Driving track analysis method and device based on autonomous vehicle, medium and product

Abstract

The embodiment of the invention relates to the technical field of traffic, and discloses a driving track analysis method and device based on an automatic driving vehicle, a medium and a product. The method comprises the following steps: acquiring a target trajectory file; the target track file comprises at least one of a first original track file determined based on a true value vehicle, a second original track file determined based on a camera and a third original track file determined based on a radar; determining a target area and an electronic fence file corresponding to the target area; and generating a driving track of the autonomous vehicle according to the target track file, the target area and the electronic fence file. The technical problems of relatively high human resource cost and relatively low test efficiency or verification efficiency in related technologies can be at least solved.

Description

Technical Field

[0001] The present application relates to the field of transportation technology, and in particular to a driving trajectory analysis method, equipment, medium and product based on an autonomous driving vehicle. Background Art

[0002] With the development of the autonomous driving industry, it is necessary to obtain the position and motion status information of autonomous driving vehicles in space by using a variety of sensors and data sources, such as cameras, radars, global positioning systems (GPS), real-time kinematic measurement (RTK), etc. After this information is processed and analyzed, the driving trajectory of the autonomous driving vehicle is formed.

[0003] Generally, it is necessary to test the algorithms used for trajectory prediction and planning of autonomous vehicles; or to verify the safety of autonomous vehicles that have been put into use. In related technologies, the driving trajectory of autonomous vehicles is generally replayed through means such as three-dimensional virtual technology. For example, platforms such as Amap and Baidu platform support the playback function of the driving trajectory of autonomous vehicles. Relevant personnel can call the platform's API, and can store the geographic location and related custom information of the autonomous driving vehicle reported regularly by relevant personnel in the order of the timeline, and draw the driving trajectory of the autonomous driving vehicle accordingly.

[0004] However, the inventors have discovered that there are at least the following technical problems in the related technology: in the related technology, the test results or verification results need to rely on manual analysis of the driving trajectory of the autonomous driving vehicle. In addition, the algorithm iteration speed is getting faster and faster, resulting in high human resource costs and low testing efficiency or verification efficiency. Summary of the invention

[0005] One purpose of the present application is to provide a driving trajectory analysis method, device, medium and product based on an autonomous driving vehicle, at least to solve the technical problems in related technologies such as high human resource costs and low testing efficiency or verification efficiency.

[0006] To achieve the above objectives, some embodiments of the present application provide the following aspects:

[0007] In a first aspect, some embodiments of the present application also provide a driving trajectory analysis method based on an autonomous driving vehicle, the method comprising: obtaining a target trajectory file; the target trajectory file comprises at least one of a first original trajectory file determined based on a true value vehicle, a second original trajectory file determined based on a camera, and a third original trajectory file determined based on a radar; determining a target area and an electronic fence file corresponding to the target area; generating a driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area, and the electronic fence file.

[0008] In a second aspect, some embodiments of the present application further provide an electronic device, comprising: one or more processors; and a memory storing computer program instructions, wherein the computer program instructions, when executed, cause the processor to perform the steps of the method described above.

[0009] In a third aspect, some embodiments of the present application further provide a computer-readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method as described above.

[0010] In a fourth aspect, some embodiments of the present application further provide a computer program product, comprising a computer program / instruction, which implements the steps of the method described above when executed by a processor.

[0011] Compared with the related art, in the solution provided by the embodiment of the present application, by obtaining the target trajectory file, and determining the target area and the electronic fence file corresponding to the target area, the driving trajectory of the autonomous driving vehicle is generated according to the target trajectory file, the target area and the electronic fence file; wherein the target trajectory file includes at least one of a first original trajectory file determined based on a true value vehicle, a second original trajectory file determined based on a camera and a third original trajectory file determined based on a radar; since in the embodiment of the present application, relevant personnel can select the original trajectory file to be tested or verified according to actual needs, so that the system can generate a corresponding driving trajectory according to the corresponding original trajectory file, thereby realizing the integration of the RTK data of the true value vehicle, the recognition data of the camera and the perception data of the radar, without the need for the relevant personnel to regularly report the geographical location and related custom information of the autonomous driving vehicle, thereby achieving the purpose of reducing human resource costs; since the embodiment of the present application can realize the integration of the RTK data of the true value vehicle, the recognition data of the camera and the perception data of the radar, it is convenient for relevant personnel to verify the accuracy of the data obtained by the camera for visual recognition and the accuracy of the perception data of the radar of the surrounding environment of the autonomous driving vehicle, thereby achieving the purpose of improving the test efficiency or verification efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0013] Figure 1 An exemplary flow chart of a driving trajectory analysis method based on an autonomous driving vehicle provided according to some embodiments of the present application;

[0014] Figure 2 This is an exemplary schematic diagram of a driving trajectory analysis method based on an autonomous driving vehicle provided according to some embodiments of the present application;

[0015] Figure 3 This is an exemplary flow chart of step S103 in a driving trajectory analysis method based on an autonomous driving vehicle according to some embodiments of the present application;

[0016] Figure 4 This is another exemplary flowchart of step S103 in a driving trajectory analysis method based on an autonomous driving vehicle provided according to some embodiments of the present application;

[0017] Figure 5 This is an exemplary flow chart of step S104 in a driving trajectory analysis method based on an autonomous driving vehicle provided according to some embodiments of the present application;

[0018] Figure 6 This is an exemplary structural diagram of an electronic device provided according to some embodiments of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] The following terms are used in this article.

[0021] A true value vehicle is a test vehicle that can accurately output data such as the vehicle's own positioning, speed, and heading angle. It is mainly used for testing and verification of intelligent transportation systems.

[0022] RTK data, the full name of RTK is Real-time kinematic, which means real-time differential positioning technology. RTK data is the data obtained through real-time differential positioning technology.

[0023] The heading angle is used to describe the angle of the moving direction of the autonomous driving vehicle.

[0024] First embodiment

[0025] The first embodiment of the present application relates to a trajectory analysis method for an autonomous driving vehicle. Figure 1 As shown, the method may include the following steps:

[0026] Step S101, obtaining a target trajectory file; the target trajectory file includes at least one of a first original trajectory file determined based on a true value vehicle, a second original trajectory file determined based on a camera, and a third original trajectory file determined based on a radar;

[0027] Step S102, determining a target area and an electronic fence file corresponding to the target area;

[0028] Step S103, generating a driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area and the electronic fence file.

[0029] The following is a detailed description of each of the above steps.

[0030] For step S101, specifically, in some examples, see Figure 2 As shown, the first original trajectory file can be obtained based on the RTK data of the real value vehicle; the second original trajectory file can be obtained based on the data obtained by visual recognition of the camera; the third original trajectory file can be obtained based on the radar's perception data of the surrounding environment of the autonomous driving vehicle. For example, relevant personnel can import the RTK data of the real value vehicle, the data obtained by visual recognition of the camera, and the radar's perception data of the surrounding environment of the autonomous driving vehicle into the system. The system can perform data conversion based on the RTK data of the real value vehicle to obtain the first original trajectory file, perform data conversion based on the data obtained by visual recognition of the camera to obtain the second original trajectory file, and perform data conversion based on the radar's perception data of the surrounding environment of the autonomous driving vehicle to obtain the third original trajectory file.

[0031] Exemplarily, the radar may be a laser radar or other types of radars, which is not specifically limited in the embodiments of the present application.

[0032] Regarding step S102, specifically, in some examples, the relevant personnel can fill in the location information used to characterize the target area through the device tool provided by the embodiment of the present application installed in the system as needed; the location information can be but is not limited to the latitude and longitude coordinates of the center point on the electronic map; and the relevant personnel can import the electronic fence file corresponding to the target area into the system; in this way, the system can directly generate the driving trajectory of the autonomous driving vehicle based on the target area and the electronic fence file of the target area. Among them, the content of the electronic fence file is mainly an area defined by a number of pixel points, and the system can load multiple types of electronic fence files for the relevant personnel to choose.

[0033] It should be noted that, in the related art, it is not possible to combine multiple types of electronic fence files for display. Through this step S102, relevant personnel can combine multiple types of electronic fence files for display, so as to conduct comparative analysis. In this way, it is convenient for relevant personnel to determine whether the driving trajectory of the autonomous driving vehicle is inaccurate due to incorrect selection of the type of electronic fence file, thereby achieving the purpose of further improving test efficiency or verification efficiency.

[0034] It should be noted that in the embodiment of the present application, there is no restriction on the order of step S101 and step S102.

[0035] Regarding step S103, specifically, in some examples, the driving trajectory of the autonomous driving vehicle can be generated solely based on the first original trajectory file determined by the true value vehicle, or solely based on the second original trajectory file determined by the camera, or solely based on the third original trajectory file determined by the radar. In addition, the driving trajectory of the autonomous driving vehicle can also be generated by fusing and calculating the data in at least two of the first original trajectory file, the second original trajectory file, and the third original trajectory file through a fusion algorithm in the relevant technology.

[0036] For example, the driving trajectory of the autonomous driving vehicle may be dynamic or static, and this embodiment of the present application does not specifically limit this.

[0037] Corresponding to the dynamic effect display of the driving trajectory, the system can provide at least one of the following functions:

[0038] Selection of playback speed;

[0039] Selection of display time period;

[0040] Pause and resume playback;

[0041] Replay function;

[0042] Choose whether to display the electronic fence;

[0043] Select the type of object to be displayed (such as pedestrians, motorcycles, buses, cars, trucks, etc.);

[0044] Relevant personnel can flexibly select the above functions according to actual needs, so as to facilitate further trajectory display and analysis. It can be understood that corresponding to the above functions, the processing operations are mainly performed on the layers and target models of the electronic map in the system.

[0045] It should be noted that the method provided in the embodiment of the present application can be applicable to the scenario where relevant personnel replay the driving trajectory process of the autonomous driving vehicle.

[0046] The inventors found that in the related art, the technical solution for replaying the driving trajectory of an autonomous vehicle has certain limitations. Specifically, it is impossible to integrate the RTK data of the real value vehicle, the recognition data of the camera, and the perception data of the radar. It is not difficult to find that, compared with the related art, in the solution provided in the embodiment of the present application, by obtaining the target trajectory file, and determining the target area and the electronic fence file corresponding to the target area, the driving trajectory of the autonomous driving vehicle is generated according to the target trajectory file, the target area and the electronic fence file; wherein the target trajectory file includes at least one of a first original trajectory file determined based on a true value vehicle, a second original trajectory file determined based on a camera and a third original trajectory file determined based on a radar; since in the embodiment of the present application, relevant personnel can select the original trajectory file required for testing or verification according to actual needs, so that the system can generate a corresponding driving trajectory according to the corresponding original trajectory file, thereby realizing the integration of the RTK data of the true value vehicle, the recognition data of the camera and the perception data of the radar, without the need for the relevant personnel to regularly report the geographical location and related custom information of the autonomous driving vehicle, thereby achieving the purpose of reducing human resource costs; since the embodiment of the present application can realize the integration of the RTK data of the true value vehicle, the recognition data of the camera and the perception data of the radar, it is convenient for relevant personnel to verify the accuracy of the data obtained by the camera for visual recognition and the accuracy of the perception data of the radar on the surrounding environment of the autonomous driving vehicle, thereby achieving the purpose of improving the test efficiency or verification efficiency.

[0047] Second embodiment

[0048] The second embodiment of the present application relates to a trajectory analysis method for an autonomous driving vehicle. The second embodiment is an improvement on the first embodiment, and the specific improvement is: in the second embodiment of the present application, a specific implementation method for generating the driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area and the electronic fence file is provided.

[0049] Optionally, in some embodiments, the first original trajectory file, the second original trajectory file, and the third original trajectory file all include key information; the key information includes at least: first data for representing the timestamp of the driving trajectory of the autonomous driving vehicle, second data for representing the longitude and latitude coordinates of the driving position of the autonomous driving vehicle, third data for representing the driving speed of the autonomous driving vehicle, fourth data for representing the heading angle of the autonomous driving vehicle, and fifth data for representing the identification of the object type.

[0050] That is to say, the RTK data of the real value vehicle, the recognition data of the camera and the perception data of the radar can be collected, and these data can be converted into original trajectory files containing key information to obtain the first original trajectory file, the second original trajectory file and the third original trajectory file.

[0051] Specifically, in some embodiments, the driving trajectory of the autonomous driving vehicle is generated according to the target trajectory file, the target area and the electronic fence file, that is, step S103 may further include the following steps: Figure 3 As shown:

[0052] Step S1031, determining a map area displayed in the electronic map according to the target area;

[0053] Step S1032, performing pixel drawing according to the electronic fence file to obtain a target electronic fence in a preset layer;

[0054] Step S1033, generating a driving trajectory of the autonomous driving vehicle according to at least one of the first data, the second data, the third data, the third data and the fifth data in the target trajectory file.

[0055] For example, ArcGIS software may be used to determine the map area to be displayed in the electronic map based on the latitude and longitude coordinates of the center point on the electronic map.

[0056] Exemplarily, the electronic fence file can be parsed, and pixel drawing can be performed according to the electronic fence file to draw the electronic fence into a preset layer to obtain a target electronic fence. Exemplarily, the preset layer can be but is not limited to: a trackLayer layer.

[0057] Exemplarily, the target trajectory file can be parsed, and the driving trajectory of the autonomous driving vehicle can be generated based on at least one of the first data, the second data, the third data, the third data, and the fifth data in the target trajectory file.

[0058] Optionally, in some embodiments, the generating the driving trajectory of the autonomous driving vehicle according to at least one of the first data, the second data, the third data, the third data and the fifth data in the target trajectory file, that is, step S1033 may further include the following steps:

[0059] Step S10331, determining the type of object to be displayed according to the fifth data in the target trajectory file;

[0060] Step S10332, based on the first data in the target trajectory file, draw frame by frame in the preset layer according to the object type and the second data, the third data and the fourth data to generate the driving trajectory of the autonomous driving vehicle.

[0061] For example, the target model to be displayed can be determined according to the object type. For example, for an object whose object type is a pedestrian, a pedestrian model used to represent the pedestrian is displayed, and for an object whose object type is a car, a car model used to represent the car is displayed. Furthermore, the target model symbol and the trajectory data determined according to the second data, the third data, and the fourth data can be aligned frame by frame into the preset layer, so as to obtain the driving trajectory of the autonomous driving vehicle.

[0062] Exemplarily, in the process of playing the obtained driving trajectory of the autonomous driving vehicle, the system may also display specific trajectory data at different timestamps, and the specific trajectory data includes at least one of the key information at the corresponding timestamp.

[0063] It is not difficult to find that in the embodiment of the present application, the first original trajectory file, the second original trajectory file and the third original trajectory file are provided, all of which include key information and introduce the specific content of the key information; combined with the key information, a specific implementation method for generating the driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area and the electronic fence file is further provided. In this way, it is conducive to supporting the technical solution provided by the present application to be flexibly implemented in a diversified manner.

[0064] Third embodiment

[0065] The third embodiment of the present application relates to a trajectory analysis method for an autonomous driving vehicle. The third embodiment is an improvement on the first embodiment, and the specific improvement is: in the third embodiment of the present application, another implementation method for generating the driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area and the electronic fence file is provided.

[0066] Specifically, in some embodiments, generating the driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area and the electronic fence file may further include the following steps: Figure 4 As shown:

[0067] Step S1031', obtaining selection information of the user based on the target trajectory file;

[0068] Step S1032', generating a driving trajectory of the autonomous driving vehicle according to the selection information, the target area and the electronic fence file.

[0069] Optionally, in some embodiments, the generating the driving trajectory of the autonomous driving vehicle according to the selection information, the target area and the electronic fence file, that is, step S1032′ may further include: using a preset mode, generating the driving trajectory of the autonomous driving vehicle according to the selection information, the target area and the electronic fence file;

[0070] Wherein, the preset modes include: a single display mode and a comparative display mode;

[0071] The separate display mode includes at least one of the following: displaying the first trajectory according to the first original trajectory file alone, displaying the second trajectory according to the second original trajectory file alone, displaying the third trajectory according to the third original trajectory file alone, and displaying the fused trajectory alone; wherein the fused trajectory is obtained by fusion calculation based on at least two original trajectory files among the first original trajectory file, the second original trajectory file and the third original trajectory file;

[0072] The comparative display mode includes at least one of the following: comparative display of the fused trajectory and the first trajectory, comparative display of the fused trajectory and the second trajectory, comparative display of the fused trajectory and the third trajectory, and comparative display of the fused trajectory with at least two of the first trajectory, the second trajectory and the third trajectory.

[0073] Exemplarily, the relevant personnel can send selection information according to the target trajectory file through the device tool. In this way, a preset mode can be adopted to realize the display of any combination of the first original trajectory file, the second original trajectory file and the third original trajectory file in the target trajectory file.

[0074] The comparison display of the fused trajectory and at least two of the first trajectory, the second trajectory and the third trajectory may include the following situations:

[0075] 1. The fusion trajectory is compared with the first trajectory and the second trajectory respectively;

[0076] 2. The fusion trajectory is compared with the first trajectory and the third trajectory respectively;

[0077] 3. The fusion trajectory is compared with the second trajectory and the third trajectory respectively;

[0078] 4. The fused trajectory is compared with the first trajectory, the second trajectory and the third trajectory respectively;

[0079] It should be noted that the third embodiment of the present application may also be an improvement based on the second embodiment.

[0080] In the related art, the technical solution for replaying the driving trajectory of an autonomous driving vehicle lacks a more intuitive, clear and visual way to display the driving trajectory. It is not difficult to find that in the embodiment of the present application, the driving trajectory of the autonomous driving vehicle is generated by obtaining the user's selection information based on the target trajectory file, and according to the selection information, the target area and the electronic fence file. In this way, relevant personnel can simultaneously launch or combine multiple scenes to compare and observe the comparative display of the driving trajectory obtained by the first original trajectory file determined by the true value vehicle, the second original trajectory file determined by the camera and the third original trajectory file determined by the radar, and then perform trajectory analysis based on the effect of the comparative display, which not only provides a more intuitive, clear and visual way, but also helps to further improve the test efficiency or verification efficiency.

[0081] Fourth embodiment

[0082] The fourth embodiment of the present application relates to a trajectory analysis method for an autonomous driving vehicle. The fourth embodiment is an improvement on the first embodiment, and the specific improvement is that in the fourth embodiment of the present application, after generating the driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area and the electronic fence file, the method can also automatically determine the reason for the inaccurate fusion trajectory, thereby further improving the test efficiency or verification efficiency.

[0083] Specifically, in some embodiments, after generating the driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area, and the electronic fence file, the method may further include:

[0084] Step S104, automatically analyzing the driving trajectory of the autonomous driving vehicle to determine the reason why the fused trajectory is inaccurate; wherein the fused trajectory is obtained by fusion calculation based on at least two original trajectory files among the first original trajectory file, the second original trajectory file and the third original trajectory file;

[0085] The reason why the fused trajectory is inaccurate includes at least one of the following: an abnormality exists in a first trajectory generated based on the first original trajectory file, an abnormality exists in a second trajectory generated based on the second original trajectory file, and an abnormality exists in a third trajectory generated based on the third original trajectory file.

[0086] It should be noted that the fourth embodiment of the present application may also be an improvement based on the second embodiment and / or the third embodiment.

[0087] It is not difficult to find that in the embodiment of the present application, by automatically analyzing the driving trajectory of the autonomous driving vehicle, it can be analyzed whether the driving trajectory is inaccurate due to inaccurate RTK data of the real value vehicle, inaccurate camera recognition, or radar perception. This can help relevant personnel verify the accuracy of the RTK data of the real value vehicle, verify the accuracy of the camera's detection of the autonomous driving vehicle, and verify the accuracy of the radar's perception of the autonomous driving vehicle, further improving the test efficiency or verification efficiency.

[0088] Fifth embodiment

[0089] The fifth embodiment of the present application relates to a trajectory analysis method for an autonomous driving vehicle. The fifth embodiment is an improvement on the fourth embodiment, and the specific improvement is: providing a specific implementation method for analyzing the cause of inaccurate fusion trajectory;

[0090] Specifically, in some embodiments, the automatic analysis of the driving trajectory of the autonomous driving vehicle to determine the cause of the inaccurate fusion trajectory, that is, step S104, may further include the following steps: Figure 5 As shown:

[0091] Step S1041, determining a reference trajectory file according to the target trajectory file;

[0092] Step S1042, determining a position error, a heading angle error, and a speed error according to the reference trajectory file and the target trajectory file; wherein the position error, the heading angle error, and the speed error are obtained by aligning the timestamps based on the timestamps of the reference trajectory file;

[0093] Step S1043, determining the reason why the fused trajectory is inaccurate based on the position error, heading angle error and speed error.

[0094] It should be noted that the target trajectory file may also be only the first original trajectory file, the target trajectory file may also be only the second original trajectory file, and so on. For ease of understanding, in an embodiment of the present application, the target trajectory file includes the first original trajectory file, the second original trajectory file and the third original trajectory file as an example for explanation.

[0095] For step S1041, specifically, in some examples, the latitude and longitude coordinates, speed, heading angle and timestamp of each frame can be extracted from the first original trajectory file, the second original trajectory file and the third original trajectory file, respectively. Then, any one of the first original trajectory file, the second original trajectory file and the third original trajectory file is used as the reference trajectory file, and the timestamp of the reference trajectory file is used as the reference data; or, the fused trajectory file obtained by fusing the first original trajectory file, the second original trajectory file and the third original trajectory file through a fusion algorithm is used as the reference trajectory file, and the timestamp of the reference trajectory file is used as the reference data.

[0096] For step S1042, specifically, in some examples, the longitude and latitude coordinates, speed, heading angle and timestamp of each frame can be extracted from the first original trajectory file, the second original trajectory file and the third original trajectory file respectively. Then, the timestamp of any one of the first original trajectory file, the second original trajectory file and the third original trajectory file is used as the reference data (for example, the timestamp of the first original trajectory file is used as the reference data or the timestamp of the fused trajectory is used as the reference data), and the timestamp of the second original trajectory file and the timestamp of the third original trajectory file are respectively aligned with the reference data (the timestamp of the first original trajectory file), and the timestamp closest to the reference data (the timestamp of the first original trajectory file) in the second original trajectory file and the third original trajectory file is determined respectively. And the longitude and latitude coordinates, speed and heading angle corresponding to the timestamp closest to the reference data (the timestamp of the first original trajectory file) in the second original trajectory file and the third original trajectory file are obtained.

[0097] For step S1043, specifically, in some examples, the distance between two frames can be calculated by a geodesic formula, so that the data used to characterize the true value vehicle in the first original trajectory file can be obtained according to the distance, and the position error after the second original trajectory file and the third original trajectory file are aligned by timestamps. If the position error is greater than the first threshold, it can be explained to a certain extent that the driving trajectory generated based on the second original trajectory file and / or the third original trajectory file is abnormal.

[0098] Furthermore, the heading angle in the first original trajectory file and the heading angle in the second original trajectory file and the heading angle in the third original trajectory file at the same timestamp can be calculated based on the reference data to obtain the heading angle error. If the heading angle error is greater than the second threshold, it can be explained to a certain extent that the driving trajectory generated based on the second original trajectory file and / or the third original trajectory file is abnormal.

[0099] Furthermore, the speed in the first original trajectory file and the speed in the second original trajectory file and the speed in the third original trajectory file at the same timestamp can be calculated based on the reference data to obtain a speed error. If the speed error is greater than the third threshold, it can be explained to some extent that the driving trajectory generated based on the second original trajectory file and / or the third original trajectory file is abnormal.

[0100] It should be noted that the fifth embodiment of the present application may also be an improvement based on any one or more embodiments from the first embodiment to the third embodiment.

[0101] It is not difficult to find that in the technical solution provided in the embodiment of the present application, the algorithm logic evaluates the accuracy of the driving trajectory determined based on different data sources (data determined by the true value vehicle, data determined by the camera, and data determined by the radar) by aligning the timestamps and then calculating the position error, heading error, and speed error. The method provided in the embodiment of the present application can be used to automatically test or verify the cause of the inaccurate fusion trajectory to ensure the reliability and consistency of the data determined by the true value vehicle, the data determined by the camera, and the data determined by the radar. Since it does not need to rely entirely on the analysis of relevant personnel through observation, the test efficiency or verification efficiency can be further improved.

[0102] Sixth embodiment

[0103] The sixth embodiment of the present application relates to a trajectory analysis method for an autonomous driving vehicle. The fourth embodiment is an improvement on the first embodiment, and the specific improvement is that after generating the driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area and the electronic fence file, the method can also automatically determine the target abnormality, thereby further improving the test efficiency or verification efficiency.

[0104] Specifically, in some embodiments, after generating the driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area, and the electronic fence file, the method may further include:

[0105] Step S104', automatically analyzing the driving trajectory of the autonomous driving vehicle to determine target abnormalities; the target abnormalities include at least one of the following: trajectory retraction, trajectory advance, and trajectory trend abnormality.

[0106] Optionally, in some embodiments, the trajectory regression analysis method may include the following steps:

[0107] Step S201, determining a reference trajectory file according to the target trajectory file;

[0108] Step S202, determining the distance between every two frames according to the reference trajectory file and the target trajectory file;

[0109] Step S203, determining a first heading angle difference between a current frame and a previous frame, and a second heading angle difference between the previous frame and the previous previous frame in the reference trajectory file and the target trajectory file according to the distance between every two frames;

[0110] Step S204: determining whether trajectory reversal occurs according to the distance between every two frames, the first heading angle difference and the second heading angle difference.

[0111] It should be noted that the implementation logic of step S201 in this embodiment and step S1041 in the fifth embodiment is substantially the same, and will not be described again here to avoid repetition.

[0112] For step S202, specifically, in some examples, the first original trajectory file can be used as the reference trajectory file, and the timestamp of the reference trajectory file can be used as the reference data. For example, the timestamp of the second original trajectory file and the timestamp of the third original trajectory file can be aligned with the reference data (the timestamp of the first original trajectory file), and the timestamp closest to the reference data (the timestamp of the first original trajectory file) in the second original trajectory file and the third original trajectory file can be determined respectively. And the longitude and latitude coordinates corresponding to the timestamp closest to the reference data (the timestamp of the first original trajectory file) in the second original trajectory file and the third original trajectory file are obtained. For the second original trajectory file and the third original trajectory file, respectively, the longitude and latitude coordinates of two consecutive frames are calculated to obtain the moving distance of each frame relative to the previous frame. At this point, the distance between every two frames in the target trajectory file can be determined.

[0113] For step S203 and step S204, specifically, in some examples, for the reference trajectory file, the second original trajectory file, and the third original trajectory file, the first heading angle difference α between the current frame and the previous frame, and the second heading angle difference β between the previous frame and the previous previous frame are calculated respectively. If the difference between the first heading angle difference α and the second heading angle difference β is within the preset range, it can be said that there is a trajectory fallback, that is, the moving direction has undergone a significant reverse change. If the difference between the first heading angle difference α and the second heading angle difference β is not within the preset range, it can be further determined whether there is a trajectory fallback based on the distance between each two frames. If the distance between each two frames is large, a manual check can be initiated; if the distance between each two frames is within a reasonable range, it can be preliminarily determined that there is no trajectory fallback.

[0114] Exemplarily, the preset range may be between 90 degrees and 270 degrees. That is, in the embodiment of the present application, by comparing the heading angles of consecutive frames, the turning situation of the trajectory can be observed according to the difference in the heading angles of consecutive frames. If the difference in the heading angle between two consecutive frames is between about 90 degrees and 270 degrees, it means that the trajectory may have fallen back, which is not common in normal continuous movement, and therefore can be used as an indicator of abnormality and is a target abnormality.

[0115] Exemplarily, if it is determined based on the first original trajectory file and the second original trajectory file that neither of them has the target abnormality of the trajectory fallback, and it is determined based on the third original trajectory file that there is the target abnormality of the trajectory fallback, it can be directly obtained that the third original trajectory file has an abnormality, and then it can be determined that the radar data is inaccurate, which can be further confirmed by relevant personnel.

[0116] It can be seen that in the embodiment of the present application, a trajectory retraction analysis method is provided, which detects whether the driving trajectory has an abnormal retraction phenomenon by checking the change in the moving direction of consecutive frames in the driving trajectory. Under normal circumstances, the moving direction of the trajectory should be continuous and smooth, and a large reverse change may indicate that there is a problem in the collection or processing of the trajectory data. By comparing with the baseline data, these abnormal situations can be more intuitively identified and analyzed.

[0117] It should be noted that the sixth embodiment of the present application may also be an improvement based on any one or more embodiments from the second embodiment to the fifth embodiment.

[0118] It is not difficult to find that in the embodiment of the present application, by automatically analyzing the driving trajectory of the autonomous driving vehicle, target abnormalities can be analyzed, thereby assisting relevant personnel in analyzing trajectory regression, trajectory advance, and trajectory trend abnormalities, thereby further improving test efficiency or verification efficiency.

[0119] Seventh embodiment

[0120] The seventh embodiment of the present application relates to a trajectory analysis method for an autonomous driving vehicle. The seventh embodiment is an improvement on the sixth embodiment, and the specific improvement is that: in the seventh embodiment of the present application, a method for analyzing the trajectory advance is provided.

[0121] Specifically, in some embodiments, the trajectory analysis method may include the following steps:

[0122] Step S301, determining a reference trajectory file according to the target trajectory file;

[0123] Step S302, determining the distance between every two frames in the target trajectory file according to the reference trajectory file;

[0124] Step S303, determining the speed of the current frame and the coefficient set based on the speed in the reference trajectory file and the target trajectory file;

[0125] Step S304, determining whether a trajectory advance occurs according to the distance between every two frames, the speed and the coefficient.

[0126] It should be noted that the implementation logic of step S301 and step S302 in this embodiment and step S201 and step S202 in the sixth embodiment are substantially the same, and will not be described again here to avoid repetition.

[0127] For step S303, specifically, in some examples, the product of the speed of the current frame and the coefficient can be calculated according to the speed of the current frame in the reference trajectory file and the target trajectory file and the coefficient set based on the speed, respectively; the distance between every two frames in the reference trajectory file and the target trajectory file and the product are compared. If the distance between every two frames is greater than the product, it means that the trajectory advances forward; otherwise, the trajectory does not advance forward. It can be understood that the forward advance of the trajectory is an abnormal protrusion phenomenon, which should not occur under normal circumstances, because it means that a large position change beyond the normal speed range has occurred in a very short period of time.

[0128] For example, the coefficient based on the speed setting can be set according to actual needs or experience to determine what degree of distance change can be considered as abnormal protrusion. For example, the coefficient can be, but is not limited to, 0.1.

[0129] Further, if based on the baseline trajectory file, the result is that the trajectory does not advance forward, based on the second original trajectory file, the result is that the trajectory does not advance forward, and based on the third original trajectory file, the result is that the trajectory advances forward, it can be determined that there is an abnormality in the data in the third original trajectory file.

[0130] It should be noted that the seventh embodiment of the present application may also be an improvement based on any one or more embodiments from the first embodiment to the fifth embodiment.

[0131] It is not difficult to find that in the embodiment of the present application, by comparing the distance change between two consecutive frames with the expected change of the current speed, it is judged whether the trajectory has an abnormal protrusion phenomenon. If the moving distance of the trajectory in a very short time significantly exceeds the range that can be covered by the normal speed, this may indicate a problem in the trajectory data collection or processing process. By comparing with the benchmark data, these abnormal situations can be more intuitively identified and analyzed.

[0132] Eighth embodiment

[0133] The eighth embodiment of the present application relates to a trajectory analysis method for an autonomous driving vehicle. The eighth embodiment is an improvement on the sixth embodiment, and the specific improvement is: in the eighth embodiment of the present application, a method for analyzing the abnormal trajectory trend is provided.

[0134] Specifically, in some embodiments, the method for analyzing abnormal trajectory trends may include the following steps:

[0135] Step S401, determining a reference trajectory file according to the target trajectory file;

[0136] Step S402, determining, according to the reference trajectory file and the target trajectory file, whether the heading angles used to characterize the continuous multiple frames in the preset time period are based on the judgment result of the same direction change;

[0137] Step S403: Determine whether the trajectory trend is abnormal based on the judgment result.

[0138] It should be noted that the implementation logic of step S401 in this embodiment and step S1041 in the fifth embodiment is substantially the same, and will not be described again here to avoid repetition.

[0139] Regarding step S402, specifically, in some examples, it can be determined whether the heading angle changes based on the same direction by detecting whether the heading angles of multiple consecutive frames in a preset time period in the reference trajectory file and the target trajectory file change based on the same direction.

[0140] Optionally, in some embodiments, determining, according to the reference trajectory file and the target trajectory file, whether the heading angles of a plurality of consecutive frames in a preset time period change based on the same direction to obtain a judgment result, that is, step S402 may further include the following steps:

[0141] Step S4021, determining a difference in heading angle between a current frame and an Nth frame before the current frame; wherein N is an integer greater than or equal to 1;

[0142] Step S4022, determining whether the heading angles of multiple consecutive frames in a preset time period in the reference trajectory file and the target trajectory file change based on the same direction according to the difference between the heading angles of the current frame and the Nth frame before the current frame.

[0143] Exemplarily, the value of N may be 4, 5, 6, etc., which is not specifically limited in the embodiments of the present application.

[0144] Exemplarily, if the difference between the heading angles of the current frame and the Nth frame before the current frame is greater than a preset range threshold, it can be determined that the heading angles of multiple consecutive frames in a preset time period in the baseline trajectory file and the target trajectory file do not change in the same direction, and the trajectory trend may be abnormal; wherein the preset range threshold can be determined according to actual needs. In some examples, the preset range threshold can be but is not limited to 60 degrees.

[0145] Regarding step S403, specifically, in some examples, if based on the baseline trajectory file, a result is obtained that the trajectory trend does not show any abnormality, based on the second original trajectory file, a result is obtained that the trajectory trend does not show any abnormality, and based on the third original trajectory file, a result is obtained that the trajectory trend shows any abnormality, then it can be determined that the data in the third original trajectory file is abnormal.

[0146] It should be noted that the eighth embodiment of the present application may also be an improvement based on any one or more of the first to fifth embodiments and the seventh embodiment.

[0147] It is not difficult to find that in the embodiment of the present application, the change of the heading angle of multiple consecutive frames in the trajectory data is monitored to determine whether the trajectory trend is normal. If the change of the heading angle exceeds the set threshold in several consecutive frames, this may indicate a problem in the trajectory data collection or processing process, such as radar failure, data processing error or external interference. By comparing with the benchmark data, these abnormal situations can be more intuitively identified and analyzed, thereby evaluating the accuracy and reliability of the trajectory data.

[0148] The step division of the above methods is only for the purpose of clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0149] In addition, some embodiments of the present application also provide an electronic device. The electronic device may be a digital computer in various forms, such as a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, etc. The electronic device may also be a mobile device in various forms, such as a personal digital processing, a cellular phone, a smart phone, a wearable device, and other similar computing devices.

[0150] The electronic device includes: one or more processors; and a memory storing computer program instructions, wherein when the computer program instructions are executed, the processor executes the steps of the method provided in any one or more of the above embodiments. Figure 6 An exemplary structural diagram of the electronic device is disclosed. Figure 6 As shown, the electronic device includes: one or more processors 1101, memory 1102, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Among them, the components shown in this article, their connections and relationships, and their functions are only used as examples, and are not intended to limit the implementation of the present application described and / or required herein.

[0151] The electronic device may further include: an input device 1103 and an output device 1104. The processor 1101, the memory 1102, the input device 1103 and the output device 1104 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0152] The input device 1103 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a track ball, a joystick and other input devices. The output device 1104 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0153] To provide interaction with a user, the electronic device may be a computer. The computer has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0154] In the embodiments of the present application, a computer program / instruction is stored on a computer-readable medium, and when the computer program / instruction is executed by a processor, the steps of the method provided by any one or more of the above embodiments are implemented. The computer-readable medium may be included in the electronic device described in the above embodiments; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more computer-readable instructions.

[0155] The memory 1102 can be used as a non-transient computer-readable storage medium, which can be used to store non-transient software programs, non-transient computer executable programs and modules. The processor 1101 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 1102, so as to implement the program instructions / modules corresponding to the method provided by any one or more embodiments in the embodiments of the present application.

[0156] The memory 1102 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 1102 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 1102 may optionally include a memory remotely arranged relative to the processor 1101, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0157] It should be noted that the computer-readable medium described in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0158] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0159] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0160] In the above-described embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. For example, it can be implemented by using an application specific integrated circuit (ASIC), a general-purpose computer or any other similar hardware device. In certain embodiments, the software program of the present application can be executed by a processor to implement the above steps or functions. Similarly, the software program of the present application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present application can be implemented by hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0161] The computer program product provided in the embodiment of the present application includes one or more computer programs / instructions, and when the computer program / instructions are executed by the processor, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from a computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk (SSD)), etc.

[0162] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0163] The scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. The words "first", "second", etc. are only used to distinguish the description, and do not indicate any particular order, nor can they be understood as indicating or implying relative importance.

[0164] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily mention changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-restrictive.

Claims

1. A driving trajectory analysis method based on an autonomous driving vehicle, characterized in that: The method comprises: Acquire a target trajectory file; the target trajectory file includes at least one of a first original trajectory file determined based on a true value vehicle, a second original trajectory file determined based on a camera, and a third original trajectory file determined based on a radar; Determine a target area and an electronic fence file corresponding to the target area; A driving trajectory of the autonomous driving vehicle is generated according to the target trajectory file, the target area and the electronic fence file.

2. The method according to claim 1, characterized in that The first original trajectory file, the second original trajectory file, and the third original trajectory file all include key information; the key information includes at least: first data for representing the timestamp of the driving trajectory of the autonomous driving vehicle, second data for representing the longitude and latitude coordinates of the driving position of the autonomous driving vehicle, third data for representing the driving speed of the autonomous driving vehicle, fourth data for representing the heading angle of the autonomous driving vehicle, and fifth data for representing the object type identified; The step of generating the driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area, and the electronic fence file includes: Determining a map area displayed in an electronic map according to the target area; Perform pixel drawing according to the electronic fence file to obtain the target electronic fence in the preset layer; Generate a driving trajectory of the autonomous driving vehicle based on at least one of the first data, the second data, the third data, the third data and the fifth data in the target trajectory file.

3. The method according to claim 1, characterized in that The step of generating the driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area, and the electronic fence file includes: Acquire selection information of the user based on the target trajectory file; A driving trajectory of the autonomous driving vehicle is generated according to the selection information, the target area and the electronic fence file.

4. The method according to claim 3, characterized in that The step of generating the driving trajectory of the autonomous driving vehicle according to the selection information, the target area, and the electronic fence file includes: Using a preset mode, generating a driving trajectory of the autonomous driving vehicle according to the selection information, the target area and the electronic fence file; Wherein, the preset modes include: a single display mode and a comparative display mode; The separate display mode includes at least one of the following: displaying the first trajectory according to the first original trajectory file alone, displaying the second trajectory according to the second original trajectory file alone, displaying the third trajectory according to the third original trajectory file alone, and displaying the fused trajectory alone; wherein the fused trajectory is obtained by fusion calculation based on at least two original trajectory files among the first original trajectory file, the second original trajectory file and the third original trajectory file; The comparative display mode includes at least one of the following: comparative display of the fused trajectory and the first trajectory, comparative display of the fused trajectory and the second trajectory, comparative display of the fused trajectory and the third trajectory, and comparative display of the fused trajectory with at least two of the first trajectory, the second trajectory and the third trajectory.

5. The method according to any one of claims 1 to 4, characterized in that: After generating the driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area and the electronic fence file, the method further includes: Automatically analyzing the driving trajectory of the autonomous driving vehicle to determine the reason why the fused trajectory is inaccurate; wherein the fused trajectory is obtained by fusion calculation based on at least two original trajectory files among the first original trajectory file, the second original trajectory file and the third original trajectory file; The reason why the fused trajectory is inaccurate includes at least one of the following: an abnormality exists in a first trajectory generated based on the first original trajectory file, an abnormality exists in a second trajectory generated based on the second original trajectory file, and an abnormality exists in a third trajectory generated based on the third original trajectory file.

6. The method according to claim 5, characterized in that The automatic analysis of the driving trajectory of the autonomous driving vehicle to determine the reasons for inaccurate fusion trajectory includes: Determine a reference trajectory file according to the target trajectory file; Determine a position error, a heading angle error, and a speed error according to the reference trajectory file and the target trajectory file; wherein the position error, the heading angle error, and the speed error are obtained by aligning the timestamps based on the timestamps of the reference trajectory file; The cause of inaccurate fusion trajectory is determined based on the position error, heading angle error and speed error.

7. The method according to any one of claims 1 to 4, characterized in that After generating the driving trajectory of the autonomous driving vehicle according to the target trajectory file, the target area and the electronic fence file, the method further includes: Automatically analyzing the driving trajectory of the autonomous driving vehicle to determine target abnormalities; the target abnormalities include at least one of the following: trajectory regression, trajectory advance, and trajectory trend abnormality; The trajectory fallback analysis method includes: determining a reference trajectory file according to the target trajectory file; determining the distance between every two frames according to the reference trajectory file and the target trajectory file; determining a first heading angle difference between a current frame and a previous frame, and a second heading angle difference between the previous frame and the previous previous frame in the reference trajectory file and the target trajectory file according to the distance between every two frames; determining whether trajectory fallback occurs according to the distance between every two frames, the first heading angle difference, and the second heading angle difference; The trajectory advance analysis method includes: determining a reference trajectory file according to the target trajectory file; determining the distance between every two frames according to the reference trajectory file and the target trajectory file; determining the speed of the current frame and a coefficient set based on the speed in the reference trajectory file and the target trajectory file; determining whether a trajectory advance occurs according to the distance between every two frames, the speed and the coefficient; Among them, the analysis method of the abnormal trajectory trend includes: determining a reference trajectory file according to the target trajectory file; determining, according to the reference trajectory file and the target trajectory file, whether the heading angles used to characterize multiple consecutive frames in a preset time period are based on a judgment result of changes in the same direction; and determining whether the trajectory trend is abnormal according to the judgment result.

8. An electronic device, characterized in that: The electronic device comprises: one or more processors; and A memory storing computer program instructions, which, when executed, cause the processor to perform the steps of the method as claimed in any one of claims 1 to 7.

9. A computer readable medium having a computer program / instructions stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images