A mine vehicle-mounted perception system performance degradation identification system and method

Abstract

This invention discloses a performance degradation identification system and method for a mining vehicle-mounted sensing system, comprising: an environmental sample feature memory storage module, an environmental feature acquisition and identification module, a performance determination module, and an alarm module. The environmental sample feature memory storage module performs pre-collection and processing of environmental features at marked locations in the environment using the vehicle-mounted sensing system, and stores the results as prior sample features. The environmental feature acquisition and identification module collects operational data during vehicle operation; when the vehicle reaches a marked location, it collects vehicle-mounted sensing data and converts it into operational process sample features. The performance determination module compares the prior sample features and the operational process sample features to determine the difference; if the difference exceeds a threshold, the result is determined to be abnormal; otherwise, the result is determined to be normal. When the result is determined to be abnormal, the alarm module issues a warning signal. This provides timely warnings when the lidar performance degrades, ensuring the safe operation of unmanned mining trucks.

Description

Technical Field

[0001] This invention relates to a system and method for identifying performance degradation of a mining vehicle-mounted sensing system, belonging to the field of lidar performance testing. Background Technology

[0002] Mining areas present environments of high dust, high vibration, and low temperatures. Under these conditions, the lidar used in unmanned mining trucks is prone to performance degradation, such as reduced detection range and a decrease in the emitted point cloud data. Furthermore, this performance degradation is not easily detected by visually observing point cloud data. This performance degradation of the lidar affects the detection capabilities of the perception system, thereby impacting the driving safety of the unmanned mining trucks.

[0003] Existing solutions require the design of specific devices to detect the lidar, and the lidar needs to be placed within these devices. For unmanned mining trucks in mining areas, designing specific devices and disassembling the lidar to test its performance is costly and inefficient. Summary of the Invention

[0004] This invention provides a system and method for identifying performance degradation of a mining vehicle-mounted sensing system, which solves the problem of LiDAR performance degradation in identifying unmanned mining trucks disclosed in the background art.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is: a performance degradation identification system for a mining vehicle-mounted sensing system, comprising: an environmental sample feature memory storage module, an environmental feature acquisition and identification module, a performance determination module, and an alarm module;

[0006] The environmental sample feature memory and storage module is used to mark the location in the environment, perform pre-environmental feature acquisition and processing using the vehicle-mounted perception system, and store the results as prior sample features.

[0007] The environmental feature acquisition and recognition module is used to collect operational data during vehicle operation. When the vehicle travels to the marked location, it collects on-board perception data and converts it into operational process sample features.

[0008] The performance determination module is used to receive prior sample features from the environmental sample feature memory storage module and running process sample features from the environmental feature acquisition and recognition module, compare the prior sample features and running process sample features, and determine the difference between the two. When the difference exceeds the threshold, the determination result is abnormal; otherwise, the determination result is normal.

[0009] The alarm module receives the judgment results from the performance judgment module and issues an early warning signal when the judgment result is abnormal.

[0010] Furthermore, the prior sample feature is the number of point clouds of obstacles in the environment; the vehicle-mounted perception system includes a lidar, which collects environmental data and processes it to obtain the number of point clouds of obstacles.

[0011] Furthermore, the sample characteristics of the operation process are the number of point clouds of obstacles in the environment.

[0012] Furthermore, the environmental feature acquisition and recognition module includes: a location determination submodule, a ROI region filtering submodule, a ground segmentation submodule, and a recognition submodule;

[0013] The location determination submodule is used to receive the mining truck location information sent by the mining truck positioning system and compare it with the location information of the marked location. When the two pieces of information match, execution information is sent to the ROI region filtering submodule; when the two pieces of information do not match, execution information is not sent to the ROI region filtering submodule.

[0014] The ROI region filtering submodule is used to receive execution information from the position determination module, read in the radar point cloud data, retain only the point cloud within the ROI region according to the method of restricting the coordinate values ​​of the point cloud data, and send it to the ground segmentation submodule.

[0015] The ground segmentation submodule is used to receive point cloud data sent by the ROI region filtering submodule, use the RANSAC method to obtain ground point cloud and obstacle point cloud data, and send the obstacle point cloud data to the recognition submodule.

[0016] The identification submodule is used to receive point cloud data sent by the ground segmentation submodule, calculate the number of point clouds corresponding to obstacles, obtain the running process sample features, and send the running process sample features to the performance judgment module.

[0017] Furthermore, the difference between the prior sample features and the operational sample features is the absolute value of the difference between the two.

[0018] Accordingly, a method for identifying performance degradation in a mining vehicle-mounted sensing system is proposed:

[0019] The environmental sample feature memory storage module marks the location in the environment, uses the vehicle-mounted perception system to collect and process environmental features in advance, and stores the results as prior sample features.

[0020] The environmental feature acquisition and recognition module collects operational data during vehicle operation. When the vehicle reaches the marked location, it collects onboard perception data and converts it into operational process sample features.

[0021] The performance determination module receives prior sample features from the environmental sample feature memory storage module and running process sample features from the environmental feature acquisition and recognition module, compares the prior sample features and running process sample features, and determines the difference between the two. When the difference exceeds the threshold, the determination result is abnormal; otherwise, the determination result is normal.

[0022] The alarm module receives the judgment result from the performance judgment module and issues a warning signal when the judgment result is abnormal.

[0023] Furthermore, the prior sample feature is the number of point clouds of obstacles in the environment; the vehicle-mounted perception system includes a lidar, which collects environmental data and processes it to obtain the number of point clouds of obstacles.

[0024] Furthermore, the sample characteristics of the operation process are the number of point clouds of obstacles in the environment.

[0025] Furthermore, the environmental feature acquisition and recognition module includes: a location determination submodule, a ROI region filtering submodule, a ground segmentation submodule, and a recognition submodule;

[0026] The location determination submodule receives the mining card location information sent by the mining card positioning system and compares it with the location information of the marked location. When the two pieces of information match, execution information is sent to the ROI region filtering submodule; when the two pieces of information do not match, execution information is not sent to the ROI region filtering submodule.

[0027] The ROI region filtering submodule receives the execution information sent by the position determination module, reads the radar point cloud data, retains only the point cloud within the ROI region according to the method of restricting the coordinate values ​​of the point cloud data, and sends it to the ground segmentation submodule.

[0028] The ground segmentation submodule receives point cloud data sent by the ROI region filtering submodule, uses the RANSAC method to obtain ground point cloud and obstacle point cloud data, and sends the obstacle point cloud data to the recognition submodule.

[0029] The identification submodule receives point cloud data sent by the ground segmentation submodule, calculates the number of point clouds corresponding to obstacles, obtains the running process sample features, and sends the running process sample features to the performance determination module.

[0030] Furthermore, the difference between the prior sample features and the operational sample features is the absolute value of the difference between the two.

[0031] The beneficial effects achieved by this invention are as follows:

[0032] 1. Ensuring safety: The system and method provided by this invention can periodically detect lidar and provide timely warnings when lidar performance deteriorates, thus ensuring the safe operation of unmanned mining trucks;

[0033] 2. Quick and efficient testing method: Radar performance testing can be completed directly during operation without disassembling the radar;

[0034] 3. Low cost: No specialized testing equipment is required to test radar performance, reducing testing costs. Attached Figure Description

[0035] Figure 1 This is a schematic diagram of the system composition of the present invention;

[0036] Figure 2 This is a schematic diagram of the environmental feature acquisition and recognition module in this invention. Detailed Implementation

[0037] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0038] This embodiment of a mining vehicle-mounted sensing system performance degradation identification system includes at least: an environmental sample feature memory storage module, an environmental feature acquisition and identification module, a performance judgment module, and an alarm module, such as... Figure 1 As shown.

[0039] The environmental sample feature memory storage module is used to collect and process environmental features in advance at relatively obvious and fixed marked locations in the environment using the vehicle-mounted perception system, and store the results as prior sample features.

[0040] The marked position is a set position on the path of the mining truck. When the mining truck travels to this position, the lidar can collect point cloud data of the environment.

[0041] The prior sample feature is the number of point clouds of obstacles in the environment;

[0042] The vehicle-mounted perception system includes hardware such as lidar, which can use lidar to collect environmental data and process it to obtain the number of point clouds of obstacles, denoted as N0.

[0043] The environmental feature acquisition and recognition module is used to collect operational data during vehicle operation. When the vehicle travels to the marked location, it collects onboard perception data and converts it into operational process sample features.

[0044] The sample characteristics of the operation process are the number of point clouds of obstacles in the environment;

[0045] The environmental feature acquisition and recognition module includes a location determination submodule, a ROI region filtering submodule, a ground segmentation submodule, and a recognition submodule, such as... Figure 2 As shown.

[0046] The location determination submodule receives the mining card location information sent by the mining card positioning system and compares it with the location information of the marked location. When the two pieces of information match, it sends execution information to the ROI region filtering submodule; when the two pieces of information do not match, it does not send execution information to the ROI region filtering submodule.

[0047] The ROI region filtering submodule receives execution information from the position determination module, reads in the radar point cloud data, retains only the point cloud within the region of interest according to the method of restricting the coordinate values ​​of the point cloud data, and sends it to the ground segmentation submodule.

[0048] The ground segmentation submodule receives point cloud data sent by the ROI region filtering submodule, uses the RANSAC method to obtain ground point cloud and obstacle point cloud data, and sends the obstacle point cloud data to the recognition submodule.

[0049] The identification submodule receives point cloud data sent by the ground segmentation submodule and calculates the number of point clouds corresponding to obstacles (denoted as N). i The results are then sent to the performance evaluation module.

[0050] The performance determination module receives prior sample features from the environmental sample feature memory storage module and running process sample features from the environmental feature acquisition and recognition module. It determines whether the two are abnormal based on a set threshold and makes a result judgment on the essential difference between them. When the threshold is exceeded, the judgment result is abnormal; otherwise, the judgment result is normal.

[0051] The essential difference between the two is the absolute value of their difference.

[0052] The performance determination module receives prior sample features N0 from the environmental sample feature memory storage module and process sample features N from the environmental feature acquisition and recognition module. i Calculate |N i -N0|, if |N i If -N0|>threshold, the lidar is determined to be abnormal, and the abnormality information is sent to the alarm module; otherwise, the lidar is determined to be normal, and no information is sent to the alarm module.

[0053] The alarm module is used to receive the judgment results from the performance judgment module and issue warning signals based on the results.

[0054] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

[0055] A computer-readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform a method for identifying performance degradation of a mining vehicle-mounted sensing system.

[0056] A computing device includes one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for performing a method for identifying performance degradation of a mining vehicle-mounted sensing system.

[0057] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention 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.

[0058] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0059] 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.

[0060] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0061] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of the claims of the present invention pending approval.

Claims

1. A performance degradation identification system for a mining vehicle-mounted sensing system, characterized in that, include: The system includes an environmental sample feature memory storage module, an environmental feature acquisition and recognition module, a performance judgment module, and an alarm module. The environmental sample feature memory and storage module is used to mark the location in the environment, perform pre-environmental feature acquisition and processing using the vehicle-mounted perception system, and store the results as prior sample features. The environmental feature acquisition and recognition module is used to collect operational data during vehicle operation. When the vehicle travels to the marked location, it collects on-board perception data and converts it into operational process sample features. The performance determination module is used to receive prior sample features from the environmental sample feature memory storage module and running process sample features from the environmental feature acquisition and recognition module, compare the prior sample features and running process sample features, and determine the difference between the two. When the difference exceeds the threshold, the determination result is abnormal; otherwise, the determination result is normal. The alarm module is used to receive the judgment result from the performance judgment module and issue an early warning signal when the judgment result is abnormal. The environmental feature acquisition and recognition module includes: a location determination submodule, a ROI region filtering submodule, a ground segmentation submodule, and a recognition submodule; The location determination submodule is used to receive the mining truck location information sent by the mining truck positioning system and compare it with the location information of the marked location. When the two pieces of information match, execution information is sent to the ROI region filtering submodule; when the two pieces of information do not match, execution information is not sent to the ROI region filtering submodule. The ROI region filtering submodule is used to receive execution information from the position determination module, read in the radar point cloud data, retain only the point cloud within the ROI region according to the method of restricting the coordinate values ​​of the point cloud data, and send it to the ground segmentation submodule. The ground segmentation submodule is used to receive point cloud data sent by the ROI region filtering submodule, use the RANSAC method to obtain ground point cloud and obstacle point cloud data, and send the obstacle point cloud data to the recognition submodule. The identification submodule is used to receive point cloud data sent by the ground segmentation submodule, calculate the number of point clouds corresponding to obstacles, obtain the running process sample features, and send the running process sample features to the performance judgment module.

2. The performance degradation identification system for a mining vehicle-mounted sensing system according to claim 1, characterized in that, The prior sample features are the number of point clouds of obstacles in the environment; the vehicle-mounted perception system includes a lidar, which collects environmental data and processes it to obtain the number of point clouds of obstacles.

3. The performance degradation identification system for a mining vehicle-mounted sensing system according to claim 1, characterized in that, The characteristic of the running process sample is the number of point clouds of obstacles in the environment.

4. The performance degradation identification system for a mining vehicle-mounted sensing system according to claim 1, characterized in that, The difference between prior sample features and operational sample features is the absolute value of the difference between the two.

5. A method for identifying performance degradation in a mining vehicle-mounted sensing system, characterized in that: The environmental sample feature memory storage module marks the location in the environment, uses the vehicle-mounted perception system to collect and process environmental features in advance, and stores the results as prior sample features. The environmental feature acquisition and recognition module collects operational data during vehicle operation. When the vehicle reaches the marked location, it collects onboard perception data and converts it into operational process sample features. The performance determination module receives prior sample features from the environmental sample feature memory storage module and running process sample features from the environmental feature acquisition and recognition module, compares the prior sample features and running process sample features, and determines the difference between the two. When the difference exceeds the threshold, the determination result is abnormal; otherwise, the determination result is normal. The alarm module receives the judgment result from the performance judgment module and issues an early warning signal when the judgment result is abnormal. The environmental feature acquisition and recognition module includes: a location determination submodule, a ROI region filtering submodule, a ground segmentation submodule, and a recognition submodule; The location determination submodule receives the mining card location information sent by the mining card positioning system and compares it with the location information of the marked location. When the two pieces of information match, execution information is sent to the ROI region filtering submodule; when the two pieces of information do not match, execution information is not sent to the ROI region filtering submodule. The ROI region filtering submodule receives the execution information sent by the position determination module, reads the radar point cloud data, retains only the point cloud within the ROI region according to the method of restricting the coordinate values ​​of the point cloud data, and sends it to the ground segmentation submodule. The ground segmentation submodule receives point cloud data sent by the ROI region filtering submodule, uses the RANSAC method to obtain ground point cloud and obstacle point cloud data, and sends the obstacle point cloud data to the recognition submodule. The identification submodule receives point cloud data sent by the ground segmentation submodule, calculates the number of point clouds corresponding to obstacles, obtains the running process sample features, and sends the running process sample features to the performance determination module.

6. The method for identifying performance degradation of a mining vehicle-mounted sensing system according to claim 5, characterized in that, The prior sample features are the number of point clouds of obstacles in the environment; the vehicle-mounted perception system includes a lidar, which collects environmental data and processes it to obtain the number of point clouds of obstacles.

7. The method for identifying performance degradation of a mining vehicle-mounted sensing system according to claim 5, characterized in that, The characteristic of the running process sample is the number of point clouds of obstacles in the environment.

8. The method for identifying performance degradation of a mining vehicle-mounted sensing system according to claim 5, characterized in that, The difference between prior sample features and operational sample features is the absolute value of the difference between the two.

Images