Discharging control method, device and system

Abstract

The embodiment of the invention provides an unloading control method, device and system, a first laser radar and a first camera are arranged above an unloading port, the detection range of the first laser radar covers the unloading port, and the shooting range of the first camera covers the unloading port; the method comprises the following steps: obtaining first point cloud data detected by the first laser radar and a first image shot by the first camera; according to the first point cloud data and the first image, the material pile height of the discharging opening is determined; and when the height of the material pile is not higher than a preset height threshold value, a target vehicle is controlled to unload, the target vehicle is a vehicle reaching an unloading position, and the unloading position is a preset position where the vehicle performs automatic unloading. According to the embodiment of the invention, the automatic driving vehicle can automatically unload materials to the unloading port.

Description

Technical Field

[0001] The present application relates to the technical field of unloading control, and in particular to a unloading control method, device and system. Background Art

[0002] With the development of technology, more and more self-driving vehicles are used to transport materials. Self-driving vehicles can autonomously complete the transportation and unloading of materials. However, at present, when deciding whether to unload materials, it is still necessary to manually observe the fullness of the unloading port and control it through buttons, which cannot realize the automatic control of unloading by self-driving vehicles. Summary of the invention

[0003] The present application provides a material unloading control method, device and system, which can automatically control the unloading of an autonomous driving vehicle without manual control.

[0004] In a first aspect, an embodiment of the present application provides a method for controlling a material discharge, wherein a first laser radar and a first camera are arranged above a material discharge port, the detection range of the first laser radar covers the material discharge port, and the shooting range of the first camera covers the material discharge port; the method comprises:

[0005] Obtaining first point cloud data detected by a first laser radar and a first image captured by a first camera;

[0006] Determine the material pile height at the discharge port according to the first point cloud data and the first image;

[0007] When the height of the material pile is not higher than the preset height threshold, the target vehicle is controlled to unload the material. The target vehicle is the vehicle that reaches the unloading position, and the unloading position is the preset position for the vehicle to automatically unload the material.

[0008] The method directly controls the target vehicle to unload when the conditions are met, thereby realizing automatic control of the target vehicle unloading; moreover, only when the height of the material pile at the unloading port is not higher than the preset height threshold, the target vehicle arriving at the unloading position is controlled to unload, thereby ensuring that the target vehicle can unload successfully, thereby improving the accuracy and reliability of the vehicle's automatic unloading control.

[0009] In a possible implementation, determining the height of the material pile at the discharge port according to the first point cloud data and the first image includes:

[0010] Update the first material pile height of each grid in the grid map according to the first point cloud data and the first image; the grid map is obtained by dividing the plane area of ​​the discharge port into grids;

[0011] The material pile height at the discharge port is determined according to the first material pile height of each grid.

[0012] In a possible implementation, updating the first stockpile height of each grid in the grid map according to the first point cloud data and the first image includes:

[0013] Determine the height of the second stockpile of each grid according to the first point cloud data;

[0014] Determine a third stockpile height of each grid according to the first image;

[0015] Determining a fourth material pile height of each grid according to the second material pile height and the third material pile height of each grid;

[0016] The first material pile height of each grid is updated according to the fourth material pile height of each grid.

[0017] In a possible implementation, determining the height of the second stockpile of each grid according to the first point cloud data includes:

[0018] Determine the point cloud data of each grid from the first point cloud data;

[0019] The maximum height of the points is obtained from the point cloud data of each grid as the second stockpile height of each grid.

[0020] In a possible implementation, updating the first material pile height of each grid according to the fourth material pile height of each grid includes:

[0021] Determine the first material pile height after each grid is updated by using an alpha filtering method according to the fourth material pile height of each grid and the first material pile height before each grid is updated;

[0022] The first material pile height of each grid is updated using the updated first material pile height of each grid.

[0023] In a possible implementation, determining the material pile height at the discharge port according to the first material pile height of each grid includes:

[0024] Determine the confidence of each grid, the confidence of the grid is used to record whether the grid is blocked by the target vehicle;

[0025] The material pile height at the discharge port is determined according to the confidence level of each grid and the first material pile height.

[0026] In a possible implementation, determining the height of the material pile at the discharge port according to the confidence level of each grid and the height of the first material pile includes:

[0027] For each sub-region of the plane area of ​​the discharge port, the height of the stockpile of the sub-region is determined according to the confidence of each grid in the sub-region and the height of the first stockpile; the sub-region is obtained by dividing the plane area of ​​the discharge port;

[0028] The material pile height at the discharge port is determined according to the highest value among the material pile heights of the sub-areas.

[0029] In a possible implementation manner, before determining the material pile height of the discharge port according to the first point cloud data and the first image, the method further includes:

[0030] Calculate the horizontal azimuth angle of each point in the first point cloud data and the target angle of each point; the target angle of each point is the angle between each point and the horizontal plane;

[0031] Grouping the first point cloud data according to the target angle;

[0032] The first point cloud data in each group is sorted according to the horizontal azimuth.

[0033] In a possible implementation, the method further includes:

[0034] When the material pile height at the unloading port is higher than the preset height threshold, and there is no vehicle in the unloading position, and there is a vehicle to be unloaded outside the unloading position, the vehicle at the first position in the queue to be unloaded is determined as the target vehicle;

[0035] Determine the first time for the height of the material pile to drop to a preset height threshold according to the height of the material pile and the descending speed of the material pile, and obtain the second time required for the target vehicle to run to the unloading position;

[0036] When the first time is not greater than the second time, the target vehicle is controlled to run to the unloading position;

[0037] When the first time is greater than the second time, after a third time, the target vehicle is controlled to run to the unloading position, and the third time is the difference between the first time and the second time.

[0038] In a possible implementation, a second laser radar and a second camera are arranged above the unloading area; and the method further includes:

[0039] Obtaining second point cloud data detected by a second laser radar and a second image captured by a second camera;

[0040] When the target vehicle moves to the unloading position, if it is determined based on the second point cloud data and the second image that there is a target object whose running trajectory intersects with the running trajectory of the target vehicle and there is a risk of collision, the target vehicle is controlled to stop moving until the risk of collision ends, and then the target vehicle is controlled to continue moving to the unloading position.

[0041] In a second aspect, an embodiment of the present application provides a discharge control device, wherein a first laser radar and a first camera are arranged above a discharge port, the detection range of the first laser radar covers the discharge port, and the shooting range of the first camera covers the discharge port; the device comprises:

[0042] A data acquisition module, used to obtain first point cloud data detected by a first laser radar and a first image taken by a first camera;

[0043] A height analysis module, used to determine the height of the material pile at the discharge port according to the first point cloud data and the first image;

[0044] The unloading control module is used to control the target vehicle to unload when the material pile height is not higher than the preset height threshold. The target vehicle is the vehicle that reaches the unloading position, and the unloading position is the preset position for the vehicle to automatically unload.

[0045] In a third aspect, an embodiment of the present application provides a server, including:

[0046] Processor, memory; wherein one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the processor, cause the server to execute any method of the first aspect.

[0047] In a fourth aspect, an embodiment of the present application provides a material unloading control system, comprising: a first laser radar, a first camera and the server of the third aspect.

[0048] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes any one of the methods of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 A schematic diagram of a smart mine scenario provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of the detectable area of ​​the laser radar provided in an embodiment of the present application when it is installed horizontally;

[0052] Figure 3 This is an example diagram of the installation method of the laser radar at point 3 provided in an embodiment of the present application;

[0053] Figure 4 A structural schematic diagram of a discharge control system provided in an embodiment of the present application;

[0054] Figure 5 A schematic diagram of a flow chart of a discharge control method provided in an embodiment of the present application;

[0055] Figure 6 A schematic diagram of a method for establishing a radar coordinate system provided in an embodiment of the present application;

[0056] Figure 7 A schematic diagram of a method for establishing a grid map provided in an embodiment of the present application;

[0057] Figure 8 A schematic diagram of a target vehicle covering a discharge port provided in an embodiment of the present application;

[0058] Fig. 9 A schematic diagram of an implementation flow of step 502 in the unloading control method provided in an embodiment of the present application;

[0059] Fig.10 A schematic diagram of an implementation flow of step 901 in the unloading control method provided in an embodiment of the present application;

[0060] Fig.11 A schematic diagram of a sub-region division method provided in an embodiment of the present application;

[0061] Fig.12 A schematic diagram of the principle of calculating the material pile height at the discharge port provided in an embodiment of the present application;

[0062] Fig.13 A schematic diagram of the angle between a point and a horizontal plane and a horizontal azimuth provided in an embodiment of the present application;

[0063] Fig.14 A schematic diagram of the storage structure of the ordered point cloud data of the 32-line laser radar provided in an embodiment of the present application;

[0064] Fig.15 Another schematic flow chart of the unloading control method provided in the embodiment of the present application;

[0065] Fig.16 A schematic diagram of another flow chart of the unloading control method provided in the embodiment of the present application;

[0066] Fig.17 A schematic diagram of another flow chart of the unloading control method provided in the embodiment of the present application;

[0067] Fig.18 A schematic diagram of the structure of a discharge control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0068] The terms used in the implementation section of this application are only used to explain the specific embodiments of this application and are not intended to limit this application.

[0069] With the development of technology, more and more self-driving vehicles are used to transport materials. Self-driving vehicles can autonomously complete the transportation and unloading of materials. However, at present, when deciding whether to unload materials, it is still manually observed that the unloading port is full and controlled by command buttons, which cannot realize the automatic control of unloading by self-driving vehicles.

[0070] Taking the smart mine scenario as an example, the smart mine car (i.e., self-driving vehicle) has the ability of perception and path planning, and can complete the work of material collection, transportation, and discharge. However, the processing of indoor unloading for the "last mile" is still imperfect. The existing technology relies on manual observation of the full warehouse situation of the unloading port and the internal situation of the unloading station, and then manually pressing the unloading command button to control the smart mine car to enter the station to unload. It is impossible to achieve automatic control of the unloading of the smart mine car.

[0071] To this end, the embodiments of the present application provide a unloading control method, device and system that can achieve automated control of unloading of autonomous driving vehicles without the need for manual control.

[0072] This embodiment of the application takes the smart mine scenario as an example to illustrate the unloading control method of this embodiment of the application. Figure 1 As shown, the scene may include: an unloading area, an unloading position, a loading area, and a transportation path between the loading area and the unloading area. The unloading area and the unloading position may be collectively referred to as an unloading station. A unloading port is provided in the unloading area. The autonomous driving vehicle loads materials in the loading area, runs to the unloading station via the transportation path, enters the unloading position, unloads the materials into the unloading port, then exits the unloading position, runs to the loading area via the transportation path to load materials, and repeats the cycle.

[0073] The materials accumulated in the discharge port form a pile. The materials in the discharge port can be continuously discharged through an outlet for crushing and other treatments, and the height of the pile in the discharge port automatically decreases.

[0074] In the embodiment of the present application, three installation points are set, namely point 1 to point 3, and each point is provided with a laser radar and a camera. In order to distinguish in the subsequent description, in the following embodiments, the laser radar and camera set at point 3 are respectively referred to as the first laser radar and the first camera, the laser radar and the camera set at point 2 are respectively referred to as the second laser radar and the second camera, and the laser radar and the camera set at point 1 are respectively referred to as the third laser radar and the third camera.

[0075] Among them, point 1 can be located on the transportation path outside the unloading position, and the distance between it and the unloading position is not limited. The setting height can be higher than the height of the autonomous driving vehicle, so that the third laser radar and the third camera can better complete the data collection work. The number of third cameras set at point 1 can be one or more, as long as the total shooting range of the third camera covers a certain area outside the unloading position, so as to capture the autonomous driving vehicles queued in the area. Similarly, the number of third laser radars set can be one or more, as long as the total measurement range can cover a certain area outside the unloading position, so as to measure the autonomous driving vehicles queued in the area. For example, at Figure 1 In the example, one third laser radar and three third cameras are set at point 1. For example, the total measurement range of the third laser radar at point 1 and the total shooting range of the third camera cover the transportation path area within 100 meters outside the unloading position, so that the vehicles located at the front position of the queue to be unloaded outside the unloading position can be detected, and the vehicles in the queue to be unloaded can be accurately controlled to enter the unloading position in sequence.

[0076] Point 2 may be located above one side of the unloading position, and the specific setting height may be higher than the height of the autonomous driving vehicle, so that the second laser radar and the second camera can better complete the data collection work of the unloading position. Figure 1 In the scene diagram shown, point 2 is located on the side of the unloading position. The number of second cameras set at point 2 can be one or more, as long as the total shooting range of the second cameras covers the unloading position. Similarly, the number of second laser radars set can be one or more, as long as the total measurement range of the second laser radars covers the unloading position. For example, Figure 1 In the figure, it is taken as an example that point 2 is provided with a second laser radar and a second camera.

[0077] Point 3 may be located above the discharge port in the unloading area, and the specific setting height may be higher than the height of the autonomous driving vehicle, so that the first laser radar and the first camera can better complete the data collection work of the unloading area (discharging port). Figure 1 In the scene diagram shown, point 3 is located on one side of the unloading position. The number of first cameras set at point 3 can be one or more, as long as the total shooting range of the first cameras covers the unloading area (unloading port). Similarly, the number of first laser radars set can be one or more, as long as the total measurement range of the first laser radars covers the unloading area (unloading port). For example, Figure 1 It is taken as an example that point 3 is provided with a first laser radar and a first camera.

[0078] Understandable, Figure 1The smart mine scene diagram shown is only an example. Other scenes may include Figure 1 The scene shown may include more or fewer areas and more or fewer installation points, as long as the unloading area, unloading point, and the lidar and camera at point 3 are included.

[0079] It should be noted that in other embodiments, the laser radar can also be expanded to other radars.

[0080] It should be noted that the above-mentioned camera can also be called a camera head.

[0081] like Figure 2 As shown, taking the horizontal installation of the laser radar as an example, a schematic diagram of the detectable area of ​​the laser radar is shown. It can be seen that when installed horizontally, the area directly below the laser radar cannot be scanned by the laser radar. If the laser radar is set above the side line of the discharge port, the area above the discharge port cannot be scanned by the laser radar. For this reason, in an embodiment of the present application, when installing the laser radar at point 3, the laser radar can be installed by rotating a certain angle along the x-axis, such as 90 degrees, so that the scanning range of the laser radar can cover the discharge port and the area above the discharge port. For example, Figure 3 As shown in the figure, this is the installation position of the laser radar. The installation position is selected above one side of the discharge port, at a vertical distance of 2.8m from the upper surface of the discharge port, facing the entire discharge port, and the laser beam can scan the entire discharge port.

[0082] Figure 4 A structural diagram of a discharging control system applicable to the discharging control method provided in the embodiment of the present application is shown in FIG. Figure 4 As shown, including:

[0083] Autonomous driving vehicles, lidars and cameras installed at various locations, access gateways, base stations, and edge cloud processing servers.

[0084] Optionally, it may also include: a visualization and dispatching supervision platform, and an emergency remote takeover system.

[0085] Cameras and lidars can communicate with edge cloud processing servers through access gateways and base stations, and autonomous driving vehicles can communicate with edge cloud processing servers through base stations.

[0086] In some embodiments, the above-mentioned base station can specifically be a base station that adopts wireless communication technologies such as 4G technology and 5G technology. Communication connection can be achieved between the base station and the edge cloud processing server, between the base station and the access gateway, and between the base station and the autonomous driving vehicle through wireless communication technology.

[0087] The camera and lidar can be connected to the access gateway via wired or wireless means.

[0088] The camera can send the captured image data to the edge cloud processing server, and the lidar can send the measured point cloud data to the edge cloud processing server;

[0089] The edge cloud processing server can detect the material stacking situation at the unloading port based on the image data and point cloud data received at point 3, and control the automatic entry (automatic operation to the unloading position), unloading, and automatic exit of the autonomous driving vehicle; it can also detect the traffic situation outside the unloading station (such as vehicle operation, queuing, whether there is a blockage, etc.), road conditions, obstacles, foreign object intrusion, emergencies, etc. based on the image data and point cloud data at point 1, and send warning information to a certain vehicle, and can also send emergency stop, restart and other control instructions;

[0090] It is also possible to detect vehicles, spilled objects, foreign object intrusions, emergencies, etc. in the unloading station based on the image data and point cloud data at point 1, and issue decisions such as emergency parking and restarting of vehicles.

[0091] The edge cloud processing server can also synchronize information such as image data taken by the camera, point cloud data measured by the lidar, relevant analysis results and control results to the visualization and scheduling supervision platform. The visualization and scheduling supervision platform can be equipped with a display screen to display the above information to the user, such as early warning information, real-time video images of the unloading station, etc., for users to view, facilitate remote supervision, and realize manual scheduling.

[0092] The emergency remote takeover system can communicate with the visualization and dispatching supervision platform and the autonomous driving vehicle respectively. In the event of an emergency and when the edge cloud processing server is unable to make a decision, the visualization and dispatching supervision platform can activate the emergency remote takeover system, which can take over the control of each autonomous driving vehicle and perform manual intervention.

[0093] See also Figure 1 In the embodiment of the present application, a total of 5 cameras and 3 laser radars are set. In terms of computing power configuration, 1 video channel requires about 12tops, 80-line laser radar requires about 30tops, and 2 32-line laser radars require about 20tops. Considering redundancy and subsequent upgrade issues, the edge cloud processing server needs to be configured with about 200tops of computing power for processing.

[0094] Figure 5 This is a flow chart of the unloading control method of the embodiment of the present application, which can be specifically executed by the edge cloud processing server. Figure 5 As shown, the method may include:

[0095] Step 501: Obtain first point cloud data detected by a first laser radar and a first image taken by a first camera.

[0096] The first laser radar may be one or more. When there are multiple first laser radars, the point cloud data detected by the multiple first laser radars may be combined as the first point cloud data.

[0097] The first camera may be one or more. When there are more than one first camera, the images captured by the first camera may be stitched together, and the stitched image may be used as the first image. The image stitching technology used is not limited in the embodiment of the present application.

[0098] Among them, the first point cloud data detected by the first laser radar can be transmitted to the edge cloud processing server through the access gateway and the base station, and the first image taken by the first camera can also be transmitted to the edge cloud processing server through the access gateway and the base station.

[0099] In some embodiments, the first laser radar and the first camera can work in the same cycle and transmit data to the edge cloud processing server. At this time, the edge cloud processing server in this step can obtain the first point cloud data and the first image of the same cycle.

[0100] Step 502: Determine the material pile height at the discharge port according to the first point cloud data and the first image.

[0101] In some embodiments, considering that the point cloud will lose order after random sampling, voxel filtering and other operations during data processing, the embodiment of the present application may first perform order processing on the first point cloud data before determining the material pile height of the discharge port according to the first point cloud data and the first image, so that the management of the first point cloud data is more orderly, which facilitates the determination of the material pile height according to the first point cloud data in step 502. The specific implementation method of performing order processing on the first point cloud data can refer to the subsequent specific description, which will not be repeated here.

[0102] It is understandable that the edge cloud processing server can periodically execute steps 501 and 502 to periodically determine the height of the material pile at the discharge port.

[0103] Step 503: When the material pile height at the unloading port is not higher than a preset height threshold, control a target vehicle to unload the material. The target vehicle is a vehicle that has reached the unloading position. The unloading position is a preset position for the vehicle to automatically unload the material.

[0104] For ease of explanation, the autonomous driving vehicle will be referred to as the vehicle in the following embodiments of the present application.

[0105] In some embodiments, when the height of the material pile at the unloading port is higher than a preset height threshold, if there is no vehicle at the unloading position, and there is a queue of vehicles waiting to unload outside the unloading position (hereinafter referred to as the queue to be unloaded), the first vehicle in the queue to be unloaded can be determined as the target vehicle, and the target vehicle can be controlled to run to the unloading position; if there is a target vehicle at the unloading position, the target vehicle can be controlled to wait until the height of the material pile is no higher than the preset height threshold, and then the target vehicle is controlled to unload.

[0106] In some embodiments, when the height of the material pile at the unloading port is not higher than a preset height threshold, there may be a situation where there is no vehicle at the unloading position. At this time, if there is a queue to be unloaded outside the unloading position, the edge cloud processing server can determine the first vehicle in the queue to be unloaded as the target vehicle, control the target vehicle to run to the unloading position, and then control the target vehicle to unload.

[0107] When the height of the material pile is not higher than the preset height threshold, if there is no vehicle at the unloading position, it will be unloaded first.

[0108] In the embodiment of the present application, a first laser radar and a first camera are arranged in the unloading area, and the height of the material pile at the unloading port is determined based on the first point cloud data detected by the first laser radar and the first image taken by the first camera. When the height of the material pile at the unloading port is not higher than a preset height threshold, the target vehicle arriving at the unloading position is controlled to unload the material, thereby realizing automatic control of the vehicle unloading; moreover, only when the height of the material pile at the unloading port is not higher than the preset height threshold, the target vehicle arriving at the unloading position is controlled to unload the material, thereby ensuring that the target vehicle can unload successfully, thereby improving the accuracy and reliability of the automatic unloading control of the vehicle.

[0109] The implementation of step 502 is exemplarily described below.

[0110] In the embodiment of the present application, it is assumed that the discharge port is in the shape of a cube, and the upper surface of the cube is missing, so that the material can enter the discharge port from one side of the upper surface. The description of the embodiment of the present application is based on Figure 6 The radar coordinate system shown has the center point of the first laser radar as the origin, the vertical upward direction as the positive direction of the Y axis, the width direction along the upper surface of the discharge port as the X axis, and the long direction as the Z axis. Therefore, the upper surface of the discharge port is parallel to the XZ plane of the radar coordinate system.

[0111] In the embodiment of the present application, the upper surface of the discharge port is divided into multiple grids. Accordingly, the grid map corresponding to the radar coordinate system can be obtained. For example, the length L of the discharge port is 7m and the width W is 2m. Figure 7As shown, the width W of the grid map is 2m, the length L is 7m, the resolution is R*R=0.1*0.1m per grid, and the size of the entire grid map is 20*70 grids. The upper left corner of the grid map is the origin O of the grid map, which is located at (0m, -2.8m, 1m) in the radar coordinate system. By extending each grid in the positive and reverse directions along the Y-axis, the cube corresponding to each grid can be obtained. The point corresponding to each grid is the point located in the cube, in other words, the point whose X and Z coordinate values ​​are located in the grid. In a sense, it can also be considered that the space inside the discharge port and the space above are divided into multiple cubes, each cube is a grid.

[0112] Since it is necessary to mark the discharge port plane area and the upper and lower slopes of the discharge port plane area at the same time, each grid in the constructed grid map has two parameters, namely: the confidence of the grid and the first stockpile height of the grid.

[0113] The confidence of the grid is used to record whether the grid is blocked by the target vehicle; the height of the grid is used to record the maximum height in the point cloud of the area contained in the grid. In some embodiments, the height of the grid can be specifically recorded as the height in the Oy direction relative to the origin of the radar coordinate system, in meters.

[0114] The confidence of the grid may include two states, one is that the grid is blocked by the target vehicle, and the other is that the grid is not blocked by the target vehicle. In some embodiments, a binary state variable s may be used to mark the confidence, where s=1 represents that the grid is not blocked by the target vehicle, and s=0 represents that the grid is blocked by the target vehicle.

[0115] The reason and purpose of recording whether a grid is blocked by a target vehicle through the confidence of the grid is that when a target vehicle blocks the grid, for example Figure 8 As shown, the rear end of the target vehicle's carriage covers the top of the unloading port. Due to the high height of the rear end of the carriage, the image taken by the first camera and the point cloud data detected by the first lidar will be affected by the rear end of the carriage, resulting in the height of the grid blocked by the rear end of the carriage becoming higher. When the height of the material pile at the unloading port is subsequently calculated, if the height of this part of the grid is used, the height of the material pile at the unloading port that is finally calculated will be higher than the actual height of the material pile, and the deviation will be large. As a result, the target vehicle needs to wait for a relatively longer time before it can be controlled to unload, reducing the automatic unloading efficiency of the vehicle.

[0116] The confidence level of the grid and the height of the first stockpile may be updated in real time based on the first point cloud data and the first image.

[0117] In some embodiments, Fig. 9 As shown, step 502 may include:

[0118] Step 901: updating the first stockpile height of each grid in the grid map according to the first point cloud data and the first image.

[0119] Since the first point cloud data and the first image may be periodic, correspondingly, the first material pile height of the grid may be updated based on the first point cloud data and the first image of each period.

[0120] In some embodiments, the initial first pile height of each grid may be zero.

[0121] Step 902: Determine the material pile height at the discharge port according to the first material pile height of each grid.

[0122] In some embodiments, Fig.10 As shown, step 901 may include:

[0123] Step 1001: Determine the height of the second stockpile of each grid according to the first point cloud data.

[0124] In some embodiments, first point cloud data for each grid can be determined from first point cloud data detected by the first laser radar, and the maximum height of the point can be obtained from the first point cloud data for each grid as the second stockpile height for each grid.

[0125] Step 1002: determining a third stockpile height of each grid according to the first image;

[0126] In some embodiments, the third material pile height of each grid can be identified from the first image. The specific image recognition method is not limited in the embodiments of the present application and can be implemented by referring to relevant image recognition technologies.

[0127] Step 1003: determining a fourth material pile height of each grid according to the second material pile height and the third material pile height of each grid;

[0128] In some embodiments, the weight of the second material pile height and the weight of the third material pile height can be preset. For each grid, the first material pile height H1 of the grid is calculated based on the second material pile height H2 and weight A1, and the third material pile height H3 and weight A2 of the grid. For example, the formula can be: H1=H2A1+H3A2+A3, where A3 is an adjustment parameter.

[0129] It should be noted that the specific values ​​of weight A1, weight A2 and adjustment parameter A3 are not limited in the embodiment of the present application.

[0130] Since there will be a slope difference in the front-to-back direction and the left-to-right direction when dumping materials at the discharge port, and the slope in the left-to-right direction is larger, higher in the middle and lower on both sides, to address such a problem, the embodiment of the present application uses the method of directly recording the first material pile height of the grid in the grid map, and the height difference of the area where the grid is located relative to the origin of the radar coordinate system can be recorded. In this way, the slope information of the discharge port plane is described, thereby obtaining the height of the discharge port plane of each grid from the radar installation position.

[0131] Step 1004: Update the first material pile height of each grid according to the fourth material pile height of each grid.

[0132] In some embodiments, for each grid, the first material pile height of the grid may be updated to the fourth material pile height of the grid. In other words, for each grid, the fourth material pile height of the grid may be directly used as the first material pile height of the grid.

[0133] In some embodiments, for each grid, the first material pile height after the grid is updated can be determined using an alpha filtering method based on the fourth material pile height of the grid and the first material pile height before the grid is updated (i.e., the current first material pile height); and the first material pile height after the grid is updated is used to update the first material pile height of the grid.

[0134] The estimation of the first stockpile height of each grid is to estimate the height difference of each grid relative to the origin of the radar coordinate system. The estimated state variable is a continuous value. At this time, considering that the observed value always fluctuates around the true value, and the frequency of the observed value becomes smaller as the observed value is farther away from the true value, it is reasonable to assume that the observed value zh obeys a normal distribution centered on the true value. The first stockpile height h of the grid, that is, the state variable to be estimated, obeys a normal distribution centered on 0 and with a large variance. At this time, alpha filtering can be used to solve this problem.

[0135] Alpha filter is a filter used to smooth data to reduce the impact of noise and fluctuations while retaining the trend and change of the signal. It is often used for filtering and forecasting time series data. The core idea of ​​alpha filtering is to calculate a weighted average as a new estimate based on the current observation value and the previous estimate.

[0136] The formula for the alpha filter is as follows:

[0137] X k =α·Z k +(1-α)·X k-1

[0138] in:

[0139] 1k is the estimated value at time k.

[0140] Z k is the observation at time k.

[0141] α is the smoothing coefficient, which ranges from 0 to 1. It indicates the influence of the current observation on the estimated value. The larger the value, the greater the influence of the current observation, and the smaller the value, the greater the influence of the previous estimate.

[0142] X k-1 is the estimated value at time k-1.

[0143] The advantage of the alpha filter is that it is simple to understand and is suitable for signals with stable trends and small periodicity. However, choosing an appropriate smoothing coefficient α is crucial to the filtering effect. Too small α will cause the filtered signal to be affected by greater noise, while too large α will weaken the changes and trends of the signal.

[0144] Let h(k-1) represent the first material pile height of the grid after the grid is updated to the k-1th measurement data.

[0145] When the grid obtains the kth measurement data z hk After that, the height of the first stockpile of the grid needs to be updated:

[0146] h(k)=h(k-1)+α(z hk -h(k-1))

[0147] The value of α can be estimated according to the following formula:

[0148]

[0149] in, σ Q is the observation noise, σ R is the process noise.

[0150] Among them, the kth measurement data z hk That is, the calculated height of the kth fourth stockpile.

[0151] This filtering is essentially the same as sliding average filtering and low-pass filtering, but the recursive formula makes it easy to call the calculation frequently without taking up too much computing resources.

[0152] In some embodiments, step 902 may specifically include:

[0153] Determine the confidence of each grid, the confidence of the grid is used to record whether the grid is blocked by the target vehicle;

[0154] The material pile height at the discharge port is determined according to the confidence level of each grid and the first material pile height.

[0155] In some embodiments, determining the material pile height of the discharge port based on the confidence of each grid and the first material pile height may include: for each sub-area of ​​the planar area of ​​the discharge port, determining the material pile height of the sub-area based on the confidence of each grid in the sub-area and the first material pile height; the sub-area is obtained by dividing the planar area of ​​the discharge port; and taking the highest value of the material pile heights of the sub-area as the material pile height of the discharge port.

[0156] For example, if Fig.11 As shown, the grid of the grid map is equally divided into four sub-areas, each sub-area is 10*35 grids, occupying 350 grids. For each sub-area, the first stockpile height of the grid with a confidence level of 1 is taken, and the average of the first stockpile heights of each grid is calculated as the stockpile height of the sub-area. Then, the average values ​​of each sub-area are compared to obtain the maximum height value H. (k) , the maximum height value is the distance between the material pile plane at the discharge port and the installation position of the laser radar (that is, the distance from the origin O in the Y direction of the radar coordinate system).

[0157] Based on the maximum height value H (k) The height of the material pile at the discharge port can be calculated according to the following formula, which is the actual height of the material pile:

[0158] d (k) =T l +T p -H (k)

[0159] Where T l The edge of the discharge port (such as Fig.12 The height from the red part in the middle to the bottom of the discharge port in the empty state, T p The edge of the discharge port (such as Fig.12 The height from the red part in the middle to the radar installation location, H (k) is the maximum height of the four sub-areas from the radar installation location at the current moment, d (k) It is the height of the pile at the current moment.

[0160] When the discharge port is empty, the maximum depth of the discharge port can be calculated, and when the discharge port is full, the maximum height of the material pile can be calculated, which serves as the height threshold in the discharge control.

[0161] The following is an exemplary description of the implementation method of orderly processing point cloud data in the embodiment of the present application.

[0162] In the embodiment of the present application, the ordered processing of point cloud data specifically includes: grouping the points in the point cloud data according to the laser transmitters to which they belong, and sorting them according to the horizontal azimuth angles of the laser points.

[0163] like Fig.13 As shown, for any point (x, y, z) in the point cloud, its angle with the horizontal plane can be calculated , and the corresponding horizontal azimuth angle α. Fig.13 In the example, the xy plane is taken as the horizontal plane. It can be understood that the xz plane or the yz plane can also be taken as the horizontal plane, and the embodiment of the present application is not limited thereto.

[0164] based on Fig.13 As shown, the angle between the point (x, y, z) and the horizontal plane is And the specific calculation formula of the horizontal azimuth angle α is as follows:

[0165]

[0166] like Figure 2 As shown in the figure, since the angle between the laser transceiver and the horizontal plane is fixed, the points generated by the same laser transceiver should be on the same cone surface. In other words, if the angle between the two points in the point cloud and the horizontal plane is If the two points are the same, then it can be considered that they are generated by the same laser transceiver. Therefore, the point cloud of any mechanical laser radar can be sorted according to the following steps: For each point in the point cloud, calculate the corresponding horizontal azimuth angle α and the angle with the horizontal plane , and press Group the points; sort the points in each group by α. After the above two steps, an ordered point cloud organized in the form of a matrix can be obtained.

[0167] Fig.14 The storage structure of the ordered point cloud generated by the 32-line laser radar RS-Lidar-32 is shown. m represents the 32-line laser radar, n represents the number of point clouds per frame of each transmission channel at 10Hz, and the data of each row in the matrix is ​​the scanning point obtained by rotating the same laser transmitter of the laser radar to different angles. These points are arranged in order according to the horizontal azimuth. In fact, since the rotation of the laser radar is very stable, the interval between two laser emissions from the same laser is also fixed, so the column number of the point in the matrix can be directly calculated by the following formula:

[0168]

[0169] Among them, ΔT represents the time interval between two laser pulses emitted by the lidar sensor, ω represents the rotation rate of the lidar, in radians; α is Fig.13 The horizontal azimuth of the point shown in .

[0170] Using this structure to store point cloud data can, on the one hand, reflect the positional relationship of the points in the point cloud data. The points of a specified laser emitter can be retrieved by row, and all points of a specified horizontal azimuth can be retrieved by column. This will greatly save the overhead of operations such as point cloud indexing and neighborhood search. On the other hand, this storage structure also reflects the imaging principle of the lidar sensor, which will facilitate the semantic processing of point clouds.

[0171] It can be understood that the point cloud data in the above ordered description of point cloud data can be, for example, the first point cloud data detected by the first laser radar, or the second point cloud data detected by the second laser radar, or the third point cloud data detected by the third laser radar.

[0172] Fig.15 Another flow chart of the discharge control method provided in this application is Figure 5 The difference between the methods shown is mainly that the following steps 1501 to 1503 may be performed after step 502. It should be noted that the edge cloud processing server may decide to perform steps 503 or 1501 based on conditions such as the material pile height at the discharge port.

[0173] Step 1501: When the material pile height at the unloading port is higher than a preset height threshold, there is no vehicle in the unloading position, and there is a vehicle to be unloaded outside the unloading position, the vehicle at the first position in the queue to be unloaded is determined as the target vehicle.

[0174] Step 1502: Determine the first time for the height of the material pile to drop to a preset height threshold according to the material pile height at the unloading port and the material pile descending speed, and obtain the second time required for the target vehicle to run to the unloading position.

[0175] Among them, the descending speed of the material pile can be calculated based on the change in the material pile height at the discharge port detected in multiple consecutive cycles. The specific calculation method can be implemented by referring to the relevant technology, and the embodiments of the present application are not limited.

[0176] Among them, the second time required for the target vehicle to run to the unloading position can be calculated based on the running speed of the vehicle and the distance required to run from outside the unloading position to the unloading position, and pre-stored in the edge cloud processing server; or, it can also be calculated in real time based on the distance between the current position of the target vehicle and the position of the target vehicle in the unloading position and the running speed of the target vehicle; etc.

[0177] Step 1503: When the first time is not greater than the second time, the target vehicle is controlled to run to the unloading position; when the first time is greater than the second time, after a third time, the target vehicle is controlled to run to the unloading position, and the third time is the difference between the first time and the second time.

[0178] In this step, controlling the target vehicle to run to the unloading position may specifically be that the edge cloud processing server sends a control instruction to the target vehicle, instructing the target vehicle to run to the unloading position, and the target vehicle responds to the control instruction and automatically runs to the unloading position.

[0179] In some embodiments, the process of the target vehicle running to the unloading position needs to be transferred from outdoor to indoor. At this time, the GNSS signal is still used to locate the target vehicle. The target vehicle may brake suddenly due to signal delay or interruption, affecting the efficiency and safety of the vehicle entering the station. Therefore, the embodiment of the present application may also include the following processing steps:

[0180] After sending a control command to the target vehicle, the positioning method of the target vehicle is switched from positioning based on GNSS signals to a positioning method combining SLAM positioning and laser radar ranging positioning at the field end. After determining that the target vehicle has left the unloading position based on the position of the target vehicle, the positioning method is switched back to positioning based on GNSS signals. The specific implementation of the positioning method combining SLAM positioning with laser radar ranging positioning at the field end can refer to the relevant positioning technology, and the embodiments of this application will not be repeated.

[0181] Fig.15 The method shown can realize automatic control of the vehicle to the unloading position when the height of the material pile at the unloading port is higher than the preset height threshold. Moreover, when the first time is greater than the second time, it can also ensure that the vehicle runs to the unloading position when the height of the material pile at the unloading port reaches the preset height threshold, thereby improving the automatic unloading efficiency of the vehicle at the unloading position.

[0182] Fig.16 Another flow chart of the unloading control method provided in this application can prevent the collision risk that may occur when the target vehicle runs to the unloading position. Fig.16 As shown, the method may include:

[0183] Step 1601: Obtain second point cloud data detected by a second laser radar and a second image taken by a second camera.

[0184] The second laser radar may be one or more. When there are multiple second laser radars, the point cloud data detected by the multiple second laser radars may be combined as the second point cloud data.

[0185] The second camera may be one or more. When there are more than one second camera, the images captured by the second camera may be stitched together, and the stitched images may be used as the second image. The image stitching technology used is not limited in the embodiment of the present application.

[0186] Among them, the second point cloud data detected by the second laser radar can be transmitted to the edge cloud processing server through the access gateway and the base station, and the second image taken by the second camera can also be transmitted to the edge cloud processing server through the access gateway and the base station.

[0187] In some embodiments, the second laser radar and the second camera can operate in the same cycle and transmit data to the edge cloud processing server. At this time, the edge cloud processing server in this step can obtain the second point cloud data and the second image of the same cycle.

[0188] Step 1602: When the target vehicle is moving to the unloading position, if it is determined based on the second point cloud data and the second image that there is a target object whose running trajectory intersects with the running trajectory of the target vehicle and there is a risk of collision, the target vehicle is controlled to stop moving until the risk of collision ends, and then the target vehicle is controlled to continue moving to the unloading position.

[0189] Fig.16 The method shown can also be executed by the edge cloud processing server. In some embodiments, the edge cloud processing server can also periodically execute step 1601 to monitor the situation of the unloading position based on the second point cloud data and the second image. In the embodiment of the present application, during the process of the target vehicle running to the unloading position, the edge cloud processing server can identify the target vehicle, the position, moving direction, moving speed, motion trajectory, etc. of the target vehicle based on the second point cloud data and the second image. It can also identify objects other than the target vehicle in the unloading position, the position, moving direction, moving speed and motion trajectory of the objects. The edge cloud processing server can predict whether there is a risk of collision between the target vehicle and the above-mentioned objects other than the target vehicle based on the above information. The specific prediction method can be implemented using relevant technologies, and the embodiment of the present application is not limited.

[0190] In some embodiments, the edge cloud processing server can execute based on the third laser radar and the third camera set at point 1. Fig.17 The steps shown are used to determine the queue to be unloaded outside the unloading station.

[0191] Step 1701: Obtain third point cloud data detected by a third laser radar and a third image taken by a third camera.

[0192] The third laser radar may be one or more. When there are multiple third laser radars, the point cloud data detected by the multiple third laser radars may be combined as the third point cloud data.

[0193] The third camera may be one or more. When there are more than one third camera, the images captured by the third camera may be stitched together, and the stitched images are used as the third image. The image stitching technology used is not limited in the embodiment of the present application.

[0194] Among them, the third point cloud data detected by the third laser radar can be transmitted to the edge cloud processing server through the access gateway and the base station, and the third image taken by the third camera can also be transmitted to the edge cloud processing server through the access gateway and the base station.

[0195] In some embodiments, the third laser radar and the third camera can work in the same cycle and transmit data to the edge cloud processing server. At this time, the edge cloud processing server in this step can obtain the third point cloud data and the third image of the same cycle.

[0196] Step 1702: Identify the queue to be unloaded outside the unloading station based on the third point cloud data and the third image.

[0197] Specifically, the edge cloud processing server can perform image recognition, tracking, coordinate conversion and other processing on the third image to obtain the first target data of the vehicle. Similarly, the second target data of the vehicle can be obtained based on the third point cloud data. After the first target data and the second target data of the same vehicle are processed by a fusion algorithm, the target recognition data of the vehicle can be obtained, and the queue to be unloaded outside the unloading station can be determined based on the target recognition data of the vehicle. Among them, the implementation of performing image recognition, tracking, coordinate conversion and other processing on the third image to obtain the first target data of the vehicle can refer to the implementation of related image recognition and tracking technologies, the implementation of obtaining the second target data of the vehicle based on the third point cloud data can refer to the implementation of related target object recognition technologies based on point cloud data, and the specific implementation of the fusion algorithm processing can refer to the implementation of related fusion algorithm technologies, which will not be repeated in the embodiments of this application.

[0198] Fig.18 A structural diagram of a discharge control device provided in an embodiment of the present application is shown in FIG. Fig.18 As shown, the apparatus 1800 may include:

[0199] A data acquisition module 1810 is used to obtain first point cloud data detected by the first laser radar and a first image taken by the first camera;

[0200] A height analysis module 1820, configured to determine a material pile height at the discharge port according to the first point cloud data and the first image;

[0201] The unloading control module 1830 is used to control the target vehicle to unload when the height of the material pile is not higher than a preset height threshold. The target vehicle is a vehicle that has arrived at the unloading position, and the unloading position is a preset position for the vehicle to automatically unload.

[0202] Fig.18The device provided in the illustrated embodiment can be used to execute the technical solution of the method embodiment of the present application. Its implementation principle and technical effects can be further referred to the relevant description in the method embodiment.

[0203] It should be understood that the above Fig.18 The division of the various modules of the device shown is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software calling through processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware. For example, the height analysis module can be a separately established processing element, or it can be integrated in a chip of an electronic device. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or they can be implemented independently. In the implementation process, each step of the above method or each of the above modules can be completed by an integrated logic circuit of hardware in a processor element or instructions in the form of software.

[0204] The embodiment of the present application also provides a server, including a processor and a memory, and the processor is used to implement the method provided in the embodiment of the present application.

[0205] An embodiment of the present application also provides a material unloading control system, comprising: a first laser radar, a first camera and the above-mentioned server.

[0206] The embodiment of the present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the method provided by the embodiment of the present application.

[0207] The embodiment of the present application also provides a computer program product, which includes a computer program. When the computer program is run on a computer, it enables the computer to execute the method provided by the embodiment of the present application.

[0208] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0209] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0210] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0211] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0212] The above is only a specific implementation of the present application. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. The protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for controlling unloading, characterized in that: A first laser radar and a first camera are arranged above the discharge port, the detection range of the first laser radar covers the discharge port, and the shooting range of the first camera covers the discharge port; the method comprises: Obtaining first point cloud data detected by the first laser radar and a first image captured by the first camera; Determine the material pile height of the discharge port according to the first point cloud data and the first image; When the height of the material pile is not higher than a preset height threshold, a target vehicle is controlled to unload the material, wherein the target vehicle is a vehicle that has reached an unloading position, and the unloading position is a preset position for the vehicle to automatically unload the material.

2. The method according to claim 1, characterized in that The determining the material pile height of the discharge port according to the first point cloud data and the first image includes: Update the first material pile height of each grid in the grid map according to the first point cloud data and the first image; the grid map is obtained by dividing the plane area of ​​the discharge port into grids; The material pile height of the discharge port is determined according to the first material pile height of each grid.

3. The method according to claim 2, characterized in that The updating of the first stockpile height of each grid in the grid map according to the first point cloud data and the first image comprises: Determine a second stockpile height of each grid according to the first point cloud data; Determine a third stockpile height of each grid according to the first image; Determining a fourth material pile height of each grid according to the second material pile height and the third material pile height of each grid; The first material pile height of each grid is updated according to the fourth material pile height of each grid.

4. The method according to claim 3, characterized in that The determining the second material pile height of each grid according to the first point cloud data comprises: Determine point cloud data of each grid from the first point cloud data; The maximum height of the points is obtained from the point cloud data of each grid as the second stockpile height of each grid.

5. The method according to claim 3, characterized in that: The updating of the first material pile height of each grid according to the fourth material pile height of each grid comprises: Determine the first material pile height after each grid is updated by using an alpha filtering method according to the fourth material pile height of each grid and the first material pile height before each grid is updated; The first material pile height of each grid is updated using the updated first material pile height of each grid.

6. The method according to claim 3, characterized in that The step of determining the material pile height of the discharge port according to the first material pile height of each grid comprises: Determining a confidence level of each grid, wherein the confidence level of each grid is used to record whether the grid is blocked by the target vehicle; The material pile height at the discharge port is determined according to the confidence level of each grid and the first material pile height.

7. The method according to claim 6, characterized in that The step of determining the material pile height at the discharge port according to the confidence level of each grid and the first material pile height comprises: For each sub-region of the plane area of ​​the discharge port, the height of the material pile of the sub-region is determined according to the confidence of each grid in the sub-region and the height of the first material pile; the sub-region is obtained by dividing the plane area of ​​the discharge port; The material pile height of the discharge port is determined according to the highest value of the material pile heights of the sub-areas.

8. The method according to any one of claims 1 to 7, characterized in that: Before determining the material pile height of the discharge port according to the first point cloud data and the first image, the method further includes: Calculating the horizontal azimuth angle of each point in the first point cloud data and the target angle of each point; the target angle of each point is the angle between each point and the horizontal plane; Grouping the first point cloud data according to target angles; The first point cloud data in each group is sorted according to the horizontal azimuth.

9. The method according to any one of claims 1 to 7, characterized in that: Also includes: When the material pile height at the unloading port is higher than the preset height threshold, and there is no vehicle in the unloading position, and there is a vehicle to be unloaded outside the unloading position, the vehicle at the first position in the queue to be unloaded is determined as the target vehicle; Determine a first time for the height of the material pile to drop to the preset height threshold according to the material pile height and the material pile descending speed, and obtain a second time required for the target vehicle to run to the unloading position; When the first time is not greater than the second time, controlling the target vehicle to run to the unloading position; When the first time is greater than the second time, the target vehicle is controlled to run to the unloading position after a third time, and the third time is the difference between the first time and the second time.

10. The method according to any one of claims 1 to 7, characterized in that: A second laser radar and a second camera are arranged above the unloading area; the method further comprises: Obtaining second point cloud data detected by the second laser radar and a second image captured by the second camera; During the process of the target vehicle running to the unloading position, when it is determined based on the second point cloud data and the second image that there is a target object whose running trajectory intersects with the running trajectory of the target vehicle and there is a risk of collision, the target vehicle is controlled to stop running until the risk of collision ends, and then the target vehicle is controlled to continue running to the unloading position.

11. A discharge control device, characterized in that: A first laser radar and a first camera are arranged above the discharge port, wherein the detection range of the first laser radar covers the discharge port, and the shooting range of the first camera covers the discharge port; the device comprises: A data acquisition module, used to obtain first point cloud data detected by the first laser radar and a first image taken by the first camera; A height analysis module, used for determining the height of the material pile at the discharge port according to the first point cloud data and the first image; The unloading control module is used to control the target vehicle to unload when the height of the material pile is not higher than a preset height threshold. The target vehicle is a vehicle that has reached the unloading position, and the unloading position is a preset position for the vehicle to automatically unload.

12. A server, characterized in that: include: Processor, memory; One or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the processor, enable the server to perform the method according to any one of claims 1 to 10.

13. A material discharging control system, characterized in that: include: A first laser radar, a first camera and the server as described in claim 12.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the method according to any one of claims 1 to 10.

Images