Automatic lane changing data feedback method, device and equipment and storage medium

Abstract

The application relates to the technical field of automatic driving, in particular to a method and device for automatic lane changing data playback, equipment and a storage medium, wherein the method comprises the following steps: obtaining real vehicle test data of a vehicle, and analyzing the real vehicle test data to obtain to-be-tested scene data; determining to-be-playback signals according to the to-be-tested scene data, and compiling a data playback algorithm according to the to-be-tested scene data and the to-be-playback signals based on a preset automatic lane changing strategy; inputting the data playback algorithm into a preset playback tool for data playback, and obtaining a lane changing state in which a driver triggers a lane changing process in a playback process, so as to generate a playback result according to the lane changing state. Therefore, the low efficiency caused by repeated real vehicle road tests of a tester is solved, and problems such as complex problem point reproduction conditions and difficult problem point reproduction are solved, and the test efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a method and device for annotating automatic lane-changing data, equipment and a storage medium. BACKGROUND

[0002] During the development of an automatic driving vehicle, a large number of real vehicle road tests need to be carried out to observe the reliability and feasibility of the vehicle automatic driving technology through driving in different road conditions and the joint participation of external vehicles and pedestrians. During the real vehicle road test, the vehicle records the driving data, which involves all modules, sensors, cameras, etc. of the vehicle. When analyzing the specific causes of the automatic driving technology problems, it is crucial to analyze the historical driving scene and historical data of the automatic driving vehicle.

[0003] When a problem occurs in the road test of the automatic driving vehicle, the problem point needs to be analyzed and improved. During the analysis process, the tester often re-tests to reproduce the problem, and when the problem is improved, the tester often performs regression testing to ensure that the problem does not recur. However, repeatedly testing the same problem is inefficient, time-consuming, and when the problem reproduction conditions are harsh, it is difficult to reproduce the problem, which needs to be solved urgently. SUMMARY

[0004] The present application provides a method and device for annotating automatic lane-changing data, equipment and a storage medium, which solves the problem of low efficiency caused by repeated real vehicle road tests by testers, and the problem of complex problem point reproduction conditions and difficult problem point reproduction, thereby improving the test efficiency.

[0005] The first aspect of the present application provides a method for annotating automatic lane-changing data, comprising the following steps: obtaining real vehicle test data of a vehicle and analyzing the real vehicle test data to obtain to-be-tested scene data; determining to-be-annotated signals according to the to-be-tested scene data, and compiling a data annotation algorithm according to the to-be-tested scene data and the to-be-annotated signals based on a preset automatic lane-changing strategy; inputting the data annotation algorithm into a preset playback tool for data playback, and obtaining a lane-changing state of a driver triggering a lane-changing process during the playback process to generate an annotation result according to the lane-changing state.

[0006] According to the above technical means, the problem of low efficiency caused by repeated real vehicle road tests by testers, and the problem of complex problem point reproduction conditions and difficult problem point reproduction are solved, thereby improving the test efficiency.

[0007] Further, the preset automatic lane changing strategy is: controlling the lane changing state of the target vehicle to be a lane changing activation waiting state; determining whether the target vehicle receives a lane changing request instruction, and when the lane changing request instruction is received, determining whether the target vehicle turns on a turn signal, and triggering a lane changing action corresponding to the turn signal; if the target vehicle turns on the turn signal and triggers the lane changing action corresponding to the turn signal, the lane changing state of the target vehicle is switched from the lane changing activation waiting state to a lane changing delay state, and when the target vehicle does not have a preset lane changing inhibition condition, the target vehicle is controlled to switch from the lane changing delay state to a lane changing activation state, and a lane changing action is performed, otherwise, the lane changing action of the target vehicle is exited.

[0008] According to the above technical means, it is verified whether the ALC (Auto Lane Change, intelligent auxiliary lane changing) automatic lane changing is successful.

[0009] Further, after generating the feedback result according to the lane changing state, the method further includes: obtaining a recurring fault point from the feedback result; correcting the to-be-tested scene data according to the recurring fault point, and determining a new to-be-tested scene data as a to-be-feedback signal, until the recurring fault point does not exist in the feedback result.

[0010] According to the above technical means, the problem is no longer reproduced by correcting the fault point.

[0011] Further, the analyzing the real vehicle test data to obtain the to-be-tested scene data includes: performing data visualization processing on the real vehicle test data to obtain visualized test data; and analyzing the visualized test data based on a current road test fault time point signal to obtain the to-be-tested scene data.

[0012] According to the above technical means, by visualizing the test data, the change of the fault point is facilitated to be analyzed.

[0013] The second aspect embodiment of the application provides an automatic lane changing data feedback device, including: an acquisition module, configured to acquire real vehicle test data of a vehicle, and analyze the real vehicle test data to obtain to-be-tested scene data; a compiling module, configured to determine a to-be-feedback signal according to the to-be-tested scene data, and compile a data feedback algorithm based on a preset automatic lane changing strategy and according to the to-be-tested scene data and the to-be-feedback signal; and a generation module, configured to input the data feedback algorithm to a preset playback tool for data playback, and acquire a lane changing state of a lane changing process triggered by a driver in a playback process, so as to generate a feedback result according to the lane changing state.

[0014] Further, the compiling module is specifically configured to: control the lane changing state of the target vehicle to be a lane changing activation waiting state; determine whether the target vehicle receives a lane changing request instruction, and when the target vehicle receives the lane changing request instruction, determine whether the target vehicle turns on a turn signal, and trigger a lane changing action corresponding to the turn signal; if the target vehicle turns on the turn signal and triggers the lane changing action corresponding to the turn signal, control the lane changing state of the target vehicle to switch from the lane changing activation waiting state to a lane changing delay state, and when the target vehicle does not have a preset lane changing inhibition condition, control the target vehicle to switch from the lane changing delay state to a lane changing activation state, and perform the lane changing action, otherwise, exit the lane changing action of the target vehicle.

[0015] Further, after the generating module generates the feedback result according to the lane changing state, the generating module is specifically configured to: obtain a recurring fault point from the feedback result; correct the to-be-tested scene data according to the recurring fault point, and determine a to-be-feedback signal by using the corrected to-be-tested scene data as new to-be-tested scene data, until there is no recurring fault point in the feedback result.

[0016] Further, the obtaining module is specifically configured to: perform data visualization processing on the real vehicle test data to obtain visualized test data; and analyze the visualized test data to obtain the to-be-tested scene data based on a current road test fault time point signal.

[0017] The third aspect of the embodiments of the present application provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement the lane changing data feedback method according to the above embodiments.

[0018] The fourth aspect of the embodiments of the present application provides a computer readable storage medium, which stores a computer program executable by a processor to implement the lane changing data feedback method according to the above embodiments.

[0019] Therefore, the present application obtains real vehicle test data of a vehicle, analyzes the real vehicle test data to obtain to-be-tested scene data, determines a to-be-feedback signal according to the to-be-tested scene data, compiles a data feedback algorithm according to the to-be-tested scene data and the to-be-feedback signal based on a preset automatic lane changing strategy, inputs the data feedback algorithm into a preset playback tool for data playback, and obtains a lane changing state of a driver triggering a lane changing process in the playback process to generate a feedback result according to the lane changing state. Therefore, the low efficiency problem caused by repeated real vehicle road tests of a tester is solved, and problems such as complex problem point recurring conditions and difficult-to-recurring problem points are solved, and the test efficiency is improved.

[0020] Additional aspects and advantages of the present application will be made apparent from the following description with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0021] The above and / or additional aspects and advantages of the present application will become apparent and be more readily understood from the following description, by reference to the drawings, wherein:

[0022] Figure 1 A flow chart of a method for automatic lane change data feedback according to an embodiment of the present application;

[0023] Figure 2 A flow chart of ALC automatic lane change auxiliary lane change logic judgment according to an embodiment of the present application;

[0024] Figure 3 A block schematic diagram of an automatic lane change data feedback device according to an embodiment of the present application;

[0025] Figure 4 A structural schematic diagram of an electronic device according to an embodiment of the present application.

[0026] Reference Signs List: 10-automatic lane change data feedback device, 100-acquisition module, 200-compile module, 300-generation module, 403-communication interface, 401-memory, 402-processor. DETAILED DESCRIPTION

[0027] Embodiments of the present application are described in detail below with reference to the attached drawings, which are meant to be exemplary and not limiting.

[0028] A method, device, and storage medium for annotating automatic lane-changing data are described below with reference to the accompanying drawings. To address the inefficiency caused by repeated real vehicle road testing by testers, and the complexity of problem point reproduction conditions and difficulty of problem point reproduction, the present application provides a method for annotating automatic lane-changing data. In the method, real vehicle testing data of a vehicle is obtained, and the real vehicle testing data is analyzed to obtain to-be-tested scene data. A to-be-annotated signal is determined based on the to-be-tested scene data, and a data annotation algorithm is compiled based on the to-be-tested scene data and the to-be-annotated signal based on a preset automatic lane-changing strategy. The data annotation algorithm is input to a preset playback tool for data playback, and a lane-changing state of a driver triggering a lane-changing process is obtained during the playback process to generate an annotation result based on the lane-changing state. Thus, the inefficiency caused by repeated real vehicle road testing by testers is addressed, and the complexity of problem point reproduction conditions and the difficulty of problem point reproduction are addressed, thereby improving testing efficiency.

[0029] Specifically, Figure 1 A flowchart of a method for annotating automatic lane-changing data is provided in the present application.

[0030] As Figure 1 shown, the method for annotating automatic lane-changing data includes the following steps:

[0031] In step S101, real vehicle testing data of a vehicle is obtained, and the real vehicle testing data is analyzed to obtain to-be-tested scene data.

[0032] Specifically, in an Ubuntu environment, real vehicle testing data of a real vehicle road testing dat file is obtained, for example, including vehicle speed data and adjacent vehicle speed data, vehicle position data and adjacent vehicle position data, vehicle distance data from an adjacent vehicle, and distance data from a current lane line of a vehicle driving lane and an adjacent vehicle driving lane. The dat file is a data file recorded and stored by a camera and other sensors, containing original sensor data and processed intermediate variable data, and the vehicle information in the dat file includes data streams of all integrated module inputs and outputs.

[0033] Optionally, in some embodiments, analyzing the real vehicle testing data to obtain to-be-tested scene data includes: performing data visualization processing on the real vehicle testing data to obtain visualized testing data; and analyzing the visualized testing data based on a current road test fault time point signal to obtain to-be-tested scene data.

[0034] Specifically, the embodiment of the present application obtains the behavior data of the vehicle and the behavior data of the adjacent vehicle by analyzing the real vehicle test data of the vehicle, and visualizes the dat file through an offline visualization tool, scene processing, and signal image processing to obtain visual test data. The dat file recorded by the real vehicle is opened on the offline visualization tool to confirm the time point of the fault occurrence, analyze the current road test fault time point signal, and obtain the scene data to be tested.

[0035] In step S102, the signal to be injected back is determined according to the scene data to be tested, and the data injection back algorithm is compiled according to the scene data to be tested and the signal to be injected back based on the preset automatic lane changing strategy.

[0036] Optionally, in some embodiments, the preset automatic lane changing strategy is that the lane changing state of the target vehicle is in a lane changing activation waiting state; it is judged whether the target vehicle receives a lane changing instruction, and when the lane changing instruction is received, it is judged whether the target vehicle turns on the turn signal and triggers the lane changing action corresponding to the turn signal; if the target vehicle turns on the turn signal and triggers the lane changing action corresponding to the turn signal, the lane changing state of the target vehicle is switched from the lane changing activation waiting state to the lane changing delay state, and when the target vehicle does not have a preset lane changing inhibition condition, the target vehicle is switched from the lane changing delay state to the lane changing activation state, and the lane changing action is performed, otherwise, the lane changing action of the target vehicle is exited.

[0037] Specifically, the preset automatic lane changing strategy of the embodiment of the present application can be as shown in Figure 2 After the ALC automatic lane changing assistance function is turned on, the vehicle executes step S201.

[0038] In step S201, the lane changing state (i.e. the UDLC (Universal Digital Loop Carrier) state signal) is in a lane changing activation waiting state.

[0039] In step S202, it is judged whether the ALC slow vehicle flow lane changing trigger request signal is issued to the UDLC module to request the slow vehicle in front to change lane to the left. If no request is issued, step S201 is executed, and at this time, the target vehicle is still in the lane changing activation waiting state, and if the request is issued, step S203 is executed.

[0040] In step S203, it is judged whether the target vehicle turns on the left turn signal and triggers the UDLC left lane changing. If the target vehicle does not turn on the turn signal and does not trigger the left lane changing, step S208 is entered, at this time, the lane changing state is in an inactivatable standby state, indicating that the lane changing is exited, and if the target vehicle turns on the left turn signal and triggers the left lane changing, step S204 is entered, at this time, the lane changing state is switched from the lane changing activation waiting state to the lane changing delay state.

[0041] In step S204, the lane-changing state jumps to a lane-changing delay state.

[0042] In step S205, it is determined whether the target vehicle is free of preset lane-changing inhibition conditions. If the target vehicle is not free of lane-changing inhibition conditions, step S208 is executed, at which time the lane-changing state jumps to an inactivatable standby state, indicating that the lane-changing is exited. If the target vehicle is free of preset lane-changing inhibition conditions, the lane-changing state jumps from the lane-changing delay state to an active lane-changing state, and step S206 is executed, in which the lane-changing action is performed.

[0043] In step S206, the lane-changing is performed. If the lane-changing assistance is successful, step S207 is executed.

[0044] In step S207, the success is output.

[0045] In step S208, the lane-changing is exited. If the lane-changing assistance fails, the lane-changing trigger condition is not met, and thus the lane-changing is exited, and step S209 is executed.

[0046] In step S209, the failure is output.

[0047] In step S103, the data playback algorithm is input to a preset playback tool to perform data playback, and a lane-changing state in which the driver triggers the lane-changing process is acquired during the playback, so as to generate a playback result according to the lane-changing state.

[0048] Specifically, the dat file is fed back into the test code to reproduce the fault point, stop the fault point, and the dat file and the playback test code are added to the preset playback tool, the playback tool integrated with the automatic driving software is run, and the playback result generated by the lane-changing state is observed.

[0049] Further, in some embodiments, after the playback result is generated according to the lane-changing state, the playback result is further generated according to the lane-changing state, and the reproduction of the fault point is acquired from the playback result. The to-be-tested scene data is corrected according to the reproduction of the fault point, and the corrected to-be-tested scene data is determined as new to-be-tested scene data to determine the to-be-playback signal until there is no reproduction of the fault point in the playback result.

[0050] It can be understood that when the playback result is a failure, problem version playback is required. The dat file is fed back into the test code to reproduce the fault point. After the developer repairs the software that generates the fault point, the playback tool integrated with the modified version of the software is used to perform data playback. If the problem does not reproduce, the software can be released.

[0051] In this embodiment, if the version is switched, only the playback tool integrated with the corresponding version is replaced, and the above operations are repeated to verify whether the problem reproduces.

[0052] According to the automatic lane changing data playback method provided in the embodiments of the present application, real vehicle test data of a vehicle is obtained, and the real vehicle test data is analyzed to obtain to-be-tested scene data, and a to-be-playback signal is determined according to the to-be-tested scene data. Based on a preset automatic lane changing strategy, a data playback algorithm is compiled according to the to-be-tested scene data and the to-be-playback signal, the data playback algorithm is input to a preset playback tool for data playback, and a lane changing state of a driver triggering a lane changing process is obtained in the playback process, so as to generate a playback result according to the lane changing state. In this way, the problem of low efficiency caused by repeated real vehicle road tests of a tester is solved, and problems such as complex problem point reproduction conditions and difficult problem point reproduction are solved, and the test efficiency is improved.

[0053] Secondly, the automatic lane changing data playback device provided in the embodiments of the present application is described with reference to the accompanying drawings.

[0054] Figure 3 is a block schematic diagram of the automatic lane changing data playback device in the embodiments of the present application.

[0055] As shown in Figure 3 , the automatic lane changing data playback device 10 comprises an obtaining module 100, a compiling module 200 and a generating module 300.

[0056] The obtaining module 100 is configured to obtain real vehicle test data of a vehicle, analyze the real vehicle test data, and obtain to-be-tested scene data. The compiling module 200 is configured to determine a to-be-playback signal according to the to-be-tested scene data, and compile a data playback algorithm according to the to-be-tested scene data and the to-be-playback signal based on a preset automatic lane changing strategy. The generating module 300 is configured to input the data playback algorithm to a preset playback tool for data playback, and obtain a lane changing state of a driver triggering a lane changing process in the playback process, so as to generate a playback result according to the lane changing state.

[0057] Optionally, in some embodiments, the compiling module 200 is specifically configured to: control a lane changing state of a target vehicle to be a lane changing activation waiting state; determine whether the target vehicle receives a lane changing instruction, and when the lane changing instruction is received, determine whether the target vehicle turns on a turn signal and triggers a lane changing action corresponding to the turn signal; if the target vehicle turns on the turn signal and triggers the lane changing action corresponding to the turn signal, control the lane changing state of the target vehicle to be switched from the lane changing activation waiting state to a lane changing delay state, and when the target vehicle does not have a preset lane changing inhibition condition, control the target vehicle to be switched from the lane changing delay state to a lane changing activation state, and execute the lane changing action, otherwise, exit the lane changing action of the target vehicle.

[0058] Optionally, in some embodiments, after the lane changing state is generated according to the back-annotation result, the generation module 300 is specifically configured to: obtain a recurring fault point from the back-annotation result; correct the to-be-tested scene data according to the recurring fault point, and determine the to-be-annotated signal as new to-be-tested scene data until there is no recurring fault point in the back-annotation result.

[0059] Optionally, in some embodiments, the acquisition module 100 is specifically configured to: perform data visualization processing on the real vehicle test data to obtain visualized test data; and analyze the visualized test data based on the current road test fault time point signal to obtain the to-be-tested scene data.

[0060] It should be noted that the foregoing explanation and description of the automatic lane changing data back-annotation method embodiment also applies to the automatic lane changing data back-annotation device of this embodiment, which will not be described here again.

[0061] The automatic lane changing data back-annotation device according to the embodiments of the present application, by acquiring real vehicle test data of a vehicle, analyzing the real vehicle test data to obtain to-be-tested scene data, determining a to-be-annotated signal according to the to-be-tested scene data, compiling a data back-annotation algorithm based on a preset automatic lane changing strategy according to the to-be-tested scene data and the to-be-annotated signal, inputting the data back-annotation algorithm into a preset playback tool for data playback, and obtaining a lane changing state in which a driver triggers a lane changing process in the playback process to generate a back-annotation result according to the lane changing state. Thus, the low efficiency problem caused by repeated real vehicle road tests by test personnel is solved, and problems such as complex problem point recurring conditions and difficult-to-recurring problem points are solved, thereby improving the test efficiency.

[0062] Figure 4 The structure schematic diagram of the electronic device provided by the embodiments of the present application is provided. The electronic device can include:

[0063] The memory 401, the processor 402, and the computer program stored in the memory 401 and executable on the processor 402.

[0064] The processor 402 executes the program to implement the automatic lane changing data back-annotation method provided in the above embodiments.

[0065] Further, the electronic device further includes:

[0066] The communication interface 403 is configured to communicate between the memory 401 and the processor 402.

[0067] The memory 401 is configured to store the computer program executable on the processor 402.

[0068] The memory 401 can include a high-speed RAM (Random Access Memory) memory, and can also include a nonvolatile memory, such as at least one disk memory.

[0069] If the memory 401, the processor 402 and the communication interface 403 are independently implemented, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and complete communication between each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 4 In the figure, only one thick line is used to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0070] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can complete communication between each other through an internal interface.

[0071] The processor 402 can be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement one or more embodiments of the present application.

[0072] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the automatic lane changing data feedback method as above.

[0073] In the description of the application, reference to "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" etc. means that a particular feature, structure, material or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. The illustrative appearances of the above-mentioned terms in various places in the specification are not necessarily referred to the same embodiment or example. Moreover, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples. Furthermore, in non-contradictory cases, those skilled in the art can combine and combine the features described in different embodiments or examples and the features of different embodiments or examples in the description.

[0074] In addition, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically limited.

[0075] Any process or method descriptions or descriptions of the flow diagrams in the flow charts described herein, or otherwise described herein, can be understood as representing the steps of the code modules, segments, or portions for implementing the custom logic functions or processes, and the preferred embodiments of the application include additional or fewer steps, in different orders, including use of hardware or software counter-parts in place of one or more of the steps as is well understood by those skilled in the art. The various steps or methods can be embodied in machine-executable code, which can create an execution environment on a processor, which when executed, implements the steps or functions.

[0076] It should be understood that portions of the application can be implemented in hardware, software, firmware, or combinations thereof. In the above embodiments, the N steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As in another embodiment, if implemented in hardware, any of the following technologies known in the art or their combinations can be used: discrete logic circuit with logic gates for implementing logic functions on data signals, application specific integrated circuit with appropriate combination logic gates, programmable gate array, field programmable gate array, etc.

[0077] Those skilled in the art of the art can understand that all or part of the steps carried out by the above-mentioned embodiment method can be completed by a program instructing the relevant hardware, and the program can be stored in a computer readable storage medium. The program, when executed, includes one of the steps of the method embodiment or a combination thereof.

[0078] Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary, and are not to be interpreted as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A method for re-annotation of automatic lane change data, characterized in that, The method comprises the following steps: obtaining real vehicle test data of a vehicle and analyzing the real vehicle test data to obtain to-be-tested scene data; determining a to-be-annotated signal according to the to-be-tested scene data, and compiling a data annotation algorithm according to the to-be-tested scene data and the to-be-annotated signal based on a preset automatic lane changing strategy; and inputting the data annotation algorithm into a preset playback tool for data playback, and obtaining a lane changing state of a driver triggering a lane changing process in a playback process to generate an annotation result according to the lane changing state; the preset automatic lane changing strategy is: controlling the lane changing state of a target vehicle to be a lane changing activation waiting state; judging whether the target vehicle receives a lane changing instruction, and when the lane changing instruction is received, judging whether the target vehicle turns on a turn signal and triggers a lane changing action corresponding to the turn signal; if the target vehicle turns on the turn signal and triggers the lane changing action corresponding to the turn signal, the lane changing state of the target vehicle is switched from the lane changing activation waiting state to a lane changing delay state, and when the target vehicle does not have a preset lane changing inhibition condition, the target vehicle is switched from the lane changing delay state to a lane changing activation state, and the lane changing action is performed, otherwise, the lane changing action of the target vehicle is exited; after generating the annotation result according to the lane changing state signal value, further comprising: obtaining a recurring fault point from the annotation result; correcting the to-be-tested scene data according to the recurring fault point, and determining a to-be-annotated signal based on the corrected to-be-tested scene data as new to-be-tested scene data until the recurring fault point does not exist in the annotation result.

2. The method of claim 1, wherein, The analysis of the real vehicle test data to obtain the to-be-tested scene data comprises: performing data visualization processing on the real vehicle test data to obtain visualized test data; based on a current road test fault time point signal, analyzing the visualized test data to obtain the to-be-tested scene data.

3. A device for automatically annotating data of a lane change, characterized in that comprise: an acquisition module for acquiring real vehicle test data of a vehicle and analyzing the real vehicle test data to obtain to-be-tested scene data; a compiling module for determining a to-be-annotated signal according to the to-be-tested scene data, and compiling a data annotation algorithm according to the to-be-tested scene data and the to-be-annotated signal based on a preset automatic lane changing strategy; and a generation module for inputting the data annotation algorithm into a preset playback tool for data playback, and obtaining a lane changing state of a driver triggering a lane changing process in a playback process to generate an annotation result according to the lane changing state; the compiling module is specifically used for: controlling the lane changing state of a target vehicle to be a lane changing activation waiting state; judging whether the target vehicle receives a lane changing instruction, and when the lane changing instruction is received, judging whether the target vehicle turns on a turn signal and triggers a lane changing action corresponding to the turn signal; If the target vehicle turns on the turn light and triggers a lane changing action corresponding to the turn light, the lane changing state of the target vehicle is switched from a lane changing activation waiting state to a lane changing delay state, and when the target vehicle does not have a preset lane changing inhibition condition, the target vehicle is switched from the lane changing delay state to a lane changing activation state, and a lane changing action is performed, otherwise, the lane changing action of the target vehicle is exited; After the generation module generates the feedback result according to the lane changing state, the generation module is specifically configured to: Obtain a recurring fault point from the feedback result; According to the recurring fault point, the to-be-tested scene data is corrected, and the corrected to-be-tested scene data is used as new to-be-tested scene data to determine a to-be-feedback signal until there is no recurring fault point in the feedback result.

4. The apparatus of claim 3, wherein, The acquisition module is specifically configured to: Perform data visualization processing on the real vehicle test data to obtain visualized test data; Based on a current road test fault time point signal, the visualized test data is analyzed to obtain the to-be-tested scene data.

5. An electronic device, comprising: comprise a memory, a processor; The processor runs a program corresponding to executable program code stored in the memory by reading the executable program code, to implement the automatic lane changing data feedback method of any one of claims 1-2.

6. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 5. The program is executed by the processor to implement the automatic lane changing data feedback method of any one of claims 1-2.

Images