
[0053] For example, see Figure 3 This is a macroscopic schematic diagram of a grid map provided by the present invention. The starting point 301 is the position in the grid map corresponding to the starting point of the search path in the target area, and the ending point 302 is the position in the grid map corresponding to the ending point of the search path in the target area.
[0054] In some embodiments, at least one path can be determined in the raster map based on a preset neighborhood search algorithm. For example, see [link to previous document]. Figure 3 It can determine path 310, path 320 and path 330 in the grid map based on a preset neighborhood search algorithm.
[0055] The preset neighborhood search algorithm in this application embodiment is based on an improvement of the traditional 16-neighborhood search method. The preset neighborhood search algorithm in this application embodiment is described in detail below.
[0056] The traditional A* algorithm searches in the eight neighboring directions of each parent node. However, the 16-neighbor search algorithm adds a knight search to the eight-neighbor search, expanding the search range. This inevitably leads to some useless nodes participating in the calculation.
[0057] Therefore, to avoid spending more time on irrelevant nodes, this embodiment can set the category of the angle θ between the line connecting the current node and the target point and a preset direction (e.g., due east), and establish the association between the category of the angle θ and the processing method of the corresponding node. Then, the search direction can be assigned in real time based on the category of the angle θ.
[0058] For example, see Figure 4 This is another partially enlarged schematic diagram of the grid map provided in this application embodiment. Each square represents a grid cell, and the number within the grid cell indicates the node where the corresponding grid cell is located. For example, nodes 1, 2, 3, 4, 5, 6, 7, 8, a, b, c, d, e, f, g, h, i. Given the correlation between the type of angle θ and the processing method of the corresponding node as shown in Table 1, if the angle θ between the line connecting the current node and the target point and the preset direction is 25°, then nodes d, g, h, 5, and 7 can be deleted; that is, searching in the direction from the current node to nodes d, g, h, 5, and 7 is not considered.
[0059] Table 1
[0060]
[0061] Table 2 shows the results obtained after searching using the preset neighborhood search algorithm in this embodiment and the results obtained using the traditional 16-neighborhood search algorithm. It can be seen that the search using the preset neighborhood search algorithm in this embodiment reduces the number of path nodes found in the search neighborhood, thus improving search efficiency. The number of search nodes is reduced by 16.784%, and the search efficiency is improved by 39.42%. Therefore, the preset neighborhood search algorithm in this embodiment is more efficient in searching, thus verifying the effectiveness and feasibility of the preset neighborhood search algorithm in this embodiment.
[0062] Table 2
[0063] Neighborhood Distance (m) Number of nodes Search efficiency (s) Traditional Algorithm 13930.81 1692 45.18 This algorithm 13804.03 1408 27.37
[0064] S104: For any path in at least one path, obtain the sum of the cost function values corresponding to each grid cell that the path passes through in the grid map.
[0065] The cost function is associated with the slope value of the terrain features included in the corresponding grid, the type of terrain features, the speed of the preset vehicle (e.g., an off-road vehicle) through the terrain features included in the corresponding grid, and the Euclidean distance between the starting point and the ending point.
[0066] In some embodiments, the cost function includes:
[0067] A = Cost + H(node, goal);
[0068] Wherein, Cost is the first cost function, which is associated with the slope value and type of terrain features included in the corresponding grid. H(node,goal) is the second cost function, which is associated with the preset speed of the vehicle passing through the terrain features included in the corresponding grid and the Euclidean distance between the starting point and the ending point.
[0069] In some embodiments, for any grid cell traversed by any path in a grid map, elevation data of the terrain features included in that grid cell can be obtained. Based on the elevation data of the terrain features included in that grid cell, the slope grade of the terrain features included in that grid cell can be determined. Based on the slope grade of the terrain features included in that grid cell, and the type of terrain features included in that grid cell, the value of the first cost function corresponding to that grid cell can be determined.
[0070] In some embodiments, the slope value of the terrain feature included in any grid can be determined based on the elevation data of the terrain feature included in any grid. The slope grade of the terrain feature included in any grid is determined based on a first preset relationship and the slope value of the terrain feature included in any grid. The first preset relationship includes the correspondence between slope values and slope grades.
[0071] For example, the first preset relationship can be as shown in Table 3. The slope level can include levels 0-6, with different slope levels corresponding to different slope values.
[0072] Table 3
[0073] Slope grade slope Slope Value 0 0°～5° 1 1 5°～10° 0.8 2 10°～15° 0.6 3 15°～20° 0.4 4 20°～25° 0.2 5 25°～31° 0.1 6 ≥31° 0
[0074] In some embodiments, the first cost function includes:
[0075] Cost = D + Cost terrain +Cost slope ;
[0076] Where D represents the Euclidean distance between the starting point and the ending point, and Cost terrain Cost represents the terrain cost of the terrain features included in the corresponding grid when a vehicle passes through a preset area. slope This represents the slope cost of the terrain features passed by the corresponding grid. The terrain cost is related to the type of terrain feature passed by the corresponding grid. The slope cost is related to the slope grade of the terrain feature passed by the corresponding grid.
[0077] In some embodiments, the first preset relationship may also include, as shown in Table 3, the correspondence between slope grade and slope cost. Based on the slope grade of the terrain features included in the corresponding grid, the slope cost of the terrain features included in the corresponding grid can be determined.
[0078] In some embodiments, the terrain value of the terrain features included in any grid can be determined based on the type of terrain features included in any grid and a second preset relationship. The second preset relationship, as shown in Table 4, includes the correspondence between the types of terrain features and their terrain values.
[0079] Table 4
[0080] Types of terrain features Velocity decay rate Topographical value Wilderness Roads 0 1 saline-alkali land 0.2 0.8 grassland 0.3 0.7 gravel ground 0.6 0.4 sandy land 0.8 0.2
[0081] In some embodiments, the value of a second cost function corresponding to any grid cell can also be determined. The second cost function includes:
[0082]
[0083] Where α is the first penalty coefficient, which is related to the number of road grids traversed by any path in the grid map. β is the second penalty coefficient, which is related to the number of non-road grids traversed by any path in the grid map. α + β = 1. v represents the preset speed of the vehicle traversing the terrain features included in the corresponding grid. α(terrain) represents the preset speed attenuation rate of the vehicle traversing the terrain features included in the corresponding grid. α(terrain) is related to the type of terrain features included in the corresponding grid.
[0084] Furthermore, setting the first and second penalty coefficients can guide the search process based on the road grid. Experiments show that the optimal path selection occurs when α = 0.4 and β = 0.6.
[0085] In some embodiments, referring again to Table 4, the second preset relationship may further include a correspondence between the types of terrain features and the speed attenuation rate. Based on the types of terrain features included in the corresponding grid, the preset speed attenuation rate of a vehicle passing through the terrain features included in the corresponding grid can be determined.
[0086] S105: Determine the path corresponding to the minimum sum among at least one path as the target path.
[0087] S106: In the target area, determine the path corresponding to the target path as the driving path.
[0088] This invention can also provide a multi-terrain integrated path planning system that integrates road factors. The path planning system provided by this invention can implement some or all of the steps in the multi-terrain integrated path planning method that integrates road factors provided by this invention.
[0089] This invention addresses the off-road path planning problem by considering the accessibility of terrain slope and terrain type, and by substituting the effects of soil softness and terrain friction on off-road vehicle traffic by taking into account the speed decay of off-road vehicles on various terrain types. Through a combination of theoretical analysis and simulation experiments, a method for determining the cost of slope and terrain is established, defining the off-road vehicle's off-road accessibility. Considering that off-road roads offer better accessibility for off-road vehicles, this study sets penalty coefficients (first and second penalty coefficients) and uses a pre-defined neighborhood search algorithm to find a path more favorable to off-road terrain. By setting a cost function that integrates multiple factors (slope, grade, speed across corresponding terrain features, and speed decay rate, etc.), the path selection becomes more rational, resulting in higher path planning efficiency and the ability to plan the optimal path at a lower time cost, which is crucial for real-time off-road path planning scenarios.
[0090] In some solutions, multiple embodiments of this application can be combined, and the combined solution can be implemented. Optionally, some operations in the processes of each method embodiment may be combined, and / or the order of some operations may be changed. Furthermore, the execution order between the steps of each process is merely exemplary and does not constitute a limitation on the execution order between steps; other execution orders are also possible. It is not intended to indicate that the execution order is the only possible order in which these operations can be performed. Those skilled in the art will conceive of various ways to reorder the operations described herein. In addition, it should be noted that the process details involved in one embodiment of this document are similarly applicable to other embodiments, or different embodiments may be combined.
[0091] Furthermore, some steps in the method embodiments can be equivalently replaced with other possible steps. Alternatively, some steps in the method embodiments may be optional and can be deleted in certain use cases. Or, other possible steps may be added to the method embodiments. Moreover, the various method embodiments can be implemented individually or in combination.
[0092] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above.
[0093] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.
[0094] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0095] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, in essence, or the part that contributes, or all or part of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0096] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A multi-terrain integrated path planning method that incorporates road factors, characterized in that, include: Based on the image information of the target area, determine at least one terrain feature included in the target area; Based on the at least one terrain feature, a raster map corresponding to the target area is constructed; the raster map includes at least one raster; the same raster includes the same type of terrain feature; In response to an input path search instruction, at least one path is determined in the grid map; the path search instruction is used to instruct the search of a driving path between a starting point and an ending point in the target area; the starting point of the path is the position corresponding to the starting point in the grid map, and the ending point of the path is the position corresponding to the ending point in the grid map. For any of the at least one paths, obtain the sum of the cost function values corresponding to each grid cell passed by the path in the grid map; the cost function is associated with the slope value of the terrain feature included in the corresponding grid cell, the type of terrain feature, the preset speed of the vehicle passing through the terrain feature included in the corresponding grid cell, and the Euclidean distance between the starting point and the ending point. The path corresponding to the minimum value of the sum among the at least one path is determined as the target path; The path corresponding to the target path in the target area is determined as the driving path.
2. The method according to claim 1, characterized in that, The determination of at least one terrain feature included in the target area based on image information of the target area includes: The image information is preprocessed; the preprocessing includes at least one of noise removal, edge enhancement, and image smoothing. At least one terrain feature is extracted from the preprocessed image information based on a preset extraction algorithm; the preset extraction algorithm is used for supervised classification of the corresponding image information.
3. The method according to claim 2, characterized in that, The step of constructing a raster map corresponding to the target area based on the at least one terrain feature includes: Based on the at least one terrain feature, a raster map corresponding to the target area is constructed using the area dominance method.
4. The method according to claim 3, characterized in that, The cost function includes: A = Cost + H(node, goal); Wherein, Cost is the first cost function, which is associated with the slope value and type of terrain features included in the corresponding grid; H(node,goal) is the second cost function, which is associated with the preset speed of the vehicle passing through the terrain features included in the corresponding grid and the Euclidean distance between the starting point and the ending point.
5. The method according to claim 4, characterized in that, The step of obtaining the sum of the cost function values corresponding to each grid cell traversed by any path in the grid map includes: For any grid cell that any path passes through in the grid map, obtain the elevation data of the terrain features included in any grid cell; Based on the elevation data of the terrain features included in any of the grids, determine the slope level of the terrain features included in any of the grids; Based on the slope level of the terrain features included in any given grid, and the type of terrain features included in any given grid, the value of the first cost function corresponding to any given grid is determined.
6. The method according to claim 5, characterized in that, The first cost function includes: Cost=D+Cost terrain +Cost slope ; Where D represents the Euclidean distance between the starting point and the ending point, and Cost terrain Cost represents the terrain cost of the terrain features included in the corresponding grid when the preset vehicle passes through. slope The slope value represents the gradient of the terrain features passed through the corresponding grid by the preset vehicle; the gradient value is associated with the type of terrain features passed through the corresponding grid by the preset vehicle; the type of terrain features includes at least one of saline-alkali land, grassland, gravel land, and sandy land; the gradient value is associated with the gradient grade of the terrain features passed through the corresponding grid by the preset vehicle.
7. The method according to claim 6, characterized in that, Determining the slope grade of the terrain features included in any given grid, based on the elevation data of the terrain features included in any given grid, includes: Based on the elevation data of the terrain features included in any of the grids, determine the slope value of the terrain features included in any of the grids; Based on the first preset relationship and the slope value of the terrain feature included in any grid, the slope level of the terrain feature included in any grid is determined; the first preset relationship includes the correspondence between slope value and slope level.
8. The method according to claim 7, characterized in that, The grid map includes road grids and non-road grids; the terrain features included in the road grids correspond to a structured environment in the target area; the terrain features included in the non-road grids correspond to an unstructured environment in the target area; obtaining the sum of the cost function values corresponding to each grid traversed by any path in the grid map includes: Determine the value of the second cost function corresponding to any of the grid cells; the second cost function includes: Wherein, α is the first penalty coefficient, which is associated with the number of road grids passed by any path in the grid map; β is the second penalty coefficient, which is associated with the number of non-road grids passed by any path in the grid map; α+β=1; v represents the speed of the preset vehicle passing through the terrain features included in the corresponding grid; α(terrain) represents the speed attenuation rate of the preset vehicle passing through the terrain features included in the corresponding grid; α(terrain) is associated with the type of terrain features included in the corresponding grid.
9. The method according to claim 8, characterized in that, The process of determining at least one path in the grid map in response to an input path search command includes: Based on a preset neighborhood search algorithm, at least one path is determined in the grid map.
10. The method according to claim 9, characterized in that, The image information includes at least one of high-resolution image information, hyperspectral image information, and elevation image information.