Lidar fault evaluation method and device, computer device and storage medium

Abstract

The application relates to a laser radar fault evaluation method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a sensing data missing duration and a sensing data missing area of a laser radar; entering a fault processing branch according to the sensing data missing duration, different laser radar fault levels are set in different fault processing branches; generating a laser radar fault level upgrading instruction according to the sensing data missing area and a vehicle running state; and obtaining a laser radar fault level according to the laser radar fault level upgrading instruction. The method can improve the safety performance of vehicle driving by combining the sensing of the vehicle body environment, improve the safety and smoothness of driving, coordinate the faults of the self vehicle system, and reduce the safety risk.

Description

Technical Field

[0001] This application relates to the field of vehicle safety technology, and in particular to a lidar fault assessment method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] With the development of autonomous driving technology, LiDAR, as an important environmental perception device, is widely used to detect and acquire information about the surrounding environment. LiDAR emits laser beams and receives the reflected light signals to provide accurate data such as distance, position, and shape, assisting vehicles in tasks such as navigation, obstacle detection, and target recognition. However, due to environmental factors, equipment aging, or malfunctions during operation, LiDAR may fail or partially fail. When LiDAR fails, it may cause the autonomous driving system to perceive the surrounding environment inaccurately, thereby reducing system safety. Therefore, accurate assessment and monitoring of LiDAR failures and malfunctions are crucial.

[0003] Currently, the measures taken to protect vehicles in the event of lidar failure or malfunction mainly focus on the following three aspects: First, external protection for lidar, such as adding a casing to reduce external impacts caused by weather conditions or external collisions; second, utilizing the principle of sensor fusion to ensure the perception capabilities of autonomous vehicles through redundant sensors (such as millimeter-wave radar and cameras); and third, judging the validity of the data received by lidar.

[0004] However, these methods can often only detect lidar malfunctions, but cannot analyze and judge the vehicle's safety status when lidar fails. Summary of the Invention

[0005] Therefore, it is necessary to provide a lidar fault assessment method, device, computer equipment, computer-readable storage medium, and computer program product that can ensure vehicle safety in the event of lidar failure, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for assessing lidar faults. The method includes:

[0007] Obtain the duration and area of ​​missing sensing data from the LiDAR;

[0008] The fault handling branch is entered based on the duration of missing sensing data, and different LiDAR fault levels are set in different fault handling branches.

[0009] Based on the missing perception data areas and vehicle operating status, generate a LiDAR fault level upgrade command;

[0010] The fault level of the lidar is obtained based on the lidar fault level upgrade instruction.

[0011] In one embodiment, the method further includes:

[0012] Divide the area around the vehicle and number the area around the vehicle;

[0013] The sensing area of ​​the first lidar is matched with the area around the vehicle to obtain the first lidar sensing number. The sensing area of ​​the second lidar is matched with the area around the vehicle to obtain the second lidar sensing number. The lidar sensing number is the number of the area around the vehicle that the lidar can sense.

[0014] The perception numbers of the first and second lidars are calculated to obtain the number of the area around the vehicle that can be perceived by the total lidar; the total lidar includes the first and second lidars.

[0015] In one embodiment, the process of generating a lidar fault level upgrade instruction based on the area of ​​missing perception data and the vehicle's operating status includes:

[0016] Obtain fault blind spots and vehicle operating status; fault blind spots are areas around any vehicle that are missing data for all LiDARs, i.e., areas around the vehicle that cannot be perceived by the total LiDAR; vehicle operating status includes stationary state and moving state.

[0017] When the vehicle is stationary, the fault level of the lidar does not escalate; when the vehicle is in motion, it is determined whether there is a fault blind spot.

[0018] When the vehicle's direction of travel coincides with the blind spot of the fault, the fault level of the lidar is upgraded.

[0019] The lidar fault level will not be upgraded when the vehicle's direction of travel does not coincide with the blind spot of the fault.

[0020] In one embodiment, when the vehicle's direction of travel does not coincide with the blind spot, the lidar fault level is not upgraded, including:

[0021] Obtain the valid perception results of the previous frame in the fault blind zone and determine the status of obstacles within a preset range; obstacle status includes no obstacles, stationary obstacles, and dynamic obstacles;

[0022] When there are no obstacles or stationary obstacles within the preset range, the fault level of the lidar will not be upgraded;

[0023] When dynamic obstacles exist within a preset range, determine whether all dynamic obstacles are within the lidar sensing area;

[0024] When the device is within the LiDAR sensing area, the LiDAR fault level does not escalate; when the device is outside the LiDAR sensing area, the LiDAR fault level escalates.

[0025] In one embodiment, the first lidar perception number and the second lidar perception number are calculated to obtain the total area around the vehicle that can be perceived by the lidar, including:

[0026] The first lidar sensing number and the second lidar sensing number are represented in binary format.

[0027] The first and second lidar sensing numbers are processed by bitwise operations to determine whether the total lidar sensing area meets the requirements for a complete sensing area.

[0028] In one embodiment, the method further includes:

[0029] Configure lidar sensing numbers for the first lidar and the second lidar respectively;

[0030] By configuring the parameters in the LiDAR sensing number, a LiDAR failure scenario is simulated.

[0031] Secondly, this application also provides a lidar fault assessment device. The device includes:

[0032] The data acquisition module is used to acquire the duration and area of ​​missing sensing data from the LiDAR.

[0033] The branch module is used to enter the fault handling branch based on the duration of missing sensing data, and to set different LiDAR fault levels in different fault handling branches.

[0034] The judgment module is used to generate a LiDAR fault level upgrade instruction based on the area of ​​missing perception data and the vehicle's operating status.

[0035] The decision module is used to determine the fault level of the lidar based on the lidar fault level upgrade command.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0037] Obtain the duration and area of ​​missing sensing data from the LiDAR;

[0038] The fault handling branch is entered based on the duration of missing sensing data, and different LiDAR fault levels are set in different fault handling branches.

[0039] Based on the missing perception data areas and vehicle operating status, generate a LiDAR fault level upgrade command;

[0040] The fault level of the lidar is obtained based on the lidar fault level upgrade instruction.

[0041] Fourthly, this application also provides a computer-readable storage medium. This computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0042] Obtain the duration and area of ​​missing sensing data from the LiDAR;

[0043] The fault handling branch is entered based on the duration of missing sensing data, and different LiDAR fault levels are set in different fault handling branches.

[0044] Based on the missing perception data areas and vehicle operating status, generate a LiDAR fault level upgrade command;

[0045] The fault level of the lidar is obtained based on the lidar fault level upgrade instruction.

[0046] Fifthly, this application also provides a computer program product. This computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0047] Obtain the duration and area of ​​missing sensing data from the LiDAR;

[0048] The fault handling branch is entered based on the duration of missing sensing data, and different LiDAR fault levels are set in different fault handling branches.

[0049] Based on the missing perception data areas and vehicle operating status, generate a LiDAR fault level upgrade command;

[0050] The fault level of the lidar is obtained based on the lidar fault level upgrade instruction.

[0051] The aforementioned LiDAR fault assessment method, device, computer equipment, storage medium, and computer program products, when a LiDAR sensing failure occurs, set different fault handling branches based on the duration of missing sensing data, and set different LiDAR fault levels within each branch. Then, a LiDAR fault level escalation command is generated based on the area of ​​missing sensing data, and this command is input into the corresponding fault handling branch to obtain the LiDAR fault level. By setting different fault handling branches, classification based on the duration of missing sensing data allows for targeted measures to be taken, avoiding unnecessary interruptions or redundant operations to the entire system. Precise fault handling branch settings improve system efficiency and reliability. By analyzing the area of ​​missing sensing data, the degree and scope of the LiDAR fault are determined, and corresponding fault level escalation commands are generated. This helps maintenance personnel quickly and accurately locate and resolve LiDAR faults, reducing troubleshooting time and costs, minimizing system downtime, and improving system stability and availability. Attached Figure Description

[0052] Figure 1 This is an application environment diagram of a lidar fault assessment method in one embodiment;

[0053] Figure 2 This is a flowchart illustrating a lidar fault assessment method in one embodiment;

[0054] Figure 3 This is a flowchart illustrating a lidar fault assessment method in one embodiment;

[0055] Figure 4 This is a schematic diagram illustrating the division of the area around a vehicle in one embodiment;

[0056] Figure 5 This is a flowchart illustrating a failure and fault assessment system in one embodiment;

[0057] Figure 6 This is a flowchart illustrating a lidar fault assessment method in another embodiment;

[0058] Figure 7 This is a structural block diagram of a lidar fault assessment device in one embodiment;

[0059] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0061] The lidar fault assessment method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0062] In one embodiment, such as Figure 2 As shown, a method for assessing lidar faults is provided, which can be applied to... Figure 1 Taking the server in the example, the following steps are included:

[0063] Step 202: Obtain the duration and area of ​​missing sensing data from the LiDAR.

[0064] Step 204: Enter the fault handling branch according to the duration of missing perception data, and set different LiDAR fault levels in different fault handling branches.

[0065] Step 206: Generate a LiDAR fault level upgrade command based on the area of ​​missing perception data and the vehicle's operating status.

[0066] Step 208: Obtain the LiDAR fault level according to the LiDAR fault level upgrade instruction.

[0067] Specifically, in combination Figure 3 As shown, Figure 3This is a schematic diagram of the LiDAR fault assessment process. An autonomous vehicle can have any combination of LiDARs configured to receive perception data from multiple LiDARs. When all LiDAR data is successfully received, normal perception is confirmed. If any LiDAR data reception fails, the time difference between the current time and the last time that LiDAR's perception data was received is calculated. This time difference is the perception data loss duration, and the system proceeds to the fault handling branch based on the perception data loss duration. For example, if the perception data loss duration is less than T1, the system continues to attempt to receive data; if the perception data loss duration is between T1 and T2, between T2 and T3, or greater than T3, the system will enter the LiDAR failure and fault assessment system.

[0068] In the LiDAR failure and fault assessment system, the vehicle's operating status is determined, including both stationary and moving states. When the vehicle is stationary, no LiDAR fault level escalation command is generated. When the vehicle is moving, the fault blind zone is determined based on the missing perception data areas of the LiDAR. The missing perception data areas are areas that any LiDAR should have detected but failed to detect due to a fault; the fault blind zone is the area around the vehicle that cannot be detected by any LiDAR. The system checks if a fault blind zone exists. If it does not exist, no LiDAR fault level escalation command is generated. If it exists, the system checks if the vehicle's movement state matches the fault blind zone. If they do not match, no LiDAR fault level escalation command is generated. If they match, the system reads the valid perception result from the previous frame for further analysis and judgment. Upon receiving a LiDAR fault level escalation command from the LiDAR failure and fault assessment system, various fault level errors are triggered, and the corresponding LiDAR fault level is issued.

[0069] In one optional embodiment, different error levels are set for each fault handling branch. When the duration of missing sensing data is between T1 and T2, a level A error is triggered if no LiDAR fault level escalation command is received; a level B error is triggered if a LiDAR fault level escalation command is received. When the duration of missing sensing data is between T2 and T3, a level B error is triggered if no LiDAR fault level escalation command is received; a level C error is triggered if a LiDAR fault level escalation command is received. When the duration of missing sensing data exceeds T3, a level C error is triggered if no LiDAR fault level escalation command is received; a level D error is triggered if a LiDAR fault level escalation command is received.

[0070] In the aforementioned LiDAR fault assessment method, when a LiDAR sensing failure occurs, different fault handling branches are set according to the duration of missing sensing data, and different LiDAR fault levels are set in different fault handling branches. Then, a LiDAR fault level escalation command is generated based on the area of ​​missing sensing data, and this command is input into the corresponding fault handling branch to obtain the LiDAR fault level. By setting different fault handling branches, classification based on the duration of missing sensing data allows for targeted measures to be taken, avoiding unnecessary interruptions or redundant operations to the entire system. Precise fault handling branch settings improve system efficiency and reliability. By analyzing the area of ​​missing sensing data, the degree and scope of the LiDAR fault are determined, and a fault level escalation command is generated accordingly. This allows for quick and accurate location and resolution of LiDAR faults, reducing troubleshooting time and costs, minimizing system downtime, and improving system stability and availability.

[0071] In one embodiment, the lidar fault assessment method further includes: dividing the vehicle's surrounding area and numbering the surrounding area; matching the sensing area of ​​the first lidar with the vehicle's surrounding area to obtain a first lidar sensing number, and matching the sensing area of ​​the second lidar with the vehicle's surrounding area to obtain a second lidar sensing number; the lidar sensing number is the number of the vehicle's surrounding area that the lidar can sense; performing calculations on the first lidar sensing number and the second lidar sensing number to obtain the total number of vehicle's surrounding area that the lidar can sense; the total lidar includes the first lidar and the second lidar.

[0072] For example, refer to Figure 4 As shown, Figure 4 This diagram illustrates the area around the vehicle. Based on the length and width of each vehicle, the area around the vehicle is divided into 8 regions, starting with the region directly in front of the vehicle, numbered 1. Subsequent regions are numbered sequentially. Assuming lidar_1 (LiDAR 1) can only see the directly in front (region 1), its corresponding perception area is "10000000". Assuming lidar_2 is installed at the rear of the vehicle and can see regions 4, 5, and 6, its corresponding perception area is "00011100". The complete perception area of ​​an autonomous vehicle is "11111111". Vehicles typically have one or more lidars, and the complete perception area is determined by calculating the perception areas of all onboard lidars.

[0073] Furthermore, based on the length, width, and radar sensing angle of each vehicle, the area around the vehicle can be divided more finely. For example, the area around the vehicle can be divided into 16 regions, with the area at the front left of the vehicle starting with number 1, and then the regions around the vehicle numbered sequentially. Assuming that lidar_1 can see the sensing region 1 directly in front of it, then the sensing region corresponding to lidar_1 is "11000000000000000"; assuming that lidar_2 is installed at the rear of the vehicle and can see the four regions 8, 9, 10, and 11 behind the vehicle, then the sensing region corresponding to lidar_2 is "0000000111100000", and the complete sensing region of the autonomous vehicle is "11111111111111111".

[0074] In this embodiment, by dividing the area around the vehicle and numbering the sensing areas of the LiDAR, the environment around the vehicle can be perceived and analyzed more accurately. For different areas around the vehicle, a sensing number can be obtained for each LiDAR, so that each number represents a specific area that the LiDAR can perceive. This provides a precise description and division of the vehicle's surrounding environment, facilitating subsequent data processing and analysis, improving the vehicle-mounted LiDAR system's understanding and processing capabilities of the environment, and thus enhancing the LiDAR's perception and decision-making abilities.

[0075] In one embodiment, generating a LiDAR fault level escalation command by sensing the data-deficient area and the vehicle's operating status includes: acquiring the fault blind zone and the vehicle's operating status; the fault blind zone is any area around the vehicle that is a data-deficient area for all LiDARs, i.e., the area around the vehicle that cannot be perceived by the total LiDARs; the vehicle's operating status includes a stationary state and a moving state; when the vehicle is stationary, the LiDAR fault level is not escalated; when the vehicle is moving, it is determined whether a fault blind zone exists; when the vehicle's direction of travel coincides with the fault blind zone, the LiDAR fault level is escalated; when the vehicle's direction of travel does not coincide with the fault blind zone, the LiDAR fault level is not escalated.

[0076] Specifically, refer to Figure 5 As shown, Figure 5This is a flowchart illustrating the failure and fault assessment system. When the vehicle's LiDAR experiences a perception fault, the autonomous vehicle triggers the LiDAR failure and fault assessment system to obtain the vehicle's operating status. If the vehicle is stationary, no LiDAR fault level escalation command is issued. When the vehicle is moving, the system calculates the field of view (fov) of the received LiDAR data, determining if the effective LiDAR data covers the eight areas surrounding the vehicle. If it does, no LiDAR fault level escalation command is issued; otherwise, the uncovered area is identified as a LiDAR fault blind spot. The system then determines if this blind spot aligns with the vehicle's direction of movement. For example, if the vehicle is moving forward and area number 1 is a LiDAR fault blind spot, or if the vehicle is moving backward and area number 5 is a LiDAR fault blind spot, the blind spot is determined to be consistent with the vehicle's direction of movement, and a LiDAR fault level escalation command is issued. Furthermore, if the vehicle is turning left, the system determines if areas 1, 8, and 7 are LiDAR fault blind spots.

[0077] In this embodiment, by making consistent judgments on vehicle status and fault blind spots, the system processing steps are reduced, and the vehicle's safety status is effectively assessed. This further reminds relevant personnel of the lack of LiDAR perception data, enhances the ability to identify and handle potential obstacles, improves the reliability of the LiDAR fault assessment system, and enhances the safety of vehicle operation.

[0078] In one embodiment, refer to Figure 5 As shown, Figure 5 This is a schematic diagram of a failure and fault assessment system. When the vehicle's direction of travel does not coincide with the fault blind zone, the LiDAR fault level does not escalate. The process includes: acquiring the previous frame's valid perception result for the fault blind zone and determining the obstacle status within a preset range; obstacle status includes no obstacles, stationary obstacles, and dynamic obstacles; if there are no obstacles or stationary obstacles within the preset range, the LiDAR fault level does not escalate; if dynamic obstacles exist within the preset range, it is determined whether all dynamic obstacles are within the LiDAR's perception area; if they are within the LiDAR's perception area, the LiDAR fault level does not escalate; if they are not within the LiDAR's perception area, the LiDAR fault level escalates.

[0079] Specifically, when the vehicle's direction of travel does not coincide with the blind spot, the LiDAR system reads the previous valid perception result of the blind spot and determines whether an obstacle exists within a preset range. If no obstacle exists within the preset range, no LiDAR fault level escalation command is generated. If an obstacle exists within the preset range, the system further determines the obstacle's state, including stationary and dynamic obstacles. If the obstacle within the preset range is stationary, no LiDAR fault level escalation command is generated. If the obstacle within the preset range is dynamic, the system traverses the directions of the dynamic obstacles and determines whether they are all within the perceived direction. If the dynamic obstacle is within the LiDAR's perception area, no LiDAR fault level escalation command is generated; if the dynamic obstacle is not within the LiDAR's perception area, a LiDAR fault level escalation command is generated.

[0080] In this embodiment, the vehicle's driving environment is combined with LiDAR's fault detection to determine whether there are obstacles in the driving environment that may pose a threat to vehicle safety. These obstacles are categorized into static and dynamic obstacles, thus better ensuring the safety and reliability of autonomous driving. Increased environmental awareness improves the smoothness of safe vehicle operation when LiDAR malfunctions, reducing the safety threats to passengers and other road users caused by sudden braking.

[0081] In one embodiment, the vehicle's surrounding area that can be perceived by the total lidar is obtained by performing calculations on the first lidar perception number and the second lidar perception number, including: representing the first lidar perception number and the second lidar perception number in binary; and processing the first lidar perception number and the second lidar perception number through bitwise operations to determine whether the perception area of ​​the total lidar meets the requirements of a complete perception area.

[0082] Bitwise operations are operations in computers that manipulate binary bits. They perform logical calculations on each bit of a binary number, including operations such as AND, OR, XOR, and NOT.

[0083] Specifically, in combination Figure 4 As shown, Figure 4 A schematic diagram showing the area around the vehicle is provided. Based on the LiDAR's perception area, the perception areas are numbered using binary representation. Specifically, lidar_1's perception area is "10000111", lidar_2's is "11110000", lidar_3's is "10000000", lidar_4's is "00001100", and lidar_5's is "00011000". The process of obtaining the complete perception area of ​​the vehicle with the above LiDAR configuration through bitwise operations is as follows:

[0084] lidar_1: 10000111

[0085] lidar_2:11110000

[0086] lidar_3: 10000000

[0087] lidar_4: 00001100

[0088] lidar_5: 00011000

[0089] Result: 11111111

[0090] In this embodiment, the perception areas of each LiDAR are numbered using binary encoding, simplifying and identifying complex perception data. This encoding method is easy to understand and process, facilitating subsequent data analysis and processing. By using bitwise operations, the perception areas of different LiDARs can be combined to obtain the complete perception area of ​​the vehicle, thus obtaining the overall perception area encompassing all LiDAR perception areas. This helps improve the understanding and decision-making capabilities of autonomous vehicles or other related applications regarding the environment.

[0091] In one embodiment, the lidar fault assessment method further includes: configuring lidar perception numbers for the first lidar and the second lidar respectively; and simulating lidar fault scenarios by configuring parameters in the lidar perception numbers.

[0092] Specifically, by setting data input parameters for the sensing areas of the first and second lidars, a sensing fault is identified in the corresponding sensing area of ​​the lidar, specifically the area with missing sensing data for both lidars. At this point, simply setting the lidar sensing numbers accordingly simulates a lidar fault scenario. Under this scenario, a vehicle environment is simulated to test and verify the feasibility of the function.

[0093] In this embodiment, by setting a fault injection mechanism for the lidar, parameter configuration of the lidar sensing area is performed to simulate lidar faults. This eliminates the cumbersome operation of disconnecting the lidar cable; the lidar fault scenario can be simulated simply by modifying the parameters. This improves the system's verification efficiency and the accuracy of the results.

[0094] In one embodiment, such as Figure 6 As shown, the lidar fault assessment methods include:

[0095] Step 602: Divide the area around the vehicle and number the area around the vehicle.

[0096] Step 604: Match the sensing area of ​​the first lidar with the area around the vehicle to obtain the first lidar sensing number; match the sensing area of ​​the second lidar with the area around the vehicle to obtain the second lidar sensing number; the lidar sensing number is the number of the area around the vehicle that the lidar can sense.

[0097] Step 606: Represent the first lidar sensing number and the second lidar sensing number in binary.

[0098] Step 608: Process the first lidar sensing number and the second lidar sensing number through bit operations to determine whether the total lidar sensing area meets the requirements of a complete sensing area.

[0099] Step 610: Configure lidar perception numbers for the first lidar and the second lidar respectively.

[0100] Step 612: Simulate a lidar failure scenario by configuring the parameters in the lidar perception number.

[0101] Step 614: Obtain the duration and area of ​​missing sensing data from the LiDAR.

[0102] Step 616: Enter the fault handling branch according to the duration of missing perception data, and set different LiDAR fault levels in different fault handling branches.

[0103] Step 618: Obtain the fault blind zone and vehicle operating status; the fault blind zone is any area around the vehicle where data is missing for all LiDARs, and therefore the total LiDAR cannot perceive the area around the vehicle; the vehicle operating status includes stationary state and driving state.

[0104] Step 620: When the vehicle is stationary, the fault level of the lidar is not upgraded; when the vehicle is in motion, determine whether there is a fault blind spot.

[0105] Step 622: When the vehicle's direction of travel coincides with the blind spot of the fault, the fault level of the lidar is upgraded.

[0106] Step 624: When the vehicle's direction of travel does not coincide with the blind spot of the fault, the fault level of the lidar will not be upgraded.

[0107] Step 626: Obtain the valid perception results of the previous frame in the fault blind zone and determine the obstacle status within the preset range. The obstacle status includes no obstacles, stationary obstacles, and dynamic obstacles.

[0108] Step 628: When there are no obstacles or stationary obstacles within the preset range, the fault level of the lidar will not be upgraded.

[0109] Step 630: When there are dynamic obstacles within a preset range, determine whether all dynamic obstacles are within the lidar sensing area.

[0110] Step 632: When the device is within the LiDAR sensing area, the LiDAR fault level is not upgraded; when the device is not within the LiDAR sensing area, the LiDAR fault level is upgraded.

[0111] Step 634: Obtain the LiDAR fault level according to the LiDAR fault level upgrade instruction.

[0112] In this embodiment, when a LiDAR sensing failure occurs, different fault handling branches are set according to the duration of missing LiDAR sensing data, and different LiDAR fault levels are set in different fault handling branches. Then, a LiDAR fault level escalation command is generated based on the missing sensing data area, and the LiDAR fault level escalation command is input to the corresponding fault handling branch to obtain the LiDAR fault level. By setting different fault handling branches, classification can be performed based on the duration of missing sensing data, thereby taking targeted measures to avoid unnecessary interruptions or redundant operations to the entire system. Precise fault handling branch settings can improve system efficiency and reliability. For environmental perception, corresponding fault level escalation commands are proposed, compensating for the lack of focus on LiDAR. By perceiving the vehicle's environment, more intelligent and reasonable braking can be issued, improving driving safety and smoothness, while also coordinating with vehicle system faults to reduce safety risks. This allows for quick and accurate location and resolution of LiDAR faults, reducing troubleshooting time and costs, minimizing system downtime, and improving system stability and availability.

[0113] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially, these steps are not necessarily executed in the indicated order. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0114] Based on the same inventive concept, this application also provides a lidar fault assessment device for implementing the lidar fault assessment method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more lidar fault assessment device embodiments provided below can be found in the limitations of the lidar fault assessment method described above, and will not be repeated here.

[0115] In one embodiment, such as Figure 7 As shown, a lidar fault assessment device is provided, comprising: a data acquisition module 702, a branch module 704, a judgment module 706, and a decision module 708, wherein:

[0116] The data acquisition module 702 is used to acquire the duration and area of ​​missing sensing data from the lidar.

[0117] Branch module 704 is used to enter the fault handling branch according to the duration of missing sensing data, and to set different LiDAR fault levels in different fault handling branches.

[0118] The judgment module 706 is used to generate a lidar fault level upgrade command based on the area of ​​missing perception data and the vehicle's operating status.

[0119] The decision module 708 is used to obtain the fault level of the lidar based on the lidar fault level upgrade instruction.

[0120] In one embodiment, the data acquisition module 702 further includes:

[0121] The segmentation module is used to segment the area around the vehicle and number the area around the vehicle.

[0122] The matching module is used to match the sensing area of ​​the first lidar with the area around the vehicle to obtain the first lidar sensing number, and to match the sensing area of ​​the second lidar with the area around the vehicle to obtain the second lidar sensing number; the lidar sensing number is the number of the area around the vehicle that the lidar can sense.

[0123] The calculation module is used to calculate the perception number of the first lidar and the perception number of the second lidar to obtain the number of the area around the vehicle that can be perceived by the total lidar; the total lidar includes the first lidar and the second lidar.

[0124] In one embodiment, the computing module further includes:

[0125] The numbering module is used to represent the first lidar sensing number and the second lidar sensing number in binary.

[0126] The bit operation module is used to process the first lidar sensing number and the second lidar sensing number through bit operations to determine whether the total lidar sensing area meets the requirements of the complete sensing area.

[0127] In one embodiment, the determining module 706 further includes:

[0128] The acquisition module is used to obtain fault blind spots and vehicle operating status; the fault blind spot is any area around the vehicle where data is missing for all LiDARs, that is, the area around the vehicle that cannot be perceived by the total LiDAR; the vehicle operating status includes stationary state and driving state.

[0129] The analysis module is used to prevent the LiDAR fault level from escalating when the vehicle is stationary, and to determine whether there is a fault blind spot when the vehicle is in motion.

[0130] The first upgrade module is used to upgrade the fault level of the lidar when the vehicle's direction of travel coincides with the fault blind spot.

[0131] The second upgrade module is used to prevent the LiDAR fault level from being upgraded when the vehicle's direction of travel does not coincide with the fault blind spot.

[0132] In one embodiment, the second upgrade module further includes:

[0133] The obstacle perception module is used to acquire the valid perception results of the previous frame in the fault blind zone and determine the obstacle status within a preset range; the obstacle status includes no obstacles, stationary obstacles, and dynamic obstacles.

[0134] The static perception module is used to prevent the LiDAR fault level from escalating when there are no obstacles or stationary obstacles within a preset range.

[0135] The dynamic perception module is used to determine whether all dynamic obstacles are within the LiDAR perception area when they exist within a preset range.

[0136] The upgrade judgment module is used to prevent the LiDAR fault level from being upgraded when the device is within the LiDAR sensing area, and to upgrade the LiDAR fault level when the device is not within the LiDAR sensing area.

[0137] In one embodiment, the lidar fault assessment device further includes:

[0138] The numbering configuration module is used to configure the LiDAR perception number for the first LiDAR and the second LiDAR respectively.

[0139] The simulation module is used to simulate lidar failure scenarios by configuring parameters in the lidar sensing number.

[0140] Each module in the aforementioned lidar fault assessment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0141] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and databases. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media to run. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for assessing the failure and malfunction of a lidar system.

[0142] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0143] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0144] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0145] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0146] 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 used for analysis, data stored, data displayed, 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 related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0147] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory 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), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0148] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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, they should be considered to be within the scope of this specification.

[0149] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for assessing lidar faults, characterized in that, The method includes: The area around the vehicle is divided and numbered; the sensing area of ​​the first lidar is matched with the area around the vehicle to obtain the first lidar sensing number; the sensing area of ​​the second lidar is matched with the area around the vehicle to obtain the second lidar sensing number. The sensor numbers of the first and second lidars are calculated to obtain the number of the area around the vehicle sensed by the total lidar; the total lidar includes the first and second lidars. Obtain the duration and area of ​​missing sensing data from the LiDAR; The fault handling branch is entered according to the duration of the missing sensing data, and different LiDAR fault levels are set in different fault handling branches. Based on the missing perception data area and vehicle operating status, a LiDAR fault level upgrade instruction is generated, including: acquiring the fault blind zone and vehicle operating status; the fault blind zone is any area around the vehicle that is a missing perception data area for all LiDARs; The lidar fault level will not be upgraded when the vehicle is stationary. Determine if there are any blind spots while the vehicle is in motion; When the vehicle's direction of travel coincides with the blind spot of the fault, the fault level of the lidar is upgraded. When the vehicle's direction of travel does not coincide with the blind spot, the fault level of the lidar will not be upgraded, and the effective perception result of the previous frame of the blind spot will be obtained to determine the status of obstacles within the preset range. When there are no obstacles or stationary obstacles within the preset range, the fault level of the lidar will not be upgraded; When dynamic obstacles exist within a preset range, determine whether all dynamic obstacles are within the lidar sensing area; When within the lidar's sensing area, the lidar fault level does not escalate; The LiDAR fault level is upgraded when the device is not within the LiDAR's sensing area. The fault level of the lidar is obtained according to the lidar fault level upgrade instruction.

2. The method according to claim 1, characterized in that, The step of calculating the sensing numbers of the first and second lidar sensors to obtain the total number of the vehicle's surrounding area sensed by the lidar includes: The first and second lidar sensing numbers are represented in binary. The first and second lidar sensing numbers are processed by bitwise operations to determine whether the total lidar sensing area meets the requirements of a complete sensing area.

3. The method according to claim 1, characterized in that, The method further includes: Configure lidar sensing numbers for the first lidar and the second lidar respectively; By configuring the parameters in the LiDAR sensing number, a LiDAR failure scenario is simulated.

4. The method according to claim 1, characterized in that, The determination of whether a fault blind spot exists includes: Calculate the field of view covered by the LiDAR data that has received valid sensing data; Determine whether the field of view covers the entire area around the vehicle; When the field of view cannot completely cover the entire area around the vehicle, the uncovered area around the vehicle is determined to be the fault blind spot.

5. A lidar fault assessment device, characterized in that, The device includes: The data acquisition module is used to divide the area around the vehicle and number the area around the vehicle; match the sensing area of ​​the first lidar with the area around the vehicle to obtain the first lidar sensing number; match the sensing area of ​​the second lidar with the area around the vehicle to obtain the second lidar sensing number; perform calculations on the first lidar sensing number and the second lidar sensing number to obtain the total number of the area around the vehicle sensed by the lidar; the total lidar includes the first lidar and the second lidar; and acquire the duration and area of ​​missing sensing data of the lidar. The branch module is used to enter the fault handling branch according to the duration of the missing sensing data, and to set different LiDAR fault levels in different fault handling branches. The judgment module is used to generate a lidar fault level upgrade instruction based on the area of ​​missing perception data and the vehicle's operating status, including: obtaining the fault blind zone and the vehicle's operating status; the fault blind zone is any area around the vehicle that is a region of missing perception data for all lidars; The lidar fault level will not be upgraded when the vehicle is stationary. Determine if there are any blind spots while the vehicle is in motion; When the vehicle's direction of travel coincides with the blind spot of the fault, the fault level of the lidar is upgraded. When the vehicle's direction of travel does not coincide with the blind spot, the fault level of the lidar will not be upgraded, and the effective perception result of the previous frame of the blind spot will be obtained to determine the status of obstacles within the preset range. When there are no obstacles or stationary obstacles within the preset range, the fault level of the lidar will not be upgraded; When dynamic obstacles exist within a preset range, determine whether all dynamic obstacles are within the lidar sensing area; When within the lidar's sensing area, the lidar fault level does not escalate; The LiDAR fault level is upgraded when the device is not within the LiDAR's sensing area. The decision module is used to obtain the fault level of the lidar based on the lidar fault level upgrade instruction.

6. The apparatus according to claim 5, characterized in that, The data acquisition module includes: The numbering module is used to represent the first lidar sensing number and the second lidar sensing number in binary. The bit operation module is used to process the first lidar sensing number and the second lidar sensing number through bit operations to determine whether the total lidar sensing area meets the requirements of the complete sensing area.

7. The apparatus according to claim 5, characterized in that, The device further includes: The numbering configuration module is used to configure the LiDAR perception number for the first LiDAR and the second LiDAR respectively. The simulation module is used to simulate lidar failure scenarios by configuring parameters in the lidar sensing number.

8. A computer device comprising a memory and a processor, wherein the memory stores 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 4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images