Method, device and computer equipment for uploading abnormalities in autonomous driving tests

Abstract

This application provides a method, apparatus, computer equipment, and storage medium for uploading autonomous driving test anomalies. The method includes: during a road test of an autonomous vehicle, determining whether each log file reflects an anomaly in the corresponding function; if so, identifying the log file reflecting the anomaly in the corresponding function as a target anomaly file, and evaluating the severity level of the target anomaly file; and uploading the target anomaly files to a server in descending order of severity. This method enables pre-identification and priority scheduling of important road test data, effectively accelerating the process of accurately uploading important data, saving engineering personnel time and improving their work efficiency.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving test technology, and in particular to a method, apparatus, computer equipment, and storage medium for uploading autonomous driving test anomalies. Background Art

[0002] To determine the performance of autonomous vehicles, they often need to be tested on the road. Real road test data is crucial for scenario simulation and analysis. Relying on real road test data, such as vehicle behavior data in different scenarios, log records of sudden failures inside the vehicle, or some data flow logs inside the vehicle hardware, can analyze and debug the vehicle's behavior and logic in a real physical environment, thereby better modifying the internal operating logic to ensure that the vehicle can better cope with real road conditions and improve the performance of autonomous vehicles.

[0003] However, due to the huge amount of traditional road test data, it is difficult to ensure that important parts of it are uploaded accurately, which affects the work efficiency of engineers and is not conducive to improving the performance of autonomous driving vehicles. Summary of the Invention

[0004] The purpose of this application is to solve at least one of the above-mentioned technical defects, especially the problem of frequent hard page fault anomalies in the autonomous driving process in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a method for uploading abnormalities in an autonomous driving test, comprising:

[0006] During the road test of the autonomous vehicle, determine whether each log file reflects an abnormality in the corresponding function;

[0007] If so, the log file reflecting the abnormality of the corresponding function is determined as the target abnormal file, and the severity level of the target abnormal file is evaluated;

[0008] Upload the target abnormal files to the server in descending order of severity.

[0009] In one embodiment, determining whether each log file reflects that a corresponding function has an abnormality includes:

[0010] Determine whether the target parameter in the log file is within the normal value range corresponding to the target parameter;

[0011] If so, it is determined that there is no abnormality in the function corresponding to the log file;

[0012] If not, it is determined that the function corresponding to the log file is abnormal.

[0013] In one embodiment, the severity level corresponds to the abnormality value range one by one, and the severity of the target abnormal file is evaluated, including:

[0014] Determine the abnormal value interval of the target parameter of the target abnormal file as the target abnormal value interval;

[0015] The severity level corresponding to the target abnormal value interval is determined as the severity level of the target abnormal file.

[0016] In one embodiment, evaluating the severity level of the target abnormal file further includes:

[0017] The severity level of the target abnormal file and the meta information of the target abnormal file are stored in the meta information set.

[0018] In one embodiment, uploading target abnormal files to the server in descending order of severity includes:

[0019] After the autonomous driving vehicle road test is completed, target abnormal files with the same severity level are merged into uploaded abnormal files corresponding to the severity level based on the metadata in the metadata set;

[0020] In descending order of severity, upload exception files corresponding to each severity level to the server.

[0021] In one embodiment, based on each piece of metadata in the metadata set, target abnormal files at the same severity level are merged into uploaded abnormal files corresponding to the severity level, including:

[0022] Read the content of the target abnormal file according to the meta information;

[0023] Combining the content and meta information of the target abnormal file to obtain combined information corresponding to the target abnormal file;

[0024] The combination information corresponding to the target abnormal files at the same severity level is spliced, and a preset separator is added between each combination information to obtain the uploaded abnormal file corresponding to the severity level.

[0025] In one embodiment, the method for uploading anomalies in an autonomous driving test further includes:

[0026] After receiving the uploaded abnormal file, the server decomposes the uploaded abnormal file according to the preset delimiter to obtain the combination information corresponding to each target abnormal file;

[0027] The combined information is restored to obtain the target abnormal file corresponding to the combined information.

[0028] In a second aspect, an embodiment of the present application provides a device for uploading abnormalities in an autonomous driving test, comprising:

[0029] The abnormality judgment module is used to judge whether each log file reflects an abnormality in the corresponding function during the road test of the autonomous driving vehicle;

[0030] An evaluation module is used to determine the log file reflecting the abnormality of the corresponding function as a target abnormal file and evaluate the severity level of the target abnormal file;

[0031] The upload module is used to upload target abnormal files to the server in descending order of severity.

[0032] In a third aspect, an embodiment of the present application provides a computer device comprising one or more processors and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the steps of the autonomous driving test abnormality uploading method in any of the above embodiments are executed.

[0033] In a fourth aspect, an embodiment of the present application provides a storage medium in which computer-readable instructions are stored. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the autonomous driving test abnormality uploading method in any of the above embodiments.

[0034] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0035] Based on any of the above embodiments, during a road test of an autonomous vehicle, the various log files generated during the process are identified, target abnormal files are screened out, and the severity level of each target abnormal file is assessed. Finally, the target abnormal files are uploaded in descending order of severity. This method enables the pre-identification and priority scheduling of important road test data, effectively accelerating the accurate upload process of important data, saving engineering personnel time and improving their work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0037] Figure 1 A flowchart of a method for uploading abnormalities in autonomous driving tests provided in one embodiment of the present application;

[0038] Figure 2 A flowchart of a method for uploading abnormalities in autonomous driving tests provided in another embodiment of the present application;

[0039] Figure 3 A schematic diagram of a module of a device for uploading abnormalities during autonomous driving tests provided in one embodiment of the present application;

[0040] Figure 4 A diagram of the internal structure of a computer device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0042] See also Figure 1 , an embodiment of the present application provides a method for uploading abnormalities of an autonomous driving test, including steps S102 to S106.

[0043] S102 , during the road test of the autonomous driving vehicle, determining whether each log file reflects an abnormality in the corresponding function.

[0044] As can be understood, road testing refers to the testing of autonomous vehicles on roads when new features are launched or new changes are deployed. During the operation of an autonomous vehicle, the autonomous driving system generates multiple log files. These log files correspond to the functional modules of the autonomous driving system and are used to record the operation of the corresponding modules. In other words, when an anomaly occurs in a function of the autonomous driving system, it will be reflected in the corresponding log file. Log files that reflect the anomaly are the focus of analysis and improvement by engineering personnel. To improve work efficiency, these log files must be transmitted to engineering personnel first. Therefore, the first step is to identify the log files that reflect the anomaly of the corresponding function. During the autonomous driving vehicle road testing process, each log file generated can be evaluated and marked to distinguish normal log files from abnormal log files.

[0045] S104: If yes, the log file reflecting the abnormality of the corresponding function is determined as a target abnormal file, and the severity level of the target abnormal file is evaluated.

[0046] It can be understood that the severity level reflects the degree of impact of the abnormality of the functional module on the operation of the autonomous vehicle. The greater the impact of the abnormality of the functional module on the operation of the autonomous vehicle, the higher the severity level.

[0047] S106: Upload the target abnormal files to the server in descending order of severity.

[0048] As you can understand, severity levels are positively correlated with the priority of engineering analysis. That is, anomalies with higher severity levels should be prioritized for analysis and optimization. During the anomaly reporting phase, it is crucial to ensure that target anomaly files with higher severity levels are uploaded first, prioritizing the dispatch of important drive test data. This allows engineers to prioritize receiving and resolving critical anomalies. Target anomaly files can also be tagged with their severity levels to facilitate classification and screening by engineering personnel.

[0049] The autonomous driving test anomaly upload method of this embodiment identifies the various log files generated during a road test by an autonomous vehicle, filters out target anomaly files, and assesses their severity. Finally, each target anomaly file is uploaded in descending order of severity. This method pre-identifies and prioritizes important road test data, effectively accelerating the accurate upload process for critical data, saving engineering staff time and improving their work efficiency.

[0050] In one embodiment, determining whether each log file reflects that a corresponding function has an abnormality includes:

[0051] (1) Determine whether the target parameter in the log file is within the normal value range corresponding to the target parameter.

[0052] It is understood that in addition to text information, the log file will also automatically generate target parameters related to the function's operating status in order to facilitate quantitative evaluation of abnormal conditions in the corresponding function of the log file. For example, the log file corresponding to the communication module can record the communication delay between the vehicle and the control center. The size of the communication delay has a significant impact on the operation of the automatic vehicle. The target parameter includes the communication delay. For another example, the log file corresponding to the computing module can record the resource utilization rate of the computer equipment. When the autonomous driving system enters an infinite loop, it may cause abnormal resource utilization. The target parameter includes the resource utilization rate. The target parameters can be quantitatively analyzed in advance by engineering personnel to divide the target parameter values ​​into normal and abnormal boundaries.

[0053] (2) If so, it is determined that there is no abnormality in the function corresponding to the log file.

[0054] (3) If not, it is determined that there is an abnormality in the function corresponding to the log file.

[0055] In one embodiment, the severity level corresponds to the abnormal numerical interval one-to-one. That is, the numerical interval can be divided into two categories: normal numerical interval and abnormal numerical interval. The abnormal numerical interval can be further divided into multiple categories, each corresponding to a different severity level. For example, the abnormal numerical interval includes a first abnormal numerical interval and a second abnormal numerical interval. The first abnormal numerical interval corresponds to an abnormality with a severity level of "deviation", and the second abnormal numerical interval corresponds to an abnormality with a severity level of "serious". Based on this, the severity of the target abnormal file is evaluated, including:

[0056] (1) The abnormal value interval of the target parameter of the target abnormal file is determined as the target abnormal value interval.

[0057] (2) Determine the severity level corresponding to the target abnormal value interval as the severity level of the target abnormal file.

[0058] That is, after determining the abnormal value interval of the target parameter, the severity level of the abnormality of the function corresponding to the log file containing the target parameter can be determined based on the one-to-one correspondence between the abnormal value interval and the severity level.

[0059] In one embodiment, evaluating the severity level of the target abnormal file further includes: storing the severity level of the target abnormal file and meta information of the target abnormal file in a meta information set.

[0060] It is understood that meta-information refers to information describing a log file, and may specifically include the log file's name, appearance time, file size, storage directory, etc. In this embodiment, when the autonomous vehicle is conducting a road test, each time a target abnormal file is screened out, the target abnormal file is not immediately uploaded. Instead, its meta-information and severity level are first recorded in a meta-information set. After the autonomous vehicle completes the road test, the files are then uploaded in a unified manner based on the data in the meta-information set.

[0061] In one embodiment, see Figure 2 , the autonomous driving test abnormality uploading method includes steps S202 to S208.

[0062] S202 , during the road test of the autonomous driving vehicle, determining whether each log file reflects an abnormality in the corresponding function.

[0063] The description of step S202 can be found above.

[0064] S204: If yes, the log file reflecting the abnormality of the corresponding function is determined as the target abnormal file, the severity level of the target abnormal file is evaluated, and the severity level of the target abnormal file and the meta information of the target abnormal file are stored in the meta information set.

[0065] The description of step S204 can be found above.

[0066] S206, after the road test of the autonomous driving vehicle is completed, target abnormal files at the same severity level are merged into uploaded abnormal files corresponding to the severity level based on the metadata in the metadata set.

[0067] Understandably, since the number of target exception files may be large, transmitting them independently could result in excessive upload requests between the vehicle and the server, potentially blocking the communication link and affecting transmission efficiency. Therefore, after the autonomous vehicle road test is completed, the metadata and severity level of each target exception file are recorded in the metadata collection. Based on this metadata, the corresponding target exception file can be read from the hard drive. All target exception files with the same severity level are merged to obtain the upload exception file corresponding to each severity level. The log files for each severity level required by the engineering staff are packaged in the upload exception file.

[0068] S208 , uploading the upload exception files corresponding to each severity level to the server in descending order of severity.

[0069] Finally, there is only one upload exception file for each severity level, and only a small number of upload requests are needed to upload the log files required for each severity level to the server, greatly improving transmission efficiency.

[0070] In one embodiment, based on each piece of metadata in the metadata set, target abnormal files at the same severity level are merged into uploaded abnormal files corresponding to the severity level, including:

[0071] (1) Read the content of the target abnormal file based on the meta information.

[0072] Specifically, the meta information may record the storage directory of the target abnormal file, so that the corresponding target abnormal file can be queried and read out in the hard disk, thereby obtaining the content recorded in the target abnormal file.

[0073] (2) Combining the content and meta-information of the target abnormal file to obtain the combined information corresponding to the target abnormal file.

[0074] Specifically, to facilitate the server's restoration of an uploaded exception file into multiple independent target exception files, in addition to adding the target exception file's content to the uploaded exception file, the target exception file's metadata must also be included. The metadata corresponding to each target exception file can be added to the first line of the target exception file's content to obtain the corresponding combined information for that target exception file.

[0075] (3) The combination information corresponding to the target abnormal files at the same severity level is spliced, and a preset separator is added between each combination information to obtain the uploaded abnormal files corresponding to the severity level.

[0076] It is understood that to prevent the combined information corresponding to target abnormal files of the same severity level from being mixed up in the uploaded abnormal file and becoming difficult to separate, this embodiment adds a preset delimiter between each combined information. This delimiter demarcates the boundaries between different target abnormal files, facilitating restoration based on the uploaded abnormal file. It should be noted that since the target abnormal file may contain symbols, the preset delimiter should be a character or character combination that does not appear in the log file.

[0077] In one embodiment, the method for uploading anomalies in an autonomous driving test further includes:

[0078] (1) After receiving the uploaded abnormal file, the server decomposes the uploaded abnormal file according to the preset delimiter to obtain the combination information corresponding to each target abnormal file.

[0079] It is understandable that when engineers conduct analysis and improvements, they do so based on independent log files, while the uploaded exception files received by the server have been merged and therefore need to be decomposed. Each target exception file has been demarcated in the uploaded exception file using a preset delimiter. By identifying the preset delimiter in the uploaded exception file and then performing segmentation based on the identified preset delimiter, the corresponding combination information for each target exception file can be obtained. Specifically, one can start traversing from the first line of the uploaded exception file, and each time a preset delimiter is identified, separate the data before the preset delimiter to obtain the corresponding combination information for each target exception file.

[0080] (2) Restore the combined information to obtain the target abnormal file corresponding to the combined information.

[0081] It can be understood that since the combined information includes the meta information and content of the target abnormal file, the combined information can be restored to the target abnormal file with the same file name, file size, appearance time, etc. as before the merger based on the meta information.

[0082] This application embodiment provides a device for uploading abnormalities in autonomous driving tests. Figure 3 , including an abnormality judgment module 310, an evaluation module 320 and an upload module 330.

[0083] The anomaly determination module 310 is used to determine whether each log file reflects an anomaly in the corresponding function during a road test of an autonomous vehicle. The evaluation module 320 is used to identify log files reflecting an anomaly in the corresponding function as target anomaly files and evaluate the severity level of the target anomaly files. The upload module 330 is used to upload the target anomaly files to the server in descending order of severity.

[0084] In one embodiment, the abnormality judgment module 310 is used to determine whether the target parameter in the log file is in the normal value range corresponding to the target parameter; if so, it is determined that there is no abnormality in the function corresponding to the log file; if not, it is determined that there is an abnormality in the function corresponding to the log file.

[0085] In one embodiment, the severity level corresponds to the abnormal numerical interval one by one, and the evaluation module 320 is used to determine the abnormal numerical interval in which the target parameter of the target abnormal file is located as the target abnormal numerical interval; and determine the severity level corresponding to the target abnormal numerical interval as the severity level of the target abnormal file.

[0086] In one embodiment, the evaluation module 320 is configured to store the severity level of the target abnormal file and the meta information of the target abnormal file in a meta information set.

[0087] In one embodiment, the upload module 330 is used to merge target exception files at the same severity level into uploaded exception files corresponding to the severity level based on the metadata in the metadata set after the road test of the autonomous driving vehicle is completed; and upload the uploaded exception files corresponding to each severity level to the server in descending order of severity.

[0088] In one embodiment, the upload module 330 is used to read the content of the target abnormal file based on the metadata; combine the content of the target abnormal file and the metadata to obtain the combined information corresponding to the target abnormal file; splice the combined information corresponding to the target abnormal files at the same severity level, and add a preset separator between each combined information to obtain the uploaded abnormal file corresponding to the severity level.

[0089] For the specific definition of the autonomous driving test anomaly uploading device, please refer to the definition of the autonomous driving test anomaly uploading method above, which will not be repeated here. The various modules in the above-mentioned autonomous driving test anomaly uploading device can be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0090] An embodiment of the present application provides a computer device, comprising one or more processors and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the one or more processors, the device performs the following steps: during a road test of an autonomous driving vehicle, determining whether each log file reflects an abnormality in a corresponding function; if so, determining the log file reflecting the abnormality in the corresponding function as a target abnormality file, and evaluating the severity level of the target abnormality file; and uploading the target abnormality files to a server in descending order of severity level.

[0091] In one embodiment, when the computer-readable instructions are executed by one or more processors, the following is performed: determining whether the target parameter in the log file is within the normal numerical range corresponding to the target parameter; if so, determining that there is no abnormality in the function corresponding to the log file; if not, determining that there is an abnormality in the function corresponding to the log file.

[0092] In one embodiment, when the computer-readable instructions are executed by one or more processors, the following are performed: determining the abnormal numerical interval in which the target parameter of the target abnormal file is located as the target abnormal numerical interval; and determining the severity level corresponding to the target abnormal numerical interval as the severity level of the target abnormal file.

[0093] In one embodiment, when the computer readable instructions are executed by one or more processors, the computer readable instructions perform the following steps: storing the severity level of the target abnormal file and the meta information of the target abnormal file in a meta information set.

[0094] In one embodiment, when the computer-readable instructions are executed by one or more processors, the following are performed: after the road test of the autonomous driving vehicle is completed, based on the metadata in the metadata set, the target abnormal files at the same severity level are merged into uploaded abnormal files corresponding to the severity level; and the uploaded abnormal files corresponding to each severity level are uploaded to the server in order from high to low severity levels.

[0095] In one embodiment, when the computer-readable instructions are executed by one or more processors, the following are performed: reading the content of the target abnormal file according to the metadata; combining the content of the target abnormal file and the metadata to obtain combined information corresponding to the target abnormal file; splicing the combined information corresponding to the target abnormal files at the same severity level, and adding a preset separator between each combined information to obtain an uploaded abnormal file corresponding to the severity level.

[0096] In one embodiment, when the computer-readable instructions are executed by one or more processors, the following steps are performed: after receiving the uploaded abnormal file, the server decomposes the uploaded abnormal file according to a preset delimiter to obtain combination information corresponding to each target abnormal file; and restores the combination information to obtain the target abnormal file corresponding to the combination information.

[0097] Schematically, as Figure 4 As shown, Figure 4 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 400 can be configured in an autonomous driving vehicle. Figure 4 Computer device 400 includes a processing component 402, which further includes one or more processors, and a memory resource represented by memory 401 for storing instructions executable by processing component 402, such as an application. The application stored in memory 401 may include one or more modules, each corresponding to a set of instructions. In addition, processing component 402 is configured to execute the instructions to perform the steps of the autonomous driving test anomaly upload method of any of the above-mentioned embodiments.

[0098] The computer device 400 may further include a power supply component 403 configured to perform power management of the computer device 400, a wired or wireless network interface 404 configured to connect the computer device 400 to a network, and an input / output (I / O) interface 405. The computer device 400 may operate based on an operating system stored in the memory 401, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or the like.

[0099] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure 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 shown in the figure, or combine certain components, or have a different component arrangement.

[0100] An embodiment of the present application provides a storage medium having computer-readable instructions stored therein. When the computer-readable instructions are executed by one or more processors, the one or more processors are caused to execute: during a road test of an autonomous driving vehicle, determine whether each log file reflects an abnormality in a corresponding function; if so, determine the log file reflecting the abnormality in the corresponding function as a target abnormality file, and evaluate the severity level of the target abnormality file; and upload the target abnormality files to a server in descending order of severity.

[0101] In one embodiment, when the computer-readable instructions are executed by one or more processors, the one or more processors execute: determining whether the target parameter in the log file is within the normal numerical range corresponding to the target parameter; if so, determining that there is no abnormality in the function corresponding to the log file; if not, determining that there is an abnormality in the function corresponding to the log file.

[0102] In one embodiment, when the computer-readable instructions are executed by one or more processors, the one or more processors are caused to perform: determining the abnormal numerical interval in which the target parameter of the target abnormal file is located as the target abnormal numerical interval; and determining the severity level corresponding to the target abnormal numerical interval as the severity level of the target abnormal file.

[0103] In one embodiment, when the computer readable instructions are executed by one or more processors, the one or more processors are caused to perform: storing the severity level of the target abnormal file and the meta information of the target abnormal file in a meta information set.

[0104] In one embodiment, when the computer-readable instructions are executed by one or more processors, the one or more processors are caused to execute: after the road test of the autonomous driving vehicle is completed, based on the metadata in the metadata set, the target abnormal files at the same severity level are merged into uploaded abnormal files corresponding to the severity level; and the uploaded abnormal files corresponding to each severity level are uploaded to the server in order from high to low severity levels.

[0105] In one embodiment, when the computer-readable instructions are executed by one or more processors, the one or more processors are caused to execute: reading the content of the target abnormal file according to the metadata; combining the content of the target abnormal file and the metadata to obtain combined information corresponding to the target abnormal file; splicing the combined information corresponding to the target abnormal files at the same severity level, and adding a preset separator between each combined information to obtain an uploaded abnormal file corresponding to the severity level.

[0106] In one embodiment, when the computer-readable instructions are executed by one or more processors, the one or more processors are caused to perform the following steps: after receiving the uploaded abnormal file, the server decomposes the uploaded abnormal file according to a preset delimiter to obtain combination information corresponding to each target abnormal file; and restores the combination information to obtain the target abnormal file corresponding to the combination information.

[0107] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0108] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referenced to each other.

[0109] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for uploading abnormal data of autonomous driving tests, characterized in that: include: During the road test of the autonomous vehicle, determine whether each log file reflects an abnormality in the corresponding function; If so, the log file reflecting the abnormality of the corresponding function is determined as a target abnormal file, the severity level of the target abnormal file is evaluated, and the severity level of the target abnormal file and the meta information of the target abnormal file are stored in a meta information set; Uploading the target abnormal files to the server in descending order of severity levels; specifically comprising: reading the content of the target abnormal files according to the meta information after the autonomous driving vehicle road test is completed; The content of the target abnormal file and the meta-information are combined to obtain the combined information corresponding to the target abnormal file; the combined information corresponding to the target abnormal files at the same severity level are spliced, and a preset separator is added between each of the combined information to obtain an uploaded abnormal file corresponding to the severity level; the uploaded abnormal files corresponding to each severity level are uploaded to the server in descending order of the severity levels; the preset separator is a character or character combination that does not appear in the log file.

2. The method for uploading abnormal autonomous driving test data according to claim 1, characterized in that: Determining whether each log file reflects that the corresponding function has an abnormality includes: Determine whether the target parameter in the log file is within a normal value range corresponding to the target parameter; If so, it is determined that there is no abnormality in the function corresponding to the log file; If not, it is determined that the function corresponding to the log file is abnormal.

3. The method for uploading abnormal autonomous driving test data according to claim 2, characterized in that: The severity level corresponds to the abnormality value range one by one, and the severity of the target abnormal file is evaluated, including: Determining the abnormal value interval in which the target parameter of the target abnormal file is located as a target abnormal value interval; The severity level corresponding to the target abnormal value interval is determined as the severity level of the target abnormal file.

4. The method for uploading abnormal autonomous driving test data according to claim 1, characterized in that: Also includes: After receiving the uploaded abnormal file, the server decomposes the uploaded abnormal file according to the preset delimiter to obtain the combination information corresponding to each target abnormal file; The combination information is restored to obtain the target abnormal file corresponding to the combination information.

5. A device for uploading abnormal data of autonomous driving tests, characterized in that: include: The abnormality judgment module is used to judge whether each log file reflects an abnormality in the corresponding function during the road test of the autonomous driving vehicle; an evaluation module, configured to determine the log file reflecting the abnormality of the corresponding function as a target abnormal file, evaluate the severity level of the target abnormal file, and store the severity level of the target abnormal file and meta information of the target abnormal file in a meta information set; An uploading module is configured to upload the target abnormality files to a server in descending order of severity levels; specifically, after the autonomous driving vehicle road test is completed, read the contents of the target abnormality files according to the meta-information; The content of the target abnormal file and the meta-information are combined to obtain the combined information corresponding to the target abnormal file; the combined information corresponding to the target abnormal files at the same severity level are spliced, and a preset separator is added between each of the combined information to obtain an uploaded abnormal file corresponding to the severity level; the uploaded abnormal files corresponding to each severity level are uploaded to the server in descending order of the severity levels; the preset separator is a character or character combination that does not appear in the log file.

6. A computer device, characterized in that: The system comprises one or more processors and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the one or more processors, the steps of the method for uploading abnormalities of an autonomous driving test are performed as described in any one of claims 1 to 4.

7. A storage medium, characterized in that: The storage medium stores computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to execute the steps of the method for uploading anomalies in an autonomous driving test as described in any one of claims 1 to 4.

Images