Mining area vehicle operation point location generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a mining area vehicle operation point location generation method and device, electronic equipment and a storage medium, and relates to the field of automatic driving. The method comprises the following steps: receiving a local point cloud map of a mining area generated by a vehicle-mounted terminal based on collected first environment information of a target vehicle; determining at least one local point cloud map received in a preset time period; updating the current first global point cloud map according to the at least one local point cloud map to obtain an updated target global point cloud map; and based on the target global point cloud map and the positions of the dumping area and the loading area of the mining area in the target global point cloud map, generating an operation point location of the mining area. According to the application, synchronous updating of the map and the operation point location is realized, and the operation efficiency and safety of each vehicle in the mining area are improved.

Description

Technical Field

[0001] The present application relates to the field of unmanned driving technology. Specifically, the present application relates to a method, device, electronic equipment and storage medium for generating vehicle operation points in a mining area. Background Art

[0002] At present, unmanned driving technology in open-pit mines is developing rapidly. The application of unmanned mining vehicles in mining areas is gradually becoming an important technology for improving efficiency, reducing costs and improving safety in the mining industry. Unmanned mining vehicles perform various tasks through work points allocated by the cloud.

[0003] However, the efficiency of existing high-precision map update technology cannot meet the needs of rapid update of high-precision maps for autonomous driving in open-pit mines, and the method of generating work points in open-pit mines is difficult to achieve real-time dynamic update, resulting in the work points being out of sync with the actual changes in the mining area's working surface, making the real-time and accuracy of the work points problematic, thereby affecting the efficiency and safety of the operation. Summary of the invention

[0004] The embodiments of the present application provide a method, device, electronic device and storage medium for generating vehicle operation points in a mining area, which are used to solve the technical problem that the operation points and the global map of the mining area are updated differently, affecting the efficiency and safety of the operation.

[0005] According to a first aspect of an embodiment of the present application, a method for generating a vehicle operation point in a mining area is provided, the method comprising: Receiving a local point cloud map of the mining area generated by the vehicle-mounted terminal based on the collected first environmental information of the target vehicle; determining at least one local point cloud map received within a preset time period; Update the current first global point cloud map according to at least one local point cloud map to obtain an updated target global point cloud map; Based on the target global point cloud map and the positions of the dumping area and loading area of ​​the mining area in the target global point cloud map, the operation points of the mining area are generated.

[0006] In a possible implementation, the operation points of the mining area include operation points in the dumping area; the point update subsystem determines a bounding box of the dumping area in the target global point cloud map, and expands the size of the bounding box to obtain a first expansion area; Determine a bounding box of the soil dumping area in the target global point cloud map, and expand the size of the bounding box to obtain a first expansion area; Determine the height of each sampling point in the first extended area based on the target global point cloud map, and determine a first road surface area in the first extended area from the target global point cloud map based on the height of each sampling point; the height of any sampling point in the first road surface area is less than a first height threshold; Smoothing a first road surface area in the target global point cloud map, performing edge detection on the first road surface area after the smoothing, and extracting a contour of the first road surface area after the edge detection to obtain a first point set representing a contour of the first road surface area; Simplifying the contour curve represented by the first point set to obtain a first target point set representing the simplified contour curve; Taking the area corresponding to the first target point set in the target global point cloud map as the first target road surface area, and determining a plurality of candidate operation points in the first target road surface area; An operation point that meets a preset evaluation standard is selected from a plurality of candidate operation points as the operation point in the dumping area.

[0007] In another possible implementation, the curvature and normal of each candidate operation point are calculated based on the target global point cloud map; For each candidate operation point in the target global point cloud map, when the identification frame representing the target vehicle is located at the candidate operation point, determine the first obstacle ratio within the identification frame, and obtain the first obstacle ratio corresponding to the candidate operation point; For each candidate operation point in the target global point cloud map, the candidate operation point is used as the starting point, and the identification frame is moved toward the retaining wall of the dumping area until the area representing the rear wheel of the target vehicle in the identification frame contacts the retaining wall, and the second obstacle ratio in the tail area of ​​the identification frame is determined to obtain the second obstacle ratio corresponding to the candidate operation point; For each candidate operation point in the target global point cloud map, the distance between the candidate operation point and the target dumping line in the dumping area is calculated, and it is determined whether the candidate operation point is in the dumping area.

[0008] An operation point that meets a preset evaluation standard is selected from a plurality of candidate operation points as the operation point in the dumping area.

[0009] In another possible implementation, the preset evaluation criteria include: The curvature of the candidate operation point is not greater than the preset curvature threshold; The normal line of the candidate operation point does not face the target discharge line of the discharge area; The first obstacle ratio corresponding to the candidate operation point is not greater than the preset identification frame obstacle ratio threshold; The second obstacle ratio corresponding to the candidate operation point is not less than the preset tail obstacle ratio threshold; The distance between the candidate operation point and the target dumping line is not greater than the preset distance threshold; The candidate operation point is located in the dumping area.

[0010] In another possible implementation, The operation points in the dumping area are stored in a temporary buffer area; The method also includes: Determine the tasks to be assigned; Acquire at least one target operation point from the temporary buffer area based on the operation task to be assigned, and delete the at least one target operation point from the temporary buffer area; Generate path information based on at least one target operation point, and send an operation task containing the path information to the vehicle terminal; When it is determined that the number of working points in the temporary cache area is less than the preset point number threshold, new working points in the dumping area are generated based on the currently applied global point cloud map and the dumping area, and the working points stored in the temporary cache area are updated.

[0011] In another possible implementation, the operation points of the mining area include operation points in the loading area; the point updating subsystem determines a bounding box of the loading area in the target global point cloud map, and performs expansion processing on the size of the bounding box of the loading area to obtain a second expanded area; Determine the height of each sampling point in the second extended area based on the target global point cloud map, and determine the second road surface area and the retaining wall area in the second extended area from the target global point cloud map based on the height of each sampling point; the height of any point in the second road surface area is less than the first height threshold, and the height of any point in the retaining wall area is higher than the second height threshold; Smoothing the second road surface area and the retaining wall area in the target global point cloud map, performing edge detection on the smoothed second road surface area, and extracting the contour of the second road surface area after edge detection to obtain a second point set representing the contour of the second road surface area; Simplifying the contour curve represented by the second point set to obtain a second target point set representing the simplified contour curve; The area corresponding to the second target point set in the target global point cloud map is used as the second target road surface area, and the operation point in the loading area is determined based on the second target road surface area and the retaining wall area.

[0012] In another possible implementation, in the target global point cloud map, the identification frame representing the target vehicle is moved to a preset starting point to determine whether there is a non-ground point in the identification frame; the non-ground point is used to represent a point that does not belong to the second target road surface area; If it is determined that there is a non-ground point in the identification frame, the identification frame is moved along the front direction of the target vehicle in the target global point cloud map until there is no non-ground point in the identification frame, and then based on the first distance between the rear wheels of the target vehicle and the rear of the target vehicle, the identification frame is moved along the rear direction of the target vehicle, and the first position of the identification frame is recorded; In the target global point cloud map, the identification frame is moved to a preset starting point, and the identification frame is moved along the front direction of the target vehicle until there is no retaining wall area in the identification frame, and the second position where the identification frame is currently located is recorded; In the target global point cloud map, the distances between the first position and the second position and the preset starting point are determined, and the position with the larger distance is selected from the first position and the second position as the position of the working point of the loading area.

[0013] In another possible implementation, if it is determined that there is no non-ground point in the identification frame, in the target global point cloud map, the identification frame is moved along the rear direction of the target vehicle until there is a non-ground point in the identification frame, and then based on the first distance between the rear wheel of the target vehicle and the rear of the target vehicle, the identification frame is moved along the rear direction of the target vehicle, and the third position where the identification frame is currently located is recorded; In the target global point cloud map, the identification frame is moved to a preset starting point, and the identification frame is moved along the rear direction of the parking space of the target vehicle until a retaining wall area exists in the identification frame, and the fourth position where the identification frame is currently located is recorded; In the target global point cloud map, the distances between the third position and the fourth position and the preset starting point are determined, and a position with a smaller distance is selected from the third position and the fourth position as the position of the working point of the loading area.

[0014] In yet another possible implementation, the preset starting point is a working point of the loading area determined based on the current first global point cloud map.

[0015] In yet another possible implementation, determining a position of each of the at least one local point cloud maps on the first global point cloud map; For each local point cloud map, at the position of the local point cloud map in the first global point cloud map, updating the first global point cloud map based on the local point cloud map to obtain an updated first global point cloud map; The updated first global point cloud map is rasterized to obtain a target global point cloud map.

[0016] In another possible implementation, The first environmental information includes terrain data and obstacle data within a preset range; the first environmental information is obtained by the vehicle-mounted terminal through the sensor kit to collect information about the environment within the preset range of the target vehicle; the local point cloud map is obtained by the vehicle-mounted terminal by inputting the first environmental information into the generation model; The generative model is trained by using the first environmental information of the area where the sample object is located as a training sample and using the local point cloud map corresponding to the area where the sample object is located as a training label.

[0017] In yet another possible implementation, a target global point cloud map including operating points in the mining area is displayed.

[0018] According to a second aspect of an embodiment of the present application, a device for generating a mining vehicle operation point is provided, comprising: A receiving module, used for receiving a local point cloud map of the mining area generated by the vehicle-mounted terminal based on the collected first environmental information of the target vehicle; A confirmation module, used to determine at least one local point cloud map received within a preset time period; An updating module, configured to update a current first global point cloud map according to at least one local point cloud map to obtain an updated target global point cloud map; The generation module is used to generate the operation points of the mining area based on the target global point cloud map and the positions of the dumping area and the loading area of ​​the mining area in the target global point cloud map.

[0019] According to a third aspect of an embodiment of the present application, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory, and when the processor executes the program, the steps of the method provided in the first aspect are implemented.

[0020] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method provided in the first aspect are implemented.

[0021] According to the fifth aspect of the embodiment of the present application, a computer program product is provided, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. When a processor of a computer device reads the computer instructions from the computer-readable storage medium, the processor executes the computer instructions, so that the computer device executes the steps of implementing the method provided in the first aspect.

[0022] The beneficial effects of the technical solution provided by the embodiment of the present application are: The method for generating vehicle operation points in a mining area provided in an embodiment of the present application receives a local point cloud map of the mining area generated by a vehicle-mounted terminal based on the first environmental information of the target vehicle collected, confirms that all local point cloud maps received by the cloud within a preset time period are updated based on all received local point cloud maps to the current first global point cloud map, and obtains an updated target global point cloud map. Based on the target global point cloud map and the positions of the dumping area and the loading area of ​​the mining area in the target global point cloud map, the operation points of the mining area are generated. By receiving the local point cloud map generated by the vehicle-mounted terminal of each target vehicle based on the first environmental information, the local point cloud map of each area in the mining area can be obtained efficiently and conveniently, so that the cloud can update the first global point cloud map according to the received local point cloud map, thereby realizing a rapid update of the map of the mining area, and then generates the operation points of the mining area according to the target global point cloud map, ensuring the synchronous update of the operation points and the mining area map, ensuring the real-time and accuracy of the operation points, and significantly improving the operation efficiency and safety of the target vehicles in the mining area. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in describing the embodiments of the present application.

[0024] Figure 1 A schematic diagram of the system architecture for realizing a method for generating vehicle operation points in a mining area provided in an embodiment of the present application; Figure 2 A schematic diagram of a flow chart of a method for generating vehicle operation points in a mining area provided in an embodiment of the present application; Figure 3 A schematic flow chart of a method for generating an operation point in a dumping area in a method for generating an operation point in a mining area provided in an embodiment of the present application; Figure 4 A flowchart of a method for selecting an operation point that meets a preset evaluation standard in a method for generating an operation point for a vehicle in a mining area provided in an embodiment of the present application; Figure 5 A schematic flow chart of a method for managing operating positions in a dumping area in a method for generating operating positions for vehicles in a mining area provided in an embodiment of the present application; Figure 6 A schematic flow chart of a method for searching for operating points in a loading area in a method for generating operating points for vehicles in a mining area provided in an embodiment of the present application; Figure 7 A flowchart of a method for searching for operating points in a method for generating operating points for vehicles in a mining area provided in an embodiment of the present application; Figure 8A flow chart of a method for searching operating points in another method for generating operating points for vehicles in a mining area provided in an embodiment of the present application; Fig. 9 A schematic flow chart of a method for generating a target global point cloud map in a method for generating a mining vehicle operation point provided in an embodiment of the present application; Fig.10 A schematic diagram of the structure of a device for generating vehicle operation points in a mining area provided in an embodiment of the present application; Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The embodiments of the present application are described below in conjunction with the drawings in the present application. It should be understood that the implementation methods described below in conjunction with the drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions of the embodiments of the present application.

[0026] It will be understood by those skilled in the art that, unless specifically stated, the singular forms "one", "an" and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present application refer to that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude the implementation as other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the technical field. It should be understood that when we call an element "connected" or "coupled" to another element, the one element can be directly connected or coupled to the other element, or it can refer to that the one element and the other element establish a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used here may include wireless connection or wireless coupling. The term "and / or" used here indicates at least one of the items defined by the term, for example, "A and / or B" can be implemented as "A", or as "B", or as "A and B".

[0027] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0028] The following describes several exemplary embodiments to illustrate the technical solutions of the embodiments of the present application and the technical effects produced by the technical solutions of the present application. It should be noted that the following embodiments can refer to, draw on or combine with each other, and the same terms, similar features and similar implementation steps in different embodiments will not be described repeatedly.

[0029] Figure 1A schematic diagram of the system architecture for implementing a method for generating vehicle operation points in a mining area provided in an embodiment of the present application, wherein the system architecture includes: a vehicle-mounted terminal 120 and a cloud 140, and the cloud 140 includes: a monitoring subsystem 140-1, a map update subsystem message 140-2, and a point update subsystem 140-3.

[0030] The vehicle-mounted terminal 120 installs and runs an application program having a method for generating vehicle operation points in a mining area, and the vehicle-mounted terminal 120 is used to send a local point cloud map to the cloud.

[0031] The vehicle terminal 120 is connected to the cloud 140 via a wireless network or a wired network.

[0032] The cloud 140 includes at least one of a server, multiple servers, a cloud computing platform, and a virtualization center. The cloud 140 is used to provide background services for the application of the vehicle-cloud communication method. Optionally, the cloud 140 undertakes the main computing work and the vehicle terminal 120 undertakes the secondary computing work; or, the cloud 140 undertakes the secondary computing work and the vehicle terminal 120 undertakes the main computing work; or, the cloud 140 and the vehicle terminal 120 adopt a distributed computing architecture for collaborative computing.

[0033] Those skilled in the art will appreciate that the number of the above terminals may be more or less. For example, the above terminal may be only one, or the above terminals may be dozens or hundreds, or more. The embodiment of the present application does not limit the number of terminals and device types.

[0034] The present application provides a method for generating a mining vehicle operation point, such as Figure 2 As shown, the method includes: S101, receiving a local point cloud map of a mining area generated by a vehicle-mounted terminal based on first environmental information collected from a target vehicle.

[0035] In an embodiment of the present application, the first environmental information refers to the environmental information around the target vehicle. The first environmental information may be information related to the mining environment around the target vehicle. The first environmental information may also be information related to obstacles around the target vehicle. The first environmental information may be collected by various sensors installed on the target vehicle, such as lidar, high-resolution cameras, real-time motion measurement equipment, and inertial measurement units.

[0036] In an embodiment of the present application, the local point cloud map is a three-dimensional point set map containing local area environmental information, and the local point cloud map generated by the vehicle-mounted terminal is a map containing the mining environment around the target vehicle.

[0037] In an embodiment of the present application, after the vehicle-mounted terminal collects the first environmental information, it constructs a local point cloud map of the mining environment around the target vehicle based on the environmental information, and then sends the local point cloud map to the cloud. The cloud receives the local point cloud map sent by the vehicle-mounted terminal for data update.

[0038] In an embodiment of the present application, the target vehicle is any vehicle in the mining area, that is, all target vehicles in the mining area will collect the first environmental information through the vehicle-mounted terminal, and then generate a local point cloud map based on the first environmental information, and then send the local point cloud map to the cloud, so that the cloud can update the data based on a large number of local point cloud maps, providing comprehensive data update support for the cloud.

[0039] In an embodiment of the present application, after the cloud receives the local point cloud map, it will store the local point cloud map in a database platform, and the database platform is used to store all local point cloud maps and different versions of global point cloud maps.

[0040] In an embodiment of the present application, the vehicle-mounted terminal is also used to receive specific work tasks and path information, and then control the target vehicle to travel to the corresponding work point according to the path information to perform specific work tasks.

[0041] S102: Determine at least one local point cloud map received within a preset time period.

[0042] In an embodiment of the present application, all local point cloud maps received within a preset time period are collected to facilitate subsequent updating of the target global point cloud map. For example, a local point cloud map is collected once every hour. The last time a local point cloud map was collected was 18:00, and the next time a local point cloud map is collected is 19:00.

[0043] In an embodiment of the present application, a monitoring subsystem in the cloud can be responsible for regularly detecting local point cloud maps received in the cloud database. When a new local point cloud map is detected to be stored in the cloud database, all local point cloud maps received within a preset time period will be sent to the map update subsystem in the cloud for updating the target global point cloud map, thereby ensuring the continuity and real-time nature of map updates.

[0044] In the embodiment of the present application, the monitoring subsystem sends the local point cloud map received in the preset time period on the cloud to the map update subsystem, and also sends the current global point cloud map of the mining area to the map update subsystem. Figure 1 At the same time, the map update subsystem is sent so that the map update subsystem can update the map in time.

[0045] S103: Update the current first global point cloud map according to at least one local point cloud map to obtain an updated target global point cloud map.

[0046] In an embodiment of the present application, the global point cloud map refers to a point cloud map containing environmental information of the entire mining area, and the first global point cloud map refers to the latest global point cloud map that characterizes the mining area environment, that is, all current mining area operation tasks are generated based on the first global point cloud map.

[0047] In an embodiment of the present application, the cloud updates the current first global point cloud map based on all local point cloud maps within a preset time period, thereby obtaining an updated target global point cloud map.

[0048] In an embodiment of the present application, a target global point cloud map can be generated by a map update subsystem in the cloud. The map update subsystem receives the local point cloud map sent by the monitoring subsystem, indicating that the global point cloud map representing the mining environment needs to be updated. Therefore, the current first global point cloud map is updated based on all local point cloud maps to obtain an updated target global point cloud map.

[0049] In the embodiment of the present application, since the local point cloud map can only provide environmental information of the local area of ​​the mining area, it is necessary to update it based on the first global point cloud map, and only the area involved in the local point cloud map will be updated. By updating the first global point cloud map through the local point cloud map, real-time update of the mining environment is achieved, and accurate geographic information is provided for target vehicles in the mining area.

[0050] S104, generating operation points of the mining area based on the target global point cloud map and the positions of the dumping area and the loading area of ​​the mining area in the target global point cloud map.

[0051] In an embodiment of the present application, the operation point of a mining area refers to a specific location within the mining area used to carry out specific mining operations. The operation point is used to guide the target vehicle to perform various operation activities within the mining area. For example, the operation point can be a mining point, and the target vehicle moves to the mining point to carry out mining activities; the operation point can also be a transportation point, that is, the starting point or end point of the target vehicle's transportation; the operation point can also be a stacking point, and the target vehicle moves to the stacking point to stack waste or ore.

[0052] In an embodiment of the present application, since the map representing the mining area environmental information has been updated, in order to ensure that accurate geographic information is provided for various operations of the target vehicle, the cloud needs to generate new mining area operation points based on the updated target global point cloud map to ensure that the operation points are generated based on the latest environmental information.

[0053] In an embodiment of the present application, a dumping area and a loading area are provided in the mining area. The dumping area of ​​the mining area is a larger open platform. The dumping area refers to the area for stacking, storing and processing waste generated during the mining process in the mining area. The target vehicle will carry out operations such as waste transportation and waste stacking in the dumping area; the loading area is an area including an entry point, a turning point, a loading position, a loading position and an exit point. The loading area of ​​the mining area is specifically used for loading ore, waste soil, tailings or other mined materials. The target vehicle will carry out material loading operations in the loading area.

[0054] In the embodiment of the present application, the operating points in the mining area are mainly concentrated in the dumping area and loading area of ​​the mining area. Therefore, it is necessary to first determine the positions of the dumping area and loading area of ​​the mining area in the target global point cloud map, and then generate the operating points of the mining area.

[0055] In an embodiment of the present application, a point update subsystem in the cloud for generating work points can be used to generate work points in the mining area based on the target global point cloud map and the positions of the mine's dumping area and loading area in the target global point cloud map.

[0056] The method for generating vehicle operation points in a mining area provided in an embodiment of the present application receives a local point cloud map of the mining area generated by a vehicle-mounted terminal based on the first environmental information of the target vehicle collected, confirms that all local point cloud maps received by the cloud within a preset time period are updated based on all received local point cloud maps to the current first global point cloud map, and obtains an updated target global point cloud map. Based on the target global point cloud map and the positions of the dumping area and the loading area of ​​the mining area in the target global point cloud map, the operation points of the mining area are generated. By receiving the local point cloud map generated by the vehicle-mounted terminal of each target vehicle based on the first environmental information, the local point cloud map of each area in the mining area can be obtained efficiently and conveniently, so that the cloud can update the first global point cloud map according to the received local point cloud map, thereby realizing a rapid update of the map of the mining area, and then generates the operation points of the mining area according to the target global point cloud map, ensuring the synchronous update of the operation points and the mining area map, ensuring the real-time and accuracy of the operation points, and significantly improving the operation efficiency and safety of the target vehicles in the mining area.

[0057] Based on the above embodiments, as an optional embodiment, the operation points in the mining area include the operation points in the dumping area, and the method for generating the operation points in the dumping area is as follows: Figure 3 The specific contents include: S201, determining a bounding box of a soil dumping area in a target global point cloud map, and performing expansion processing on the size of the bounding box to obtain a first expansion area; S202, determining the height of each sampling point in the first extended area based on the target global point cloud map, and determining a first road surface area in the first extended area from the target global point cloud map based on the height of each sampling point; the height of any sampling point in the first road surface area is less than a first height threshold; S203, performing smoothing processing on the first road surface area in the target global point cloud map, performing edge detection on the first road surface area after the smoothing processing, and performing contour extraction on the first road surface area after the edge detection to obtain a first point set representing the contour of the first road surface area; S204, simplifying the contour curve represented by the first point set to obtain a first target point set representing the simplified contour curve; S205, taking the area corresponding to the first target point set in the target global point cloud map as the first target road surface area, and determining a plurality of candidate operation points in the first target road surface area; S206, selecting an operation point that meets a preset evaluation standard from a plurality of candidate operation points as an operation point in the dumping area.

[0058] In S201 of the embodiment of the present application, the bounding box of the soil disposal area is a rectangular box that describes the boundary of the soil disposal area in the target global point cloud map. Dilatating the bounding box refers to enlarging the size of the bounding box, that is, expanding the area of ​​the soil disposal area, thereby obtaining a first expanded area.

[0059] In one example, the coordinates of the soil discharge area on the target global point cloud map are determined, and the soil discharge area is expanded in four directions of up, down, left and right according to a preset expansion distance. That is, on the X-axis, the left and right boundaries of the enclosing box are expanded outward by a preset expansion distance, and on the Y-axis, the upper and lower boundaries of the enclosing box are expanded by a preset expansion distance, thereby obtaining a first expansion area.

[0060] In the embodiment of the present application, the preset extension distance can be determined based on factors such as the operational requirements, safety distance and terrain of the dumping area.

[0061] In the embodiment of the present application, by expanding the enclosing frame of the earth discharge area, a safer, more flexible and efficient working environment is provided for the earth discharge operation. By expanding the scope, the safety of equipment and personnel can be ensured and sufficient space can be reserved for the transportation channel.

[0062] In S202 of the embodiment of the present application, after determining the area of ​​the first extended area in the target global point cloud map, it is necessary to extract the first road surface area in the first extended area. The first road surface area refers to the area where the target vehicle can travel. In order to extract the first road surface area in the first extended area, it can be determined based on the height of each sampling point in the first extended area. For sampling points with too high a height, it is obviously not a sampling point in the area where the vehicle can travel. Therefore, by setting a first height threshold, sampling points in the first extended area whose height is less than the first height threshold can be extracted, thereby obtaining the first road surface area in the first extended area, that is, the height of any sampling point in the first road surface area is less than the first height threshold.

[0063] In an embodiment of the present application, the first height threshold can be set based on the wheel radius of the target vehicle. In order to ensure that the vehicle can drive normally, the height of the ground is usually not higher than the wheel radius. Therefore, the first height threshold can be set to a number smaller than the wheel radius.

[0064] In S203 of the embodiment of the present application, smoothing the extracted first road surface area refers to smoothing each sampling point in the first road surface area, thereby obtaining a smoothed first road surface area with reduced noise and fluctuations, edge detection on the smoothed first road surface area refers to extracting an edge image of the first road surface area, and contour extraction on the first road surface area after edge detection is to identify the various connected areas in the edge image as contour lines, thereby obtaining a first point set representing the contour of the first road surface area.

[0065] In one example, a 4×4 mean filter is used to filter each sampling point in the first road surface area to generate new smoothed height data, and the new height data replaces the original height data to obtain the smoothed first road surface area. After obtaining the smoothed first road surface area, the edge of the first road surface area is determined by an edge detection algorithm such as Canny edge detection or Sobel edge detection. Based on the first road surface area after edge detection, contour extraction is performed to determine the contour of the first road surface area, thereby obtaining a first point set representing the contour of the first road surface area.

[0066] In S204 of the embodiment of the present application, the contour curve represented by the first point set may be simplified by a simplification algorithm, such as using a Douglas-Peucker algorithm to simplify the curve, thereby obtaining a first target point set representing the simplified contour curve.

[0067] In one example, by setting a preset screening distance threshold, sampling points in a first point set representing a contour curve are eliminated to obtain a first target point set representing a simplified contour curve, and a vertical distance from the eliminated sampling points in the first point set to a straight line segment formed by two points in the first target point set is less than a preset distance threshold. By setting the preset distance threshold, it is possible to ensure that the simplified contour is highly similar to the original contour while eliminating redundant points, thereby obtaining an accurate and efficient pavement area of ​​a loading zone.

[0068] In an embodiment of the present application, unnecessary intermediate points are removed by simplifying the contour curve, which greatly reduces storage requirements, and the simplified contour contains fewer points, that is, the points in the first target point set are fewer than the points in the first point set, which can speed up path calculation and optimization.

[0069] In S205 of the embodiment of the present application, the operation point in the spoil area must be located in the first target road surface area. Therefore, the area corresponding to the first target point set in the target global point cloud map is used as the first target road surface area, and the candidate operation point is determined from the first target road surface area.

[0070] In one example, the area corresponding to the first target point set is taken as the first target road surface area, that is, the area where the target vehicle can operate, and candidate operation points are selected from the first target road surface area. The candidate operation points can be selected in a manner that the candidate operation points are spaced at a preset interval distance.

[0071] In S206 of the embodiment of the present application, all candidate work points are comprehensively evaluated according to preset evaluation criteria, and work points that do not meet the work conditions are eliminated, so as to obtain work points that meet the preset evaluation criteria as work points in the spoil area.

[0072] In the embodiment of the present application, the preset evaluation criteria are set based on screening any factors that affect the operation of the target vehicle, such as steep and unstable terrain, failure to meet the operating specifications of the dumping area, and a large number of ground obstacles.

[0073] In the above scheme, the area is expanded based on the soil dumping area to obtain the first expansion area, and then the first pavement area in the first expansion area is determined according to the height of each sampling point in the first expansion area and the first height threshold; then the first pavement area is smoothed, edge detected and contour extracted to obtain the first point set representing the contour of the first pavement area, and the points in the first point set are simplified according to the simplification algorithm to obtain the first target point set, thereby obtaining an accurate and simple-shaped first target pavement area; candidate operation points are determined from the first target pavement area, and operation points that meet the preset evaluation criteria are selected from multiple candidate operation points as the operation points of the soil dumping area. Through this refined point generation and management strategy, the system can ensure the efficiency and safety of open-pit mining operations and minimize human intervention, thereby improving overall operation efficiency.

[0074] Based on the above embodiments, as an optional embodiment, the preset evaluation criteria include: The curvature of the candidate operation point is not greater than the preset curvature threshold; The normal line of the candidate operation point does not face the target discharge line of the discharge area; The first obstacle ratio corresponding to the candidate operation point is not greater than the preset identification frame obstacle ratio threshold; The second obstacle ratio corresponding to the candidate operation point is not less than the preset tail obstacle ratio threshold; The distance between the candidate operation point and the target dumping line is not greater than the preset distance threshold; The candidate operation point is located in the dumping area.

[0075] In an embodiment of the present application, the curvature and normal of each candidate operating point are calculated based on the target global point cloud map.

[0076] In an embodiment of the present application, the curvature of the candidate work point is used to describe the steepness of the terrain of the candidate work point. The larger the curvature of the candidate work point, the steeper the terrain at the location of the candidate work point. Therefore, the work points that are too steep and inconvenient for the target vehicle to communicate can be screened out by setting a preset curvature threshold. Only the terrain of the candidate work points whose curvature is below the preset curvature threshold is smooth and meets the requirements.

[0077] In the embodiment of the present application, the target dumping line of the dumping area is used to indicate the maximum boundary of earthwork accumulation to ensure that the dumping activity does not exceed the specified area. This is an important criterion for mining and dumping operations, the purpose of which is to effectively plan the earthwork accumulation area to avoid adverse effects on the surrounding environment and the mining area itself.

[0078] In an embodiment of the present application, the normal of the candidate work point is used to characterize the direction of the work point. The work point whose normal is facing the target soil discharge line does not comply with the work specifications, which will increase safety risks and violate engineering design specifications. Therefore, the candidate work points can be screened by setting the normal of the work point not to be allowed to face the target soil discharge line.

[0079] In an embodiment of the present application, the curvature of the candidate operating point can be calculated by selecting a point set and fitting a circle, and the normal of the candidate operating point can be estimated by the slope between adjacent candidate operating points.

[0080] In the implementation of the present application, for each candidate work point in the target global point cloud map, when the identification box representing the target vehicle is located at the candidate work point, the first obstacle ratio within the identification box is determined to obtain the first obstacle ratio corresponding to the candidate work point.

[0081] In an embodiment of the present application, when screening candidate work locations in the spoil dumping area, it should be ensured that when the target vehicle drives to the work location, there are no obstacles at the work location that can affect the vehicle's driving or operation. Therefore, the candidate work locations are screened by pre-setting the identification box obstacle ratio threshold, and the selected work location will not affect the target vehicle.

[0082] In an embodiment of the present application, by placing an identification box representing the target vehicle at each candidate work point and calculating the ratio of obstacles in the identification box to the identification box, the first obstacle ratio corresponding to each candidate work point is obtained to simulate the impact of obstacles at each candidate work point on the target vehicle when the target vehicle is at each candidate work point. The larger the first obstacle ratio, the greater the impact on the target vehicle at the current candidate work point. Therefore, the work point whose first obstacle ratio is not greater than the preset identification box obstacle ratio threshold is selected as the work point in the soil discharge area.

[0083] In an embodiment of the present application, the point cloud data within the identification box in the global point cloud map can be determined through the target global point cloud map, the coordinates of the candidate work points, and the size of the identification box, and obstacle detection can be performed on the point cloud data within the identification box. The proportion of the obstacle within the identification box is calculated based on the detection results, thereby obtaining the first obstacle proportion corresponding to the candidate work point.

[0084] In an embodiment of the present application, for each candidate work point in the target global point cloud map, the candidate work point is used as the starting point, and the identification frame is moved toward the retaining wall of the spoil dumping area until the area in the identification frame representing the rear wheels of the target vehicle contacts the retaining wall, and the second obstacle ratio in the tail area of ​​the identification frame is determined to obtain the second obstacle ratio corresponding to the candidate work point.

[0085] In the embodiment of the present application, the earth-dumping area is a relatively large open platform. The edge of the earth-dumping area is provided with a retaining wall of a preset height, and the outside is a steep slope for dumping earth. When the rear wheels of the target vehicle are against the retaining wall, there must be a certain proportion of obstacles in the rear area of ​​the identification frame. In order to ensure the safety of the operation, the working point in the earth-dumping area needs to be near the retaining wall. Therefore, by setting a preset rear obstacle ratio, candidate working points that are far away from the retaining wall or where no retaining wall is set are screened.

[0086] In an embodiment of the present application, the target global point cloud map, the coordinates of the candidate work points, and the size of the identification frame can be used, and then the identification frame can be moved in the direction of the retaining wall until the area representing the rear wheels of the target vehicle contacts the retaining wall. The point cloud data in the tail area of ​​the identification frame in the global point cloud map at this time can be determined, and obstacle detection is performed on the point cloud data in the tail area of ​​the identification frame. The proportion of the obstacle in the tail area of ​​the identification frame is calculated based on the detection result, thereby obtaining the second obstacle proportion corresponding to the candidate work point.

[0087] In an embodiment of the present application, for each candidate operation point in the target global point cloud map, the distance between the candidate operation point and the target dumping line in the dumping area is calculated, and it is determined whether the candidate operation point is in the dumping area.

[0088] In an embodiment of the present application, when the work point is far away from the target earth discharge line, the transportation time and driving distance required for the target vehicle to perform earth discharge operations will be greatly increased, thereby reducing the overall work efficiency and increasing operating costs. Therefore, by setting a preset distance threshold, the work points whose distance from the target earth discharge line is not greater than the preset distance threshold are screened out from the candidate work points, that is, the work points close to the target earth discharge line are selected.

[0089] In an embodiment of the present application, the coordinates of each candidate work point and the target soil discharge line on the target global point cloud map are determined, and based on the coordinates of the candidate work point and the coordinates of the target soil discharge line, the vertical distance from the candidate work point to the target soil discharge line is calculated to obtain the distance between the candidate work point and the target soil discharge line in the soil discharge area.

[0090] In the embodiment of the present application, by requiring all operation points to be located in the soil dumping area and not more than the set threshold from the soil dumping line, the rationality and safety of waste soil dumping can be ensured, thus avoiding waste soil dumping beyond the predetermined area, resulting in unnecessary waste of resources or environmental pollution.

[0091] In the embodiment of the present application, an operation point that meets a preset evaluation standard is selected from a plurality of candidate operation points as the operation point in the dumping area.

[0092] In an embodiment of the present application, the curvature, normal, first obstacle ratio, second obstacle ratio, distance from the target dumping line and preset evaluation criteria corresponding to each candidate work point are used to screen out the work points that meet all conditions in the preset evaluation criteria as the work points in the dumping area from all candidate work points.

[0093] refer to Figure 4 As shown, it exemplarily shows a flow chart of a method for selecting an operation point that meets a preset evaluation standard, and the specific contents include: S301, determine whether the curvature of the candidate operation point is greater than the curvature threshold; if not, execute S302, if yes, execute S308; S302, determining whether the normal line of the candidate operation point is toward the target discharge line of the discharge area, if not, executing S303, if yes, executing S308; S303, determining whether the first obstacle ratio corresponding to the candidate operation point is greater than a preset identification frame obstacle ratio threshold; if not, executing S304; if yes, executing S308; S304, determining whether the second obstacle ratio corresponding to the candidate operation point is less than a preset tail obstacle ratio threshold; if not, executing S305; if yes, executing S308; S305, determining whether the distance between the candidate operation point and the target dumping line is greater than a preset distance threshold; if not, executing S306; if yes, executing S308; S306, determine whether the candidate operation point is not in the soil dumping area; if not, execute S307; take the current candidate operation point as the operation point in the soil dumping area, if yes, execute S308; S307, taking the current candidate operation point as the operation point in the dumping area; S308: Determine whether the current candidate operation point is unavailable.

[0094] In the above scheme, by excluding those candidate working points that are not suitable for working due to steep terrain, obstacles or other unsafe factors, the working points in the dumping area are accurately and effectively generated.

[0095] Based on the above embodiments, as an optional embodiment, the operation points in the dumping area are stored in a temporary buffer area.

[0096] In the embodiment of the present application, after the working position of the soil dumping area is determined, the relevant information of the working position of the soil dumping area is stored in a temporary buffer area. When the working position of the soil dumping area needs to be assigned to the target vehicle, the relevant information of the working position is directly obtained from the temporary buffer area. In the embodiment of the present application, a method for managing the working position of the soil dumping area is proposed, such as Figure 5 The specific contents are as follows: S401, determining the job tasks to be assigned; S402, obtaining at least one target operation point from the temporary buffer area based on the operation task to be assigned, and deleting the at least one target operation point from the temporary buffer area; S403, generating path information based on at least one target operation point, and sending an operation task including the path information to the vehicle terminal; S404, when it is determined that the number of working points in the temporary cache area is less than the preset point number threshold, new working points in the dumping area are generated based on the currently applied global point cloud map and the dumping area, and the working points stored in the temporary cache area are updated.

[0097] In S401 of the embodiment of the present application, the current work task to be assigned is determined. The purpose of determining the work task to be assigned is to determine the work point required for executing the work task to be assigned.

[0098] In S402 of the embodiment of the present application, at least one target operation point is obtained from the temporary cache area according to the task to be assigned. All target operation points obtained from the temporary cache area need to be deleted from the temporary cache area to avoid obtaining used operation points when the next operation point allocation is performed.

[0099] In an embodiment of the present application, when taking work points from a temporary buffer area, they can be taken out from the temporary buffer area in an intermittent manner. The intermittent taking method can distribute tasks more evenly, ensuring that all points in the soil discharge area can receive appropriate work arrangements, avoiding excessive concentration of work in a certain area, and the intermittent taking method can disperse the selection of work points, ensuring that the target vehicle's operation path is more flexible, avoiding mutual interference between target vehicles, and improving the overall fluidity of the operation.

[0100] In S403 of the embodiment of the present application, path information is generated based on at least one target operation point, and then the operation task containing the path information is sent to the vehicle-mounted terminal, so that the vehicle-mounted terminal travels to the target operation point according to the path information to perform the operation task.

[0101] In S404 of the embodiment of the present application, when it is monitored that the number of working points in the temporary cache area is less than the preset point quantity threshold, it means that the working points currently stored in the temporary cache area are insufficient to support the next allocation. Therefore, the generation operation of the working points in the earth discharge area is re-executed based on the current global point cloud map, and the generated new working points in the earth discharge area are stored in the temporary cache area to realize the update of the working positions stored in the temporary cache area.

[0102] It should be noted that the embodiment of the present application does not specifically limit the execution order of S404. Once it is monitored that the working points in the temporary buffer area are insufficient to support the next point allocation, the working points in the soil discharge area are generated based on the current global point cloud map.

[0103] In the above scheme, all the generated operation points of the soil discharge area are stored in a temporary buffer area and retrieved when they are needed for allocation. When the points are insufficient to support the next allocation, the points are generated based on the global point cloud map currently being applied, thereby improving the utilization rate of the points and reducing manual intervention. The target operation points are obtained from the temporary buffer area based on the interval retrieval method, which not only avoids the burden of excessive concentration, but also can distribute tasks more evenly, avoid excessive concentration of operations in certain areas, and ensure that all points in the mining area can get appropriate operation arrangements, thereby maximizing the utilization rate of the operation points, reducing operation delays and resource waste caused by improper selection of operation points, and also reducing the workload of manual soil clearing.

[0104] Based on the above embodiments, as an optional embodiment, the operation points in the mining area include the operation points in the loading area, and the method for searching the operation points in the loading area is as follows: Figure 6 The specific contents are as follows: S501, determining a bounding box of a loading area in a target global point cloud map, and dilating the size of the bounding box of the loading area to obtain a second extended area; S502, determining the height of each sampling point in the second extended area based on the target global point cloud map, and determining a second road surface area and a retaining wall area in the second extended area from the target global point cloud map based on the height of each sampling point; the height of any point in the second road surface area is less than the first height threshold, and the height of any point in the retaining wall area is higher than the second height threshold; S503, smoothing the second road surface area and the retaining wall area in the target global point cloud map, performing edge detection on the second road surface area after the smoothing, and extracting the contour of the second road surface area after the edge detection to obtain a second point set representing the contour of the second road surface area; S504, simplifying the contour curve represented by the second point set to obtain a second target point set representing the simplified contour curve; S505: Taking the area corresponding to the second target point set in the target global point cloud map as the second target road surface area, and determining the operation point in the loading area based on the second target road surface area and the retaining wall area.

[0105] In S501 of the embodiment of the present application, the bounding box of the loading area is a rectangular box that describes the boundary of the loading area in the target global point cloud map, and expanding the bounding box refers to enlarging the size of the bounding box, that is, expanding the area of ​​the loading area, thereby obtaining a second extended area.

[0106] In one example, the coordinates of the loading area on the target global point cloud map are determined, and the loading area is expanded in four directions of up, down, left and right according to a preset expansion distance. That is, on the X-axis, the left and right boundaries of the enclosing box of the loading area are expanded outward by the preset expansion distance, and on the Y-axis, the upper and lower boundaries of the enclosing box are expanded by the preset expansion distance, thereby obtaining a second expansion area.

[0107] In S502 of the embodiment of the present application, after determining the area of ​​the second extended area in the target global point cloud map, the road surface is extracted in the second extended area to obtain the second road surface area. The second road surface area refers to the area in the second extended area where the target vehicle can travel. In order to extract the second road surface area in the second extended area, it can be determined based on the height of each sampling point in the second extended area. For sampling points with too high height, it is obviously not a sampling point in the area where the vehicle can travel. Therefore, by setting a first height threshold, sampling points in the second extended area with a height less than the first height threshold can be extracted to obtain the first road surface area in the second extended area. In other words, the height of any sampling point in the second road surface area is less than the first height threshold; the loading area also includes a retaining wall, and the height of the retaining wall is usually much higher than the height of the drivable ground. Therefore, by setting a second height threshold, the area where the sampling points in the second extended area with a height higher than the second height threshold are located is used as a retaining wall area. In other words, the height of any point in the retaining wall area is higher than the second height threshold.

[0108] In S503 of the embodiment of the present application, smoothing the extracted second pavement area and retaining wall area refers to smoothing each sampling point in the second pavement area and the retaining wall area, which helps to eliminate noise interference and ensure the accuracy of the second pavement area and the retaining wall area. Edge detection is performed on the smoothed second pavement area, which refers to extracting the edge image of the second pavement area. Contour extraction is performed on the second pavement area after edge detection in order to identify the connected areas in the edge image as contour lines, thereby obtaining a second point set representing the contour of the second pavement area.

[0109] In one example, a 4×4 mean filter is used to filter each sampling point in the second road surface area to generate new smoothed height data, and the new height data replaces the original height data to obtain a smoothed second road surface area. After obtaining the smoothed second road surface area, an edge of the second road surface area is determined by an edge detection algorithm such as Canny edge detection or Sobel edge detection. Contour extraction is performed on the second road surface area after edge detection to determine the contour of the second road surface area, thereby obtaining a second point set representing the contour of the second road surface area.

[0110] In S504 of the embodiment of the present application, the contour curve represented by the second point set may be simplified by a simplification algorithm, such as using a Douglas-Peucker algorithm to simplify the curve, thereby obtaining a second target point set representing the simplified contour curve.

[0111] In one example, by setting a preset screening distance threshold, sampling points in the second point set representing the contour curve are eliminated to obtain a second target point set representing the simplified contour curve, and the vertical distance from the eliminated sampling points in the second point set to a straight line segment formed by two points in the second target point set is less than the preset distance threshold. By setting the preset distance threshold, it is possible to ensure that the simplified contour is highly similar to the original contour while eliminating redundant points, thereby obtaining an accurate and efficient pavement area of ​​the loading zone.

[0112] In S505 of an embodiment of the present application, after determining the second target point set, the area corresponding to the second target point set can be used as the second target road surface area on the target global map. The work points in the loading area must be located within the second target road surface area that can be used for the target vehicle to travel, and must maintain a reasonable distance from the retaining wall area. Therefore, based on the second target road surface area and the retaining wall area, the work points in the loading area are determined.

[0113] In the above scheme, the second extended area is obtained by expanding the area in the preset loading area, and then the second road surface area and the retaining wall area are determined based on the first height threshold and the second height threshold, and the second road surface area and the retaining wall area are smoothed, edge detected and contour extracted to obtain a second point set representing the second road surface area, and finally the contour curve represented by the second point set is simplified, and by simplifying the complex terrain data, a drivable, simple and clear second target road surface area is obtained; finally, based on the second target road surface area and the retaining wall area, the working point in the loading area can be determined, and the accuracy of the road surface and the retaining wall area is ensured through the above steps, and finally it is ensured that in the complex and changeable mining environment, the suitable working point can be quickly and accurately located.

[0114] Based on the above embodiments, as an optional embodiment, the method for searching the operation point is as follows: Figure 7 The specific contents include: S601, in the target global point cloud map, moving the identification frame representing the target vehicle to a preset starting point, and determining whether there is a non-ground point in the identification frame; the non-ground point is used to represent a point that does not belong to the second target road surface area; S602, if it is determined that there is a non-ground point in the identification frame, the identification frame is moved along the front direction of the target vehicle in the target global point cloud map until there is no non-ground point in the identification frame, and then based on a first distance between the rear wheels of the target vehicle and the rear of the target vehicle, the identification frame is moved along the rear direction of the target vehicle, and the first position of the identification frame is recorded; S603, in the target global point cloud map, move the identification frame to a preset starting point, move the identification frame along the front direction of the target vehicle until there is no retaining wall area in the identification frame, and record the second position where the identification frame is currently located; S604, in the target global point cloud map, determining the distances between the first position and the second position and the preset starting point respectively, and selecting the position with the larger distance from the first position and the second position as the position of the working point of the loading area.

[0115] In S601 of the embodiment of the present application, in order to search for a suitable point in the loading area as an operation point, it is necessary to simulate the situation of the target vehicle in the loading area based on the target global point cloud map, so as to search for an operation point map in the target global point cloud map. Therefore, the identification frame representing the target vehicle is first moved to the preset starting point, and the point that does not belong to the second target road surface area is regarded as a non-ground point. Then, by determining whether there is a non-ground point in the identification frame, it is determined whether the target vehicle is completely located in the second target road surface area when it is at the preset starting point.

[0116] In an embodiment of the present application, based on the data provided by the target global point cloud map, the preset starting point, the size of the identification box and the second target road surface area, the sampling points within the identification box and the sampling points within the second target road surface area can be determined. If there are sampling points in the identification box that do not exist in the second target road surface area, it can be determined that there are non-ground points in the identification box. If all the sampling points in the identification box exist in the second target road surface area, it can be determined that there are no non-ground points in the identification box.

[0117] In the embodiment of the present application, since the target vehicle is located at the working point in the loading area and the rear wheels of the target vehicle are against the retaining wall, it can ensure that the target vehicle enters the loading area stably and accurately, reduce unnecessary displacement and adjustment, and optimize working efficiency and safety. Therefore, the working point can be searched by simulating the rear wheels of the target vehicle against the retaining wall.

[0118] In S602 of the embodiment of the present application, after determining that there are non-ground points in the identification frame, it means that the current identification frame is not completely in the second target road surface area, that is, the identification frame detects a retaining wall, and therefore it is necessary to move the identification frame away from the retaining wall area, that is, move the identification frame along the front direction of the target vehicle in the target global point cloud map to make the identification frame away from the retaining wall area until there are no non-ground points in the identification frame. Since the retaining wall area in the loading area is inclined outward, even if the rear wheels of the target vehicle abut against the retaining wall area, there is a possibility that the target vehicle will not collide with the retaining wall area. Therefore, after determining that there are no non-ground points in the identification frame, based on the first distance between the rear wheels of the target vehicle and the rear of the target vehicle, the identification frame is moved along the rear direction of the target vehicle, that is, the identification frame is moved to the area close to the retaining wall, thereby simulating the position of the target vehicle on the target global point cloud map when the wheels of the target vehicle abut against the retaining wall, and recording the current first position of the identification frame.

[0119] In the embodiment of the present application, when the target vehicle is located at the operating point in the loading area, when the tail of the target vehicle abuts against the retaining wall, the stability of the target vehicle in the loading area can be ensured, the accuracy and efficiency of the loading operation can be improved, and the risk of displacement of the mine car can be reduced, the use of space can be optimized, and the safety and smoothness of the overall operation can be improved. Therefore, the operating point is searched by simulating the tail of the target vehicle abutting against the retaining wall in the loading area.

[0120] In S603 of the embodiment of the present application, after determining that there are non-ground points in the identification frame, it means that the current identification frame is not completely in the second target road surface area, that is, there are sampling points of the area in the identification frame. In order to simulate the tail of the target vehicle against the retaining wall, the identification frame is moved along the front direction of the target vehicle from a preset starting point in the target global point cloud map to make the identification frame gradually move away from the retaining wall area until there is no retaining wall area in the identification frame, that is, when there is no intersection area between the identification frame and the retaining wall area, the movement of the identification frame is stopped. At this time, the state that the tail of the identification frame just against the retaining wall is simulated, and the second position of the identification frame on the target global point cloud map is recorded.

[0121] In the embodiment of the present application, the execution order of S602 and S603 is not specifically limited. It is possible to first determine the first position of the identification box representing the target vehicle on the target global point cloud map when the rear wheel of the target vehicle abuts against the retaining wall area, or it is possible to first determine the second position of the identification box on the target global point cloud map when the tail of the identification box of the target vehicle abuts against the retaining wall.

[0122] In an embodiment of the present application, after determining the first position when the rear wheels of the target vehicle abut against the retaining wall and the second position when the rear end of the target vehicle abuts against the retaining wall, one position needs to be selected from the above two positions as the position of the working point of the loading area.

[0123] In S604 of the embodiment of the present application, since the working point of the loading area is set at a position close to the retaining wall, the isolation and restraint effect of the retaining wall on the materials can be utilized to improve the safety, efficiency and stability of the operation. Therefore, the working point of the loading area needs to be as close to the retaining wall as possible under the condition that the rear wheels of the target vehicle do not exceed the retaining wall and the rear end of the target vehicle does not exceed the retaining wall. Therefore, by determining the distances between the first position and the second position and the preset starting point respectively in the target global point cloud map, since there are non-ground points in the identification box when the identification box is at the preset starting point, therefore, a position with a larger distance from the first position and the second position is selected as the position of the working point of the loading area, so as to meet the conditions that the rear wheels of the target vehicle do not exceed the retaining wall area and the rear end of the target vehicle does not exceed the retaining wall area, and finally the working point of the loading area is searched out.

[0124] In the above scheme, the search direction of the operating point is determined according to whether there is a non-ground point in the identification frame when the identification frame is at the preset starting point. When there is a non-ground point in the identification frame, it means that the target vehicle is too close to the retaining wall or has overlapped with the retaining wall at the preset starting point. Therefore, it is necessary to move toward the front of the target vehicle, that is, move away from the retaining wall, until there is no non-ground point in the identification frame. Since there is a distance difference between the edge of the identification frame representing the tail of the target vehicle and the rear wheels of the target vehicle, the identification frame is moved again in the direction close to the retaining wall by a first distance to simulate the state of the rear wheels of the target vehicle against the retaining wall, and the position of the current identification frame on the target global point cloud map is recorded to obtain the first position of the target vehicle when the wheels are against the retaining wall; In order to obtain the second position when the rear end of the target vehicle is against the retaining wall, the identification frame is moved from the preset starting point in the direction away from the retaining wall until the retaining wall area can no longer be detected in the identification frame, so as to simulate the state of the rear end of the target vehicle against the retaining wall, and the position of the current identification frame on the target global map is used as the second position when the rear end of the target vehicle is against the retaining wall. Finally, a position far from the preset starting point is selected as the position of the operating point of the loading area, and the identification frame is moved to simulate the rear wheel and the rear end against the retaining wall respectively, and finally the final operating point of the loading area is determined according to the distance between the identification frame and the starting point, which ensures the practicability and safety of the operating point, while also improving the operating efficiency of the operating point, providing strong technical support for high-efficiency operations in mining areas.

[0125] Based on the above embodiments, as an optional embodiment, when it is determined that there is no non-ground point in the identification frame, the method for searching the operation point is as follows: Figure 8The specific contents include: S701, in the target global point cloud map, moving the identification frame along the rear direction of the target vehicle until a non-ground point exists in the identification frame, and then moving the identification frame along the rear direction of the target vehicle based on a first distance between the rear wheels of the target vehicle and the rear of the target vehicle, and recording a third position where the identification frame is currently located; S702, in the target global point cloud map, move the identification frame to a preset starting point, move the identification frame along the rear direction of the parking space of the target vehicle until a retaining wall area exists within the identification frame, and record the fourth position where the identification frame is currently located; S703, in the target global point cloud map, determine the distances between the third position and the fourth position and the preset starting point respectively, and select a position with a smaller distance from the third position and the fourth position as the position of the working point of the loading area.

[0126] In the embodiment of the present application, there are no non-ground points in the identification frame, indicating that the current identification frame is completely in the second target road surface area. Since the working point in the loading area needs to be as close to the retaining wall as possible while the rear wheels of the target vehicle do not exceed the retaining wall and the rear of the target vehicle does not exceed the retaining wall, when it is determined that there are no non-ground points in the identification frame, it is necessary to move closer to the retaining wall to search for the working point.

[0127] In S701 of the embodiment of the present application, the identification frame is moved along the rear direction of the target vehicle from a preset starting point in the target global point cloud map to simulate the target vehicle approaching the retaining wall from the preset starting point until a non-ground point exists in the identification frame, indicating that the current identification frame has just detected the retaining wall. In order to simulate the rear wheels of the target vehicle against the retaining wall, based on the first distance between the rear wheels of the target vehicle and the rear of the target vehicle, the identification frame is moved along the rear direction of the target vehicle, that is, the identification frame is moved a first distance in the direction close to the retaining wall. The current position of the identification frame is the position of the target vehicle when it is against the retaining wall. The position of the identification frame on the target global point cloud map is determined, and the current third position of the identification frame is recorded.

[0128] In the embodiment of the present application, since during the operation in the loading area, the retaining wall usually only moves in one direction, that is, moves to its rear, therefore, in the embodiment of the present application, within the search cycle of the new operation point, when it is determined that there is no non-ground point at the starting point, the search direction is consistent with the moving direction of the retaining wall, that is, moves toward the rear of the target vehicle, so as to avoid repeated searches of outdated areas.

[0129] In S702 of the embodiment of the present application, in order to simulate the rear end of the target vehicle against the retaining wall, starting from a preset starting point in the target global point cloud map, the identification frame is moved along the rear direction of the target vehicle so that the identification frame is close to the retaining wall area until there is a retaining wall area in the identification frame, that is, when the identification frame just intersects with the retaining wall area, the movement of the identification frame is stopped. At this time, the state of the rear end of the target vehicle just against the retaining wall is simulated, and the fourth position of the identification frame currently on the target global point cloud map is recorded.

[0130] In the embodiment of the present application, the execution order of S701 and S702 is not specifically limited. It is possible to first determine that when the rear wheels of the target vehicle are against the retaining wall area, the third position of the identification box representing the target vehicle on the target global point cloud map is determined, or it is possible to first determine that when the tail of the target vehicle is against the retaining wall, the fourth position of the identification box on the target global point cloud map is determined.

[0131] In S703 of the embodiment of the present application, since the working point of the loading area is set at a position close to the retaining wall, the isolation and restraint effect of the retaining wall on the materials can be utilized to improve the safety, efficiency and stability of the operation. Therefore, the working point of the loading area needs to be as close to the retaining wall as possible when the rear wheels of the target vehicle do not exceed the retaining wall and the rear end of the target vehicle does not exceed the retaining wall. Therefore, by determining the distances between the third position and the fourth position and the preset starting point respectively in the target global point cloud map, since there is no non-ground point in the identification box when the identification box is at the preset starting point, therefore, a position with a smaller distance is selected from the third position and the fourth position as the position of the working point of the loading area, so as to meet the conditions that the rear wheels of the target vehicle do not exceed the retaining wall area and the rear end of the target vehicle does not exceed the retaining wall area, and finally the working point of the loading area is searched out.

[0132] In the above scheme, when the identification frame is at the preset starting point and there is no non-ground point in the identification frame, it means that the distance between the target vehicle and the retaining wall is far. Therefore, the operating point should be searched in the direction close to the retaining wall, and the identification frame should be moved toward the rear of the target vehicle until there is a non-ground point in the identification frame. Since there is a distance difference between the edge of the identification frame representing the rear of the target vehicle and the rear wheels of the target vehicle, the identification frame is moved again in the direction close to the retaining wall by a first distance to simulate the state of the rear wheels of the target vehicle against the retaining wall, and the position of the current identification frame on the target global point cloud map is recorded to obtain the third position when the wheels of the target vehicle against the retaining wall; in order to obtain the position of the rear of the target vehicle against the retaining wall The fourth position when the target vehicle hits the retaining wall is determined by moving the identification frame from the preset starting point toward the direction close to the retaining wall until the retaining wall area is detected in the identification frame and stops to simulate the state of the target vehicle's rear end against the retaining wall. The current position of the identification frame on the target global map is used as the fourth position when the target vehicle's rear end is against the retaining wall. Finally, a position close to the preset starting point is selected as the position of the operating point in the loading area. The identification frame is used to simulate the rear wheels hitting the retaining wall and the rear of the vehicle hitting the retaining wall respectively. Finally, the final operating point in the loading area is determined according to the distance between the identification frame and the starting point, which ensures the practicability and safety of the operating point, while also improving the operating efficiency of the operating point, providing strong technical support for high-efficiency operations in mining areas.

[0133] On the basis of the above embodiments, as an optional embodiment, the preset starting point is an operation point of the loading area determined based on the current first global point cloud map.

[0134] In an embodiment of the present application, the working point of the loading area determined by the current first global point cloud map is used as the preset starting point. The working point of the loading area determined based on the global point cloud map before the update can be used as the preset starting point, or the working point searched in the loading area last time can be used as the preset starting point.

[0135] In an embodiment of the present application, based on the work point of the loading area that has been successfully searched as the preset starting point for the search of a new work point, it can ensure that each adjacent area is covered to avoid missing potential work points. At the same time, the search range can be reduced and the search efficiency of the work point can be improved.

[0136] Based on the above embodiments, as an optional embodiment, a method for generating a target global point cloud map is as follows: Fig. 9 The specific contents include: S801, determining a position of at least one local point cloud map on a first global point cloud map; S802, for each local point cloud map, at the position of the local point cloud map in the first global point cloud map, updating the first global point cloud map based on the local point cloud map to obtain an updated first global point cloud map; S803: rasterize the updated first global point cloud map to obtain a target global point cloud map.

[0137] In S801 of the embodiment of the present application, the local point cloud map is a map of a local area of ​​the mining area. Therefore, before updating the global point cloud map of the mining area based on the local point cloud map, it is necessary to first determine the position of the local point cloud map on the first global point cloud map, that is, to align the point cloud in the local point cloud map with the existing point cloud in the global point cloud map, and determine the position of the local point cloud in the global coordinate system.

[0138] In the embodiments of the present application, algorithms such as iterative closest point algorithm, nonlinear optimization algorithm and feature matching algorithm can be generally used to determine the position of the local point cloud in the global coordinate system. By effectively positioning the local point cloud map in the first global point cloud map, accurate position information is provided for updating the global point cloud map.

[0139] In S802 of the embodiment of the present application, after determining the position of each local point cloud map on the first global point cloud map, the local point cloud is fused with the existing global point cloud on the first global point cloud map to obtain an updated first global point cloud map.

[0140] In an embodiment of the present application, the positions corresponding to the local point cloud and the global point cloud can be spliced, or the points in the overlapping area of ​​the local point cloud and the global point cloud can be weighted averaged. At the same time, in order to avoid duplicate points, after the local point cloud map is fused into the first global point cloud map, a deduplication algorithm is used to eliminate redundant information. It should be noted that the specific fusion strategy can be selected according to the application scenario and actual needs of the embodiment of the present application.

[0141] In S803 of the embodiment of the present application, rasterizing the updated first global point cloud map refers to converting the original point cloud data into a regular grid structure. The key to rasterization lies in how to select the resolution of the grid (i.e., the size of the grid unit). The resolution determines the size of the spatial area that each grid unit can represent, which affects the accuracy and amount of calculation after rasterization. The grid size can be set according to actual needs.

[0142] In an embodiment of the present application, the three-dimensional coordinates of each point cloud in the first global point cloud map are mapped to a grid in a two-dimensional grid space, and each grid unit can carry specific information, so that the first global point cloud map becomes a rasterized target global point cloud map.

[0143] In an embodiment of the present application, rasterizing the first global point cloud map to obtain a target global point cloud map can simplify the data structure and reduce the computational complexity, making tasks such as environmental perception and path planning more efficient and stable. The rasterized map not only improves the computational efficiency but can also adapt to different environments and application scenarios.

[0144] In the above scheme, the current first global point cloud map is updated through the local point cloud map uploaded by the vehicle terminal to ensure that the operation point information is synchronized with the actual changes in the mining area operation surface. In addition, the embodiment of the present application can use the local point cloud map uploaded by the vehicle terminal of each target vehicle and the first global point cloud map currently in use to update the geological environment of the mining area in real time, thereby ensuring the real-time and accuracy of the operation point, and significantly improving the efficiency and safety of the operation.

[0145] Based on the above embodiments, as an optional embodiment, the first environmental information includes terrain data and obstacle data within a preset range, and the first environmental information is obtained by the vehicle-mounted terminal through a sensor kit to collect information on the environment within a preset range of the target vehicle; the local point cloud map is obtained by the vehicle-mounted terminal by inputting the first environmental information into a generation model.

[0146] In an embodiment of the present application, a sensor kit is installed on the target vehicle, and the sensor kit may include at least one of the following: a lidar, an ultrasonic sensor, a stereo camera, an inertial measurement unit, a radar, an accelerometer, a temperature sensor, etc. Different sensors can collect different types of first environmental information.

[0147] In an embodiment of the present application, the first environmental information may be obstacles around the target vehicle, such as rocks, walls, and equipment; the first environmental information may also be the height of the terrain around the target vehicle, such as uphill, downhill, or uneven ground; the first environmental information may also be information such as the size, shape, and material of the obstacles.

[0148] In an embodiment of the present application, the vehicle-mounted terminal collects information about the surrounding environment of the target vehicle through a sensor kit installed on the target vehicle, thereby obtaining various types of first environmental information around the target vehicle.

[0149] In an embodiment of the present application, the generation model is trained using the first environmental information of the area where the sample object is located as a training sample and using the local point cloud map corresponding to the area where the sample object is located as a training label.

[0150] In the embodiment of the present application, when training the generation model, a large amount of environmental information (such as terrain information, obstacle information and location information) and the corresponding real point cloud map are required for training. The generation model is intended to generate a point cloud map of a specific area (such as the area where the target vehicle is located) based on the input first environmental information.

[0151] In one example, the sensor suite collects slope information of the surrounding environment, obstacle information, and the position information and orientation of the target vehicle and inputs them into a generation model. The generation model generates an accurate point cloud map based on the above inputs to represent the current environment around the target vehicle.

[0152] In the above scheme, a generation model that can be used to generate local point cloud maps in real time is stored in the vehicle terminal, which can ensure that the local point cloud maps are quickly generated in a dynamic environment, so that the cloud can receive the latest local point cloud maps in time, thereby providing strong information support for the update of the global point cloud map.

[0153] Based on the above embodiments, as an optional embodiment, after the operation points of the mining area are generated, when the display subsystem detects that the operation points of the mining area are generated, a target global point cloud map including the operation points of the mining area is displayed.

[0154] In an embodiment of the present application, when an operating point or a global point cloud map update is detected, the latest global point map and operating point are obtained from the database and displayed intuitively, which not only enables engineering personnel to intuitively view the operating conditions of the mine area, but also enables real-time evaluation of the effectiveness of point generation, thereby achieving efficient supervision of mine operations.

[0155] In the embodiment of the present application, the generated operation points are carefully divided into three categories: used, available, and in use. The used operation points indicate that the operation tasks have been completed, and they may have been developed, mined, or no longer suitable for the current operation needs. Marking as used can help mine managers know clearly which areas have been used, thereby avoiding repeated development or waste of resources; available operation points indicate that they can be used in future operations; in use operation points refer to points that are currently performing operation tasks, which can help managers clearly understand the progress of current operations and which areas are currently operating, avoiding operation conflicts.

[0156] In an embodiment of the present application, by classifying the work points and uploading the classification of each work point to the database, managers can effectively manage resources, optimize work scheduling, ensure safety, and improve work efficiency. Through this classification, mine managers can better understand the progress of operations, resource conditions, and environmental impacts, while providing decision support for job scheduling and resource allocation.

[0157] The present application embodiment provides a device for generating a mining vehicle operation point, such as Fig.10 As shown, the point generation system 100 may include: a receiving module 1001 , a confirmation module 1002 , an updating module 1003 and a generating module 1004 .

[0158] Specifically, the receiving module 1001 is used to receive a local point cloud map of the mining area generated by the vehicle-mounted terminal based on the collected first environmental information of the target vehicle; A confirmation module 1002 is used to determine at least one local point cloud map received within a preset time period; An updating module 1003 is used to update the current first global point cloud map according to at least one local point cloud map to obtain an updated target global point cloud map; The generation module 1004 is used to generate the operation points of the mining area based on the target global point cloud map and the positions of the dumping area and the loading area of ​​the mining area in the target global point cloud map.

[0159] The device of the embodiments of the present application can execute the method provided by the embodiments of the present application, and the implementation principles are similar. The actions performed by each module in the device of each embodiment of the present application correspond to the steps in the method of each embodiment of the present application. For the detailed functional description of each module of the device, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.

[0160] In an embodiment of the present application, an electronic device (computer device / equipment / system) is provided, including a memory, a processor and a computer program stored in the memory, and the processor executes the above-mentioned computer program to implement the steps of a method for generating vehicle operation points in a mining area. Compared with the related art, it can be achieved that: by receiving the local point cloud map generated by the on-board terminal of each target vehicle based on the first environmental information, the local point cloud map of each area in the mining area can be obtained efficiently and conveniently, so that the cloud can update the first global point cloud map according to the received local point cloud map, thereby realizing a rapid update of the map of the mining area, and then generating the operation points of the mining area according to the target global point cloud map, ensuring the synchronous update of the operation points and the mining area map, ensuring the real-time and accuracy of the operation points, and significantly improving the operation efficiency and safety of the target vehicles in the mining area.

[0161] In an alternative embodiment, an electronic device is provided, such as Fig.11 As shown, Fig.11The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present application.

[0162] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0163] The bus 4002 may include a path to transmit information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.11 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0164] The memory 4003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation herein.

[0165] The memory 4003 is used to store the computer program for executing the embodiment of the present application, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the computer program stored in the memory 4003 to implement the steps shown in the above method embodiment.

[0166] Among them, the electronic equipment package may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.11 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0167] The embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented. Compared with the prior art, it can be achieved that: by receiving the local point cloud map generated by the vehicle-mounted terminal of each target vehicle based on the first environmental information, the local point cloud map of each area in the mining area can be obtained efficiently and conveniently, so that the cloud can update the first global point cloud map according to the received local point cloud map, and realize the rapid update of the map of the mining area, and then generate the operation point of the mining area according to the target global point cloud map, ensuring the synchronous update of the operation point and the mining area map, ensuring the real-time and accuracy of the operation point, and significantly improving the operation efficiency and safety of the target vehicle in the mining area.

[0168] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0169] The present application also provides a computer program product, including a computer program, which can implement the steps and corresponding contents of the above method embodiments when executed by a processor. Compared with the prior art, it can achieve: By receiving the local point cloud map generated by the vehicle terminal of each target vehicle based on the first environmental information, the local point cloud map of each area in the mining area can be obtained efficiently and conveniently, so that the cloud can update the first global point cloud map according to the received local point cloud map, realizing the rapid update of the map of the mining area, and then generating the operation point of the mining area according to the target global point cloud map, ensuring the synchronous update of the operation point and the mining area map, ensuring the real-time and accuracy of the operation point, and significantly improving the operation efficiency and safety of the target vehicle in the mining area. The terms "first", "second", "third", "fourth", "1", "2", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described here can be implemented in an order other than the diagram or text description.

[0170] It should be understood that, although each operation step is indicated by arrows in the flowchart of the embodiment of the present application, the implementation order of these steps is not limited to the order indicated by the arrows. Unless clearly stated herein, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flowchart can be performed in other orders according to demand. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on actual implementation scenarios. Some or all of these sub-steps or stages may be executed at the same time, and each sub-step or stage in these sub-steps or stages may also be executed at different times respectively. In different scenarios of execution time, the execution order of these sub-steps or stages may be flexibly configured according to demand, and the embodiment of the present application does not limit this.

[0171] The above are only optional implementation methods for some implementation scenarios of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the scheme of the present application, other similar implementation methods based on the technical ideas of the present application are also within the protection scope of the embodiments of the present application.

Claims

1. A method for generating vehicle operation points in a mining area, characterized in that: The method comprises: Receiving a local point cloud map of the mining area generated by the vehicle-mounted terminal based on the collected first environmental information of the target vehicle; determining at least one local point cloud map received within a preset time period; Updating the current first global point cloud map according to the at least one local point cloud map to obtain an updated target global point cloud map; Based on the target global point cloud map and the positions of the dumping area and the loading area of ​​the mining area in the target global point cloud map, the operation points of the mining area are generated.

2. The method according to claim 1, characterized in that The operation points of the mining area include the operation points in the dumping area, and the method for generating the operation points in the dumping area includes: Determine a bounding box of the soil dumping area in the target global point cloud map, and expand the size of the bounding box to obtain a first extended area; Determine the height of each sampling point in the first extended area based on the target global point cloud map, and determine a first road surface area in the first extended area from the target global point cloud map based on the height of each sampling point; the height of any sampling point in the first road surface area is less than a first height threshold; Smoothing the first road surface area in the target global point cloud map, performing edge detection on the smoothed first road surface area, and extracting contours of the first road surface area after edge detection to obtain a first point set representing the contour of the first road surface area; Simplifying the contour curve represented by the first point set to obtain a first target point set representing the simplified contour curve; Taking the area corresponding to the first target point set in the target global point cloud map as a first target road surface area, and determining a plurality of candidate operation points in the first target road surface area; An operation point that meets a preset evaluation standard is selected from the plurality of candidate operation points as the operation point in the dumping area.

3. The method according to claim 2, characterized in that The step of selecting a work point that meets a preset evaluation standard from the plurality of candidate work points as the work point in the dumping area includes: Calculating the curvature and normal of each candidate operation point based on the target global point cloud map; For each candidate operation point in the target global point cloud map, when the identification frame representing the target vehicle is located at the candidate operation point, determining a first obstacle ratio within the identification frame, and obtaining a first obstacle ratio corresponding to the candidate operation point; For each candidate operation point in the target global point cloud map, take the candidate operation point as the starting point, move the identification frame toward the retaining wall of the dumping area until the area representing the rear wheel of the target vehicle in the identification frame contacts the retaining wall, determine the second obstacle ratio in the tail area of ​​the identification frame, and obtain the second obstacle ratio corresponding to the candidate operation point; For each candidate operation point in the target global point cloud map, calculate the distance between the candidate operation point and the target dumping line in the dumping area, and determine whether the candidate operation point is in the dumping area; An operation point that meets a preset evaluation standard is selected from the plurality of candidate operation points as the operation point in the dumping area.

4. The method according to claim 2, characterized in that: The preset evaluation criteria include: The curvature of the candidate operation point is not greater than a preset curvature threshold; The normal line of the candidate operation point is not oriented toward the target discharge line of the discharge area; The first obstacle ratio corresponding to the candidate operation point is not greater than a preset identification frame obstacle ratio threshold; The second obstacle ratio corresponding to the candidate operation point is not less than a preset tail obstacle ratio threshold; The distance between the candidate operation point and the target dumping line is not greater than a preset distance threshold; The candidate operation point is located within the soil dumping area.

5. The method according to claim 2, characterized in that: The step of selecting a work point that meets a preset evaluation standard from the plurality of candidate work points as the work point in the dumping area further comprises: Storing the operation points in the dumping area in a temporary buffer area; The method further comprises: Determine the tasks to be assigned; Acquire at least one target operation point from the temporary buffer area based on the operation task to be assigned, and delete the at least one target operation point from the temporary buffer area; Generate path information based on the at least one target operation point, and send an operation task including the path information to the vehicle terminal; When it is determined that the number of working points in the temporary cache area is less than the preset point quantity threshold, new working points in the dumping area are generated based on the currently applied global point cloud map and the dumping area, and the working points stored in the temporary cache area are updated.

6. The method according to claim 1, characterized in that The operation points of the mining area include the operation points in the loading area, and the method for searching the operation points in the loading area includes: Determine a bounding box of the loading area in the target global point cloud map, and expand the size of the bounding box of the loading area to obtain a second extended area; Determine the height of each sampling point in the second extended area based on the target global point cloud map, and determine the second road surface area and the retaining wall area in the second extended area from the target global point cloud map based on the height of each sampling point; the height of any point in the second road surface area is less than the first height threshold, and the height of any point in the retaining wall area is higher than the second height threshold; Smoothing the second road surface area and the retaining wall area in the target global point cloud map, performing edge detection on the smoothed second road surface area, and performing contour extraction on the second road surface area after edge detection to obtain a second point set representing the contour of the second road surface area; Simplifying the contour curve represented by the second point set to obtain a second target point set representing the simplified contour curve; An area corresponding to the second target point set in the target global point cloud map is used as a second target road surface area, and an operation point in the loading area is determined based on the second target road surface area and the retaining wall area.

7. The method according to claim 6, characterized in that The step of determining the operation point in the loading area based on the target road surface area and the retaining wall area includes: In the target global point cloud map, the identification frame representing the target vehicle is moved to a preset starting point to determine whether there is a non-ground point in the identification frame; the non-ground point is used to represent a point that does not belong to the second target road surface area; If it is determined that there is a non-ground point in the identification frame, the identification frame is moved along the front direction of the target vehicle in the target global point cloud map until there is no non-ground point in the identification frame, and then based on a first distance between the rear wheels of the target vehicle and the rear of the target vehicle, the identification frame is moved along the rear direction of the target vehicle, and the first position of the identification frame is recorded; In the target global point cloud map, the identification frame is moved to a preset starting point, the identification frame is moved along the front direction of the target vehicle until the retaining wall area does not exist in the identification frame, and the second position where the identification frame is currently located is recorded; In the target global point cloud map, the distances between the first position and the second position and the preset starting point are determined respectively, and a position with a larger distance is selected from the first position and the second position as the position of the working point of the loading area.

8. The method according to claim 7, characterized in that If it is determined that there is no non-ground point in the identification frame, the method includes: In the target global point cloud map, the identification frame is moved along the rear direction of the target vehicle until a non-ground point exists in the identification frame, and then based on a first distance between the rear wheels of the target vehicle and the rear of the target vehicle, the identification frame is moved along the rear direction of the target vehicle, and a third position where the identification frame is currently located is recorded; In the target global point cloud map, the identification frame is moved to a preset starting point, and the identification frame is moved along the rear direction of the parking space of the target vehicle until the retaining wall area is within the identification frame, and a fourth position where the identification frame is currently located is recorded; In the target global point cloud map, the distances between the third position and the fourth position and the preset starting point are determined respectively, and a position with a smaller distance is selected from the third position and the fourth position as the position of the working point of the loading area.

9. The method according to claim 7, characterized in that: The preset starting point is an operating point of the loading area determined based on the current first global point cloud map.

10. The method according to claim 1, characterized in that The updating of the current first global point cloud map according to the at least one local point cloud map to obtain an updated target global point cloud map includes: Determining a position of each of the at least one local point cloud map on the first global point cloud map; For each local point cloud map, at the position of the local point cloud map in the first global point cloud map, updating the first global point cloud map based on the local point cloud map to obtain an updated first global point cloud map; The updated first global point cloud map is rasterized to obtain the target global point cloud map.

11. The method according to claim 1, characterized in that: The first environmental information includes terrain data and obstacle data within a preset range; The first environmental information is obtained by the vehicle-mounted terminal collecting information about the environment within a preset range of the target vehicle through a sensor kit; The local point cloud map is obtained by the vehicle-mounted terminal by inputting the first environmental information into a generation model; The generation model is trained using the first environmental information of the area where the sample object is located as a training sample and using the local point cloud map corresponding to the area where the sample object is located as a training label.

12. The method according to claim 1, characterized in that The step of generating the operation point of the mining area further includes: A target global point cloud map including the operating points of the mining area is displayed.

13. A device for generating vehicle operation points in a mining area, characterized in that: include: A receiving module, used for receiving a local point cloud map of the mining area generated by the vehicle-mounted terminal based on the collected first environmental information of the target vehicle; A confirmation module, used to determine at least one local point cloud map received within a preset time period; An updating module, configured to update the current first global point cloud map according to the at least one local point cloud map to obtain an updated target global point cloud map; A generation module is used to generate the operation points of the mining area based on the target global point cloud map and the positions of the dumping area and the loading area of ​​the mining area in the target global point cloud map.

14. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 12.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

Images