Method, device and equipment for automatic driving of underground carry-scraper and medium

Abstract

The invention provides an automatic driving method, device and equipment for an underground carry-scraper and a medium, and the method comprises the steps: constructing an initial driving map according to initial position data collected in an underground automatic driving process, and carrying out the carrying work based on the initial driving map; when first position data is collected, updating the initial driving map according to the first position data to obtain a first driving map; wherein the first position data is position data different from the initial position data. According to the method, the automatic driving system can be guaranteed to operate orderly, stably and continuously, the environmental adaptability is enhanced, the technical development of the underground mining industry field is promoted, and the intelligentization and industrialization level of the automatic driving field of the underground carry-scraper is promoted.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and more specifically, to a method, device, equipment and medium for autonomous driving of an underground scraper. Background Art

[0002] In today's society, information technology and automated mining technology have made rapid progress. Intelligent mines have become the mainstream trend of future development. In the process of realizing large-scale mining in intelligent mines, underground loader mining and transportation are at the forefront of underground operations. The application of underground loader unmanned driving system is of vital importance to promoting the construction of intelligent mining process in mines.

[0003] The research and development and application of underground unmanned driving systems are in a stage of continuous exploration and improvement, especially in map processing. In the existing technology, the scraper can only work according to the preset map and cannot make timely adjustments when the terrain changes. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide a method, device, equipment and medium for automatic driving of an underground scraper to overcome the problems in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a method for automatic driving of an underground scraper, which acts on a target scraper, and the method includes:

[0006] According to the initial position data collected during the underground automatic driving process, an initial driving map is constructed to perform shovel work based on the initial driving map;

[0007] When the first position data is collected, the initial driving map is updated according to the first position data to obtain a first driving map; wherein the first position data is position data different from the initial position data.

[0008] In some technical solutions of the present application, the above method further includes:

[0009] When the second position data is collected, the first driving map is updated according to the second position data to obtain a second driving map; wherein the second position data is position data different from the initial position data and the first position data.

[0010] In some technical solutions of the present application, the first position data includes first point cloud data and second point cloud data; the first point cloud data is data outside the initial driving map; the second point cloud data is data that has changed in the initial driving map;

[0011] When the first position data is collected, the initial driving map is updated according to the first position data to obtain a first driving map; wherein the first position data is position data different from the initial position data, including:

[0012] When the first position data is the first point cloud data, updating the initial driving map using a first updating method to obtain a first driving map;

[0013] When the first position data is the second point cloud data, the initial driving map is updated using a second updating method to obtain a first driving map.

[0014] In some technical solutions of the present application, the first position data is collected in a relative coordinate system, and the initial driving map is in an earth coordinate system; when the first position data is the first point cloud data, the initial driving map is updated using a first updating method to obtain a first driving map, including:

[0015] Performing coordinate registration on the first point cloud data in the relative coordinate system to obtain a driving map to be updated in the earth coordinate system;

[0016] The driving map to be updated and the initial driving map are merged to obtain the first driving map.

[0017] In some technical solutions of the present application, the above method further includes collecting target point cloud data when collecting the first point cloud data; wherein the target point cloud data is part or all of the point cloud data in the initial position data;

[0018] The step of performing coordinate registration on the first point cloud data in the relative coordinate system to obtain the driving map to be updated in the earth coordinate system includes:

[0019] Determining transformation parameters of the first point cloud data according to the first point cloud data and the target point cloud data;

[0020] Coordinate registration is performed on the first point cloud data according to the transformation parameters to obtain a driving map to be updated in the earth coordinate system.

[0021] In some technical solutions of the present application, when the first position data is the second point cloud data, updating the initial driving map using the second updating method to obtain the first driving map includes:

[0022] The point cloud data in the initial driving map is replaced by the second point cloud data to obtain the first driving map.

[0023] In some technical solutions of the present application, the above method includes:

[0024] The first driving map is sent to other loaders, so that the target loader and the other loaders perform load carrying work based on the first driving map.

[0025] In a second aspect, an embodiment of the present application provides an automatic driving device for an underground scraper, which acts on a target scraper, and the device includes:

[0026] A construction module, used to construct an initial driving map according to the initial position data collected during the underground automatic driving process, so as to perform shoveling work based on the initial driving map;

[0027] An updating module is used to update the initial driving map according to the first position data to obtain a first driving map when the first position data is collected; wherein the first position data is position data different from the initial position data.

[0028] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for automatic driving of an underground loader when executing the computer program.

[0029] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for automatic driving of an underground shovel loader are executed.

[0030] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0031] The method of the present application includes constructing an initial driving map according to initial position data collected during the underground automatic driving process, so as to perform shoveling work based on the initial driving map; when the first position data is collected, the initial driving map is updated according to the first position data to obtain a first driving map; wherein the first position data is position data different from the initial position data.

[0032] This application can ensure the orderly, stable and sustainable operation of the autonomous driving system, enhance environmental adaptability, promote technological development in the underground mining field, and promote the field of underground shovel loaders to move towards intelligence and industrialization.

[0033] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] 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. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 A schematic diagram of a process of an automatic driving method for an underground scraper provided in an embodiment of the present application is shown;

[0036] Figure 2 A schematic diagram of an automatic driving system provided by an embodiment of the present application is shown;

[0037] Figure 3 A schematic diagram of updating an initial driving map with a first point cloud provided in an embodiment of the present application is shown;

[0038] Figure 4 A schematic diagram of an automatic driving device for an underground scraper provided in an embodiment of the present application is shown;

[0039] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0040] Description of the attached figures: 1. Initial driving map; 2. Target loader; 3. Area to be updated. DETAILED DESCRIPTION

[0041] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of order, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0042] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0043] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0044] In today's society, information technology and automated mining technology have made rapid progress. Intelligent mines have become the mainstream trend of future development. In the process of realizing large-scale mining in intelligent mines, underground loader mining and transportation are at the forefront of underground operations. The application of underground loader unmanned driving system is of vital importance to promoting the construction of intelligent mining process in mines.

[0045] The research and development and application of underground unmanned driving systems are in a stage of continuous exploration and improvement, especially in map processing. In the existing technology, the scraper can only work according to the preset map and cannot make timely adjustments when the terrain changes.

[0046] Based on this, the embodiments of the present application provide a method, device, equipment and medium for automatic driving of an underground scraper loader, which is described below through embodiments.

[0047] Figure 1 A schematic flow chart of a method for automatic driving of an underground scraper provided in an embodiment of the present application is shown, wherein the method acts on a remote control system and includes steps S101-S102; specifically:

[0048] S101, constructing an initial driving map according to initial position data collected during the underground automatic driving process, so as to perform shoveling work based on the initial driving map;

[0049] S102. When first position data is collected, update the initial driving map according to the first position data to obtain a first driving map; wherein the first position data is position data different from the initial position data.

[0050] This application can ensure the orderly, stable and sustainable operation of the autonomous driving system, enhance environmental adaptability, promote technological development in the underground mining field, and promote the field of underground shovel loaders to move towards intelligence and industrialization.

[0051] Some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0052] The method in the embodiment of the present application acts on an automatic driving system, which includes a remote control system and a scraper, such as Figure 2 As shown. Among them, the remote control system includes a controller (function buttons, execution handles and display function lights), a server (remote control interface, autonomous interface and management platform), and a switch. The scraper includes an on-board communication interrupter (connected to the remote control system through networking), an on-board industrial computer, a switch, an underlying controller, an electronically controlled modified actuator, an intelligent sensor, a state acquisition sensor and an on-board industrial computer system. Among them, the intelligent sensor is connected to the on-board industrial computer and the switch. Intelligent sensors include lidar, inertial measurement units, anti-collision kits and on-board monitoring systems. The state acquisition sensor is connected to the underlying controller, and the state acquisition sensor includes a hydraulic sensor and a temperature sensor. The on-board industrial computer system can realize anti-collision, coordinate system construction, map construction, positioning, path learning, control instruction techniques, tracking control, map update detection and map update maintenance.

[0053] For the remote control system, it has a simple and clear visual operation interface, which can realize basic operations and instructions, and is mainly responsible for remote monitoring, vehicle control, and intelligent service guarantee functions. It can obtain and monitor the operating status of the self-driving car in real time, including real-time status and key parameters such as speed, position, steering wheel angle, acceleration, etc. Through data analysis, it can timely discover potential vehicle failures or abnormal conditions, and send early warning information to prevent failures.

[0054] The generated driving trajectory accurately controls the vehicle's steering wheel angle and acceleration through the control algorithm to achieve stable driving and trajectory tracking of the vehicle; in emergency situations, it can quickly respond and control the vehicle to perform emergency braking or obstacle avoidance operations to ensure driving safety; based on real-time environmental information, the vehicle's control parameters are dynamically adjusted to optimize driving performance and safety.

[0055] When a vehicle breaks down, remote services can be used to make a preliminary diagnosis and provide repair suggestions and guidance for troubleshooting. Multiple safety mechanisms are in place, such as emergency braking systems and backup power supplies, to ensure vehicle safety at critical moments. Remote communication data is encrypted to prevent data leakage and illegal access, ensuring the security of the communication process.

[0056] For the shovel loader (for the convenience of description, this application will refer to any shovel loader that executes the method as the target shovel loader), the shovel loader automatic driving module has multiple functions such as high-precision positioning and navigation, environmental perception and obstacle avoidance, path planning and automation, remote monitoring and control, vehicle networking and communication, and adaptive update of mapping. These functions together constitute an important part of the underground shovel loader automatic driving system, providing a safer, more efficient, intelligent, stable and sustainable operation solution for underground shoveling.

[0057] Since the satellite positioning system cannot be used in the underground environment, the scraper loader adopts a multi-line laser radar and IMU tightly coupled method to construct a high-precision three-dimensional point cloud map for auxiliary positioning, thereby achieving continuous and high-precision positioning; based on the high-precision three-dimensional map of the underground tunnel and real-time road conditions, the scraper loader vehicle terminal uses the on-board industrial computer module to perform path learning and planning navigation, automatically generates the optimal driving path, and updates and adjusts it in real time to ensure that the vehicle can reach its destination accurately and efficiently.

[0058] The loader integrates multiple sensors such as laser radar (LiDAR), inertial measurement unit (IMU), camera, anti-collision kit, hydraulic sensor, temperature sensor, etc., which can monitor the environmental information of underground tunnels in real time, including road conditions, environmental conditions, obstacle locations, etc.; through intelligent sensing technology, the vehicle terminal can accurately identify obstacles in underground tunnels and measure their distance and speed. According to the obstacle information and vehicle status, the vehicle terminal can independently formulate obstacle avoidance strategies, such as slowing down to avoid, detouring, etc., to ensure driving safety.

[0059] Based on the high-precision map, the vehicle terminal can autonomously learn the path and perform path planning and control for the issuance of subsequent instructions; during vehicle operation, according to the distance and speed of the vehicle or obstacle in front, the vehicle terminal can automatically adjust the vehicle speed and following distance to maintain safe driving; during the loading and unloading of materials or train formation, the vehicle terminal can automatically complete parking and formation operations to improve transportation efficiency.

[0060] The vehicle terminal can upload the vehicle's operating status, location information, fault warning and other data to the remote monitoring center in real time, so that management personnel can conduct real-time monitoring and scheduling; in an emergency, the remote monitoring center can perform emergency braking or intervention operations on the vehicle through the vehicle terminal to ensure driving safety.

[0061] The vehicle terminal supports V2X technology, which enables communication between vehicles and other vehicles, improving road traffic efficiency and safety; the vehicle terminal achieves stable and high-speed communication with the remote monitoring center through a dedicated wireless communication base station underground.

[0062] In an optional embodiment, the target shovel loader can perform automatic driving underground, and collect initial position data of the existing lanes during the automatic driving process. Then, high-precision three-dimensional mapping is performed based on the collected initial position data to form a global map of the original lane (initial driving map), and path planning is performed on this basis to drive to the shoveling point and pour into the shoveling position. The positions of the shoveling point and the surrounding obstacles are collected according to the rear-facing laser radar, and compared with the global map to determine whether it is necessary to locally update the global map; when the map needs to be updated, the position data collected at this time is called the first position data. For example, if it is determined that there are new obstacles or large changes in the original existing lane (initial driving map), which affects the driving and shoveling of the original unmanned shovel loader, it is necessary to update the global map with the local map; or if it exceeds the scope of the existing lane (initial driving map), it is necessary to update the global map with the local map; otherwise, there is no need to locally update the global map, and the shoveling operation continues.

[0063] For example, when the first position data is collected, the initial driving map is updated according to the first position data to obtain a first driving map; wherein the first position data is position data different from the initial position data. Since the present application is a continuous updating process, the target shovel loader will continue to work after the initial driving map is updated. The map will be updated again during the continued working process, that is, when the second position data is collected, the first driving map is updated according to the second position data to obtain a second driving map; wherein the second position data is position data different from the initial position data and the first position data.

[0064] When updating the initial driving map, the embodiment of the present application divides the collected first position data into different types for the above-mentioned different types of situations (increases in existing lanes and changes in existing lanes): first point cloud data and second point cloud data. Among them, the first point cloud data is data outside the initial driving map (increases in existing lanes); the second point cloud data is data that has changed in the initial driving map (changes in existing lanes). For different types of point cloud data, the embodiment of the present application uses different update methods. When the first position data is the first point cloud data, the first update method is used to update the initial driving map to obtain a first driving map; when the first position data is the second point cloud data, the second update method is used to update the initial driving map to obtain a first driving map.

[0065] For the first point cloud data, the target scraper adaptive update mapping process is as follows: Figure 3As shown in the figure, if the map is updated, the unmanned scraper records the local sub-map of the loading point, receives the rearward LiDAR point cloud in real time, and uses the real-time position information collected by the inertial navigation system for high-precision positioning and mapping to generate a new local sub-map; after the new local sub-map is generated, the local dynamic sub-map is updated and integrated into the global map using the deep learning registration algorithm, and the fused information is differentially calculated with the old version of the map, and the changes are detected based on the differential results. After the changes are confirmed, they are sent to all corresponding unmanned scrapers for map incremental update operations (the first driving map is sent to other scrapers). After the scraper updates the global map, it completes the underground loading task according to the latest global map.

[0066] The first position data is collected in a relative coordinate system, and the initial driving map is in an earth coordinate system; when the first position data is the first point cloud data, the initial driving map is updated using a first updating method to obtain a first driving map, including: performing coordinate registration on the first point cloud data in the relative coordinate system to obtain a driving map to be updated in the earth coordinate system; and fusing the driving map to be updated with the initial driving map to obtain the first driving map.

[0067] The method also includes that when the shovel loader collects the first point cloud data, it also collects target point cloud data; wherein the target point cloud data is part or all of the point cloud data in the initial position data; and the first point cloud data in the relative coordinate system is coordinate-aligned to obtain the driving map to be updated in the earth coordinate system, including: determining transformation parameters of the first point cloud data according to the first point cloud data and the target point cloud data; and the first point cloud data is coordinate-aligned according to the transformation parameters to obtain the driving map to be updated in the earth coordinate system.

[0068] Specifically, in view of the characteristics of underground tunnel scenes such as dynamic changes in time and space, weak geometric features, repeated components, and symmetrical structures, this application proposes an improved high-precision deep learning point cloud registration algorithm to ensure that the updated global map remains stable and has higher accuracy, meeting the accuracy requirements of automatic driving of shovel loaders in underground scenes.

[0069] Given N 3D point cloud correspondences are the points in the first and second point clouds respectively. For example, N is two: p i is the point in the overall point cloud data (the first point cloud data and the target point cloud), q i is the point in the target point cloud data. The goal is to calculate the transformation parameters (rotation matrix and translation vectors ):

[0070]

[0071] ρ(a,b) is a distance metric.

[0072] First, voxelize each point cloud to be registered to improve the registration efficiency while ensuring the registration accuracy. Each point cloud map contains the spatial position information (x, y, z) and time series information t∈N of each point. According to the resolution required for remote autonomous driving operations, a voxel model of N point clouds to be registered is established with a given voxel grid size v, and all voxel grids are numbered and recorded as (i, j, k). The information of each voxel unit is represented as:

[0073] I i,j,k =Y(P,t)

[0074] Among them, i, j, k are the serial numbers of the current point cloud in the x-axis, y-axis, and z-axis directions, I is a voxel unit, P is the position information of each point in the voxel unit, and t is the time sequence information of the point cloud. Next, the N point clouds processed by voxelization are aligned with the deep learning network in units of voxels. The input of the deep learning network is the correspondence between the N point clouds, and the output is an N+M+3-dimensional vector. The first N represent the weight vector represents the i-th corresponding pair (p i ,q i ) is the confidence of the internal point. By comparing w i and threshold τ, classify the input voxel correspondence into inliers and outliers. The next M are rotation parameters, i.e. (v1,v2,…,v M ). Although 3D rotation has 3 degrees of freedom, different parameterizations are possible: quaternions, rotation matrices, etc. The remaining three parameters are the translation parameters (t1, t2, t3).

[0075] The method of the present application includes a classification module and a registration module. The classification module includes three parts: a 1×1 convolution layer + C ResNet neural network layers + 1×1 convolution layer. When processing a 6-tuple 3D voxel correspondence set between N point clouds, the N x6 input is transformed into 3D data such as (1, N, 6). The first convolution layer learns the initial feature dimension, generates 128-dimensional features from each point correspondence, and turns it into data with a dimension of (1, N, 128); the next C ResNet neural network modules, each network has a data dimension of (1, N, 128), and the output of the i-th ResNet module is the input of the i+1-th ResNet module; the last convolution layer converts (1, N, 128) into (1, N, 1), and then passes through a hyperbolic tangent function and a ReLU activation function to obtain the weight w∈[0, 1] of each point correspondence, with a dimension of (N).

[0076] The input of the registration module comes from the output of the first convolutional layer of the classification module and the C ResNet neural network modules. Their outputs are of the same dimension (1, N, 128). Pooling is performed on the axis = 2 dimension to obtain (1, 1, 128). The outputs of the C + 1 modules of the classification module are pooled and fused on the axis dimension using the concat fusion method of deep learning, outputting features of (1, C + 1, 128) dimensions; (1, C + 1, 128) passes through a convolution layer with a convolution kernel of 3x 3 and a convolution sampling interval of 1x 2, outputting features of (1, D, 8), which can be converted into (D*8); after 1 or 2 fully connected layers (256 → 256 → M + 3), a vector of (M + 3) is obtained. The first M values ​​represent rotation information, and the following 3 values ​​represent translation information.

[0077] The corresponding loss function of this algorithm includes classification loss function and registration loss function.

[0078] The classification loss function is a cross entropy loss:

[0079]

[0080] Wherein, k represents the kth voxel pair to be registered. represents the classification loss of the kth voxel pair to be registered. is the output of the classification module before the hyperbolic tangent function and the ReLU activation function. The dimension is (N, 1). σ represents the sigmoid activation function. H(…,…) represents the cross entropy loss function. represents the ground truth, and the i-th voxel correspondence is an inlier or outlier. Used to balance the classification loss of the k-th voxel for different categories.

[0081] The registration loss function is:

[0082]

[0083] Where k represents the kth voxel pair to be registered, represents the registration loss of the kth voxel pair to be registered, and ρ represents the distance metric function.

[0084] The classification loss and registration loss together are the overall loss of this algorithm:

[0085]

[0086] Among them, α and β are hyperparameters.

[0087] Assume that the first rotation matrix and translation vector are R 1 ,t1 , the second rotation matrix and translation vector are R 2 ,t 2 , input is X0.

[0088] After the first rotation and translation: X1 = R 1 X0+t 1 ;

[0089] After the second rotation and translation: X2 = R 2 X1+t 2 =R 2 (R 1 X0+t 1 )+t 2 =R 2 R 1 X0+R 2 t 1 +t 2 .

[0090] Therefore, after two rotations and translations, R = R 2 R 1 ,t=R 2 t 1 +t 2 .

[0091] The final point cloud registration result can be obtained by iterative solution. In order to ensure that there is no redundancy in the point cloud map update process, the point cloud in each voxel after the registration is completed is subjected to spatiotemporal analysis, the point cloud data updated in time is retained, and filtered with a certain threshold to update the initial driving map.

[0092] For the second point cloud data, the point cloud is voxelized using the second point cloud data using the voxelization method, and the point cloud data in the initial driving map is replaced based on time to obtain the first driving map.

[0093] This application proposes an underground shovel loader automatic driving system with adaptive updating and mapping, which can ensure the orderly, stable and sustainable operation of the automatic driving system, enhance environmental adaptability, promote technological development in the underground mining field, and promote the field of underground shovel loader automatic driving to the level of intelligence and industrialization.

[0094] This application proposes a complete unmanned driving system for underground shovel loaders. The underground environment is complex and there are many safety hazards. Accidents may easily occur due to fatigue, misjudgment and other reasons when humans are driving. This application supports remote monitoring and management. Operators can remotely monitor the operating status of the vehicle in a safe and comfortable environment, adjust and optimize system parameters in a timely manner, maintain continuous and stable operation, reduce the risk of accidents caused by human errors, and ensure safe production underground.

[0095] This application integrates multi-source sensors, matches lidar scanning and inertial measurement units with three-dimensional models, and combines automatic recognition of the loader body video to detect obstacles in front of the loader and whether there is enough safe distance between passing vehicles, thereby ensuring safe driving and transportation. When necessary, the system can take automatic emergency braking measures to avoid collisions and accidents, thereby ensuring the safety of equipment and property and reducing operating costs.

[0096] The present application can perform path planning based on the three-dimensional model of the underground environment, can control multiple loaders for shoveling at the same time, select the optimal transportation route, reduce unnecessary driving and waiting time, and improve transportation efficiency.

[0097] Figure 4 The structure diagram of a device for automatic driving of an underground scraper provided in an embodiment of the present application is shown, and acts on a target scraper. The device includes:

[0098] A construction module, used to construct an initial driving map according to the initial position data collected during the underground automatic driving process, so as to perform shoveling work based on the initial driving map;

[0099] An updating module is used to update the initial driving map according to the first position data to obtain a first driving map when the first position data is collected; wherein the first position data is position data different from the initial position data.

[0100] An updating module is used to update the first driving map according to the second location data to obtain a second driving map when the second location data is collected; wherein the second location data is location data different from the initial location data and the first location data.

[0101] The first position data includes first point cloud data and second point cloud data; the first point cloud data is data outside the initial driving map; the second point cloud data is data that has changed in the initial driving map;

[0102] When the first position data is collected, the initial driving map is updated according to the first position data to obtain a first driving map; wherein the first position data is position data different from the initial position data, including:

[0103] When the first position data is the first point cloud data, updating the initial driving map using a first updating method to obtain a first driving map;

[0104] When the first position data is the second point cloud data, the initial driving map is updated using a second updating method to obtain a first driving map.

[0105] The first position data is collected in a relative coordinate system, and the initial driving map is in an earth coordinate system; when the first position data is the first point cloud data, updating the initial driving map using a first updating method to obtain a first driving map includes:

[0106] Performing coordinate registration on the first point cloud data in the relative coordinate system to obtain a driving map to be updated in the earth coordinate system;

[0107] The driving map to be updated and the initial driving map are merged to obtain the first driving map.

[0108] When the first point cloud data is collected, target point cloud data is also collected; wherein the target point cloud data is part or all of the point cloud data in the initial position data;

[0109] The step of performing coordinate registration on the first point cloud data in the relative coordinate system to obtain the driving map to be updated in the earth coordinate system includes:

[0110] Determining transformation parameters of the first point cloud data according to the first point cloud data and the target point cloud data;

[0111] Coordinate registration is performed on the first point cloud data according to the transformation parameters to obtain a driving map to be updated in the earth coordinate system.

[0112] When the first position data is the second point cloud data, updating the initial driving map using a second updating method to obtain a first driving map includes:

[0113] The point cloud data in the initial driving map is replaced by the second point cloud data to obtain the first driving map.

[0114] The device also includes a sending module for sending the first driving map to other shovel loaders, so that the target shovel loaders and the other shovel loaders perform shoveling work based on the first driving map.

[0115] like Figure 5 As shown, an embodiment of the present application provides an electronic device for executing the method for automatic driving of an underground loader in the present application, the device includes a memory, a processor, a bus, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for automatic driving of an underground loader when executing the computer program.

[0116] Specifically, the above-mentioned memory and processor can be general-purpose memory and processor, which are not specifically limited here. When the processor runs the computer program stored in the memory, the above-mentioned method of automatic driving of the underground loader can be executed.

[0117] Corresponding to the method for automatic driving of an underground loader in the present application, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for automatic driving of an underground loader are executed.

[0118] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, the above-mentioned method of automatic driving of the underground scraper can be executed.

[0119] In the embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. The system embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0120] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0122] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product 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 methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0123] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0124] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for automatic driving of an underground scraper, characterized in that: Acting on a target scraper, the method comprises: According to the initial position data collected during the underground automatic driving process, an initial driving map is constructed to perform shovel work based on the initial driving map; When the first position data is collected, the initial driving map is updated according to the first position data to obtain a first driving map; wherein the first position data is position data different from the initial position data.

2. The method according to claim 1, characterized in that The method further comprises: When the second position data is collected, the first driving map is updated according to the second position data to obtain a second driving map; wherein the second position data is position data different from the initial position data and the first position data.

3. The method according to claim 1, characterized in that The first position data includes first point cloud data and second point cloud data; the first point cloud data is data outside the initial driving map; the second point cloud data is data that has changed in the initial driving map; When the first position data is collected, the initial driving map is updated according to the first position data to obtain a first driving map; wherein the first position data is position data different from the initial position data, including: When the first position data is the first point cloud data, updating the initial driving map using a first updating method to obtain a first driving map; When the first position data is the second point cloud data, the initial driving map is updated using a second updating method to obtain a first driving map.

4. The method according to claim 3, characterized in that The first position data is collected in a relative coordinate system, and the initial driving map is in an earth coordinate system; when the first position data is the first point cloud data, updating the initial driving map using a first updating method to obtain a first driving map includes: Performing coordinate registration on the first point cloud data in the relative coordinate system to obtain a driving map to be updated in the earth coordinate system; The driving map to be updated and the initial driving map are merged to obtain the first driving map.

5. The method according to claim 4, characterized in that The method further includes collecting target point cloud data when collecting the first point cloud data; wherein the target point cloud data is part or all of the point cloud data in the initial position data; The step of performing coordinate registration on the first point cloud data in the relative coordinate system to obtain the driving map to be updated in the earth coordinate system includes: Determining transformation parameters of the first point cloud data according to the first point cloud data and the target point cloud data; Coordinate registration is performed on the first point cloud data according to the transformation parameters to obtain a driving map to be updated in the earth coordinate system.

6. The method according to claim 3, characterized in that When the first position data is the second point cloud data, updating the initial driving map using a second updating method to obtain a first driving map includes: The point cloud data in the initial driving map is replaced by the second point cloud data to obtain the first driving map.

7. The method according to claim 1, characterized in that The method comprises: The first driving map is sent to other loaders, so that the target loader and the other loaders perform load carrying work based on the first driving map.

8. An automatic driving device for an underground scraper, characterized in that: Acting on a target scraper, the device comprises: A construction module, used to construct an initial driving map according to the initial position data collected during the underground automatic driving process, so as to perform shoveling work based on the initial driving map; An updating module is used to update the initial driving map according to the first position data to obtain a first driving map when the first position data is collected; wherein the first position data is position data different from the initial position data.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for automatic driving of an underground shovel loader as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the method for automatic driving of an underground loader as described in any one of claims 1 to 7.

Images