Path planning method, electronic device, storage medium and computer program product

Abstract

The application provides a path planning method, an electronic device, a storage medium and a computer program product. The method comprises the following steps: acquiring environment data of a work area, wherein the environment data comprises obstacle data and radiation field data; generating a passable graph corresponding to the work area based on the obstacle data; the passable graph represents a passable state corresponding to each grid unit; constructing a risk graph corresponding to the work area based on the radiation field data; the risk graph represents a residual radiation risk cost corresponding to each grid unit, and the residual radiation risk cost reflects a residual radiation dose from the grid unit to a target position; and planning a work path from a starting position to the target position based on the passable graph and the risk graph, so as to obtain a target work path, wherein the passable state is used as a constraint condition, and the total radiation risk cost is minimized. The application scheme can meet the demand for path planning in a radiation environment.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a path planning method, electronic device, storage medium, and computer program product. Background Technology

[0002] Path planning is a core technology in the field of autonomous navigation. Essentially, it involves searching for a feasible path from a starting position to a target position within a known or unknown environment containing obstacles. Path planning technology is widely used in various application scenarios such as smart warehousing, autonomous driving, and exploration operations.

[0003] In tasks involving radiation scenarios such as nuclear facility inspection, radioactive environment detection, nuclear accident emergency response, and radioactive material transportation, path planning must be completed in an environment where radiation sources coexist with complex obstacles. Compared with conventional operating scenarios, radiation environments are characterized not only by strong terrain constraints and chaotic obstacle distribution, but also by uneven spatial distribution of radiation fields. The path selection directly determines the amount of radiation received.

[0004] Currently, path planning schemes typically optimize for the shortest geometric path or the shortest travel time. However, these planned paths may traverse high-radiation areas, subjecting the equipment to higher cumulative radiation doses, potentially causing radiation damage, reducing equipment reliability, and compromising mission effectiveness. Therefore, current path planning schemes are insufficient to meet the demands of path planning in radiation environments. Summary of the Invention

[0005] This application provides a path planning method, an electronic device, a storage medium, and a computer program product.

[0006] The technical solution of this application embodiment is implemented as follows: This application provides a path planning method, the method comprising: Acquire environmental data of the work area, including obstacle data and radiation field data; Based on the obstacle data, a passage map corresponding to the work area is generated; wherein, the passage map represents the passage status corresponding to each grid cell, and the passage status includes a passable state and a non-passable state; Based on the radiation field data, a risk map corresponding to the work area is constructed; wherein, the risk map represents the residual radiation risk cost corresponding to each grid cell, and the residual radiation risk cost reflects the residual radiation dose from the grid cell to the target location; Based on the access map and the risk map, with the goal of minimizing the total radiation risk cost and the constraint of passability, the operation path from the starting position to the target position is planned to obtain the target operation path.

[0007] In the above scheme, constructing a risk map corresponding to the work area based on the radiation field data includes: Based on the radiation field data, a first risk map is constructed; wherein the resolution of the first risk map is smaller than the resolution of the access map; The first risk map is interpolated to obtain a second risk map, wherein the resolution of the second risk map is greater than the resolution of the first risk map, and the resolution of the second risk map is the same as the resolution of the access map; Based on the accessibility map and the risk map, with the objective of minimizing the total radiation risk cost and the constraint of passability status, the operation path from the starting position to the target position is planned to obtain the target operation path, including: Based on the access map and the second risk map, with the goal of minimizing the total radiation risk cost and the constraint of passability, the operation path from the starting position to the target position is planned to obtain the target operation path.

[0008] In the above scheme, constructing a first risk map based on the radiation field data includes: Based on the radiation field data, a first radiation matrix corresponding to the work area is determined; wherein, the first radiation matrix represents the radiation field distribution of the work area; The first radiation matrix is ​​downsampled to obtain a second radiation matrix; wherein the resolution of the second radiation matrix is ​​smaller than that of the first radiation matrix. Based on the second radiation matrix, a first risk map is constructed.

[0009] In the above scheme, constructing the first risk map based on the second radiation matrix includes: A mesh graph is established based on the second radiation matrix, wherein the vertices of the mesh graph represent grid cells of the first resolution, and the connecting edges of the mesh graph represent the adjacency relationship between different grid cells; the first resolution is consistent with the resolution of the second radiation matrix. The risk cost weight of the corresponding connecting edge is determined based on the edge radiation risk cost between each group of adjacent grid cells; wherein, the edge radiation risk cost reflects the radiation dose between adjacent grid cells; Using the target vertex as the search source point, the shortest path between each vertex and the search source point is searched in the grid graph based on the sum of the risk cost weights of one or more connecting edges between each vertex and the search source point; wherein, the target vertex corresponds to the grid cell corresponding to the target position; Based on the sum of the risk cost weights of the shortest path between each vertex and the search source point, the residual radiation risk cost corresponding to the grid cell is determined, and the first risk map is obtained.

[0010] In the above scheme, the radiation field data is three-dimensional radiation field data; the method further includes: For each 3D mesh cell at the same planar coordinate position, determine the overlap height between each 3D mesh cell and the preset height range; By utilizing the overlap height of each three-dimensional mesh cell with a preset height range, a weighted average is performed on multiple three-dimensional mesh cells at the same planar coordinate position to obtain two-dimensional radiation field data at the same planar coordinate position; The construction of a risk map corresponding to the work area based on the radiation field data includes: Based on the two-dimensional radiation field data, a risk map corresponding to the work area is constructed.

[0011] In the above scheme, based on the access map and the risk map, with the goal of minimizing the total radiation risk cost and with accessibility as a constraint, the operation path from the starting position to the target position is planned to obtain the target operation path, including: Based on the access map, identify the passable cells that are in a passable state among the multiple grid cells in the work area; Determine the edge radiation risk cost of one or more groups of adjacent passable cells; Based on the edge radiation risk cost of one or more adjacent passable units and the residual radiation risk cost corresponding to the passable units in the risk map, starting from the grid unit corresponding to the starting position, one or more rounds of neighborhood search are performed on the passable units to obtain the target operation path from the starting position to the target position.

[0012] In the above scheme, the step of taking the grid cell corresponding to the starting position as the starting point and performing one or more rounds of neighborhood search on the passable cells to obtain the target operation path from the starting position to the target position includes: Starting from the grid cell corresponding to the starting position, perform one or more rounds of neighborhood search for the passable cell; In each round of neighborhood search, if the candidate grid cell found is not the grid cell corresponding to the target location, the accumulated radiation risk cost corresponding to the adjacent cell and the remaining radiation risk cost corresponding to the adjacent cell are determined; wherein, the adjacent cell is a passable cell adjacent to the candidate grid cell, and the accumulated radiation risk cost is the sum of the edge radiation risk costs of one or more sets of adjacent passable cells from the grid cell corresponding to the starting location to the adjacent cell; Based on the accumulated radiation risk cost of the adjacent unit and the remaining radiation risk cost of the adjacent unit, the evaluation value corresponding to the adjacent unit is determined. The evaluation value is used to assess the total radiation risk cost of the operation path passing through the adjacent unit. The candidate grid cells for the next round of neighborhood search are determined based on the evaluation values ​​of each adjacent cell. If the candidate grid cell is the grid cell corresponding to the target position, the target operation path is obtained by tracing back from the grid cell corresponding to the target position to the grid cell corresponding to the starting position.

[0013] This application provides an electronic device, including: a processor and a memory for storing computer programs capable of running on the processor; The processor is used to execute the path planning method provided in the embodiments of this application when running a computer program.

[0014] This application provides a computer-readable storage medium storing a computer program or computer-executable instructions for implementing the path planning method provided in this application when executed by a processor.

[0015] This application provides a computer program product, including a computer program or computer executable instructions, which, when executed by a processor, implements the path planning method provided in this application.

[0016] The path planning method, electronic device, storage medium, and computer program product provided in this application generate a access map and a risk map corresponding to the work area by acquiring environmental data of the work area. The access map reflects the accessibility of the work area and provides obstacle clearance constraints for path planning; the risk map provides the radiation risk distribution of the work area and provides global radiation risk guidance for path planning. By combining the access map and the risk map, a work path planning from the starting position to the target position is realized, taking into account both path accessibility and radiation safety. It fully utilizes the spatial distribution characteristics of the radiation field. Under the influence of the global radiation risk distribution provided by the risk map, not only is globally optimal path planning achieved, but also invalid path searches are reduced, improving path planning efficiency. This ensures that the target work path avoids obstacles and high-radiation areas, meeting the needs of path planning in complex work scenarios and improving the rationality and reliability of path planning in complex work scenarios. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the path planning method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the process for generating the first risk map provided in the embodiments of this application; Figure 3 This is a flowchart illustrating the neighborhood search process provided in an embodiment of this application; Figure 4 This is a schematic diagram illustrating the relationship between dual-resolution data provided in the embodiments of this application; Figure 5 This is a schematic diagram of the path planning device provided in the embodiments of this application; Figure 6 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the application will now be described in further detail with reference to the accompanying drawings.

[0019] In radiation environments, robots or autonomous operating systems are typically used for path planning and navigation to complete tasks. If only geometric path length or travel time is used as the optimization objective for path planning, the planned path may pass through high-radiation areas, subjecting robots and other operating equipment to high cumulative radiation doses, affecting equipment safety and task execution effectiveness.

[0020] Currently, path planning solutions for radioactive work scenarios mainly include the following categories: 1. Path planning scheme based on Dijkstra's algorithm. This scheme incorporates radiation dose information into the edge cost of the grid network, which can solve for low radiation dose paths for discrete grid nodes. However, in high-resolution and complex operating environments, calculating the minimum risk reach value for all grid nodes will result in a large search scale and computational load.

[0021] 2. Based on A The algorithm's path planning scheme uses radiation dose, geometric distance, or a weighted average of the two as the basis for calculating path cost and heuristic cost. The remaining cost is estimated by the radiation field value of the grid node, the geometric distance between the node and the target location, or a weighted average of the two. However, heuristic information can only reflect the local radiation state and geometric position relationship, which can easily lead to a decrease in search efficiency and the path planning result getting trapped in a local suboptimal solution.

[0022] 3. Based on Rapidly Expanding Random TreeStar (RRT) The path planning scheme is based on the Rapidly-exploring Random Trees Star (RADS) algorithm. This scheme is suitable for path planning in continuous radiation fields, dynamic disturbances, and large-scale unknown nuclear environments. However, due to the randomness of sampling and the asymptotic convergence characteristics, its stability and timeliness are still significantly insufficient in operational scenarios that require stable path reproduction or rapid solution of low-radiation-risk paths.

[0023] It is evident that the current path planning schemes in radiation environments suffer from the following main problems: First, most path planning schemes still rely primarily on geometric distance or local costs for optimization, making it difficult to balance path efficiency and radiation safety in the planning results. Second, many path planning schemes are limited to cost function reconstruction or local weight parameter adjustments, lacking heuristic guidance mechanisms that can reflect the global radiation risk distribution characteristics, resulting in low search efficiency. Third, in operational scenarios with dense obstacles and complex radiation field distributions, the current path planning schemes still fall short in terms of computational efficiency, environmental adaptability, and real-time planning performance, making it difficult to meet the high safety, high robustness, and high real-time requirements of path planning in complex nuclear facility operational scenarios.

[0024] Based on this, embodiments of this application provide a path planning scheme to solve at least some of the aforementioned technical problems. In the scheme provided by embodiments of this application, environmental data of the work area is acquired to generate a access map and a risk map corresponding to the work area. The access map reflects the accessibility of the work area and provides obstacle clearance constraints for path planning; the risk map provides the radiation risk distribution of the work area and provides global radiation risk guidance for path planning. By combining the access map and the risk map, a work path planning from the starting position to the target position is achieved, balancing path accessibility and radiation safety. It fully utilizes the spatial distribution characteristics of the radiation field. Under the influence of the global radiation risk distribution provided by the risk map, not only is globally optimal path planning achieved, but also invalid path searches are reduced, improving path planning efficiency. The resulting path planning result (i.e., the target work path) avoids obstacles and high-radiation areas, meeting the needs of path planning in complex work scenarios and improving the rationality and reliability of path planning in complex work scenarios.

[0025] The following describes the path planning scheme provided in the embodiments of this application, using an electronic device as the execution subject. The electronic device provided in the embodiments of this application can be a terminal device or a backend device with path planning capabilities. For example, the electronic device can be a robot, an inspection terminal, a backend server, an edge device, etc., and the embodiments of this application do not limit it in this way.

[0026] First, the path planning method provided in the embodiments of this application will be introduced. For example... Figure 1 As shown, this path planning method includes the following steps: Step 101: Obtain environmental data of the work area, including obstacle data and radiation field data; Step 102: Based on obstacle data, generate a access map corresponding to the work area; the access map represents the access status corresponding to each grid cell, which includes passable status and inaccessible status; Step 103: Based on the radiation field data, construct a risk map corresponding to the work area; the risk map represents the residual radiation risk cost corresponding to each grid cell, which reflects the cumulative radiation dose from the grid cell to the target location; Step 104: Based on the access map and risk map corresponding to the work area, with the goal of minimizing the total radiation risk cost and the constraint of passability, plan the work path from the starting position to the target position to obtain the target work path.

[0027] In practical applications, electronic devices can actively collect environmental data from the work area. Alternatively, electronic devices can acquire environmental data from other devices.

[0028] In some implementations, electronic devices are terminal devices with path planning capabilities, such as mobile robots. These devices are equipped with sensing units such as radiation detection sensors, lidar, and cameras. They collect environmental data of the work area through these sensing units and perform path planning based on this data.

[0029] In other implementations, the electronic device is a backend device with path planning capabilities, such as a remote server. The electronic device receives environmental data of the work area transmitted by a data acquisition device (such as a mobile robot or other data acquisition device with data acquisition capabilities) and performs path planning based on the acquired environmental data. After path planning, the electronic device can also send the path planning results to the working device, enabling the working device to execute the task according to the path planning results. The working device and the data acquisition device can be the same device or different devices.

[0030] In this embodiment of the application, the environmental data of the work area includes obstacle data and radiation field data.

[0031] Obstacle data is used to represent the spatial distribution and morphological characteristics of obstacles within the work area. For example, obstacle data includes the location, outline boundaries, dimensions, and geometric information of obstacles. Electronic devices can collect obstacle data of the work area through sensing units or devices such as LiDAR, cameras, and ultrasonic sensors. In some implementations, electronic devices can also obtain obstacle data of the work area by importing a survey map of the work area.

[0032] Radiation field data is used to represent the radiation field distribution in the work area. For example, radiation field data can include radiation dose rate, radiation intensity, and other data. Electronic equipment can collect and interpolate radiation field data at multiple sampling points using radiation detectors deployed in the work area. Alternatively, electronic equipment can simulate the radiation field of the work area using Monte Carlo simulation software to obtain the radiation field data for the work area.

[0033] In practical applications, electronic devices establish a unified real coordinate system for the work area, such as a two-dimensional coordinate system. After establishing the coordinate system, the electronic devices acquire data on the area boundaries and obstacles within that coordinate system. To ensure data consistency and spatial matching within the work area, the electronic devices acquire radiation field data using the same origin, axis directions, length units, and spatial range as the established coordinate system, such as two-dimensional radiation field data. This ensures complete alignment between obstacle data and radiation field data, eliminating spatial offset errors between multi-source environmental data.

[0034] The radiation field data initially acquired by the electronic device can be either two-dimensional or three-dimensional. When the radiation field data is two-dimensional, the electronic device matches it to the established coordinate system, achieving coordinate consistency between the radiation field data and obstacle data. When the radiation field data is three-dimensional, the electronic device first converts the three-dimensional radiation field data into two-dimensional radiation field data, and then matches the two-dimensional radiation field data to the established coordinate system.

[0035] In some implementations, when the radiation field data is three-dimensional radiation field data, for example, when the radiation field data is three-dimensional radiation field data in the form of a three-dimensional mesh, the electronic device will determine the overlap height between each three-dimensional mesh cell and a preset height range for each three-dimensional mesh cell at the same planar coordinate position. Then, using the overlap height between each three-dimensional mesh cell and the preset height range, a weighted average will be performed on multiple three-dimensional mesh cells at the same planar coordinate position to obtain two-dimensional radiation field data at the same planar coordinate position.

[0036] For example, the formula for converting three-dimensional radiation field data into two-dimensional radiation field data is as follows: Formula (1) in, Representing coordinates 3D mesh cells at the location The three-dimensional radiation field value (i.e., three-dimensional radiation field data); This represents the overlap height between the k-th 3D mesh cell and a preset height range in the height direction; Represented as the projection of a 3D mesh element onto the xy plane The location corresponds to the two-dimensional radiation field value (i.e., two-dimensional radiation field data). After projection transformation, the three-dimensional radiation field data is uniformly mapped to the two-dimensional radiation field data in the two-dimensional coordinate system, realizing the coordinate alignment between the radiation field data and the obstacle data.

[0037] Understandably, the preset height range can be set according to actual application requirements. For example, the preset height range corresponds to the operating height of the work equipment, and can be flexibly adjusted according to the size, access height, and operating posture of the work equipment. By setting a reasonable preset height range, radiation field data outside the operating height can be filtered out, retaining only the radiation field data within the operating height area of ​​the work equipment. This reduces interference from invalid radiation field data, enabling the two-dimensional radiation field data to accurately reflect the actual radiation exposure level experienced by the work equipment during operation, thus improving the adaptability and accuracy of path planning.

[0038] After acquiring obstacle data and radiation field data for the work area, in step 102, the electronic device generates a access map corresponding to the work area based on the obstacle data. This access map represents the distribution of access status in the work area. Correspondingly, in step 103, the electronic device constructs a risk map corresponding to the work area based on the radiation field data. This risk map represents the remaining radiation risk cost corresponding to each grid cell.

[0039] It is understood that steps 102 and 103 are not sequential; the electronic device may execute step 102 first, or step 103 first, or the electronic device may execute steps 102 and 103 simultaneously. This application embodiment does not limit the order of steps 102 and 103.

[0040] To meet the requirements of path search calculations, after acquiring the environmental data of the work area, in some implementations, electronic devices rasterize the work area, such as dividing the work area into... The system uses high-resolution grid cells (i.e., second-resolution grid cells). Then, based on environmental data, the electronic equipment determines the accessibility and residual radiation risk cost corresponding to each grid cell, thus obtaining the accessibility map and risk map for the work area.

[0041] In some implementations, the electronic device determines whether an obstacle exists at the coordinates of each grid cell based on obstacle data. If an obstacle exists at the grid cell's coordinates, the corresponding passage status of the grid cell is set to "impeded." If no obstacle exists at the grid cell's coordinates, the corresponding passage status is set to "passable." The electronic device then generates a passage map corresponding to the work area based on the passage status of each grid cell.

[0042] For example, the coordinates of the grid cells are the coordinates of the grid center, and the passage map is represented by the passage matrix. For example, for any grid cell The electronic device determines whether an obstacle exists at the center coordinates of a grid cell based on obstacle data in the coordinate system, such as whether the grid center coordinates are inside an obstacle. If an obstacle exists at the grid center coordinates, the electronic device confirms that the passage status corresponding to that grid cell is a non-passage status and sets the passage status of that grid cell in the passage map to the first value, such as... If there are no obstacles at the center coordinates of the grid, the passage status corresponding to that grid cell is confirmed as passable. The electronic device sets the passage status of that grid cell in the passage map to the second value, such as... The electronic equipment generates a passage matrix corresponding to the work area based on the passage status of each grid cell. .

[0043] Accordingly, the electronic equipment determines the first radiation matrix corresponding to the work area based on the radiation field data, and then constructs a risk map of the work area based on the first radiation matrix. The first radiation matrix represents the radiation field distribution of the work area.

[0044] The first radiation matrix includes the radiation field values ​​corresponding to each grid cell in the working area. The electronic equipment determines the radiation field value corresponding to the coordinates of each grid cell, and then generates the first radiation matrix based on the radiation field values ​​corresponding to the coordinates of each grid cell.

[0045] For example, taking the grid cell coordinates as the grid center coordinates as an example, for any grid cell, if there is corresponding two-dimensional radiation field data for the grid center coordinates of the grid cell, then the two-dimensional radiation field value corresponding to the grid cell is used as the element value of the first radiation matrix corresponding to the grid cell. If there is no corresponding two-dimensional radiation field data for the grid center coordinates of the grid cell, the electronic device determines the two-dimensional radiation field value of the grid center coordinates through two-dimensional interpolation based on the two-dimensional radiation field values ​​of the coordinates adjacent to the grid center coordinates, and then uses the two-dimensional radiation field value obtained through two-dimensional interpolation as the element value of the first radiation matrix corresponding to the grid cell.

[0046] The resolution of the first radiation matrix is ​​the same as that of the passage matrix; both are generated based on raster cells of the same resolution (i.e., high-resolution raster cells). That is, the first radiation matrix and the passage matrix have the same row and column dimensions, and the same index position corresponds to the same raster cell in the work area. In some implementations, the electronic device can also synthesize the actual coordinate boundaries of the work area, the raster center coordinates of each raster cell, the first radiation matrix, and the passage matrix into a high-resolution map of the work area.

[0047] To reduce the computational overhead of pathfinding and improve the efficiency of risk map construction, in some implementations, when constructing the risk map based on the first radiation matrix corresponding to the work area, the electronic device first downsamples the first radiation matrix to obtain a second radiation matrix. Then, based on the second radiation matrix, the risk map corresponding to the work area is constructed. The resolution of the second radiation matrix is ​​lower than that of the first radiation matrix. By obtaining a low-resolution second radiation matrix through downsampling, and using the second radiation matrix to represent the global distribution characteristics of the radiation field in the work area, the computational load for constructing the risk map can be reduced, thus improving the efficiency of risk map construction.

[0048] Understandably, since the resolution of the second radiation matrix is ​​lower than that of the first radiation matrix, the first radiation matrix can also be called a high-resolution radiation matrix, and the second radiation matrix can also be called a low-resolution radiation matrix. A passage matrix with the same resolution as the first radiation matrix can also be called a high-resolution matrix. Correspondingly, the risk map constructed based on the second radiation matrix has the same resolution as the second radiation matrix, and this risk map can be called a first risk map or a low-resolution risk map.

[0049] For example, an electronic device can downsample a high-resolution radiation matrix using a uniform sampling method to obtain a low-resolution radiation matrix. The formula for converting a high-resolution radiation matrix to a low-resolution radiation matrix is ​​as follows: Formula (2) Formula (3) in, This represents the total number of rows in the high-resolution radiation matrix; represents the total number of columns in the high-resolution radiation matrix; i represents the row index of the high-resolution radiation matrix. ;j represents the column index of the high-resolution radiation matrix, ; This indicates the row index of the u-th row of the low-resolution radiation matrix that maps to the high-resolution radiation matrix; The column index indicating how the v-th column of the low-resolution radiation matrix maps to the high-resolution radiation moment; This represents the total number of rows in the low-resolution radiation matrix; This represents the total number of columns in the low-resolution radiometric matrix; u represents the row index of the low-resolution radiometric matrix. ; v represents the column index of the low-resolution radiation matrix, ; ,and .

[0050] The low-resolution radiation matrix represents the global trend of the radiation field in the work area and is independent of obstacle data, while obstacle data is fully preserved through the high-resolution access matrix. Electronic devices use the low-resolution radiation matrix to quickly estimate the overall radiation risk trend, providing heuristic guidance for path searching; during path planning, the electronic devices combine the high-resolution access matrix for fine-grained judgment. Unlike methods that simultaneously downsample the access matrix and radiation matrix, this embodiment only downsamples the radiation matrix, thereby reducing errors in judgment due to grid cell merging in narrow passages, obstacle gaps, and other small feasible areas.

[0051] When constructing the first risk map corresponding to the work area based on the second radiation matrix, in some implementations, the electronic device establishes a mesh map according to the second radiation matrix. The vertices of the mesh map represent grid cells of the first resolution (i.e., low-resolution grid cells), and the connecting edges of the mesh map represent the adjacency relationships between different grid cells. The first resolution is consistent with the resolution of the second radiation matrix; that is, the first resolution is less than the second resolution, the first resolution represents low resolution, and the second resolution represents high resolution.

[0052] For example, the electronic device uses the grid cell corresponding to each index in the second radiation matrix as the vertex of the mesh graph, and constructs connecting edges between the two vertices corresponding to two adjacent grid cells to obtain a mesh graph with four or eight neighborhood connections. .in, Represents a set consisting of multiple vertices. This represents the set of connecting edges. That is, the mesh graph corresponding to the second radiation matrix includes multiple vertices and multiple connecting edges.

[0053] Electronic devices can also determine the risk cost weight of corresponding connecting edges based on the edge radiation risk cost between each group of adjacent grid cells. This edge radiation risk cost reflects the radiation dose of a group of adjacent grid cells.

[0054] For example, for any two adjacent grid cells (i.e. a set of adjacent grid cells), the electronic device determines the radiation field value corresponding to each grid cell in the two adjacent grid cells in the second radiation matrix, and determines the edge radiation risk cost between the two adjacent grid cells based on the radiation field value corresponding to each grid cell and the distance between the two grid cells.

[0055] Using any two adjacent raster cells (i.e., low-resolution raster cells). and For example, electronic devices according to and The average value of the radiation field and the distance between their physical centers are used to determine... and The cost of side radiation risks.

[0056] In one example, the formula for calculating the edge radiation risk cost of two adjacent grid cells is as follows: Formula (4) in, Represents a group of adjacent grid cells and The physical distance of the physical center in the real coordinate system; Represents grid cells The radiation field value in the second radiation matrix; Represents grid cells The radiation field value in the second radiation matrix; express and The cost of side radiation risks.

[0057] In another example, taking the radiation field value as the radiation dose rate, the formula for calculating the edge radiation risk cost of two adjacent grid cells is as follows: Formula (5) in, Represents a group of adjacent grid cells and The physical distance of the physical center in the real coordinate system; Represents grid cells Radiation dose rate in the second radiation matrix; Represents grid cells Radiation dose rate in the second radiation matrix; express and The edge radiation risk cost, which represents the radiation dose; This indicates the moving speed of the operating equipment.

[0058] It is understandable that when the working equipment moves at a constant speed, due to For all work paths, the same positive constant is used. Minimizing the radiation risk cost of formula (4) is equivalent to minimizing the radiation risk cost of formula (5). When the work equipment is in variable speed motion, the operating speed of different road segments varies. In this case, the radiation risk cost is determined based on the operating speed corresponding to each road segment. Determine the edge radiation risk cost for each group of adjacent grid cells, that is, in formula (5) Replace with The radiation dose corresponding to each group of adjacent grid cells can be calculated.

[0059] After determining the edge radiation risk cost of each group of adjacent grid cells, the electronic device determines the edge radiation risk cost of each group of adjacent grid cells as the risk cost weight of the corresponding connecting edge, thereby setting the corresponding risk cost weight for the connecting edge in the mesh graph.

[0060] After constructing the mesh graph, the electronic device calculates the sum of the risk cost weights of one or more connecting edges between each vertex and the search source point, based on the risk cost weights of the connecting edges. Taking the grid cell corresponding to the target location as the target vertex as an example, the electronic device uses the target vertex as the search source point. Based on the sum of the risk cost weights, the electronic device searches for the shortest path between each vertex and the search source point in the mesh graph. Then, based on the sum of the risk cost weights of the shortest paths between each vertex and the search source point, it determines the residual radiation risk cost corresponding to the grid cell, thus obtaining the first risk map. The first risk map includes the residual radiation risk cost corresponding to each low-resolution grid cell.

[0061] For example, the electronic device uses the low-resolution raster cell corresponding to the target location as the vertex in the mesh graph as the search source point, and starts the iterative search from the search source point. The iterative relationship is as follows: Formula (6) in, The residual radiation risk cost from the grid cell corresponding to the target location to itself is 0; This represents the grid cell corresponding to the target location; This represents the minimum residual radiation risk cost of the grid cell corresponding to the target location from grid cell p; Indicates two adjacent grid cells and The cost of side radiation risks; This represents the minimum residual radiation risk cost of the grid cell corresponding to the target location from grid cell q. This represents the set of connecting edges in a mesh graph.

[0062] The following is combined Figure 2 The generation process of the first risk map is illustrated by example.

[0063] In constructing a grid diagram Next, the electronic device initializes the low-resolution risk map, setting the low-resolution grid cells corresponding to the target location. The residual radiation risk cost is set to 0, excluding low-resolution raster cells. The residual radiation risk cost of other low-resolution raster cells is set to infinity, and the target vertex corresponding to that raster cell is placed in a priority queue.

[0064] If the priority queue is not empty, the electronic device executes the following steps in a loop: The vertex corresponding to the grid cell with the lowest remaining radiation risk cost is retrieved from the priority queue. Then, all adjacent vertices of the grid cells adjacent to this grid cell are traversed. For each adjacent vertex, the sum of the risk cost weights of one or more connecting edges between each adjacent vertex and the search source point is calculated. This is equivalent to calculating the remaining radiation risk cost between each adjacent grid cell and the grid cell corresponding to the target location (i.e., the remaining radiation risk cost corresponding to each adjacent grid cell) (denoted as the first risk value). If the first risk value of any grid cell is less than the second risk value recorded in the low-resolution risk map, the remaining radiation risk cost of that grid cell in the low-resolution risk map is updated to the first risk value, and the grid cell is added to the priority queue.

[0065] After traversing all adjacent vertices corresponding to adjacent grid cells, the electronic device checks if the priority queue is empty. If the priority queue is not empty, the above steps are repeated. If the priority queue is empty, a low-resolution risk map is output, i.e., the first risk map is obtained.

[0066] Because the resolution of the first risk map is lower than that of the access map, in order to match the grid cells of the risk map and the access map in terms of spatial scale, in some implementations, after obtaining the first risk map, the electronic device performs interpolation processing on the first risk map to obtain a second risk map. The resolution of the second risk map is higher than that of the first risk map, and consistent with the resolution of the access map. The second risk map can also be called a high-resolution risk map.

[0067] For example, the electronic device will display the high-resolution grid cells corresponding to the high-resolution risk map. The index is mapped to the index of the low-resolution raster cell corresponding to the low-resolution risk map: Formula (7) in, This indicates the total number of rows in the high-resolution risk map; Indicates the total number of columns in the high-resolution risk map; i represents a high-resolution raster cell. row index, ;j represents a high-resolution raster cell column index, ; This indicates the total number of rows in the low-resolution risk map; This represents the total number of columns in the low-resolution risk map; u represents a low-resolution raster cell. row index, ;v indicates a low-resolution raster unit column index, ; ,and .

[0068] Then, the electronic device, based on the index of the low-resolution raster cells, performs a low-resolution risk map... Bilinear interpolation is performed to obtain a high-resolution risk map: Formula (8) in, This indicates the low-resolution risk map In low-resolution raster units Perform bilinear interpolation at the location; Raster cells representing high-resolution risk maps The corresponding residual radiation risk cost. After performing bilinear interpolation on each low-resolution raster cell of the low-resolution risk map, a high-resolution risk map is obtained, i.e., the second risk map.

[0069] After obtaining the second risk map, the electronic equipment plans the operation path from the starting position to the target position based on the accessibility map and the second risk map, with the goal of minimizing the total radiation risk cost and the accessibility status as the constraint, and obtains the target operation path.

[0070] In some implementations, the electronic device determines the passable cells in the work area that are passable based on the access map. Then, it determines the edge radiation risk cost of one or more sets of adjacent passable cells. Based on the edge radiation risk cost of one or more sets of adjacent passable cells and the remaining radiation risk cost corresponding to the passable cells in the risk map (such as the second risk map), it performs one or more rounds of neighborhood search for the passable cells, starting from the grid cell corresponding to the starting position, to obtain the target work path from the starting position to the target position.

[0071] For example, an electronic device considers a grid cell in a work area to be passable if the grid cell's passability status is passable in a high-resolution passability map. This applies to two adjacent passable cells. and Electronic devices based on these two passable units and The average value of the radiation field and the distance between their physical centers are used to determine... and The cost of side radiation risks.

[0072] The walkable cell is a high-resolution grid cell. The formula for calculating the edge radiation risk cost between two adjacent high-resolution grid cells is as follows: Formula (9) in, Represents a group of adjacent grid cells and The physical distance of the physical center in the real coordinate system; Represents grid cells The radiation field value in the first radiation matrix; Represents grid cells The radiation field value in the first radiation matrix; express and The cost of side radiation risks.

[0073] After determining the edge radiation risk cost between two adjacent passable cells, based on the edge radiation risk cost between adjacent passable cells and the remaining radiation risk cost corresponding to the passable cell in the risk map, one or more rounds of neighborhood search are performed for the passable cell, starting from the grid cell corresponding to the starting position.

[0074] In each round of neighborhood search, if a candidate grid cell is not the grid cell corresponding to the target location, the edge radiation risk cost between the candidate grid cell and its adjacent cells is determined, and the residual radiation risk cost corresponding to the adjacent cell is determined in the risk map (such as the second risk map). A candidate grid cell is a grid cell found by the electronic device in a round of neighborhood search. An adjacent cell is a passable cell adjacent to a candidate grid cell.

[0075] The electronic device calculates the accumulated radiation risk cost corresponding to an adjacent cell based on the edge radiation risk cost of one or more sets of adjacent passable cells from the grid cell corresponding to the starting position. Then, based on the accumulated radiation risk cost and the remaining radiation risk cost of the adjacent cell, it determines the evaluation value corresponding to the adjacent cell. This evaluation value is used to assess the total radiation risk cost of the work path passing through the adjacent cell. The accumulated radiation risk cost is the sum of the edge radiation risk costs of one or more sets of adjacent passable cells from the grid cell corresponding to the starting position to the adjacent cell.

[0076] In one example, the formula for calculating the evaluation value of a grid cell is as follows: Formula (10) in, This represents the accumulated radiation risk cost from grid cell s at the starting position to grid cell n; This represents the set of all adjacent grid cells along the path from grid cell s to grid cell n; This represents the edge radiation risk cost between adjacent grid cells p and q; This represents the residual radiation risk cost corresponding to grid cell n; This represents the evaluation value corresponding to grid cell n, which is equal to the sum of the accumulated radiation risk cost from grid cell s to grid cell n and the remaining radiation risk cost corresponding to grid cell n.

[0077] The electronic device determines candidate grid cells for the next round of neighborhood search based on the evaluation values ​​of each adjacent cell. For example, the adjacent cell with the smallest evaluation value is selected as the candidate grid cell for the next round of search. If the candidate grid cell is the grid cell corresponding to the target position, the electronic device backtracks from the grid cell corresponding to the target position to the grid cell corresponding to the starting position to obtain the target operation path.

[0078] The following is combined Figure 3 The process of neighborhood search is illustrated by example.

[0079] First, the electronic device establishes an open list and a closed set, and records the accumulated radiation risk cost corresponding to the starting unit (i.e., the grid unit corresponding to the starting position). Set to 0, and read the residual radiation risk cost corresponding to the starting unit in the second risk map. The electronic device calculates the evaluation value corresponding to the starting unit based on the accumulated radiation risk cost and the remaining radiation risk cost corresponding to the starting unit, and adds the starting unit to the open list.

[0080] The electronic device repeatedly performs the following steps: The grid cell with the lowest evaluation value is selected from the open list as a candidate grid cell and added to the closed set. In each round of neighborhood search, the electronic device determines whether the candidate grid cell is the target cell (i.e., the grid cell corresponding to the target location).

[0081] If a candidate grid cell is not the target cell, the system traverses the four- or eight-neighborhood of the candidate grid cell within the operating area, i.e., it traverses the adjacent cells of the candidate grid cell. For each adjacent cell, the electronic device calculates the accumulated radiation risk cost (e.g., first-generation value) corresponding to the adjacent cell. If the first-generation value of any adjacent cell is less than its original accumulated radiation risk cost (e.g., second-generation value), the accumulated radiation risk cost g of the adjacent cell is updated from the second-generation value to the first-generation value. The remaining radiation risk cost h corresponding to the adjacent cell is read from the second risk map, and the evaluation value f corresponding to the adjacent cell is updated based on the remaining radiation risk cost and the accumulated radiation risk cost. At the same time, the parent node information of the adjacent cell is updated to the candidate grid cell.

[0082] If the adjacent cell is not yet in the open list, it is added to the open list; if the adjacent cell already exists in the open list, its corresponding evaluation value in the open list is updated. After traversing all adjacent cells of the candidate grid cells, the electronic device continues to select the grid cell with the smallest evaluation value from the open list as the candidate grid cell for the next round of search, repeating the above neighborhood search process.

[0083] If the candidate grid cell is the target cell, the neighborhood search process is terminated. Starting from the target cell, the electronic device sequentially reads the parent node information stored in the grid cells, and backtracks back to the starting cell according to the parent node information. The grid cell sequence obtained from the backtracking is then organized into a target operation path from the starting position to the target position.

[0084] The following is combined Figure 4 The method provided in the embodiments of this application is illustrated through an application example.

[0085] First, the electronic equipment uniformly constructs the working area in a centimeter-level coordinate system, with the horizontal and vertical coordinates of the working area set to 0 to 900 cm. The electronic equipment acquires the true coordinate boundaries of each obstacle in the working area (i.e., obstacle data) and reads the three-dimensional mesh radiation response data (i.e., three-dimensional radiation field data) obtained by simulation calculation through the Monte Carlo N-Particle Transport Code (MCNP). The original data of MCNP is divided into 90 grids in both the horizontal and vertical directions, with a nominal grid spacing of 10 cm. Using a preset effective range of 0 to 180 cm in height, the three-dimensional radiation data is converted into two-dimensional radiation field data using formula (1).

[0086] Subsequently, the electronic device subdivides each grid of the two-dimensional radiation field data by a factor of 3 both horizontally and vertically, and uses a two-dimensional linear interpolation algorithm to interpolate the two-dimensional radiation field data, generating a high-resolution radiation matrix with a resolution of 270×270. The nominal size of the high-resolution grid is approximately 3.33 cm. Based on the positional relationship between the center coordinates of each high-resolution grid and the obstacle boundary, a 270×270 high-resolution access matrix is ​​constructed. Taking the starting position coordinates of the task as (300, 50) cm and the target position coordinates as (850, 850) cm as an example, the electronic device maps the two positions to the nearest accessible cell in the high-resolution access matrix.

[0087] Then, the electronic device uniformly samples the 270×270 high-resolution radiation matrix according to formulas (2) and (3) to obtain a 40×40 low-resolution radiation matrix. The low-resolution radiation matrix only retains the radiation field data and discards the obstacle data. The passage status of the obstacle boundary and the grid cell is stored in the 270×270 high-resolution passage matrix, providing constraints for subsequent path search. The electronic device maps the target position coordinates (850,850) cm to the corresponding low-resolution grid cell. Using this grid cell as the reverse single source point, the shortest path search is performed in the 40×40 low-resolution radiation matrix using the eight-neighbor rule (such as executing the Dijkstra algorithm). During the shortest path search, the connecting side lengths in the horizontal, vertical, or diagonal directions are calculated using the actual physical distance between the centers of two adjacent grid cells. After the shortest path search is completed, a 40×40 low-resolution risk map is generated. In the low-resolution risk map, each grid cell stores the minimum cumulative radiation risk cost (i.e., the residual radiation risk cost) from the corresponding grid cell to the grid cell corresponding to the target location.

[0088] In terms of radiation risk cost conversion, when the input radiation field data is radiation dose rate, and the operating equipment operates at a constant speed... When traveling at a constant speed, the actual cumulative radiation dose corresponding to the work path can be normalized by considering the radiation risk cost and speed. The ratio is determined; assuming the speed is consistent across all work paths, the normalized radiation risk cost is consistent with the ranking of the actual cumulative radiation dose. If the work equipment travels at variable speeds, the corresponding cumulative radiation dose is calculated based on the actual travel time of each path segment.

[0089] After obtaining the low-resolution risk map, the electronic device maps the coordinates of the 270×270 high-resolution grid cells to continuous floating-point coordinates under the 40×40 low-resolution risk map according to formula (7), and performs bilinear interpolation on the low-resolution risk map using formula (8) to obtain the high-resolution risk map, which can be used as a heuristic function. Then, the electronic device starts the neighborhood search (e.g., using an eight-neighborhood A) starting from the high-resolution grid cell corresponding to the starting position. The algorithm performs a neighborhood search, expanding only the raster cells marked as passable in the high-resolution access matrix. During the search, the actual radiation risk cost of each path segment is accumulated using formula (9), and the evaluation value corresponding to the operation path is calculated using formula (10). When the raster cell corresponding to the target location is removed from the open list, the search is terminated and the path backtracking is completed based on the stored parent node information. At the same time, the high-resolution raster index obtained from the backtracking is converted into real physical coordinates, and the target operation path is output.

[0090] In practical applications, electronic devices can also output multiple path planning parameters in real time. These parameters include the physical length of the work path, the normalized radiation risk cost or cumulative radiation dose, the time taken to generate the low-resolution risk map, the time taken to search for the neighborhood, the total running time, the number of expanded nodes (i.e., the number of grid cells retrieved from the open list and subjected to neighborhood expansion), and the percentage of expanded nodes to the number of high-resolution passable cells. This allows for the evaluation of the overall performance of path planning in terms of radiation risk, search efficiency, and spatial search range.

[0091] The path planning method provided in this application adopts a high- and low-resolution layered architecture, separating the radiation risk guidance layer from the obstacle passage constraint layer. The low-resolution layer discards obstacle information, retaining only radiation field features, and performs reverse shortest path calculation with the target location as the source. This ensures that each value in the risk map directly represents the minimum residual radiation risk cost from the corresponding grid cell to the target location, thus providing heuristic information with global radiation distribution characteristics for path search. After a risk map pre-calculation is completed in the low-resolution layer, it is then interpolated and mapped to the high-resolution layer to serve high-resolution search. This reduces the pre-calculation scale of global risk arrival estimation and minimizes node expansion deviating from low-risk areas. For the same target location and multiple different starting locations, both the generated low-resolution and high-resolution risk maps can be reused. The high-resolution layer fully preserves obstacle boundaries and passage constraints, representing the actual passage status of narrow passages, obstacle edges, and wall-mounted grids. The final planned target operation path satisfies the high-resolution obstacle constraints.

[0092] The embodiments of this application, through the aforementioned layered architecture, address the deficiencies existing in related technologies: 1. By performing reverse shortest path calculation on the low-resolution radiation field matrix with the grid cell corresponding to the target location as the source, a risk map representing the minimum cumulative radiation risk cost from each grid cell to the target location is generated, which solves the problem that the path planning method does not make sufficient use of the spatial distribution characteristics of the radiation field and is difficult to accurately reflect the overall environmental risk. 2. By combining low-resolution global radiation risk guidance with high-resolution obstacle passage constraints through risk maps and passage maps, and accumulating the actual radiation risk cost along the path at the high-resolution layer, the problem of high-risk paths or local suboptimal paths easily generated in environments with dense obstacles and complex radiation distribution is solved. 3. By mapping and interpolating the low-resolution risk map to a high-resolution risk map as the heuristic cost, and then combining it with the accumulated radiation risk cost from the starting point to the current grid cell to form the evaluation function, the problem that the heuristic function of the traditional path planning algorithm is mainly based on geometric distance and lacks global radiation risk guidance, which leads to limited search efficiency and path safety is solved. 4. By fusing obstacle data and radiation field data in a unified real coordinate system, implementing collision constraints using a high-resolution access matrix, and completing risk map generation and path search in a modular process, the problems of insufficient adaptability, poor stability and practicality of path planning in complex radiation environments are solved.

[0093] To implement the path planning method provided in the embodiments of this application, the embodiments of this application also provide a path planning device, such as... Figure 5 As shown, the device includes: The environmental modeling module 51 is used to acquire environmental data of the work area, including obstacle data and radiation field data. The environment modeling module 51 is further configured to generate a access map corresponding to the work area based on the obstacle data; wherein, the access map represents the access status corresponding to each grid cell, and the access status includes a passable status and a non-passable status; The risk map generation module 52 is used to construct a risk map corresponding to the work area based on the radiation field data; wherein, the risk map represents the residual radiation risk cost corresponding to each grid cell, and the residual radiation risk cost reflects the residual radiation dose from the grid cell to the target location; The path search module 53 is used to plan the operation path from the starting position to the target position based on the access map and the risk map, with the goal of minimizing the total radiation risk cost and the constraint of passability status, so as to obtain the target operation path.

[0094] In some optional embodiments, the risk map generation module 52 is specifically used for: Based on the radiation field data, a first risk map is constructed; wherein the resolution of the first risk map is smaller than the resolution of the access map; The first risk map is interpolated to obtain a second risk map, wherein the resolution of the second risk map is greater than the resolution of the first risk map, and the resolution of the second risk map is the same as the resolution of the access map; The path search module 53 is specifically used for: Based on the access map and the second risk map, with the goal of minimizing the total radiation risk cost and the constraint of passability, the operation path from the starting position to the target position is planned to obtain the target operation path.

[0095] In some optional embodiments, the risk map generation module 52 is specifically used for: Based on the radiation field data, a first radiation matrix corresponding to the work area is determined; wherein, the first radiation matrix represents the radiation field distribution of the work area; The first radiation matrix is ​​downsampled to obtain a second radiation matrix; wherein the resolution of the second radiation matrix is ​​smaller than that of the first radiation matrix. Based on the second radiation matrix, a first risk map is constructed.

[0096] In some optional embodiments, the risk map generation module 52 is specifically used for: A mesh graph is established based on the second radiation matrix, wherein the vertices of the mesh graph represent grid cells of the first resolution, and the connecting edges of the mesh graph represent the adjacency relationship between different grid cells; the first resolution is consistent with the resolution of the second radiation matrix. The risk cost weight of the corresponding connecting edge is determined based on the edge radiation risk cost between each group of adjacent grid cells; wherein, the edge radiation risk cost reflects the radiation dose between adjacent grid cells; Using the target vertex as the search source point, the shortest path between each vertex and the search source point is searched in the grid graph based on the sum of the risk cost weights of one or more connecting edges between each vertex and the search source point; wherein, the target vertex corresponds to the grid cell corresponding to the target position; Based on the sum of the risk cost weights of the shortest path between each vertex and the search source point, the residual radiation risk cost corresponding to the grid cell is determined, and the first risk map is obtained.

[0097] In some optional embodiments, the radiation field data is three-dimensional radiation field data; the environment modeling module 51 is further used for: For each 3D mesh cell at the same planar coordinate position, determine the overlap height between each 3D mesh cell and the preset height range; By utilizing the overlap height of each three-dimensional mesh cell with a preset height range, a weighted average is performed on multiple three-dimensional mesh cells at the same planar coordinate position to obtain two-dimensional radiation field data at the same planar coordinate position; The risk map generation module 52 is specifically used for: Based on the two-dimensional radiation field data, a risk map corresponding to the work area is constructed.

[0098] In some optional embodiments, the path search module 53 is specifically used for: Based on the access map, identify the passable cells that are in a passable state among the multiple grid cells in the work area; Determine the edge radiation risk cost of one or more groups of adjacent passable cells; Based on the edge radiation risk cost of one or more adjacent passable units and the residual radiation risk cost corresponding to the passable units in the risk map, starting from the grid unit corresponding to the starting position, one or more rounds of neighborhood search are performed on the passable units to obtain the target operation path from the starting position to the target position.

[0099] In some optional embodiments, the path search module 53 is specifically used for: Starting from the grid cell corresponding to the starting position, perform one or more rounds of neighborhood search for the passable cell; In each round of neighborhood search, if the candidate grid cell found is not the grid cell corresponding to the target location, the accumulated radiation risk cost corresponding to the adjacent cell and the remaining radiation risk cost corresponding to the adjacent cell are determined; wherein, the adjacent cell is a passable cell adjacent to the candidate grid cell, and the accumulated radiation risk cost is the sum of the edge radiation risk costs of one or more sets of adjacent passable cells from the grid cell corresponding to the starting location to the adjacent cell; Based on the accumulated radiation risk cost of the adjacent unit and the remaining radiation risk cost of the adjacent unit, the evaluation value corresponding to the adjacent unit is determined. The evaluation value is used to assess the total radiation risk cost of the operation path passing through the adjacent unit. The candidate grid cells for the next round of neighborhood search are determined based on the evaluation values ​​of each adjacent cell. If the candidate grid cell is the grid cell corresponding to the target position, the target operation path is obtained by tracing back from the grid cell corresponding to the target position to the grid cell corresponding to the starting position.

[0100] It should be noted that the path planning device provided in the above embodiments is only illustrated by the division of the above-described program units. In practical applications, the above processing can be assigned to different program units as needed, that is, the internal structure of the device can be divided into different program units to complete all or part of the processing described above. In addition, the path planning device and the path planning method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0101] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiments of this application, the embodiments of this application also provide an electronic device, such as... Figure 6 As shown, the electronic device includes: The communication interface 601 enables information exchange with other devices (such as operating equipment); The processor 602 is connected to the communication interface 601 to enable information interaction with other devices (such as operating equipment) and to execute the methods provided by one or more of the above technical solutions when running a computer program; The computer program is stored in memory 603.

[0102] Specifically, the processor 602 is used for: The communication interface 601 is used to acquire environmental data of the work area, including obstacle data and radiation field data. Based on the obstacle data, a passage map corresponding to the work area is generated; wherein, the passage map represents the passage status corresponding to each grid cell, and the passage status includes a passable state and a non-passable state; Based on the radiation field data, a risk map corresponding to the work area is constructed; wherein, the risk map represents the residual radiation risk cost corresponding to each grid cell, and the residual radiation risk cost reflects the residual radiation dose from the grid cell to the target location; Based on the access map and the risk map, with the goal of minimizing the total radiation risk cost and the constraint of passability, the operation path from the starting position to the target position is planned to obtain the target operation path.

[0103] In some alternative embodiments, the processor 602 is specifically used for: Based on the radiation field data, a first risk map is constructed; wherein the resolution of the first risk map is smaller than the resolution of the access map; The first risk map is interpolated to obtain a second risk map, wherein the resolution of the second risk map is greater than the resolution of the first risk map, and the resolution of the second risk map is the same as the resolution of the access map; Based on the access map and the second risk map, with the goal of minimizing the total radiation risk cost and the constraint of passability, the operation path from the starting position to the target position is planned to obtain the target operation path.

[0104] In some alternative embodiments, the processor 602 is specifically used for: Based on the radiation field data, a first radiation matrix corresponding to the work area is determined; wherein, the first radiation matrix represents the radiation field distribution of the work area; The first radiation matrix is ​​downsampled to obtain a second radiation matrix; wherein the resolution of the second radiation matrix is ​​smaller than that of the first radiation matrix. Based on the second radiation matrix, a first risk map is constructed.

[0105] In some alternative embodiments, the processor 602 is specifically used for: A mesh graph is established based on the second radiation matrix, wherein the vertices of the mesh graph represent grid cells of the first resolution, and the connecting edges of the mesh graph represent the adjacency relationship between different grid cells; the first resolution is consistent with the resolution of the second radiation matrix. The risk cost weight of the corresponding connecting edge is determined based on the edge radiation risk cost between each group of adjacent grid cells; wherein, the edge radiation risk cost reflects the radiation dose between adjacent grid cells; Using the target vertex as the search source point, the shortest path between each vertex and the search source point is searched in the grid graph based on the sum of the risk cost weights of one or more connecting edges between each vertex and the search source point; wherein, the target vertex corresponds to the grid cell corresponding to the target position; Based on the sum of the risk cost weights of the shortest path between each vertex and the search source point, the residual radiation risk cost corresponding to the grid cell is determined, and the first risk map is obtained.

[0106] In some optional embodiments, the radiation field data is three-dimensional radiation field data; the processor 602 is specifically used for: For each 3D mesh cell at the same planar coordinate position, determine the overlap height between each 3D mesh cell and the preset height range; By utilizing the overlap height of each three-dimensional mesh cell with a preset height range, a weighted average is performed on multiple three-dimensional mesh cells at the same planar coordinate position to obtain two-dimensional radiation field data at the same planar coordinate position; Based on the two-dimensional radiation field data, a risk map corresponding to the work area is constructed.

[0107] In some alternative embodiments, the processor 602 is specifically used for: Based on the access map, identify the passable cells that are in a passable state among the multiple grid cells in the work area; Determine the edge radiation risk cost of one or more groups of adjacent passable cells; Based on the edge radiation risk cost of one or more adjacent passable units and the residual radiation risk cost corresponding to the passable units in the risk map, starting from the grid unit corresponding to the starting position, one or more rounds of neighborhood search are performed on the passable units to obtain the target operation path from the starting position to the target position.

[0108] In some alternative embodiments, the processor 602 is specifically used for: Starting from the grid cell corresponding to the starting position, perform one or more rounds of neighborhood search for the passable cell; In each round of neighborhood search, if the candidate grid cell found is not the grid cell corresponding to the target location, the accumulated radiation risk cost corresponding to the adjacent cell and the remaining radiation risk cost corresponding to the adjacent cell are determined; wherein, the adjacent cell is a passable cell adjacent to the candidate grid cell, and the accumulated radiation risk cost is the sum of the edge radiation risk costs of one or more sets of adjacent passable cells from the grid cell corresponding to the starting location to the adjacent cell; Based on the accumulated radiation risk cost of the adjacent unit and the remaining radiation risk cost of the adjacent unit, the evaluation value corresponding to the adjacent unit is determined. The evaluation value is used to assess the total radiation risk cost of the operation path passing through the adjacent unit. The candidate grid cells for the next round of neighborhood search are determined based on the evaluation values ​​of each adjacent cell. If the candidate grid cell is the grid cell corresponding to the target position, the target operation path is obtained by tracing back from the grid cell corresponding to the target position to the grid cell corresponding to the starting position.

[0109] It should be noted that the specific processing procedures of the processor 602 and the communication interface 601 can be understood with reference to the above method.

[0110] Of course, in practical applications, the various components in an electronic device are coupled together through a bus system 604. It can be understood that the bus system 604 is used to realize the connection and communication between these components. In addition to a data bus, the bus system 604 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in... Figure 6 The general designated all buses as Bus System 604.

[0111] The memory 603 in this embodiment is used to store various types of data to support the operation of the electronic device. Examples of such data include any computer program used to operate on the electronic device.

[0112] The methods disclosed in the embodiments of this application can be applied to the processor 602, or implemented by the processor 602. The processor 602 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 602 or by instructions in the form of software. The processor 602 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 602 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in the memory 603. The processor 602 reads the information in the memory 603 and combines its hardware to complete the steps of the aforementioned method.

[0113] In an exemplary embodiment, the electronic device may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontroller units (MCUs), microprocessors, or other electronic components to perform the aforementioned method.

[0114] It is understood that the memory 603 in this embodiment can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of this application are intended to include, but are not limited to, these and any other suitable types of memories.

[0115] In an exemplary embodiment, this application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as a memory 603 storing a computer program, which can be executed by a processor 602 of an electronic device to complete the steps described in the aforementioned method. The computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM.

[0116] In an exemplary embodiment, this application also provides a computer program product, including a computer program that can be executed by a processor 602 of an electronic device to perform the steps described in the foregoing method.

[0117] It should be noted that terms such as "first" and "second" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0118] Furthermore, the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.

[0119] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application.

Claims

1. A path planning method, characterized in that, The method includes: Acquire environmental data of the work area, including obstacle data and radiation field data; Based on the obstacle data, a passage map corresponding to the work area is generated; wherein, the passage map represents the passage status corresponding to each grid cell, and the passage status includes a passable state and a non-passable state; Based on the radiation field data, a risk map corresponding to the work area is constructed; wherein, the risk map represents the residual radiation risk cost corresponding to each grid cell, and the residual radiation risk cost reflects the residual radiation dose from the grid cell to the target location; Based on the access map and the risk map, with the goal of minimizing the total radiation risk cost and the constraint of passability, the operation path from the starting position to the target position is planned to obtain the target operation path.

2. The method according to claim 1, characterized in that, The step of constructing a risk map corresponding to the work area based on the radiation field data includes: Based on the radiation field data, a first risk map is constructed; wherein the resolution of the first risk map is smaller than the resolution of the access map; The first risk map is interpolated to obtain a second risk map, wherein the resolution of the second risk map is greater than the resolution of the first risk map, and the resolution of the second risk map is the same as the resolution of the access map; Based on the accessibility map and the risk map, with the objective of minimizing the total radiation risk cost and the constraint of passability status, the operation path from the starting position to the target position is planned to obtain the target operation path, including: Based on the access map and the second risk map, with the goal of minimizing the total radiation risk cost and the constraint of passability, the operation path from the starting position to the target position is planned to obtain the target operation path.

3. The method according to claim 2, characterized in that, The construction of the first risk map based on the radiation field data includes: Based on the radiation field data, a first radiation matrix corresponding to the work area is determined; wherein, the first radiation matrix represents the radiation field distribution of the work area; The first radiation matrix is ​​downsampled to obtain a second radiation matrix; wherein the resolution of the second radiation matrix is ​​smaller than the resolution of the first radiation matrix. Based on the second radiation matrix, a first risk map is constructed.

4. The method according to claim 3, characterized in that, The construction of the first risk map based on the second radiation matrix includes: A mesh graph is established based on the second radiation matrix, wherein the vertices of the mesh graph represent grid cells of the first resolution, and the connecting edges of the mesh graph represent the adjacency relationship between different grid cells; the first resolution is consistent with the resolution of the second radiation matrix. The risk cost weight of the corresponding connecting edge is determined based on the edge radiation risk cost between each group of adjacent grid cells; wherein, the edge radiation risk cost reflects the radiation dose between adjacent grid cells; Using the target vertex as the search source point, the shortest path between each vertex and the search source point is searched in the grid graph based on the sum of the risk cost weights of one or more connecting edges between each vertex and the search source point; wherein, the target vertex corresponds to the grid cell corresponding to the target position; Based on the sum of the risk cost weights of the shortest path between each vertex and the search source point, the residual radiation risk cost corresponding to the grid cell is determined, and the first risk map is obtained.

5. The method according to claim 1, characterized in that, The radiation field data is three-dimensional radiation field data; the method further includes: For each 3D mesh cell at the same planar coordinate position, determine the overlap height between each 3D mesh cell and the preset height range; By utilizing the overlap height of each three-dimensional mesh cell with a preset height range, a weighted average is performed on multiple three-dimensional mesh cells at the same planar coordinate position to obtain two-dimensional radiation field data at the same planar coordinate position; The step of constructing a risk map corresponding to the work area based on the radiation field data includes: Based on the two-dimensional radiation field data, a risk map corresponding to the work area is constructed.

6. The method according to claim 1, characterized in that, Based on the accessibility map and the risk map, with the objective of minimizing the total radiation risk cost and the constraint of passability status, the operation path from the starting position to the target position is planned to obtain the target operation path, including: Based on the access map, identify the passable cells that are in a passable state among the multiple grid cells in the work area; Determine the edge radiation risk cost of one or more groups of adjacent passable cells; Based on the edge radiation risk cost of one or more adjacent passable units and the residual radiation risk cost corresponding to the passable units in the risk map, starting from the grid unit corresponding to the starting position, one or more rounds of neighborhood search are performed on the passable units to obtain the target operation path from the starting position to the target position.

7. The method according to claim 6, characterized in that, The step of taking the grid cell corresponding to the starting position as the starting point and performing one or more rounds of neighborhood search on passable cells to obtain the target operation path from the starting position to the target position includes: Starting from the grid cell corresponding to the starting position, perform one or more rounds of neighborhood search for the passable cell; In each round of neighborhood search, if the candidate grid cell found is not the grid cell corresponding to the target location, the accumulated radiation risk cost corresponding to the adjacent cell and the remaining radiation risk cost corresponding to the adjacent cell are determined; wherein, the adjacent cell is a passable cell adjacent to the candidate grid cell, and the accumulated radiation risk cost is the sum of the edge radiation risk costs of one or more sets of adjacent passable cells from the grid cell corresponding to the starting location to the adjacent cell; Based on the accumulated radiation risk cost of the adjacent unit and the remaining radiation risk cost of the adjacent unit, the evaluation value corresponding to the adjacent unit is determined. The evaluation value is used to assess the total radiation risk cost of the operation path passing through the adjacent unit. The candidate grid cells for the next round of neighborhood search are determined based on the evaluation values ​​of each adjacent cell. If the candidate grid cell is the grid cell corresponding to the target position, the target operation path is obtained by tracing back from the grid cell corresponding to the target position to the grid cell corresponding to the starting position.

8. An electronic device, characterized in that, include: Processor and memory used to store computer programs that can run on the processor; When the processor is used to run a computer program, it executes the steps of the method according to any one of claims 1 to 7.

9. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images