Method, apparatus and storage medium for determining work machine driving strategy

Abstract

The application relates to the technical field of engineering machinery, in particular to a method and device for determining a driving strategy of engineering machinery and a storage medium. The method comprises the following steps: acquiring three-dimensional point cloud data and dust concentration of the surrounding environment of the engineering machinery at a current time; projecting the three-dimensional point cloud data to a plane where the engineering machinery is located, and generating a point cloud picture according to the projected two-dimensional point cloud data; detecting the two-dimensional point cloud data in the point cloud picture when the dust concentration is greater than a preset concentration; determining suspended dust noise points in the two-dimensional point cloud data and processing the suspended dust noise points to obtain a de-noised point cloud picture; determining target obstacles located around the engineering machinery according to the de-noised point cloud picture; and determining a driving strategy of the engineering machinery at a next time based on the target obstacles, so that the misjudgment rate of the dust noise on the obstacles is reduced.

Description

Technical Field

[0001] This application relates to the field of engineering machinery technology, and more specifically to a method, apparatus and storage medium for determining driving strategies for engineering machinery. Background Technology

[0002] Open-pit mines present complex environments with dust, fluctuating lighting, and dynamic obstacles, posing numerous challenges to the operation of construction machinery. Current methods typically employ distributed processing, such as directly voxel downsampling LiDAR point cloud data and simple image stitching after histogram equalization. This approach is crude, wasteful, and ineffective, failing to accurately and promptly identify obstacles and compromising the safety of construction machinery operation. Summary of the Invention

[0003] The purpose of this application is to provide a method, apparatus, and storage medium for determining driving strategies for construction machinery, in order to solve the problem that the prior art cannot effectively process data, thus affecting driving safety.

[0004] To achieve the above objectives, the first aspect of this application provides a method for determining a driving strategy for construction machinery, the method comprising: Acquire 3D point cloud data and dust concentration of the surrounding environment of the construction machinery at the current moment; The 3D point cloud data is projected onto the plane where the construction machinery is located, and a point cloud image is generated based on the projected 2D point cloud data. When the dust concentration is greater than the preset concentration, detect two-dimensional point cloud data in the point cloud image of the traversed area based on the preset radius; In two-dimensional point cloud data, suspended dust noise points are identified and processed to obtain a denoised point cloud image. Identify the target obstacles located around the construction machinery based on the denoised point cloud image; Determine the driving strategy for the construction machinery in the next moment based on the target obstacle.

[0005] In this embodiment of the application, determining the target obstacle located around the construction machinery based on the denoised point cloud image includes: determining a first image region and its feature entropy in the denoised point cloud image when the reflection intensity of all two-dimensional point cloud data in the denoised point cloud image is greater than a preset intensity; determining the target point cloud image based on the feature entropy of the first image region; and determining the target obstacle based on the target point cloud image.

[0006] In this embodiment of the application, determining the first image region and the feature entropy of the first image region in the denoised point cloud image includes: obtaining the position of an object in front of the construction machinery in the denoised point cloud image, and determining the image region between the position of the object and the front of the construction machinery as the first image region; obtaining the texture features and color histogram of the first image region; and determining the feature entropy of the first image region based on the texture features and color histogram.

[0007] In this embodiment, determining the target point cloud image based on the feature entropy of the first image region includes: determining that the object in the first image region is a suspected noise target when the feature entropy is less than a preset threshold; obtaining the velocity and position of the suspected noise target at the current moment; generating a motion state transition matrix of the suspected noise target based on the velocity and position of the suspected noise target; determining whether the suspected noise target constitutes static interference based on the motion state transition matrix; and, if the suspected noise target constitutes static interference, performing mask filtering on the two-dimensional point cloud data corresponding to the object in the first image region of the denoised point cloud image to obtain the target point cloud image.

[0008] In this embodiment of the application, determining whether a suspected noise target constitutes static interference based on the motion state transition matrix includes: determining the target displacement and velocity covariance of the suspected noise target at the current moment based on the motion state transition matrix; and determining that the suspected noise target constitutes static interference if the target displacement is less than a preset displacement and the difference between the velocity covariance and the preset value is less than a preset difference.

[0009] In this embodiment of the application, determining the target obstacle based on the target point cloud image includes: dividing the target point cloud image into grids and determining the point cloud density of each grid; identifying grids with point cloud density greater than a preset density as high-density regions; acquiring images of the high-density regions; determining a second image region based on the images; identifying the object type in the second image region and acquiring the velocity and position of the objects in the second image region; and determining the target obstacle based on the object type, velocity, and position of the second image region.

[0010] In this embodiment of the application, determining the second image region based on the image includes: performing edge detection and color space filtering on the image to identify the object corresponding to the two-dimensional point cloud data of the high-density region; obtaining the longitudinal distance of the two-dimensional point cloud data of the high-density region relative to the center of the engineering machinery; and generating the second image region based on the object corresponding to the two-dimensional point cloud data of the high-density region and the longitudinal distance.

[0011] In this embodiment of the application, determining and processing suspended dust noise points within two-dimensional point cloud data to obtain a denoised point cloud image includes: for any traversed region, if the number of two-dimensional point cloud data included in the traversed region is less than a preset number, determining the two-dimensional point cloud data within the traversed region as suspended dust noise points; removing suspended dust noise points from the point cloud image to obtain a denoised point cloud image.

[0012] In this embodiment of the application, generating a point cloud image based on the projected two-dimensional point cloud data includes: obtaining a preset number of three-dimensional point cloud data from all three-dimensional point cloud data, and obtaining two-dimensional point cloud data corresponding to the preset number of three-dimensional point cloud data from the projected image; performing error correction on the projected image based on the preset number of three-dimensional point cloud data and the two-dimensional point cloud data to obtain a corrected projected image; and performing frame interpolation processing on the corrected projected image to obtain a point cloud image.

[0013] A second aspect of this application provides an apparatus for determining a driving strategy for construction machinery, comprising: The memory is configured to store instructions; The processor is configured to retrieve instructions from memory and, when executing the instructions, to implement the aforementioned method for determining the driving strategy of the construction machinery.

[0014] A third aspect of this application provides a machine-readable storage medium storing instructions for causing a machine to perform the aforementioned method for determining a driving strategy for construction machinery.

[0015] The above technical solution acquires 3D point cloud data and dust concentration of the surrounding environment of the construction machinery at the current moment; projects the 3D point cloud data onto the plane where the construction machinery is located, and generates a point cloud image based on the projected 2D point cloud data; when the dust concentration is greater than a preset concentration, detects the 2D point cloud data in the point cloud image in a traversal area constructed based on a preset radius; identifies and processes suspended dust noise points within the 2D point cloud data to obtain a denoised point cloud image; identifies target obstacles around the construction machinery based on the denoised point cloud image; and determines the driving strategy of the construction machinery in the next moment based on the target obstacles, reducing the false detection rate of obstacles due to dust noise, improving data processing accuracy, and providing a reliable basis for subsequent driving safety and path planning.

[0016] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings: Figure 1 The illustration shows a flowchart of a method for determining a driving strategy for construction machinery according to an embodiment of this application; Figure 2 The diagram illustrates the internal structure of a computer device according to an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0019] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0020] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0021] Figure 1 The illustration schematically shows a flowchart of a method for determining a driving strategy for construction machinery according to an embodiment of this application. Figure 1 As shown in the figure, this application provides a method for determining the driving strategy of construction machinery, which may include the following steps.

[0022] Step 101: Obtain the 3D point cloud data and dust concentration of the surrounding environment of the construction machinery at the current moment.

[0023] Step 102: Project the 3D point cloud data onto the plane where the construction machinery is located, and generate a point cloud image based on the projected 2D point cloud data.

[0024] Construction machinery, especially autonomous mining trucks in open-pit mines, often encounters numerous obstacles during operation. To ensure the safe operation of construction machinery, it is crucial to effectively identify these obstacles in the surrounding environment. A processor can acquire 3D point cloud data and dust concentration of the surrounding environment at the current moment. For example, the processor can acquire 3D point cloud data of the surrounding environment collected by a lidar sensor installed on the construction machinery, and acquire dust concentration data, such as PM2.5 or PM10 concentration, collected by a dust sensor. After obtaining the 3D point cloud data, the processor can project the 3D point cloud data onto the plane where the construction machinery is located, and generate a point cloud image based on the projected 2D point cloud data. In a specific embodiment, the processor can determine the coordinate transformation matrix between the lidar coordinate system and the construction machinery coordinate system. The construction machinery coordinate system is constructed with the center of the construction machinery as the origin, the x-axis as the axis extending from the origin and pointing directly forward in the plane where the construction machinery is located, the z-axis as the normal vector perpendicular to the plane where the construction machinery is located, and the y-axis as the normal vector of the plane containing the x-axis and z-axis. After obtaining the coordinate transformation matrix, the processor can perform coordinate transformation on the 3D point cloud coordinates based on the transformation matrix to project the 3D point cloud data onto the plane where the construction machinery is located, thereby obtaining the projected 2D point cloud data. After obtaining the projected 2D point cloud data, the processor can generate a point cloud image based on the projected 2D point cloud data.

[0025] In this embodiment of the application, generating a point cloud image based on the projected two-dimensional point cloud data includes: obtaining a preset number of three-dimensional point cloud data from all three-dimensional point cloud data, and obtaining two-dimensional point cloud data corresponding to the preset number of three-dimensional point cloud data from the projected image; performing error correction on the projected image based on the preset number of three-dimensional point cloud data and the two-dimensional point cloud data to obtain a corrected projected image; and performing frame interpolation processing on the corrected projected image to obtain a point cloud image.

[0026] The processor can generate a point cloud image based on the projected 2D point cloud data. Specifically, the processor can obtain a preset number of 3D point cloud data from all the 3D point cloud data, and obtain the corresponding 2D point cloud data from the projected image. The preset number can be determined based on actual conditions. The processor can perform error correction on the projected image based on the preset number of 3D and 2D point cloud data to obtain a corrected projected image. After obtaining the corrected projected image, the processor can perform frame interpolation processing on the corrected projected image to obtain a point cloud image, thereby achieving spatiotemporal alignment compensation of the point cloud data.

[0027] Step 103: When the dust concentration is greater than the preset concentration, detect the two-dimensional point cloud data in the point cloud image of the traversed area based on the preset radius.

[0028] Step 104: Identify and process suspended dust noise points within the 2D point cloud data to obtain a denoised point cloud image.

[0029] The processor can determine whether the dust concentration exceeds a preset concentration. The preset concentration can be determined based on actual conditions, such as when the PM10 concentration exceeds 50 mg / m³. 3 When the dust concentration exceeds a preset concentration, the processor can detect 2D point cloud data in a point cloud image within a traversed region constructed based on a preset radius. The preset radius can be determined based on actual conditions, such as 0.5 meters. The processor can then identify and process suspended dust noise points within the 2D point cloud data to obtain a denoised point cloud image.

[0030] In this embodiment of the application, determining and processing suspended dust noise points within two-dimensional point cloud data to obtain a denoised point cloud image includes: for any traversed region, if the number of two-dimensional point cloud data included in the traversed region is less than a preset number, determining the two-dimensional point cloud data within the traversed region as suspended dust noise points; removing suspended dust noise points from the point cloud image to obtain a denoised point cloud image.

[0031] The processor can identify and process suspended dust noise points within 2D point cloud data to obtain a denoised point cloud image. Specifically, for any given traversal region, if the number of 2D point cloud data points within that region is less than a preset number, the processor can identify the 2D point cloud data points within that region as suspended dust noise points. The preset number can be determined based on actual conditions, such as 30. After identifying the suspended dust noise points, the processor can remove these points from the point cloud image to obtain the denoised point cloud image.

[0032] Step 105: Identify the target obstacles located around the construction machinery based on the denoised point cloud image.

[0033] Step 106: Determine the driving strategy of the construction machinery in the next moment based on the target obstacle.

[0034] After obtaining the denoised point cloud image, the processor can determine the target obstacles around the construction machinery based on the denoised point cloud image. After determining the target obstacles around the construction machinery, the processor can determine the driving strategy of the construction machinery in the next moment based on the target obstacles, so as to reduce the impact of suspended dust noise, more accurately locate obstacles, and ensure the driving safety of the construction machinery.

[0035] In one specific embodiment, after identifying target obstacles around the construction machinery, the processor can output a list of target obstacles, which may include the type, speed, and location of the target obstacles. Based on the target obstacles, the processor can generate a driving strategy for the construction machinery in the next moment. For example, if the distance between the target obstacle and the construction machinery is determined to be less than 10 meters and the relative speed is greater than 0.5 m / s, the processor can send an alarm message to the construction machinery to trigger the LEDs in the construction machinery's cockpit to flash and sound an alarm.

[0036] In this embodiment of the application, determining the target obstacle located around the construction machinery based on the denoised point cloud image includes: determining a first image region and its feature entropy in the denoised point cloud image when the reflection intensity of all two-dimensional point cloud data in the denoised point cloud image is greater than a preset intensity; determining the target point cloud image based on the feature entropy of the first image region; and determining the target obstacle based on the target point cloud image.

[0037] The processor can determine target obstacles located around construction machinery based on the denoised point cloud image. Specifically, the processor can determine whether the reflection intensity of all two-dimensional point cloud data in the denoised point cloud image is greater than a preset intensity. The preset intensity can be determined based on actual conditions. If the reflection intensity of all two-dimensional point cloud data in the denoised point cloud image is greater than the preset intensity, the processor can determine a first image region and its feature entropy in the denoised point cloud image. After determining the feature entropy of the first image region, the processor can determine the target point cloud image based on its feature entropy. After determining the target point cloud image, the processor can determine the target obstacle based on the target point cloud image.

[0038] In this embodiment of the application, determining the first image region and the feature entropy of the first image region in the denoised point cloud image includes: obtaining the position of an object in front of the construction machinery in the denoised point cloud image, and determining the image region between the position of the object and the front of the construction machinery as the first image region; obtaining the texture features and color histogram of the first image region; and determining the feature entropy of the first image region based on the texture features and color histogram.

[0039] The processor can determine the first image region and its feature entropy in the denoised point cloud image. Specifically, the processor can obtain the position of an object in front of the construction machinery in the denoised point cloud image, such as being directly in front of the machinery. After obtaining the object's position, the processor can define the image region between the object's position and the front of the construction machinery as the first image region. After determining the first image region, the processor can obtain its texture features and color histogram. Having obtained the texture features and color histogram of the first image region, the processor can determine its feature entropy based on these features.

[0040] In this embodiment, determining the target point cloud image based on the feature entropy of the first image region includes: determining that the object in the first image region is a suspected noise target when the feature entropy is less than a preset threshold; obtaining the velocity and position of the suspected noise target at the current moment; generating a motion state transition matrix of the suspected noise target based on the velocity and position of the suspected noise target; determining whether the suspected noise target constitutes static interference based on the motion state transition matrix; and, if the suspected noise target constitutes static interference, performing mask filtering on the two-dimensional point cloud data corresponding to the object in the first image region of the denoised point cloud image to obtain the target point cloud image.

[0041] The processor can determine the target point cloud image based on the feature entropy of the first image region. Specifically, the processor can determine whether the feature entropy is less than a preset threshold, where the preset threshold can be determined based on actual conditions. If the feature entropy is less than the preset threshold, the processor can determine that the object in the first image region is a suspected noise target. After determining the suspected noise target, the processor can obtain the velocity and position of the suspected noise target at the current moment, and generate a motion state transition matrix for the suspected noise target based on the velocity and position. After obtaining the motion state transition matrix of the suspected noise target, the processor can determine whether the suspected noise target constitutes static interference based on the motion state transition matrix. If the suspected noise target constitutes static interference, the processor can perform mask filtering on the two-dimensional point cloud data corresponding to the object in the first image region of the denoised point cloud image to obtain the target point cloud image.

[0042] In this embodiment of the application, determining whether a suspected noise target constitutes static interference based on the motion state transition matrix includes: determining the target displacement and velocity covariance of the suspected noise target at the current moment based on the motion state transition matrix; and determining that the suspected noise target constitutes static interference if the target displacement is less than a preset displacement and the difference between the velocity covariance and the preset value is less than a preset difference.

[0043] The processor can determine whether a suspected noise target constitutes static interference based on the motion state transition matrix. Specifically, the processor can determine the target displacement and velocity covariance of the suspected noise target at the current moment based on the motion state transition matrix. The processor can determine whether the target displacement is less than a preset displacement and whether the difference between the velocity covariance and a preset value is less than a preset difference. For example, the preset displacement can be 0.1 meters, and the preset difference can be 0, or the preset value can be close to 0. If the target displacement is less than the preset displacement and the difference between the velocity covariance and the preset value is less than the preset difference, the processor can determine that the suspected noise target constitutes static interference.

[0044] In this embodiment of the application, determining the target obstacle based on the target point cloud image includes: dividing the target point cloud image into grids and determining the point cloud density of each grid; identifying grids with point cloud density greater than a preset density as high-density regions; acquiring images of the high-density regions; determining a second image region based on the images; identifying the object type in the second image region and acquiring the velocity and position of the objects in the second image region; and determining the target obstacle based on the object type, velocity, and position of the second image region.

[0045] The processor can determine target obstacles based on a target point cloud image. Specifically, the processor can divide the target point cloud image into grids and determine the point cloud density of each grid. After obtaining the point cloud density of each grid, the processor can determine whether the point cloud density of each grid is greater than a preset density, where the preset density can be determined based on actual conditions. The processor can identify grids with point cloud densities greater than the preset density as high-density regions. After identifying high-density regions, the processor can acquire images of these high-density regions. For example, images of these high-density regions can be acquired using a camera. After obtaining this image, the processor can determine a second image region based on it. After determining the second image region, the processor can identify the object type in the second image region and obtain the velocity and position of the objects in the second image region. The processor can determine target obstacles based on the object type, velocity, and position of the second image region. For example, the processor can generate an attribute table of target obstacles based on the object type, velocity, and position of the second image region.

[0046] In this embodiment of the application, determining the second image region based on the image includes: performing edge detection and color space filtering on the image to identify the object corresponding to the two-dimensional point cloud data of the high-density region; obtaining the longitudinal distance of the two-dimensional point cloud data of the high-density region relative to the center of the engineering machinery; and generating the second image region based on the object corresponding to the two-dimensional point cloud data of the high-density region and the longitudinal distance.

[0047] The processor can determine a second image region based on the image. Specifically, the processor can perform edge detection and color space filtering on the image to identify objects corresponding to the 2D point cloud data of the high-density region. The processor can obtain the longitudinal distance of the 2D point cloud data of the high-density region relative to the center of the construction machinery. After determining the objects corresponding to the 2D point cloud data of the high-density region and the longitudinal distance, the processor can generate a second image region based on the objects corresponding to the 2D point cloud data of the high-density region and the longitudinal distance.

[0048] The construction machinery in this embodiment includes traditional construction machinery vehicles, as well as new energy vehicles used in the construction machinery field, such as new energy mixer trucks, new energy pump trucks, and new energy excavators. In addition, the construction machinery vehicles in this embodiment are also intelligent connected vehicles. Construction machinery vehicles include sensing systems, communication systems, etc. The in-vehicle sensing system collects vehicle operation data and information about the vehicle's surrounding environment, and the communication system enables network connection with other vehicles and the cloud. The collected vehicle operation data and information about the vehicle's surrounding environment are shared with the cloud and other authorized vehicles to achieve data sharing, remote analysis, intelligent driving and other operations. The above technical solutions reduce the false detection rate of obstacles caused by dust and noise, improve data processing accuracy, and provide a reliable basis for subsequent driving safety and route planning.

[0049] Figure 1 This is a flowchart illustrating a method for determining a driving strategy for construction machinery in one embodiment. It should be understood that, although... Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0050] This application also provides an apparatus for determining a driving strategy for construction machinery, comprising: The memory is configured to store instructions; The processor is configured to retrieve instructions from memory and, when executing the instructions, to implement the aforementioned method for determining the driving strategy of the construction machinery.

[0051] This application also provides a machine-readable storage medium storing instructions for causing a machine to perform the above-described method for determining a driving strategy for construction machinery.

[0052] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 2 As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The database stores data such as 3D point cloud data, dust concentration, 2D point cloud data, suspended dust noise points, target obstacles, and driving strategies. The network interface A02 communicates with external terminals via a network connection. When executed by the processor A01, the computer program B02 implements a method for determining a driving strategy for construction machinery.

[0053] Those skilled in the art will understand that Figure 2 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0054] This application provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring three-dimensional point cloud data and dust concentration of the surrounding environment of the construction machinery at the current moment; projecting the three-dimensional point cloud data onto the plane where the construction machinery is located, and generating a point cloud image based on the projected two-dimensional point cloud data; when the dust concentration is greater than a preset concentration, detecting the two-dimensional point cloud data in the point cloud image based on a traversal area constructed based on a preset radius; identifying suspended dust noise points within the two-dimensional point cloud data and processing the suspended dust noise points to obtain a denoised point cloud image; identifying target obstacles located around the construction machinery based on the denoised point cloud image; and determining the driving strategy of the construction machinery at the next moment based on the target obstacles.

[0055] In one embodiment, determining a target obstacle located around the construction machinery based on a denoised point cloud image includes: determining a first image region and its feature entropy in the denoised point cloud image when the reflection intensity of all two-dimensional point cloud data in the denoised point cloud image is greater than a preset intensity; determining a target point cloud image based on the feature entropy of the first image region; and determining the target obstacle based on the target point cloud image.

[0056] In one embodiment, determining the first image region and the feature entropy of the first image region in the denoised point cloud image includes: obtaining the position of an object in front of the construction machinery in the denoised point cloud image, and determining the image region between the position of the object and the front of the construction machinery as the first image region; obtaining the texture features and color histogram of the first image region; and determining the feature entropy of the first image region based on the texture features and color histogram.

[0057] In one embodiment, determining the target point cloud image based on the feature entropy of the first image region includes: if the feature entropy is less than a preset threshold, determining that the object in the first image region is a suspected noise target; obtaining the velocity and position of the suspected noise target at the current moment; generating a motion state transition matrix of the suspected noise target based on the velocity and position of the suspected noise target; determining whether the suspected noise target constitutes static interference based on the motion state transition matrix; and if the suspected noise target constitutes static interference, performing mask filtering on the two-dimensional point cloud data corresponding to the object in the first image region of the denoised point cloud image to obtain the target point cloud image.

[0058] In one embodiment, determining whether a suspected noise target constitutes static interference based on the motion state transition matrix includes: determining the target displacement and velocity covariance of the suspected noise target at the current moment based on the motion state transition matrix; and determining that the suspected noise target constitutes static interference if the target displacement is less than a preset displacement and the difference between the velocity covariance and a preset value is less than a preset difference.

[0059] In one embodiment, determining a target obstacle based on a target point cloud image includes: dividing the target point cloud image into grids and determining the point cloud density of each grid; identifying grids with point cloud densities greater than a preset density as high-density regions; acquiring images of the high-density regions; determining a second image region based on the images; identifying the object type in the second image region and acquiring the velocity and position of the objects in the second image region; and determining the target obstacle based on the object type, velocity, and position of the second image region.

[0060] In one embodiment, determining the second image region based on the image includes: performing edge detection and color space filtering on the image to identify the object corresponding to the two-dimensional point cloud data of the high-density region; obtaining the longitudinal distance of the two-dimensional point cloud data of the high-density region relative to the center of the engineering machinery; and generating the second image region based on the object corresponding to the two-dimensional point cloud data of the high-density region and the longitudinal distance.

[0061] In one embodiment, determining and processing suspended dust noise points within two-dimensional point cloud data to obtain a denoised point cloud image includes: for any traversed region, if the number of two-dimensional point cloud data included in the traversed region is less than a preset number, determining the two-dimensional point cloud data within the traversed region as suspended dust noise points; and removing the suspended dust noise points from the point cloud image to obtain a denoised point cloud image.

[0062] In one embodiment, generating a point cloud image based on projected two-dimensional point cloud data includes: obtaining a preset number of three-dimensional point cloud data from all three-dimensional point cloud data, and obtaining two-dimensional point cloud data corresponding to the preset number of three-dimensional point cloud data from the projected image; performing error correction on the projected image based on the preset number of three-dimensional point cloud data and two-dimensional point cloud data to obtain a corrected projected image; and performing frame interpolation processing on the corrected projected image to obtain a point cloud image.

[0063] This application also provides a computer program product that, when executed on a data processing device, is adapted to perform a program that initializes method steps for determining a driving strategy for construction machinery.

[0064] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0065] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0066] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0067] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0068] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0069] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0070] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0071] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0072] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for determining the driving strategy of construction machinery, characterized in that, The method includes: Obtain the three-dimensional point cloud data and dust concentration of the surrounding environment of the construction machinery at the current moment; The three-dimensional point cloud data is projected onto the plane where the engineering machinery is located, and a point cloud image is generated based on the projected two-dimensional point cloud data; When the dust concentration is greater than a preset concentration, the two-dimensional point cloud data in the point cloud image is detected in a traversal area constructed based on a preset radius; Suspended dust noise points are identified within the two-dimensional point cloud data and processed to obtain a denoised point cloud image. Based on the denoised point cloud image, the target obstacles located around the engineering machinery are determined; The driving strategy of the construction machinery in the next moment is determined based on the target obstacle; The step of determining the target obstacles located around the construction machinery based on the denoised point cloud image includes: When the reflection intensity of all two-dimensional point cloud data in the denoised point cloud image is greater than the preset intensity, the first image region and the feature entropy of the first image region in the denoised point cloud image are determined. If the feature entropy is less than a preset threshold, the object in the first image region is determined to be a suspected noise target. Obtain the velocity and position of the suspected noise target at the current moment; Generate the motion state transition matrix of the suspected noise target based on its velocity and position; Determine whether the suspected noise target constitutes static interference based on the motion state transition matrix; In the case where the suspected noise target constitutes static interference, the two-dimensional point cloud data corresponding to the object in the first image region of the denoised point cloud image is masked to obtain the target point cloud image. The target obstacle is determined based on the target point cloud image.

2. The method for determining the driving strategy of construction machinery according to claim 1, characterized in that, Determining the first image region and the feature entropy of the first image region in the denoised point cloud image includes: The position of the object in front of the construction machinery in the denoised point cloud image is obtained, and the image area between the position of the object and the front of the construction machinery is determined as the first image area; Obtain the texture features and color histogram of the first image region; The feature entropy of the first image region is determined based on the texture features and the color histogram.

3. The method for determining the driving strategy of construction machinery according to claim 1, characterized in that, Determining whether the suspected noise target constitutes static interference based on the motion state transition matrix includes: The target displacement and velocity covariance of the suspected noise target at the current moment are determined based on the motion state transition matrix. If the target displacement is less than a preset displacement and the difference between the velocity covariance and the preset value is less than a preset difference, the suspected noise target is determined to constitute static interference.

4. The method for determining the driving strategy of construction machinery according to claim 1, characterized in that, Determining the target obstacle based on the target point cloud image includes: The target point cloud image is divided into grids, and the point cloud density of each grid is determined; Raster cells with point cloud density greater than a preset density are defined as high-density regions. Obtain an image of the high-density region; Determine the second image region based on the image; Identify the object type in the second image region and obtain the velocity and position of the object in the second image region; The target obstacle is determined based on the object type, speed, and position in the second image region.

5. The method for determining the driving strategy of construction machinery according to claim 4, characterized in that, Determining the second image region based on the image includes: Edge detection and color space filtering are performed on the image to identify the objects corresponding to the two-dimensional point cloud data of the high-density region; Obtain the two-dimensional point cloud data of the high-density area relative to the longitudinal distance of the center of the engineering machinery; The second image region is generated based on the object corresponding to the two-dimensional point cloud data of the high-density region and the longitudinal distance.

6. The method for determining the driving strategy of construction machinery according to claim 1, characterized in that, The step of determining and processing suspended dust noise points within the two-dimensional point cloud data to obtain a denoised point cloud image includes: For any given traversal region, if the number of two-dimensional point cloud data included in the traversal region is less than a preset number, the two-dimensional point cloud data within the traversal region will be identified as suspended dust noise points. The suspended dust noise points in the point cloud image are removed to obtain a denoised point cloud image.

7. The method for determining the driving strategy of construction machinery according to claim 1, characterized in that, The step of generating a point cloud image based on the projected two-dimensional point cloud data includes: A preset number of three-dimensional point cloud data are obtained from all the three-dimensional point cloud data, and two-dimensional point cloud data corresponding to the preset number of three-dimensional point cloud data are obtained from the projected image. The projected image is corrected based on the preset number of 3D point cloud data and 2D point cloud data to obtain a corrected projected image. The corrected projected image is then subjected to frame interpolation to obtain the point cloud image.

8. A device for determining the driving strategy of construction machinery, characterized in that, include: The memory is configured to store instructions; A processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the method for determining a driving strategy for construction machinery according to any one of claims 1 to 7.

9. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to perform the method for determining a driving strategy for construction machinery according to any one of claims 1 to 7.

Images