LiDAR State Detection Method, Device, Computer Equipment and Storage Medium

Abstract

The present application relates to a method, apparatus, and computer device for detecting the state of a lidar. The method includes obtaining total point cloud information corresponding to the lidar within a target time period, and determining the field-of-view point cloud information corresponding to each field of view from the total point cloud information based on the field-of-view information carried by the total point cloud information; obtaining frame information corresponding to the lidar within the target time period, and respectively performing average calculations according to the field-of-view point cloud information and the frame information corresponding to each field of view to obtain the frame average point cloud information corresponding to each field of view; performing an average calculation based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field-of-view average point cloud information; respectively performing a difference comparison between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information to obtain a point cloud data difference result; and determining a state detection result of the lidar within the target time period based on the point cloud data difference result. Using this method can improve the detection efficiency of the lidar state.

Description

Technical Field

[0001] The present application relates to the field of driverless technologies, and particularly to a method, device, computer device, storage medium, and computer program product for detecting the state of a lidar. Background Art

[0002] With the development of driverless technologies, more and more manufacturers install lidars on moving carriers such as vehicles, airplanes, ships, etc. A lidar measures the propagation distance between the sensor transmitter and the target object, and analyzes information such as the magnitude of the reflected energy on the surface of the target object, the amplitude, frequency, and phase of the reflected wave spectrum, so as to present the precise three-dimensional structure information of the target object. For example, a vehicle terminal avoids obstacles based on the three-dimensional structure of the object returned by the lidar, thereby realizing driverless driving of the vehicle. The existing method for detecting the state of a lidar is to receive the point cloud data of a preset field of view of the lidar and judge the state of the lidar according to the intensity information of the echo signal carried by the point cloud data. However, the existing lidar detection steps are cumbersome and cannot quickly detect the state of the lidar, resulting in low detection efficiency of the lidar state. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer device, computer-readable storage medium, and computer program product for detecting the working state of a lidar that can timely detect the state of the lidar and improve the detection efficiency of the lidar state.

[0004] In a first aspect, the present application provides a method for detecting the state of a lidar. The method includes:

[0005] Obtain the total point cloud information corresponding to the lidar within a target time period, and determine the field-of-view point cloud information corresponding to each field of view from the total point cloud information based on the field-of-view information carried by the total point cloud information;

[0006] Obtain the frame information corresponding to the lidar within a target time period, and perform average calculations respectively according to the field-of-view point cloud information corresponding to each field of view and the frame information to obtain the frame average point cloud information corresponding to each field of view;

[0007] Perform an average calculation based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field-of-view average point cloud information;

[0008] Perform a difference comparison between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information respectively to obtain a point cloud data difference result;

[0009] Determine the state detection result of the lidar within the target time period based on the point cloud data difference result.

[0010] In one embodiment, obtaining the total point cloud information corresponding to the lidar within a target time period includes:

[0011] Operating the lidar within the target time period to obtain the total point cloud information corresponding to the lidar, where the total point cloud information corresponding to the lidar is obtained by fusing the field-of-view point cloud information corresponding to each field of view through the lidar.

[0012] In one embodiment, determining the field-of-view point cloud information corresponding to each field of view from the total point cloud information based on the field-of-view information carried by the total point cloud information includes:

[0013] Traversing the field-of-view information carried by each point data in the total point cloud information, and dividing each point data in the total point cloud information according to the field-of-view information carried by each point data in the point cloud data to obtain the field-of-view point cloud information corresponding to each field of view.

[0014] In one embodiment, separately comparing the frame average point cloud information corresponding to each field of view with the field-of-view average point cloud information to obtain a point cloud data difference result includes:

[0015] Separately calculating the difference between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information to obtain the point cloud data difference corresponding to each field of view;

[0016] Taking the point cloud data difference corresponding to each field of view as the point cloud data difference result.

[0017] In one embodiment, determining the status detection result of the lidar within the target time period based on the point cloud data difference result includes:

[0018] When the point cloud data differences corresponding to each field of view do not reach the preset abnormal state difference threshold, the status detection result of the lidar within the target time period is the normal state;

[0019] When there is a target point cloud data difference among the point cloud data differences corresponding to each field of view that reaches the preset abnormal state difference threshold, the status detection result of the lidar within the target time period is the abnormal state.

[0020] In one embodiment, the field of view corresponding to the target point cloud data difference includes the target field of view; the lidar is applied to an unmanned driving device;

[0021] After when there is a target point cloud data difference among the point cloud data differences corresponding to each field of view that reaches the preset abnormal state difference threshold and the status detection result of the lidar within the target time period is the abnormal state, it further includes:

[0022] Generating an abnormal warning message corresponding to the target field of view;

[0023] An alarm is given based on the abnormal warning information, and a preset deceleration stop instruction is executed. The deceleration stop instruction is used to decelerate and stop the unmanned device.

[0024] In a second aspect, the present application also provides a lidar status detection device. The device includes:

[0025] An acquisition module, configured to acquire the total point cloud information corresponding to the lidar within a target time period, and determine the field-of-view point cloud information corresponding to each field of view from the total point cloud information based on the field-of-view information carried by the total point cloud information;

[0026] A frame information operation module, configured to acquire the frame information corresponding to the lidar within a target time period, and perform average calculations respectively according to the field-of-view point cloud information and the frame information corresponding to each field of view to obtain the frame average point cloud information corresponding to each field of view;

[0027] A field-of-view information operation module, configured to perform an average calculation based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field-of-view average point cloud information;

[0028] A comparison module, configured to perform a difference comparison between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information respectively to obtain a point cloud data difference result;

[0029] A determination module, configured to determine the status detection result of the lidar within the target time period based on the point cloud data difference result.

[0030] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0031] Acquire the total point cloud information corresponding to the lidar within a target time period, and determine the field-of-view point cloud information corresponding to each field of view from the total point cloud information based on the field-of-view information carried by the total point cloud information;

[0032] Acquire the frame information corresponding to the lidar within a target time period, and perform average calculations respectively according to the field-of-view point cloud information and the frame information corresponding to each field of view to obtain the frame average point cloud information corresponding to each field of view;

[0033] Perform an average calculation based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field-of-view average point cloud information;

[0034] Perform a difference comparison between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information respectively to obtain a point cloud data difference result;

[0035] Determine the status detection result of the lidar within the target time period based on the point cloud data difference result.

[0036] In a fourth aspect, the present application also provides a computer-readable storage medium. On the computer-readable storage medium, a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0037] Obtain the total point cloud information corresponding to the lidar within a target time period, and determine the field-of-view point cloud information corresponding to each field of view from the total point cloud information based on the field-of-view information carried by the total point cloud information;

[0038] Obtain the frame information corresponding to the lidar within a target time period, and perform average calculations respectively according to the field-of-view point cloud information and the frame information corresponding to each field of view to obtain the frame average point cloud information corresponding to each field of view;

[0039] Perform an average calculation based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field-of-view average point cloud information;

[0040] Perform a difference comparison between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information respectively to obtain a point cloud data difference result;

[0041] Determine the status detection result of the lidar within the target time period based on the point cloud data difference result.

[0042] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0043] Obtain the total point cloud information corresponding to the lidar within a target time period, and determine the field-of-view point cloud information corresponding to each field of view from the total point cloud information based on the field-of-view information carried by the total point cloud information;

[0044] Obtain the frame information corresponding to the lidar within a target time period, and perform average calculations respectively according to the field-of-view point cloud information and the frame information corresponding to each field of view to obtain the frame average point cloud information corresponding to each field of view; '

[0045] Perform an average calculation based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field-of-view average point cloud information;

[0046] Perform a difference comparison between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information respectively to obtain a point cloud data difference result;

[0047] Determine the status detection result of the lidar within the target time period based on the point cloud data difference result.

[0048] The above lidar state detection method, device, computer device, storage medium, and computer program product calculate the average frame point cloud information corresponding to each field of view by averaging the field of view point cloud information and frame information corresponding to each field of view. Then, the average frame point cloud information corresponding to each field of view and the number of each field of view are averaged to obtain the average point cloud information of the field of view, which is the average point cloud data of all fields of view. By comparing the frame average point cloud information corresponding to each field of view with the average point cloud information of the field of view respectively to obtain the point cloud data difference result, the state detection result of the lidar in the target time period is determined according to the point cloud data difference result. By performing two average calculations on the field of view point cloud information corresponding to each field of view, respectively comparing the data after the two average calculations, and determining the state detection result of the lidar in the target time period according to the point cloud data difference result obtained after the difference comparison, the steps of lidar state detection are simplified, and the state detection result of the lidar can be obtained quickly, thereby improving the detection efficiency of the lidar state. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 FIG. is an application environment diagram of the lidar state detection method in an embodiment;

[0050] Figure 2 FIG. is a flowchart of the lidar state detection method in an embodiment;

[0051] Figure 3 FIG. is a schematic diagram of point cloud data stitching in a specific embodiment;

[0052] Figure 4 FIG. is a structural block diagram of the lidar state detection device in an embodiment;

[0053] Figure 5 FIG. is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] In order to make the objectives, technical solutions, and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] The lidar state detection method provided by the embodiments of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the terminal 102 communicates with the driverless device 104 through the network. The terminal 102 can be a control terminal. The terminal 102 can obtain the total point cloud information corresponding to the lidar within a target time period. The lidar is installed in the driverless device 104. The terminal 102 determines the field-of-view point cloud information corresponding to each field of view from the total point cloud information based on the field-of-view information carried in the total point cloud information; the terminal 102 obtains the frame information corresponding to the lidar within the target time period, and performs average calculations according to the field-of-view point cloud information and the frame information corresponding to each field of view respectively to obtain the frame average point cloud information corresponding to each field of view; the terminal 102 performs an average calculation based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field-of-view average point cloud information; the terminal 102 performs a difference comparison between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information respectively to obtain a point cloud data difference result; the terminal 102 determines the status detection result of the lidar within the target time period based on the point cloud data difference result. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The driverless device 104 can be a vehicle, an airplane, a ship, etc.

[0056] In one embodiment, as Figure 2 shown, a lidar status detection method is provided. Taking the terminal in Figure 1 as an example, the method includes the following steps:

[0057] Step 202, obtain the total point cloud information corresponding to the lidar within a target time period, and determine the field-of-view point cloud information corresponding to each field of view from the total point cloud information based on the field-of-view information carried in the total point cloud information.

[0058] Among them, the lidar can be installed on a moving object, including devices such as vehicles, airplanes, and ships, to provide an obstacle avoidance function for the moving device. The total point cloud information includes the point cloud data of each field of view within the target time period, and is used to represent the total quantity of the point cloud data of each field of view within the target time period. The point cloud data refers to a dataset of points in a three-dimensional coordinate system, and the points in the dataset include three-dimensional coordinate information. The point cloud data is obtained by the terminal sending a laser signal to the target object through the lidar and then receiving the echo signal reflected back by the target object from the laser signal. The field-of-view information is the information used to represent the field of view to which the point cloud data belongs. The field of view is used to represent the scanning range of the lidar. The field-of-view point cloud information refers to the quantity of the point cloud data within a single field of view range.

[0059] Specifically, the lidar may be a lidar including multiple fields of view, and different fields of view have different field-of-view point cloud information. The terminal can locally obtain the total point cloud information within the target time period sent by the lidar. The terminal divides the point cloud data in the total point cloud information according to the field-of-view information carried in the total point cloud information to obtain the field-of-view point cloud information corresponding to each field of view.

[0060] Step 204: Obtain the frame information corresponding to the lidar within the target time period, and perform average calculations respectively according to the field-of-view point cloud information and the frame information corresponding to each field of view to obtain the frame average point cloud information corresponding to each field of view.

[0061] Among them, the frame information refers to the number of frames obtained after the lidar scans within the target time period. The frame information can be obtained according to the frame rate of the lidar. One frame represents the scan image obtained when the internal motor of the lidar rotates one circle. The frame average point cloud information refers to the number of point cloud data in the average per-frame image corresponding to a single field of view.

[0062] Specifically, the terminal obtains the number of frames of the lidar within the target time period, and then performs average operations on the number of point cloud data of each field of view within the target time period and the number of frames respectively, that is, calculates the ratio of the number of point cloud data of a single field of view to the number of frames respectively. The terminal can perform average calculations on the field-of-view point cloud information and the frame information corresponding to each field of view simultaneously, or perform average calculations on the field-of-view point cloud information and the frame information corresponding to each field of view successively, to obtain the number of point cloud data in the average per-frame corresponding to each field of view. And save the number of point cloud data in the average per-frame corresponding to each field of view to the data storage space for subsequent calculations.

[0063] Step 206: Perform an average calculation based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field-of-view average point cloud information.

[0064] Among them, the field-of-view average point cloud information refers to the number of point cloud data in the average per-frame image corresponding to all fields of view.

[0065] Specifically, the terminal performs a combined calculation on the frame average point cloud information corresponding to each field of view. The combined calculation can be a total calculation to obtain a combined calculation result, and then performs an average calculation on the combined calculation result and the number of each field of view to obtain the field-of-view average point cloud information.

[0066] Step 208: Perform a difference comparison between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information respectively to obtain a point cloud data difference result.

[0067] Among them, the differential comparison refers to the quantity differential comparison. The point cloud data difference result refers to the result of the quantity comparison of the point cloud data between the frame average point cloud information corresponding to each field of view and the field of view average point cloud information, and is used to determine the state of the lidar during the target time period.

[0068] Specifically, the terminal respectively performs differential comparisons on the frame average point cloud information and the field of view point cloud information corresponding to each field of view to obtain the differential comparison results corresponding to each field of view. Then, the differential comparison results corresponding to each field of view are saved to the data storage space for subsequent determination of the lidar state. The terminal can perform the differential comparison on the frame average point cloud information and the field of view point cloud information corresponding to each field of view simultaneously, or perform the differential comparison on the frame average point cloud information and the field of view point cloud information corresponding to each field of view successively.

[0069] Step 210, determine the state detection result of the lidar during the target time period based on the point cloud data difference result.

[0070] Among them, the state detection result refers to the working state of the lidar during the target time period, including the normal state and the abnormal state.

[0071] Specifically, the terminal respectively checks the differential comparison results corresponding to each field of view in the point cloud data difference result, obtains the state detection result of the lidar during the target time period according to the differential comparison results corresponding to each field of view, and determines the working state of the lidar during the target time period according to the state detection result.

[0072] In the above lidar state detection method, by performing two average calculations on the field of view point cloud information corresponding to each field of view, respectively performing differential comparisons on the data after the two average calculations, and determining the state detection result of the lidar during the target time period according to the point cloud data difference result obtained after the differential comparison, the steps of lidar state detection are simplified, the state detection result of the lidar can be quickly obtained, and thus the detection efficiency of the lidar state is improved.

[0073] In one embodiment, step 202, obtain the total point cloud information corresponding to the lidar during the target time period, including:

[0074] Run the lidar during the target time period to obtain the total point cloud information corresponding to the lidar. The total point cloud information corresponding to the lidar is obtained by fusing the field of view point cloud information corresponding to each field of view through the lidar.

[0075] Specifically, the lidar can be a lidar using a microelectromechanical system and is applied to driverless devices. The lidar can include multiple laser emission devices, and each laser emission device has its corresponding field of view. Each laser emission device in the lidar emits a laser signal to its corresponding field of view, and then the receiving device in the lidar receives the returned echo signal to obtain the point cloud data corresponding to each field of view, that is, the field of view point cloud information corresponding to each field of view. The lidar stitches together the point cloud data corresponding to each field of view to obtain the stitched point cloud data. Then the lidar counts the total number of point data in the stitched point cloud data and takes the stitched point cloud data and the total number of point data in the stitched point cloud data as the total point cloud information. The terminal can receive the total point cloud information through the lidar.

[0076] In a specific embodiment, as Figure 3 shown, a schematic diagram of point cloud data stitching is provided; the figure includes an image obtained by stitching 1 frame of images corresponding to 5 fields of view of the lidar, and the points in the image are the point data in the point cloud data corresponding to each field of view.

[0077] The target time period can be the current time period during the device's driving or the test time period. The terminal can detect that the lidar is operating when the device is driving through the vehicle speed and obtain the total point cloud information of the lidar during the current time period for detecting the working state of the lidar during the current time period. The terminal can also run the lidar and obtain the total point cloud information of the lidar during the test time period when detecting the start time of the test time period for testing the working state of the lidar.

[0078] In this embodiment, by the terminal obtaining the total point cloud information of the lidar during the target time period during the vehicle driving process and then detecting the working state of the lidar during the target time period according to the total point cloud information, the real-time detection of the working state of the lidar can be realized, thereby improving the detection efficiency of the lidar state.

[0079] In one embodiment, step 202, determining the field of view point cloud information corresponding to each field of view from the total point cloud information based on the field of view information carried by the total point cloud information, includes:

[0080] Traverse the field of view information carried by each point data in the total point cloud information, and divide each point data in the total point cloud information according to the field of view information carried by each point data in the total point cloud information to obtain the field of view point cloud information corresponding to each field of view.

[0081] Specifically, the terminal traverses the field of view information carried by each point data in the total point cloud information one by one. Through the field of view information carried by each point data, the terminal can determine the field of view to which each point belongs. Then, the terminal divides all the point data in the point cloud data of the total point cloud information according to the field of view information carried by each point, and obtains the point data corresponding to each field of view. Then, it counts the number of point data corresponding to each field of view to obtain the field of view point cloud information corresponding to each field of view.

[0082] The terminal can also divide the maximum range corresponding to the stitched point cloud data sent by the lidar according to the scanning range corresponding to each field of view. The stitched point cloud data sent by the lidar is the point cloud data within the maximum scanning range of the lidar, and the maximum scanning range is obtained by sequentially stitching the scanning ranges corresponding to each field of view. After division, the point cloud data within the scanning range corresponding to each field of view is obtained, and the number of point cloud data within the scanning range corresponding to each field of view is counted to obtain the field of view point cloud information corresponding to each field of view.

[0083] The terminal can also obtain the single-frame point cloud data corresponding to each field of view continuously sent by the lidar during the target time period. The single-frame point cloud data refers to the point cloud data in the image obtained after the lidar scans a full circle, that is, the point cloud data in 1 frame of the image. Then, the terminal counts the number of each single-frame point cloud data corresponding to each field of view, and accumulates the number of each single-frame point cloud data to obtain the field of view point cloud information corresponding to each field of view. For example, if the number of point data in the point cloud data of the first frame image of a single field of view is 1000, the number of point data in the point cloud data of the second frame image is 1100, and the number of point data in the point cloud data of the third frame image is 1200, then the field of view point cloud information corresponding to this field of view is 1000 + 1100 + 1200 = 3300.

[0084] The terminal can also directly obtain the field of view point cloud information corresponding to each field of view that has been statistically calculated and sent by the lidar.

[0085] In this embodiment, by traversing the field of view information carried by each point data in the total point cloud information, the field of view point cloud information corresponding to each field of view is obtained, which improves the accuracy of the terminal in dividing the field of view point cloud data corresponding to each field of view, and further improves the accuracy of lidar state detection.

[0086] In one embodiment, in step 208, the frame average point cloud information corresponding to each field of view and the field of view average point cloud information are respectively compared for differences to obtain a point cloud data difference result, including:

[0087] Calculate the difference between the frame average point cloud information corresponding to each field of view and the field of view average point cloud information respectively to obtain the point cloud data difference corresponding to each field of view;

[0088] The point cloud data difference corresponding to each field of view is used as the point cloud data difference result.

[0089] Among them, the point cloud data difference refers to the difference between the frame average point cloud information and the field of view average point cloud information, including positive and negative numbers, and is used to represent the difference degree between the frame average point cloud information and the field of view average point cloud information corresponding to each field of view.

[0090] Specifically, the terminal calculates the difference between the frame average point cloud information and the field of view average point cloud information corresponding to each field of view respectively, and obtains the point cloud data difference corresponding to each field of view. Then, the point cloud data difference corresponding to each field of view is used as the point cloud data difference result and saved to the data storage space for judging the working state of the lidar.

[0091] In this embodiment, by simple difference calculation, the point cloud data difference corresponding to each field of view is obtained, which simplifies the detection steps of the lidar state, thereby improving the detection efficiency of the lidar state.

[0092] In one embodiment, step 210, determining the state detection result of the lidar in the target time period based on the point cloud data difference result includes:

[0093] When the point cloud data differences corresponding to each field of view do not reach the preset abnormal state difference threshold, the state detection result of the lidar in the target time period is the normal state;

[0094] When there is a target point cloud data difference among the point cloud data differences corresponding to each field of view that reaches the preset abnormal state difference threshold, the state detection result of the lidar in the target time period is the abnormal state.

[0095] Among them, the preset abnormal state difference threshold is a threshold parameter set in advance for judging the working state of the lidar according to the point cloud data difference. The preset abnormal state difference threshold can be a single threshold parameter set according to the actual situation, or multiple threshold parameters set according to the actual situation. The target point cloud data difference refers to the point cloud data difference that reaches the preset abnormal state difference threshold.

[0096] Specifically, the terminal extracts a preset abnormal state difference threshold. The terminal compares the point cloud data differences corresponding to each field of view with the preset abnormal state difference threshold respectively to determine whether the point cloud data differences corresponding to each field of view reach the preset abnormal state difference threshold. When the terminal detects that the point cloud data differences corresponding to each field of view do not reach the preset abnormal state difference threshold, the terminal determines that the status detection result of the lidar during the target time period is a normal state. When the terminal detects that there is a target point cloud data difference among the point cloud data differences corresponding to each field of view that reaches the preset abnormal state difference threshold, it indicates that the field of view corresponding to the target point cloud data difference is abnormal. At this time, the terminal determines that the status detection result of the lidar during the target time period is an abnormal state. For example, if the point cloud data differences corresponding to 5 fields of view are -200, -100, +100, -1300, and +200 respectively, and the preset abnormal state difference threshold is -1000, then the field of view corresponding to the 4th point cloud data difference has an abnormality, and at this time the detection result of the lidar is an abnormal state.

[0097] In this embodiment, by comparing the point cloud data differences corresponding to each field of view with the preset abnormal state difference threshold respectively and determining whether the point cloud data differences corresponding to each field of view reach the preset abnormal state difference threshold. When the target point cloud data difference reaches the preset abnormal state difference threshold, it indicates that the difference between the frame average point cloud information and the field of view average point cloud information corresponding to the target point cloud data difference is relatively large, and the number of point cloud data in the field of view corresponding to the target point cloud data difference is less than the number of point cloud data in other fields of view, indicating that the field of view corresponding to the target point cloud data difference is abnormal. The field of view abnormality may be caused by fogging inside the lidar or problems with the galvanometer scanner, resulting in an abnormal phenomenon of missing point cloud data in this field of view. Thus, it is possible to quickly obtain that the status detection result of the lidar during the target time period is an abnormal state, thereby improving the detection efficiency of the lidar in the abnormal state.

[0098] In one embodiment, the field of view corresponding to the target point cloud data difference includes the target field of view; the lidar is applied in an unmanned driving device;

[0099] After the status detection result of the lidar during the target time period is an abnormal state when there is a target point cloud data difference among the point cloud data differences corresponding to each field of view that reaches the preset abnormal state difference threshold, it further includes:

[0100] Generating an abnormal warning message corresponding to the target field of view;

[0101] Based on the abnormal warning message, an alarm is issued and a preset deceleration stop instruction is executed. The deceleration stop instruction is used to make the unmanned driving device decelerate and stop.

[0102] Among them, the target field of view refers to an important field of view where an abnormality occurs in the lidar.

[0103] Specifically, the terminal can pre-label the importance of each field of view corresponding to the lidar according to the importance of the field of view, and regard the important field of view as the target field of view. The terminal can classify the severity level of the abnormal state of the lidar according to the abnormal situation of the target field of view. The terminal can be set such that the smaller the severity level of the abnormality, the more serious the abnormal state of the lidar. The target field of view can be one or more.

[0104] When the terminal detects that the field of view corresponding to the target point cloud data difference includes the target field of view, the terminal determines that the state detection result of the lidar during the target time period is a first-level abnormal state. The terminal generates a first-level abnormal warning message corresponding to the target field of view, and then alarms the first-level abnormal state to the management personnel according to the abnormal warning message, and in response to the preset deceleration stop instruction in the first-level abnormal warning message, causes the driverless device to decelerate and stop.

[0105] When the terminal detects that the field of view corresponding to the target point cloud data difference does not include the target field of view, the terminal determines that the state detection result of the lidar during the target time period is a third-level abnormal state. The terminal generates a third-level abnormal warning message, and then alarms the third-level abnormal state to the management personnel according to the third-level abnormal warning message, and enters the waiting instruction state.

[0106] In this embodiment, by classifying and processing the abnormal state of the lidar, flexible processing of the abnormal state of the lidar can be achieved, the processing process of the abnormal state of the lidar is optimized, and thus the detection accuracy of the abnormal state of the lidar is improved.

[0107] In a specific embodiment, when the vehicle-mounted terminal detects that the driverless vehicle is traveling, it obtains the total point cloud information corresponding to the lidar during the vehicle's travel within a target time period, and the target time period can be 1 minute. The terminal traverses the field of view information carried by each point data in the total point cloud information, and divides the total point cloud information into the field of view point cloud information corresponding to each field of view according to the field of view information carried by each point data. The terminal obtains the number of frames scanned by the lidar within the target time period, and then calculates the ratio of the field of view point cloud information corresponding to each field of view to the number of frames respectively to obtain the frame average point cloud information corresponding to each field of view. Then the terminal accumulatively calculates the frame average point cloud information corresponding to each field of view to obtain an accumulation result, and calculates the ratio of the accumulation result to the number of frames to obtain the field of view average point cloud information. Calculate the difference between the frame average point cloud information corresponding to each field of view and the field of view point cloud information to obtain the point cloud data difference corresponding to each field of view. Compare the point cloud data differences corresponding to each field of view with the preset abnormal state difference threshold respectively to determine whether the point cloud data differences corresponding to each field of view reach the preset abnormal state difference threshold. When the terminal detects that the point cloud data differences corresponding to each field of view do not reach the preset abnormal state difference threshold, it determines that the status detection result of the lidar within the target time period is in a normal state. When the terminal detects that there is a target point cloud data difference reaching the preset abnormal state difference threshold among the point cloud data differences corresponding to each field of view, it determines whether the field of view corresponding to the target point cloud data difference is the target field of view. When the field of view corresponding to the target point cloud data difference is the target field of view, it determines that the status detection result of the lidar within the target time period is in a first-level abnormal state, generates a first-level abnormal warning message, and then executes a deceleration stop instruction. When the field of view corresponding to the target point cloud data difference is not the target field of view, it determines that the status detection result of the lidar within the target time period is in a third-level abnormal state, generates a third-level abnormal warning message, and then enters a waiting instruction state.

[0108] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps does not have a strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages, and these steps or stages do not necessarily have to be executed at the same moment, but can be executed at different moments. The execution order of these steps or stages does not necessarily have to be sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0109] Based on the same inventive concept, an embodiment of the present application further provides a lidar status detection device for implementing the lidar status detection method involved above. The implementation solution provided by this device to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more of the following lidar status detection device embodiments can refer to the limitations on the lidar status detection method in the above text and will not be repeated here.

[0110] In one embodiment, as Figure 4 shown, a lidar status detection device 400 is provided, including: an acquisition module 402, a frame information calculation module 404, a field of view information calculation module 406, a comparison module 408, and a determination module 410, where:

[0111] The acquisition module is configured to acquire the total point cloud information corresponding to the lidar within a target time period, and determine the field of view point cloud information corresponding to each field of view from the total point cloud information based on the field of view information carried by the total point cloud information;

[0112] The frame information calculation module is configured to acquire the frame information corresponding to the lidar within a target time period, and perform average calculations according to the field of view point cloud information and the frame information corresponding to each field of view, respectively, to obtain the frame average point cloud information corresponding to each field of view;

[0113] The field of view information calculation module is configured to perform an average calculation based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field of view average point cloud information;

[0114] The comparison module is configured to perform a difference comparison between the frame average point cloud information corresponding to each field of view and the field of view average point cloud information respectively to obtain a point cloud data difference result;

[0115] The determination module is configured to determine the status detection result of the lidar within the target time period based on the point cloud data difference result.

[0116] In one embodiment, the acquisition module 402 includes:

[0117] An operation unit is configured to operate the lidar within a target time period to acquire the total point cloud information corresponding to the lidar. The total point cloud information corresponding to the lidar is obtained by fusing the field of view point cloud information corresponding to each field of view through the lidar.

[0118] In one embodiment, the acquisition module 402 includes:

[0119] A traversal unit is configured to traverse the field of view information carried by each point data in the total point cloud information, and divide each point data in the total point cloud information according to the field of view information carried by each point data in the point cloud data to obtain the field of view point cloud information corresponding to each field of view.

[0120] In one embodiment, the comparison module 408 includes:

[0121] A difference operation unit, configured to calculate the differences between the frame average point cloud information corresponding to each field of view and the field of view average point cloud information respectively, to obtain the point cloud data differences corresponding to each field of view;

[0122] The point cloud data differences corresponding to each field of view are used as the point cloud data difference results.

[0123] In one embodiment, the determination module 410 includes:

[0124] A judgment unit, configured to determine that when the point cloud data differences corresponding to each field of view do not reach the preset abnormal state difference threshold, the state detection result of the lidar in the target time period is a normal state;

[0125] When there is a target point cloud data difference among the point cloud data differences corresponding to each field of view that reaches the preset abnormal state difference threshold, the state detection result of the lidar in the target time period is an abnormal state.

[0126] In one embodiment, the lidar state detection device 400 further includes:

[0127] An alarm unit, configured to generate an abnormal warning message corresponding to the target field of view;

[0128] Based on the abnormal warning message, an alarm is made, and a preset deceleration stop instruction is executed. The deceleration stop instruction is used to decelerate and stop the unmanned device.

[0129] Each module in the above lidar state detection device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0130] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for detecting the state of a lidar. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the outer shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0131] Those skilled in the art can understand that Figure 5 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0132] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0133] Obtain the total point cloud information corresponding to the lidar within the target time period, and determine the point cloud information corresponding to each field of view from the total point cloud information based on the field of view information carried by the total point cloud information; obtain the frame information corresponding to the lidar within the target time period, and perform average calculations respectively according to the point cloud information corresponding to each field of view and the frame information to obtain the frame average point cloud information corresponding to each field of view; perform average calculations based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field of view average point cloud information; perform a difference comparison between the frame average point cloud information corresponding to each field of view and the field of view average point cloud information respectively to obtain a point cloud data difference result; determine the state detection result of the lidar within the target time period based on the point cloud data difference result.

[0134] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0135] Obtain the total point cloud information corresponding to the lidar within the target time period, including: operating the lidar within the target time period to obtain the total point cloud information corresponding to the lidar, and the total point cloud information corresponding to the lidar is obtained by fusing the field-of-view point cloud information corresponding to each field of view through the lidar.

[0136] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0137] Determine the field-of-view point cloud information corresponding to each field of view from the total point cloud information based on the field-of-view information carried by the total point cloud information, including: traversing the field-of-view information carried by each point data in the total point cloud information, and dividing each point data in the total point cloud information according to the field-of-view information carried by each point data in the point cloud data to obtain the field-of-view point cloud information corresponding to each field of view.

[0138] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0139] Perform a differential comparison between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information respectively to obtain a point cloud data difference result, including:

[0140] Calculate the difference between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information respectively to obtain the point cloud data difference corresponding to each field of view;

[0141] Use the point cloud data difference corresponding to each field of view as the point cloud data difference result.

[0142] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0143] Determine the status detection result of the lidar within the target time period based on the point cloud data difference result, including: when the point cloud data differences corresponding to each field of view do not reach the preset abnormal status difference threshold, the status detection result of the lidar within the target time period is a normal status; when there is a target point cloud data difference among the point cloud data differences corresponding to each field of view that reaches the preset abnormal status difference threshold, the status detection result of the lidar within the target time period is an abnormal status.

[0144] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0145] The field of view corresponding to the target point cloud data difference includes the target field of view; the lidar is applied to the driverless device; after the state detection result of the lidar in the target time period is an abnormal state when there is a target point cloud data difference reaching the preset abnormal state difference threshold among the point cloud data differences corresponding to each field of view, it further includes: generating an abnormal warning message corresponding to the target field of view; alarming based on the abnormal warning message, and executing a preset deceleration stop instruction, where the deceleration stop instruction is used to decelerate and stop the driverless device.

[0146] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0147] Obtain the total point cloud information corresponding to the lidar in the target time period, and determine the field-of-view point cloud information corresponding to each field of view from the total point cloud information based on the field-of-view information carried by the total point cloud information; obtain the frame information corresponding to the lidar in the target time period, and perform average calculations according to the field-of-view point cloud information and the frame information corresponding to each field of view respectively to obtain the frame average point cloud information corresponding to each field of view; perform an average calculation based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field-of-view average point cloud information; perform a difference comparison between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information respectively to obtain a point cloud data difference result; determine the state detection result of the lidar in the target time period based on the point cloud data difference result.

[0148] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0149] Obtain the total point cloud information corresponding to the lidar in the target time period, including: operating the lidar in the target time period to obtain the total point cloud information corresponding to the lidar, and the total point cloud information corresponding to the lidar is obtained by fusing the field-of-view point cloud information corresponding to each field of view through the lidar.

[0150] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0151] Determine the field-of-view point cloud information corresponding to each field of view from the total point cloud information based on the field-of-view information carried by the total point cloud information, including: traversing the field-of-view information carried by each point data in the total point cloud information, and dividing each point data in the total point cloud information according to the field-of-view information carried by each point data in the point cloud data to obtain the field-of-view point cloud information corresponding to each field of view.

[0152] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0153] The frame average point cloud information corresponding to each field of view and the field of view average point cloud information are respectively compared for differences to obtain the point cloud data difference result, including:

[0154] Calculate the differences between the frame average point cloud information corresponding to each field of view and the field of view average point cloud information respectively to obtain the point cloud data differences corresponding to each field of view;

[0155] Use the point cloud data differences corresponding to each field of view as the point cloud data difference result.

[0156] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0157] Determine the status detection result of the lidar during the target time period based on the point cloud data difference result, including: when the point cloud data differences corresponding to each field of view do not reach the preset abnormal status difference threshold, the status detection result of the lidar during the target time period is the normal status; when there is a target point cloud data difference among the point cloud data differences corresponding to each field of view that reaches the preset abnormal status difference threshold, the status detection result of the lidar during the target time period is the abnormal status.

[0158] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0159] The field of view corresponding to the target point cloud data difference includes the target field of view; the lidar is applied to an unmanned device; after the status detection result of the lidar during the target time period is the abnormal status when there is a target point cloud data difference among the point cloud data differences corresponding to each field of view that reaches the preset abnormal status difference threshold, it further includes: generating an abnormal warning information corresponding to the target field of view; alarming based on the abnormal warning information, and executing a preset deceleration stop instruction, where the deceleration stop instruction is used to make the unmanned device decelerate and stop.

[0160] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0161] Obtain the total point cloud information corresponding to the lidar during the target time period, and determine the field of view point cloud information corresponding to each field of view from the total point cloud information based on the field of view information carried by the total point cloud information; obtain the frame information corresponding to the lidar during the target time period, and perform average calculations respectively according to the field of view point cloud information and the frame information corresponding to each field of view to obtain the frame average point cloud information corresponding to each field of view; perform an average calculation based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field of view average point cloud information; compare the frame average point cloud information corresponding to each field of view and the field of view average point cloud information respectively for differences to obtain the point cloud data difference result; determine the status detection result of the lidar during the target time period based on the point cloud data difference result.

[0162] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0163] Obtain the total point cloud information corresponding to the lidar within the target time period, including: operating the lidar within the target time period to obtain the total point cloud information corresponding to the lidar, and the total point cloud information corresponding to the lidar is obtained by fusing the field-of-view point cloud information corresponding to each field of view through the lidar.

[0164] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0165] Determine the field-of-view point cloud information corresponding to each field of view from the total point cloud information based on the field-of-view information carried by the total point cloud information, including: traversing the field-of-view information carried by each point data in the total point cloud information, and dividing each point data in the total point cloud information according to the field-of-view information carried by each point data in the point cloud data to obtain the field-of-view point cloud information corresponding to each field of view.

[0166] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0167] Perform a difference comparison between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information respectively to obtain a point cloud data difference result, including:

[0168] Calculate the difference between the frame average point cloud information corresponding to each field of view and the field-of-view average point cloud information respectively to obtain the point cloud data difference corresponding to each field of view;

[0169] Use the point cloud data difference corresponding to each field of view as the point cloud data difference result.

[0170] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0171] Determine the status detection result of the lidar within the target time period based on the point cloud data difference result, including: when the point cloud data differences corresponding to each field of view do not reach the preset abnormal status difference threshold, the status detection result of the lidar within the target time period is the normal status; when there is a target point cloud data difference among the point cloud data differences corresponding to each field of view that reaches the preset abnormal status difference threshold, the status detection result of the lidar within the target time period is the abnormal status.

[0172] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0173] The field of view corresponding to the target point cloud data difference includes the target field of view; the lidar is applied to the driverless device; after the state detection result of the lidar in the target time period is an abnormal state when there is a target point cloud data difference reaching the preset abnormal state difference threshold among the point cloud data differences corresponding to each field of view, it further includes: generating an abnormal warning information corresponding to the target field of view; alarming based on the abnormal warning information, and executing a preset deceleration stop instruction, where the deceleration stop instruction is used to decelerate and stop the driverless device.

[0174] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0175] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memories can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0176] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0177] The above-described embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for detecting the state of a lidar, characterized in that, The method includes: Obtaining the total point cloud information corresponding to the lidar within a target time period, and determining the point cloud information corresponding to each field of view from the total point cloud information based on the field of view information carried by the total point cloud information; the total point cloud information includes the point cloud data of each field of view within the target time period and the total number of the point cloud data; the point cloud data is a data set of points in a three-dimensional coordinate system, including the three-dimensional coordinate information of the points; the point cloud information of the field of view is the number of point cloud data within the field of view range corresponding to a single field of view. Obtaining the frame information corresponding to the lidar within the target time period, and respectively performing average calculations according to the point cloud information of each field of view and the frame information to obtain the frame average point cloud information corresponding to each field of view; the frame information is the number of frames obtained after the lidar scans within the target time period; the frame average point cloud information is the number of point cloud data in the average per-frame image corresponding to a single field of view. Performing an average calculation based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field of view average point cloud information; the field of view average point cloud information is the number of point cloud data in the average per-frame image of the field of view cluster corresponding to each field of view. Respectively comparing the frame average point cloud information corresponding to each field of view with the field of view average point cloud information to obtain a point cloud data difference result. Determining the status detection result of the lidar within the target time period based on the point cloud data difference result.

2. The method according to claim 1, characterized in that The obtaining the total point cloud information corresponding to the lidar within the target time period includes: Operating the lidar within the target time period to obtain the total point cloud information corresponding to the lidar, and the total point cloud information corresponding to the lidar is obtained by fusing the point cloud information corresponding to each field of view through the lidar.

3. The method according to claim 1, wherein The determining the point cloud information corresponding to each field of view from the total point cloud information based on the field of view information carried by the total point cloud information includes: Traversing the field of view information carried by each point data in the total point cloud information, and dividing each point data in the total point cloud information according to the field of view information carried by each point data in the total point cloud information to obtain the point cloud information corresponding to each field of view.

4. The method according to claim 1, characterized in that The respectively comparing the frame average point cloud information corresponding to each field of view with the field of view average point cloud information to obtain a point cloud data difference result includes: Respectively calculating the difference between the frame average point cloud information corresponding to each field of view and the field of view average point cloud information to obtain the point cloud data difference corresponding to each field of view. Taking the point cloud data difference corresponding to each field of view as the point cloud data difference result.

5. The method according to claim 4, characterized in that The determining the status detection result of the lidar within the target time period based on the point cloud data difference result includes: When the point cloud data differences corresponding to each field of view do not reach the preset abnormal state difference threshold, the status detection result of the lidar within the target time period is the normal state. When there is a target point cloud data difference reaching the preset abnormal state difference threshold among the point cloud data differences corresponding to each field of view, the state detection result of the lidar in the target time period is an abnormal state.

6. The method according to claim 5, characterized in that, The field of view corresponding to the target point cloud data difference includes the target field of view; the lidar is applied to an unmanned device; After the state detection result of the lidar in the target time period is an abnormal state when there is a target point cloud data difference reaching the preset abnormal state difference threshold among the point cloud data differences corresponding to each field of view, it further includes: Generating abnormal warning information corresponding to the target field of view; Based on the abnormal warning information, an alarm is given and a preset deceleration stop instruction is executed, and the deceleration stop instruction is used to make the unmanned device decelerate and stop.

7. A lidar state detection device, characterized in that, The device includes: An acquisition module, configured to acquire the total point cloud information corresponding to the lidar in the target time period, and determine the point cloud information corresponding to each field of view from the total point cloud information based on the field of view information carried in the total point cloud information; the total point cloud information includes the point cloud data and the total number of the point cloud data of each field of view in the target time period; the point cloud data is a data set of points in a three-dimensional coordinate system, including the three-dimensional coordinate information of the points; the point cloud information of the field of view is the number of point cloud data within the field of view range corresponding to a single field of view; A frame information operation module, configured to acquire the frame information corresponding to the lidar in the target time period, and perform average calculations according to the point cloud information of each field of view and the frame information respectively to obtain the frame average point cloud information corresponding to each field of view; the frame information is the number of frames obtained after the lidar scans in the target time period; the frame average point cloud information is the number of point cloud data in the average per-frame image corresponding to a single field of view; A field of view information operation module, configured to perform an average calculation based on the frame average point cloud information corresponding to each field of view and the number of each field of view to obtain the field of view average point cloud information; the field of view average point cloud information is the number of point cloud data in the average per-frame image of the field of view cluster corresponding to each field of view; A comparison module, configured to perform a difference comparison between the frame average point cloud information corresponding to each field of view and the field of view average point cloud information respectively to obtain a point cloud data difference result; A determination module, configured to determine the state detection result of the lidar in the target time period based on the point cloud data difference result.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 6.

Images