Unmanned platform three-dimensional path planning method, device, equipment and medium

Abstract

The invention discloses an unmanned platform three-dimensional path planning method, device, equipment and medium, and relates to the technical field of path planning, and the method comprises the steps: obtaining a DEM map of a target area, extracting the elevation information of a target grid unit in the DEM map, obtaining the elevation information of the target grid unit, and storing the elevation information of the target grid unit in the DEM map; calculating the gradient, the step length and the unevenness of the target grid unit; calculating the trafficability of the target grid unit according to the gradient, the step length and the unevenness of the target grid unit; according to the trafficability of all the target grid units and a set cost threshold value, gathering adjacent target grid units to obtain a plurality of low-cost areas; all the low-cost areas form a low-cost map of the target area; according to the low-cost map, the coordinates of each low-cost area in the low-cost map and the obstacle information, path planning is carried out, a final planning path is obtained, and the rationality of the planning path is improved on the premise of ensuring that the unmanned platform can pass safely.

Description

Technical Field

[0001] This application relates to the field of path planning technology, and in particular to a method, apparatus, equipment and medium for three-dimensional path planning of unmanned platforms. Background Technology

[0002] With the continuous development of automation technology, path planning is playing an increasingly important role in fields such as industrial automation, intelligent transportation systems, drone control, and autonomous vehicles. Path planning aims to determine the optimal path from start to finish for an unmanned platform in a complex environment. Different types of algorithms can be used for path planning of unmanned platforms, involving both global and local planning, and have been well validated in relatively simple two-dimensional environments, such as Dijkstra's algorithm and A*. * Classical path planning algorithms, such as those used in traditional methods, are widely employed in practical applications. Furthermore, in recent years, deep learning techniques have been extensively applied to path planning. Through neural network models, end-to-end path planning can be achieved, avoiding the need for manual design of features and rules. In addition, researchers have also explored applying reinforcement learning to path planning in complex environments to improve the algorithm's ability to find optimal paths in such conditions.

[0003] However, when these path planning algorithms are applied to complex unstructured environments (such as unmanned platforms conducting mountain exploration, military reconnaissance, and planetary exploration missions, which may encounter outdoor environments like mountains, hills, deserts, and Gobi), the lack of sufficient consideration of terrain factors and the unmanned platform's mobility results in paths that are either impossible to traverse or excessively circuitous, failing to fully utilize the unmanned platform's mobility in unstructured environments. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, equipment and medium for three-dimensional path planning of unmanned platforms, which can fully consider the impact of terrain factors on the passability of unmanned platforms, add terrain feature factors to the heuristic function, optimize the search method of the algorithm, obtain a new three-dimensional path planning algorithm, and greatly improve the rationality of the planned path.

[0005] To achieve the above objectives, this application provides the following solution.

[0006] In the first aspect, this application provides a three-dimensional path planning method for an unmanned platform, including the following steps.

[0007] Obtain the DEM map of the target area.

[0008] For each target grid cell in the DEM map, the elevation information of the target grid cell is extracted to obtain the elevation information of the target grid cell.

[0009] The slope and step size of the target grid cell are calculated based on the elevation information of the target grid cell and the elevation information of the adjacent grid cells.

[0010] The unevenness of the target grid cell is calculated based on the elevation information of the target grid cell.

[0011] The passability of the target grid cell is calculated based on its slope, step size, and unevenness; the passability represents the cost for the unmanned platform to pass through the area corresponding to the target grid cell.

[0012] Based on the passability of all the target grid cells and the set cost threshold, adjacent target grid cells are grouped together to obtain several low-cost regions; each low-cost region includes passable areas and / or impassable areas; all low-cost regions constitute a low-cost map of the target region.

[0013] Based on the low-cost map, the coordinates of each low-cost region in the low-cost map, and obstacle information, path planning is performed to obtain the final planned path.

[0014] Optionally, based on the low-cost map, the coordinates of each low-cost region in the low-cost map, and obstacle information, path planning is performed to obtain the final planned path. Specifically, this includes: determining whether the current node is the destination; if the node is a low-cost region; if the current node is not the destination, deleting the current node from the open list and adding it to the closed list; determining whether the current node is within a low-cost region; if the current node is within a low-cost region, selecting the nearest neighbor node as the new current node, setting the current node as the parent node of the new current node, and removing the low-cost region; the nearest neighbor node is the node within the low-cost region with the smallest distance to the destination; the distance... The coordinates of the low-cost region corresponding to the node and the endpoint are calculated. If the current node is not in the low-cost region, the neighboring nodes of the current node are obtained, and the following operations are performed on each neighboring node: if the neighboring node is in the closed list or there is an obstacle, the neighboring node is skipped; the actual cost from the current node to the neighboring node is calculated; the actual cost includes distance cost and difference cost; the neighboring node with the lowest actual cost is selected as the new current node, and the current node is set as the parent node of the new current node; the above steps are repeated until the current node is the endpoint; starting from the endpoint, the final planned path is constructed by tracing back to the starting point along the parent node of each node; the endpoint is the endpoint.

[0015] Optionally, obtaining a DEM map of the target area specifically includes: using lidar mapping technology, radar elevation measurement technology, photogrammetry technology, or satellite remote sensing technology to obtain detailed surface elevation data of the target area; preprocessing the detailed surface elevation data to obtain preprocessed data; and interpolating the preprocessed data to obtain a DEM map of the target area.

[0016] Optionally, the slope and step size of the target grid cell are calculated based on the elevation information of the target grid cell and the elevation information of the adjacent grid cells. Specifically, this includes: calculating the partial derivatives of the target grid cell in the x-direction and y-direction based on the elevation information of the target grid cell and the elevation information of the adjacent grid cells; calculating the slope of the target grid cell based on the partial derivatives in the x-direction and y-direction; calculating the elevation difference between each adjacent grid cell and the target grid cell based on the elevation information of the target grid cell and the adjacent grid cells; and determining the target grid cell and step size based on the elevation difference with the largest value.

[0017] Optionally, the formula for calculating the unevenness of the target mesh element is shown below.

[0018]

[0019] Where ω(i,j) is the unevenness of the target grid cell (i,j), D is the wheel diameter of the unmanned platform, Z(i,j) is the elevation information of the target grid cell, and -z is the standard deviation of the elevation of the target grid cell and the grid cells adjacent to the target grid cell.

[0020] Optionally, the formula for calculating the passability of the target grid cell is as follows.

[0021]

[0022] Where T(i,j) represents the passability of the target grid cell (i,j), k1, k2, and k3 are the weights of slope, step size, and unevenness, respectively, θ(i,j) is the slope of the target grid cell (i,j), δ(i,j) is the step size of the target grid cell (i,j), ω(i,j) is the unevenness of the target grid cell (i,j), and θ crit δ crit and ω crit These represent the maximum terrain feature factor thresholds corresponding to slope, step length, and unevenness, respectively.

[0023] Optionally, the distance cost includes the distance from the current node to its neighboring nodes and the distance from the current node to the destination.

[0024] Secondly, this application provides a three-dimensional path planning device for an unmanned platform, which includes the following modules.

[0025] The DEM map acquisition module is used to acquire the DEM map of the target area.

[0026] The elevation information extraction module is used to: extract the elevation information of each target grid cell in the DEM map to obtain the elevation information of the target grid cell.

[0027] The slope and step length calculation module is used to calculate the slope and step length of the target grid cell based on the elevation information of the target grid cell and the elevation information of the adjacent grid cells of the target grid cell.

[0028] The unevenness calculation module is used to calculate the unevenness of the target grid cell based on the elevation information of the target grid cell.

[0029] The passability calculation module is used to: calculate the passability of the target grid cell based on the slope, step size, and unevenness of the target grid cell; the passability represents the cost for the unmanned platform to pass through the area corresponding to the target grid cell.

[0030] The low-cost region determination module is used to: group adjacent target grid cells together based on the passability of all the target grid cells and a set cost threshold to obtain several low-cost regions; each low-cost region includes passable and / or impassable regions; all low-cost regions constitute a low-cost map of the target region.

[0031] The path planning module is used to: perform path planning based on the low-cost map, the coordinates of each low-cost area in the low-cost map, and obstacle information to obtain the final planned path.

[0032] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described unmanned platform three-dimensional path planning method.

[0033] Fourthly, this application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described unmanned platform three-dimensional path planning method.

[0034] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a method, apparatus, device, and medium for three-dimensional path planning of an unmanned platform. Based on known DEM map information, a cost map is obtained by preprocessing the map, and a threshold is set according to the passability of the unmanned platform to obtain maps of impassable areas and low-cost areas. Then, in A... * Based on the algorithm, terrain feature factors (slope, step size, and unevenness) are added to the heuristic function to optimize A. * The algorithm's search method yields a new 3D path planning algorithm that integrates the unmanned platform's passability and terrain information, improving the rationality of the planned path while ensuring the unmanned platform's safe passage. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is an application environment diagram of a three-dimensional path planning method for an unmanned platform according to an embodiment of this application.

[0037] Figure 2 This is a flowchart illustrating a three-dimensional path planning method for an unmanned platform provided in one embodiment of this application.

[0038] Figure 3 This is a detailed flowchart illustrating the steps for obtaining a DEM map according to an embodiment of this application.

[0039] Figure 4 This is a detailed flowchart illustrating the cost map acquisition steps provided in an embodiment of this application.

[0040] Figure 5 This is a schematic diagram of the functional modules of a three-dimensional path planning device for an unmanned platform provided in an embodiment of this application.

[0041] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0042] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0043] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0044] Terminology explanation.

[0045] Complex unstructured environments: Irregular scenes containing a variety of different elements, which are not suitable for description using simple, regular structures (such as mountains, hills, etc.).

[0046] Three-dimensional path planning method: Considering the passability of unmanned platforms in complex unstructured environments, find a reasonable path from the starting point to the destination.

[0047] DEM map: Short for Digital Elevation Model. A digital model used to represent surface elevation information, describing terrain by storing surface elevation data in a matrix format in a raster.

[0048] A * Algorithm: A commonly used path search and graph traversal algorithm, typically used to solve shortest path or minimum cost problems.

[0049] The unmanned platform three-dimensional path planning method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on another server. Terminal 102 can send a DEM map of the target area to server 104. After receiving the DEM map, server 104 extracts the elevation information of the target grid cells from the DEM map, calculates the slope, step size, and unevenness of the target grid cells, and calculates the passability of the target grid cells based on the slope, step size, and unevenness. Based on the passability of all target grid cells and a set cost threshold, adjacent target grid cells are grouped to obtain several low-cost areas. All low-cost areas constitute a low-cost map of the target area. Based on the low-cost map, the coordinates of each low-cost area in the low-cost map, and obstacle information, path planning is performed to obtain the final planned path. Server 104 can feed back the obtained final planned path for the target area to terminal 102. In addition, in some embodiments, the unmanned platform 3D path planning method can also be implemented by the server 104 or the terminal 102 separately. For example, the terminal 102 can directly perform unmanned platform 3D path planning processing on the DEM map of the target area, or the server 104 can obtain the DEM map of the target area from the data storage system and perform unmanned platform 3D path planning processing on the DEM map of the target area.

[0050] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, and tablets. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers, or it can be a cloud server.

[0051] In one exemplary embodiment, such as Figure 2 As shown, a three-dimensional path planning method for an unmanned platform is provided. This method is executed by a computer device, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps 201 to 207.

[0052] Step 201: Obtain the DEM map of the target area.

[0053] Step 202: For each target grid cell in the DEM map, extract the elevation information of the target grid cell to obtain the elevation information of the target grid cell.

[0054] Step 203: Calculate the slope and step size of the target grid cell based on the elevation information of the target grid cell and the elevation information of the adjacent grid cells.

[0055] Step 204: Calculate the unevenness of the target grid cell based on its elevation information.

[0056] Step 205: Calculate the passability of the target grid cell based on its slope, step size, and unevenness; the passability represents the cost for the unmanned platform to pass through the area corresponding to the target grid cell.

[0057] Step 206: Based on the passability of all the target grid cells and the set cost threshold, the adjacent target grid cells are grouped together to obtain several low-cost regions; each low-cost region includes passable areas and / or impassable areas; all low-cost regions constitute a low-cost map of the target region.

[0058] Step 207: Based on the low-cost map, the coordinates of each low-cost region in the low-cost map, and obstacle information, perform path planning to obtain the final planned path.

[0059] Implementing steps 201 to 207 above, this application proposes a map preprocessing method that fully considers the impact of terrain factors on the mobility of unmanned platforms, addressing the lack of map preprocessing for complex unstructured environments in current path planning algorithms. This method can calculate the corresponding cost map required for planning from the DEM map and simultaneously mark low-cost areas. While feeding back terrain factors, it also pre-processes some planning calculations, saving subsequent planning time. To address the current lack of a planning algorithm that fully considers terrain factors and the mobility of unmanned platforms, this application proposes a cost map-based planning algorithm. Based on the cost map, terrain feature factors in the environment are added to A... * Based on this, a new search method is proposed in the algorithm's heuristic function, which improves the rationality of the planned path.

[0060] In another exemplary embodiment of this application, the map of the complex unstructured environment is first preprocessed as follows: Figure 3 As shown, step 201 above is replaced by steps 301 to 303.

[0061] Step 301: Use lidar mapping technology, radar elevation measurement technology, photogrammetry technology or satellite remote sensing technology to obtain detailed surface elevation data of the target area.

[0062] Step 302: Preprocess the detailed surface elevation data to obtain preprocessed data; preprocessing includes data cleaning, noise reduction and correction.

[0063] Step 303: Perform interpolation on the preprocessed data to obtain the DEM map of the target area.

[0064] The proposed method is a map preprocessing method that incorporates terrain factors. It extracts information about slope, step length, and unevenness from the map to determine the passage cost of an unmanned platform in each area.

[0065] First, detailed surface elevation data is acquired using technologies such as lidar mapping, radar elevation measurement, photogrammetry, or satellite remote sensing. Then, data cleaning, noise reduction, and correction steps are performed to ensure accuracy and consistency. In some cases, due to limited spatial resolution of the acquired data, interpolation techniques are used to fill in gaps between data points to obtain complete elevation data. After preprocessing and interpolation, a complete digital elevation model (DEM) can be generated, and the elevation data is stored in raster format to form a DEM map.

[0066] DEM maps provide detailed data on surface elevation, showcasing terrain features such as undulations, mountains, and rivers. Furthermore, DEM data is stored in raster format, with each pixel representing elevation information within a specific area, facilitating processing and analysis within a Geographic Information System (GIS).

[0067] In another exemplary embodiment of this application, the process of obtaining the cost map is as follows: Figure 4 As shown, the elevation Z(i,j) of each target grid cell is extracted based on the DEM map.

[0068] Step 203 above may include steps 401 to 404.

[0069] Step 401: Calculate the partial derivatives of the target grid cell in the x-direction and the partial derivatives in the y-direction based on the elevation information of the target grid cell and the elevation information of the adjacent grid cells.

[0070] Step 402: Calculate the slope of the target mesh cell based on the partial derivatives of the target mesh cell in the x-direction and the y-direction.

[0071] Step 403: Calculate the elevation difference between each adjacent grid cell and the target grid cell based on the elevation information of the target grid cell and its adjacent grid cells.

[0072] Step 404: Determine the step size of the target grid cell by the elevation difference with the largest value.

[0073] Based on the elevation information of the target grid cell and the elevation information of the adjacent grid cells, the partial derivative of each target grid cell (i,j) in the x-direction is calculated using the following formula. partial derivatives in the y-direction

[0074]

[0075] In the formula, dz(i+1,j) For target mesh element z (i+1,j) Elevation information, dz(i-1,j) For target mesh cells (i-1,j) The elevation information is given by dz(i,j+1) and dz(i,j-1). (i+1,j) , (i-1,j) z(i,j+1) and z(i,j-1) are adjacent grid cells of the target grid cell (i,j).

[0076] The partial derivative of the target mesh element (i,j) in the x-direction is obtained. partial derivatives in the y-direction Then, the slope θ(i,j) of the target grid cell is calculated according to the following formula.

[0077]

[0078] The step size δ(i,j) of the target grid cell is represented by the maximum elevation difference between the target grid cell and its neighboring grid cells in the Z direction.

[0079] The roughness of a target mesh cell characterizes the non-uniformity of the corresponding region. To calculate the roughness of a target mesh cell, the elevation Z of the mesh and its eight adjacent target mesh cells needs to be extracted. Considering the influence of the wheel diameter, the standard deviation of the elevations of these nine target mesh cells is divided by the wheel diameter to quantify the roughness information. Thus, the roughness ω(i,j) of the target mesh cell is calculated. The formula for calculating the roughness of a target mesh cell is shown below.

[0080]

[0081] Where D is the wheel diameter of the unmanned platform, Z(i,j) is the elevation information of the target grid cell, and -z is the standard deviation of the elevation of the target grid cell and the grid cells adjacent to the target grid cell.

[0082] To quantify the traversal cost of the map, the traversability of the target grid cell (i,j) is represented by T(i,j)∈[0,1], which includes the slope, step size, and unevenness of the target grid cell. The traversability of the unmanned platform at this grid is determined by this value; a value close to 1 indicates poor traversability, and a value close to 0 indicates good traversability. The formula for calculating the traversability of the target grid cell is shown below.

[0083]

[0084] Where T(i,j) represents the passability of the target grid cell (i,j), k1, k2, and k3 are the weights of slope, step size, and unevenness, respectively, and the sum of parameters k1, k2, and k3 is 1, all being non-negative values; θ(i,j) represents the slope of the target grid cell (i,j), δ(i,j) represents the step size of the target grid cell (i,j), ω(i,j) represents the unevenness of the target grid cell (i,j), and θ... crit δ crit and ω crit These represent the maximum terrain feature factor thresholds that the unmanned platform can navigate for slope, step size, and unevenness, respectively. Furthermore, when the value of any terrain feature factor (slope, step size, or unevenness) exceeds its corresponding threshold, T(i,j) is set to 1, indicating that the target grid cell cannot be passed; conversely, T(i,j) is set to 0, indicating that the target grid cell can be passed.

[0085] After obtaining the cost map, a small cost threshold is set based on the unmanned platform's mobility, meaning the platform incurs almost no cost when passing through these areas. The coordinates of these large, low-cost areas are then recorded. Based on the resolution of the grid cells in the map and specific mission requirements, a positive integer N is set. Within a continuous region of N*N target grid cells, if the cost of passing through each target grid cell is less than the previously set cost threshold, that region is considered a low-cost region.

[0086] An improved planning algorithm based on a cost map is used for path planning. To enhance the algorithm's performance in complex, unstructured environments, terrain features such as slope, step size, and unevenness are integrated into the algorithm's heuristic function. Step 207 may specifically include steps 501 to 507.

[0087] Step 501: Determine if the current node is the endpoint; the node is a low-cost region.

[0088] Step 502: If the current node is not the endpoint, remove the current node from the open list and add the current node to the closed list.

[0089] Step 503: Determine whether the current node is in the low-cost region.

[0090] Step 504: If the current node is within the low-cost region, select the nearest neighbor node as the new current node, set the current node as the parent node of the new current node, and remove the low-cost region; the nearest neighbor node is the node with the smallest distance to the destination within the low-cost region; the distance is calculated from the coordinates of the low-cost region corresponding to the node and the destination.

[0091] Step 505: If the current node is not in the low-cost region, obtain the neighboring nodes of the current node and perform the following operations on each neighboring node: If the neighboring node is in the closed list or there is an obstacle, skip the neighboring node; calculate the actual cost from the current node to the neighboring node; the actual cost includes distance cost and difference cost; select the neighboring node with the lowest actual cost as the new current node, and set the current node as the parent node of the new current node; the distance cost includes the distance from the current node to the neighboring node and the distance from the current node to the destination.

[0092] Step 506: Repeat steps 501 to 505 above until the current node is the endpoint.

[0093] Step 507: Starting from the end node, trace back to the starting point along the parent node of each node to construct the final planned path; the end node is the destination.

[0094] When searching for the next node, in addition to the traditional distance cost, the classic A algorithm is enhanced by incorporating differential costs that include terrain features. * The algorithm's heuristic function. To calculate this difference cost, first extract the passability parameter T(i,j)∈[0,1] for each point on the cost map. Then, use the formula to calculate the difference cost T between the current node and its neighboring nodes. diff .

[0095]

[0096] The distance cost c1 from the current node to its neighboring nodes is calculated using the Euclidean distance algorithm.

[0097]

[0098] The actual cost c associated with the current node and its neighboring nodes t The calculation formula is shown below.

[0099]

[0100] H n It is a classic A * The heuristic function in the algorithm represents the distance from the neighboring node to the endpoint, and is calculated using the following formula.

[0101]

[0102] In the formula, T n T represents the passability of the low-cost region corresponding to the current node. c For the passability of the low-cost regions corresponding to the neighboring nodes of the current node, (x n ,y n ,z n (x) represents the coordinates of the low-cost region corresponding to the current node. c ,y c ,z c (x) represents the coordinates of the low-cost regions corresponding to the neighboring nodes of the current node. g ,y g ,z g () is the coordinate of the endpoint.

[0103] It is important to note that the low-cost map generated from the previous map processing is extracted first. This low-cost map records the coordinates of M (n×n) low-cost regions, denoted as {U1, U2, U3...U...}. m If the current node's coordinates are in these low-cost regions U m Unlike typical stepwise searches, this algorithm directly selects the point within the cost region closest to the target as the next node, thereby reducing unnecessary computation and optimizing the search process.

[0104] This application also provides an application scenario in which the aforementioned unmanned platform 3D path planning method is applied. Specifically, the unmanned platform 3D path planning method provided in this embodiment can be applied in unmanned platform driving scenarios. An unmanned platform driving scenario includes an information acquisition stage, an unmanned platform 3D path planning link, and a driving stage; the DEM map of the target area enters the unmanned platform 3D path planning link from the information acquisition stage to obtain the corresponding final planned path, and then enters the downstream driving stage. The unmanned platform 3D path planning method provided in this embodiment belongs to the unmanned platform 3D path planning link. Specifically, in the process of 3D path planning for unmanned platforms based on video, the elevation information of target grid cells in the DEM map can be extracted to obtain the elevation information of the target grid cells. The slope, step size, and unevenness of the target grid cells can then be calculated. Based on the slope, step size, and unevenness of the target grid cells, the passability of the target grid cells can be calculated. Based on the passability of all target grid cells and a set cost threshold, adjacent target grid cells are grouped together to obtain several low-cost areas. All low-cost areas constitute a low-cost map of the target area. Based on the low-cost map, the coordinates of each low-cost area in the low-cost map, and obstacle information, path planning is performed to obtain the final planned path.

[0105] Based on the same inventive concept, this application also provides an unmanned platform three-dimensional path planning device for implementing the unmanned platform three-dimensional path planning method described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more unmanned platform three-dimensional path planning device embodiments provided below can be found in the limitations of the unmanned platform three-dimensional path planning method above, and will not be repeated here.

[0106] In one exemplary embodiment, such as Figure 5 As shown, a three-dimensional path planning device for an unmanned platform is provided, comprising the following modules.

[0107] The DEM map acquisition module T1 is used to acquire the DEM map of the target area.

[0108] The elevation information extraction module T2 is used to: extract the elevation information of each target grid cell in the DEM map to obtain the elevation information of the target grid cell.

[0109] The slope and step length calculation module T3 is used to calculate the slope and step length of the target grid cell based on the elevation information of the target grid cell and the elevation information of the adjacent grid cells of the target grid cell.

[0110] The unevenness calculation module T4 is used to calculate the unevenness of the target grid cell based on the elevation information of the target grid cell.

[0111] The passability calculation module T5 is used to: calculate the passability of the target grid cell based on the slope, step size, and unevenness of the target grid cell; the passability represents the cost for the unmanned platform to pass through the area corresponding to the target grid cell.

[0112] The low-cost region determination module T6 is used to: group adjacent target grid cells together based on the passability of all the target grid cells and a set cost threshold to obtain several low-cost regions; each low-cost region includes passable areas and / or impassable areas; all low-cost regions constitute a low-cost map of the target region.

[0113] The path planning module T7 is used to: perform path planning based on the low-cost map, the coordinates of each low-cost area in the low-cost map, and obstacle information to obtain the final planned path.

[0114] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 6As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores 3D path planning processing data for the unmanned platform. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a 3D path planning method for an unmanned platform.

[0115] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0116] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0117] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0118] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0119] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0120] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0121] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0122] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A three-dimensional path planning method for an unmanned platform, characterized in that, The unmanned platform three-dimensional path planning method includes: Obtain the DEM map of the target area; For each target grid cell in the DEM map, the elevation information of the target grid cell is extracted to obtain the elevation information of the target grid cell; The slope and step size of the target grid cell are calculated based on the elevation information of the target grid cell and the elevation information of the adjacent grid cells. The unevenness of the target grid cell is calculated based on the elevation information of the target grid cell; The passability of the target grid cell is calculated based on its slope, step size, and unevenness; the passability represents the cost for the unmanned platform to pass through the area corresponding to the target grid cell. Based on the passability of all the target grid cells and the set cost threshold, adjacent target grid cells are grouped together to obtain several low-cost regions; each low-cost region includes passable and / or impassable regions; all low-cost regions constitute a low-cost map of the target region. Based on the low-cost map, the coordinates of each low-cost region in the low-cost map, and obstacle information, path planning is performed to obtain the final planned path.

2. The unmanned platform three-dimensional path planning method according to claim 1, characterized in that, Based on the low-cost map, the coordinates of each low-cost region in the low-cost map, and obstacle information, path planning is performed to obtain the final planned path, specifically including: Determine if the current node is the endpoint; the node is a low-cost region. If the current node is not the endpoint, remove the current node from the open list and add the current node to the closed list; Determine whether the current node is within the low-cost region; If the current node is within the low-cost region, select the nearest neighbor node as the new current node, set the current node as the parent node of the new current node, and remove the low-cost region; the nearest neighbor node is the node with the smallest distance to the destination within the low-cost region; the distance is calculated from the coordinates of the low-cost region corresponding to the node and the destination. If the current node is not in the low-cost region, obtain the neighboring nodes of the current node, and perform the following operations on each neighboring node of the current node: if the neighboring node is in the closed list or there is an obstacle, skip the neighboring node; calculate the actual cost from the current node to the neighboring node; the actual cost includes distance cost and difference cost; select the neighboring node with the lowest actual cost as the new current node, and set the current node as the parent node of the new current node; Repeat the above steps until the current node is the endpoint; Starting from the end node, trace back to the starting point along the parent node of each node to construct the final planned path; the end node is the destination.

3. The unmanned platform three-dimensional path planning method according to claim 1, characterized in that, Obtain the DEM map of the target area, specifically including: Detailed surface elevation data of the target area are obtained by using lidar mapping technology, radar elevation measurement technology, photogrammetry technology or satellite remote sensing technology. The detailed surface elevation data is preprocessed to obtain preprocessed data; The preprocessed data is then interpolated to obtain a DEM map of the target area.

4. The unmanned platform three-dimensional path planning method according to claim 1, characterized in that, The slope and step size of the target grid cell are calculated based on the elevation information of the target grid cell and the elevation information of the adjacent grid cells. Specifically, this includes: Calculate the partial derivatives of the target grid cell in the x-direction and the partial derivatives in the y-direction based on the elevation information of the target grid cell and the elevation information of the adjacent grid cells of the target grid cell; The slope of the target mesh cell is calculated based on the partial derivatives of the target mesh cell in the x-direction and the partial derivatives in the y-direction. Based on the elevation information of the target grid cell and its adjacent grid cells, calculate the elevation difference between each adjacent grid cell and the target grid cell. The target grid cell and step size are determined by the elevation difference with the largest value.

5. The three-dimensional path planning method for unmanned platforms according to claim 1, characterized in that, The formula for calculating the unevenness of the target mesh element is as follows: Where ω(i,j) represents the unevenness of the target mesh element (i,j), D represents the wheel diameter of the unmanned platform, and Z(i,j) represents the elevation information of the target mesh element. The standard deviation of the elevation of the target grid cell and the grid cells adjacent to the target grid cell.

6. The three-dimensional path planning method for unmanned platforms according to claim 1, characterized in that, The formula for calculating the passability of the target grid cell is as follows: Where T(i,j) represents the passability of the target grid cell (i,j), k1, k2, and k3 are the weights of slope, step size, and unevenness, respectively, θ(i,j) is the slope of the target grid cell (i,j), δ(i,j) is the step size of the target grid cell (i,j), ω(i,j) is the unevenness of the target grid cell (i,j), and θ crit δ crit and ω crit These represent the maximum terrain feature factor thresholds corresponding to slope, step length, and unevenness, respectively.

7. The unmanned platform three-dimensional path planning method according to claim 2, characterized in that, The distance cost includes the distance from the current node to its neighboring nodes and the distance from the current node to the destination.

8. A three-dimensional path planning device for an unmanned platform, characterized in that, The unmanned platform three-dimensional path planning device includes: The DEM map acquisition module is used to: acquire the DEM map of the target area; The elevation information extraction module is used to: extract the elevation information of each target grid cell in the DEM map to obtain the elevation information of the target grid cell; The slope and step size calculation module is used to: calculate the slope and step size of the target grid cell based on the elevation information of the target grid cell and the elevation information of the adjacent grid cells of the target grid cell; The unevenness calculation module is used to: calculate the unevenness of the target grid cell based on the elevation information of the target grid cell; The passability calculation module is used to: calculate the passability of the target grid cell based on its slope, step size, and unevenness; the passability represents the cost for the unmanned platform to pass through the area corresponding to the target grid cell; The low-cost region determination module is used to: group adjacent target grid cells together based on the passability of all the target grid cells and a set cost threshold to obtain several low-cost regions; each low-cost region includes passable and / or impassable regions; all low-cost regions constitute a low-cost map of the target region. The path planning module is used to: perform path planning based on the low-cost map, the coordinates of each low-cost area in the low-cost map, and obstacle information to obtain the final planned path.

9. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the unmanned platform three-dimensional path planning method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the unmanned platform three-dimensional path planning method as described in any one of claims 1-7.

Images