Construction test method, system and medium for fusion positioning test scenario library

Abstract

The present invention discloses a construction and testing method, system and medium for a fusion positioning test scenario library, the method comprising the following steps: obtaining collected data for each unit section of a road to be tested, the collected data comprising perception camera data and fusion positioning accuracy data; obtaining time periods when the fusion positioning accuracy data meets preset accuracy conditions; obtaining time periods of different classification scenarios based on the perception camera data; obtaining fusion positioning accuracy data and classification scenarios corresponding to each time period based on all the time periods; constructing a test scenario library based on the fusion positioning accuracy data and classification scenarios corresponding to each time period; and by constructing the test scenario library, reducing the cost and cycle of actual vehicle mileage testing of the fusion positioning algorithm before application.

Description

Technical Field

[0001] The present invention relates to the field of high-precision positioning technology for autonomous driving, and in particular to a construction and testing method, system, and medium for a fusion positioning test scenario library. Background Art

[0002] Fusion positioning is a positioning algorithm based on multi-source sensors (perception cameras, GPS, IMU), vector high-precision maps, and vehicle body CAN. It can meet the multi-scenario high-precision positioning needs of autonomous vehicles. High-precision positioning systems used in autonomous vehicles require extensive mileage and scenario testing before they can be used in mass-produced vehicles.

[0003] Scenarios such as lighting, weather, and actual road conditions can affect the results of the perception camera. Scenarios such as surrounding environmental conditions, driving areas, vehicle driving conditions, and road conditions can affect the output of GPS or IMU positioning results. Road construction, etc. can affect the accuracy of high-precision map output information. It can be seen that the scenarios that affect the final output of fusion positioning are diverse and complex; therefore, the testing method based on actual vehicle mileage scenarios has the disadvantages of long cycle, low efficiency, and high cost.

[0004] Based on this, it is necessary to build a test scenario library to reduce the cost and cycle of real vehicle mileage scenario testing before the application of the fusion positioning algorithm. Summary of the Invention

[0005] The present invention provides a method, system and medium for constructing a fusion positioning test scenario library. By constructing the test scenario library, the cost and cycle of actual vehicle mileage testing of the fusion positioning algorithm before application are reduced.

[0006] In a first aspect, a method for constructing a fusion positioning test scenario library is provided, comprising the following steps:

[0007] Acquire collected data for each unit section of the road to be tested, wherein the collected data includes perception camera data and fused positioning accuracy data;

[0008] Obtaining each time period when the fused positioning accuracy data meets the preset accuracy conditions;

[0009] Obtaining time periods of different classification scenes based on the perception camera data;

[0010] According to all the time periods, obtain the fused positioning accuracy data and classification scenarios corresponding to each time period;

[0011] A test scenario library is constructed based on the fused positioning accuracy data and classification scenarios corresponding to each time period.

[0012] According to the first aspect, in a first possible implementation manner of the first aspect, the step of “obtaining time periods when the fused positioning accuracy data meets a preset accuracy condition” specifically includes the following steps:

[0013] Obtaining each time period when the fused positioning accuracy data is greater than an accuracy threshold; or,

[0014] Obtain each time period when the fused positioning accuracy data is less than an accuracy threshold.

[0015] According to the first possible implementation manner of the first aspect, in the second possible implementation manner of the first aspect, the step of “obtaining, according to all the time periods, fused positioning accuracy data and classification scenarios corresponding to each time period” specifically includes the following steps:

[0016] All the time periods are sorted according to their length, and the fused positioning accuracy data and classification scenarios corresponding to each time period are obtained.

[0017] According to the second possible implementation manner of the first aspect, in the third possible implementation manner of the first aspect, the step of “building a test scenario library according to the fused positioning accuracy data and classification scenarios corresponding to each time period” specifically includes the following steps:

[0018] The collected data includes GPS data, IMU data, vehicle body CAN data and high-precision map data;

[0019] Generate labels for the fused positioning accuracy data and classified scenes corresponding to each time period, and generate scene label fragments for the GPS data, IMU data, vehicle CAN data, high-precision map data and labels corresponding to each time period;

[0020] A test scene library is constructed based on all the scene label fragments.

[0021] According to the third possible implementation manner of the first aspect, in the fourth possible implementation manner of the first aspect, after the step of “building a test scenario library according to the fused positioning accuracy data and classification scenarios corresponding to each time period”, the following steps are specifically included:

[0022] Obtain scenario testing requirements;

[0023] Selecting corresponding scene label segments from the test scene library according to the scene test requirements;

[0024] Control the test tool to test the selected scene label segment.

[0025] In a second aspect, a test system for building a fusion positioning test scenario library is provided, including:

[0026] A data acquisition module is used to acquire the collected data of each unit section of the road to be tested, wherein the collected data includes perception camera data and fusion positioning accuracy data;

[0027] A positioning accuracy time period module, which is in communication with the data acquisition module and is used to obtain each time period when the fused positioning accuracy data is greater than an accuracy threshold;

[0028] A classification scene time period module, which is in communication with the data acquisition module and is used to obtain time periods of different classification scenes based on the perception camera data;

[0029] A time period corresponding integration module is in communication with both the positioning accuracy time period module and the classification scene time period module, and is used to obtain the fused positioning accuracy data and classification scene corresponding to each time period based on all the time periods;

[0030] The test scenario construction module is in communication with the integration module corresponding to the time period and is used to construct a test scenario library based on the fused positioning accuracy data and classification scenarios corresponding to each time period.

[0031] According to the second aspect, in a first possible implementation of the second aspect, the boundary module and the time period corresponding integration module are used to sort all the time periods according to time size and obtain the fused positioning accuracy data and classification scenarios corresponding to each time period.

[0032] According to the first possible implementation method of the second aspect, in the second possible implementation method of the second aspect, the collected data includes GPS data, IMU data, vehicle body CAN data and high-precision map data; the test scenario construction module is used to generate labels for the fused positioning accuracy data corresponding to each time period and the classification scene, and to generate scene label fragments for the GPS data, IMU data, vehicle body CAN data, high-precision map data and labels corresponding to each time period; and a test scenario library is constructed based on all the scene label fragments.

[0033] According to the second possible implementation method of the second aspect, in the third possible implementation method of the second aspect, it also includes a test module that is communicatively connected to the test scenario construction module, and the test module is used to obtain scenario test requirements; select corresponding scenario label fragments in the test scenario library according to the scenario test requirements; and control the test tool to test the selected scenario label fragments.

[0034] According to a third aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the test method for constructing a fusion positioning test scenario library as described in any one of the above items is implemented.

[0035] Compared with the existing technology, the advantages of the present invention are as follows: Since the current fusion positioning algorithm requires a large amount of actual vehicle mileage testing before commercial use in self-driving cars, which is costly and time-consuming, by building a test scenario library, the cost and cycle of actual vehicle mileage testing of the fusion positioning algorithm before application can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flow chart of an embodiment of a method for constructing a fusion positioning test scenario library according to the present invention;

[0037] Figure 2 This is a flow chart of another embodiment of a method for constructing a fusion positioning test scenario library according to the present invention;

[0038] Figure 3 It is a structural diagram of a test system for building a fusion positioning test scenario library of the present invention. Description of the drawings:

[0040] 100. Construction test system of integrated positioning test scenario library; 110. Data acquisition module; 120. Positioning accuracy time period module; 130. Classification scenario time period module; 140. Time period corresponding integration module; 150. Test scenario construction module; 160. Test module. DETAILED DESCRIPTION

[0041] Reference will now be made in detail to specific embodiments of the present invention, examples of which are illustrated in the accompanying drawings. Although the present invention will be described in conjunction with specific embodiments, it will be understood that the present invention is not intended to be limited to those embodiments. On the contrary, it is intended to cover variations, modifications, and equivalents within the spirit and scope of the present invention as defined by the appended claims. It should be noted that the method steps described herein can be implemented by any functional block or functional arrangement, and any functional block or functional arrangement can be implemented as a physical entity or a logical entity, or a combination of the two.

[0042] In order to enable those skilled in the art to better understand the present invention, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0043] Note: The following example is only a specific example and is not intended to limit the embodiments of the present invention to the following specific steps, values, conditions, data, sequence, etc. Those skilled in the art can apply the concepts of the present invention to construct more embodiments not described in this specification by reading this specification.

[0044] See also Figure 1 As shown, an embodiment of the present invention provides a method for constructing a fusion positioning test scenario library, which is characterized by comprising the following steps:

[0045] S100, acquiring collected data for each unit section of the road to be measured, wherein the collected data includes perception camera data and fused positioning accuracy data;

[0046] S200, obtaining each time period when the fused positioning accuracy data meets a preset accuracy condition;

[0047] S300, obtaining time periods of different classification scenes according to the perception camera data;

[0048] S400, obtaining fused positioning accuracy data and classification scenarios corresponding to each time period according to all the time periods;

[0049] S500: Build a test scenario library based on the fused positioning accuracy data and classification scenarios corresponding to each time period.

[0050] Preferably, in another embodiment of the present application, the step of “S200, obtaining time periods when the fused positioning accuracy data meets a preset accuracy condition” specifically includes the following steps:

[0051] Obtaining each time period when the fused positioning accuracy data is greater than an accuracy threshold; or,

[0052] Obtain each time period when the fused positioning accuracy data is less than an accuracy threshold.

[0053] Specifically, in this embodiment, the current fusion positioning algorithm requires extensive on-vehicle mileage testing before commercial use in self-driving cars, which is costly and time-consuming. Therefore, it is necessary to build a test scenario library for the fusion positioning algorithm to reduce the cost and time of on-vehicle mileage testing before application.

[0054] Specifically, S100 has developed a nationwide plan for high-speed scene fusion positioning and data collection, with a total planned mileage of L (km). The actual vehicle is equipped with a fusion positioning system. The hardware includes a perception camera, GPS module, IMU module, industrial camera, development board, CAN signal acquisition device, and other acquisition equipment to collect data on the roads to be tested.

[0055] The collected data mainly includes fused positioning accuracy data, perception camera data, vehicle body CAN data, GPS data, IMU data, perception camera data and software output high-precision map data. The data is stored in LCM format. Each time a route is collected, a piece of log data (unit data of a unit section) is saved. The data is saved on the hard disk. After the collection is completed, the hard disk stores log1, log2, ..., logN. The test bench loads log1 based on the playback tool to extract the above data.

[0056] S200, perform accuracy analysis on the fused positioning progress data to obtain the fused positioning accuracies r1....rN at t1....tN (seconds) in log1 with a duration of T1. Define an accuracy threshold R, record the start and end timestamps tn1’ and tn2’ of the period when the accuracy r > R, and obtain the periods (tn1’, tn2’), (tn3’, tn4’)... in data log1 where r > R.

[0057] S300, play back the video data of the perception camera. When the weather (sunny, rainy, foggy, snowy, etc.), road surface material (asphalt, cement, etc.), lighting condition (bright light, dim light), lane line condition (clear, slightly worn, severely worn), road condition ((dry, wet), (flat, uneven)), road construction (under construction, not under construction), road type (ordinary highway, ramp, toll station), and vehicle surrounding occlusion condition ((tunnel, non - tunnel), (mountainous area, non - mountainous area), (elevated occlusion area, non - elevated occlusion area)) change (where the change in road type can be automatically obtained from the map output information, and other scene changes are subjectively judged by humans based on video data), record the change time point tn”, and obtain different classified scenes within each period of t1, tn1”, tn2”...tN.

[0058] Finally, according to all the above - mentioned periods, obtain the fused positioning accuracy data and classified scenes corresponding to each period; then, according to the fused positioning accuracy data and classified scenes corresponding to each period, construct a test scenario library; thus, a test scenario library can be constructed to reduce the real - vehicle mileage test cost and cycle before the application of the fused positioning algorithm.

[0059] Preferably, in another embodiment of the present application, the step of “S400, according to all the above - mentioned periods, obtain the fused positioning accuracy data and classified scenes corresponding to each period” specifically includes the following steps:

[0060] Sort all the above - mentioned periods in ascending order of time, and obtain the fused positioning accuracy data and classified scenes corresponding to each period.

[0061] Specifically, in this embodiment, based on the periods (tn1’, tn2’...) greater than the accuracy threshold and the scene change time points (tn1”, tn2”...), perform time sorting to obtain the fused positioning accuracy data and classified scenes corresponding to each period of t1, tn, tn2...tN.

[0062] For example, if the scene label for t1 to tn1 is r < R, and the scene is (sunny, asphalt road, dim light, clear lane lines, dry road, flat road, not under construction, ordinary highway, non - tunnel, mountainous area, non - elevated occlusion area), it is represented as label [a1].

[0063] Preferably, in another embodiment of the present application, the step of “S500, constructing a test scenario library according to the fused positioning accuracy data and classification scenarios corresponding to each time period” specifically includes the following steps:

[0064] The collected data includes GPS data, IMU data, vehicle body CAN data and high-precision map data;

[0065] Generate labels for the fused positioning accuracy data and classified scenes corresponding to each time period, and generate scene label fragments for the GPS data, IMU data, vehicle CAN data, high-precision map data and labels corresponding to each time period;

[0066] A test scene library is constructed based on all the scene label fragments.

[0067] Specifically, in this embodiment, all time period labels in log1 are sorted, namely [a1], [a2], [a3]...; the fused positioning accuracy data corresponding to each time period is corresponding to the classification scene to generate a label, and the GPS data, IMU data, vehicle body CAN data, high-precision map data and labels corresponding to each time period are corresponding to generate a scene label fragment, that is, the scene label fragment P1 (label [a1] + log1 (t1 ~ tn1)), P2 (label [a2] + log1 (tn1 ~ tn2))... is obtained, and other logs are analyzed in the same way, and finally N scene label fragments are obtained; finally, the scene label fragments are stored in a shared memory, and the scene data can be downloaded through scene label query, and the test scene library is now constructed.

[0068] Preferably, in another embodiment of the present application, after the step of “S500, constructing a test scenario library according to the fused positioning accuracy data and classification scenarios corresponding to each time period”, the following steps are specifically included:

[0069] Obtain scenario testing requirements;

[0070] Selecting corresponding scene label segments from the test scene library according to the scene test requirements;

[0071] Control the test tool to test the selected scene label segment.

[0072] Specifically, in this embodiment, when an iterative version of the fused positioning algorithm is released, a corresponding scene label segment is selected from the test scene library based on the scenario testing requirements. This means that data is downloaded from the shared memory, and the testing tool is controlled to test the selected scene label segment and verify the test results. For example, this version of the algorithm improves the scenarios in the previous version where the accuracy is greater than R in ramp and low-light scenarios. Based on the ramp, low-light, and r>R scene labels, the scene label segment is downloaded from the test scene library and injected into the tool for iterative testing. The tool verifies whether the fused positioning accuracy is greater than R, thereby determining whether the iterative version solves the problem in this scenario.

[0073] See also Figure 2 As shown, the embodiment of the present invention also provides a method for constructing a test scenario library for fusion positioning test, and the specific steps are as follows:

[0074] 1. Develop a nationwide high-speed scene fusion positioning acquisition plan with a total planned mileage of L (km);

[0075] 2. The actual vehicle is equipped with a fusion positioning system. The hardware includes a perception camera, GPS module, IMU module, industrial camera, development board, CAN signal acquisition device and other acquisition equipment to collect data on the road to be tested. The collected data mainly includes fusion positioning accuracy data, perception camera data, vehicle body CAN data, GPS data, IMU data, perception camera data and software-output high-precision map data.

[0076] 3. The data is stored in LCM format. Each time a route is collected, a piece of log data (unit data of a unit section) is saved. The data is saved in the hard disk. After the collection is completed, the hard disk stores log1, log2, ..., logN.

[0077] 4. Data preprocessing: The rig loads log1 based on the playback tool and extracts the above data.

[0078] 5. Perform accuracy analysis on the fused positioning progress data to obtain the fused positioning accuracy r1...rN for t1...tN (seconds) in the log1 of the duration T1. Define the accuracy threshold R, record the start and end timestamps tn1' and tn2' of the time period where the accuracy r>R, and obtain the time periods (tn1', tn2'), (tn3', tn4')... where r>R in the log1 of the data.

[0079] 6. Replay the perception camera video data. When the scene changes (road type changes can be automatically detected from the map output information, and other scene changes are manually judged based on video data), record the change time point tn", and obtain different classification scenes in each time period t1, tn1", tn2", ... tN.

[0080] 7. Based on the time periods greater than the accuracy threshold (tn1', tn2'...) and the scene change time points (tn1", tn2"...), time sorting is performed to obtain the fused positioning accuracy data and classification scenes corresponding to each time period t1, tn1, tn2...tN.

[0081] 8. Arrange all time period labels in log1, namely [a1], [a2], [a3]...

[0082] 9. Generate labels for the fused positioning accuracy data and classified scenarios corresponding to each time period, and generate scene label fragments corresponding to the GPS data, IMU data, vehicle CAN data, high-precision map data and labels corresponding to each time period, that is, obtain scene label fragments P1(label[a1]+log1(t1~tn1)), P2(label[a2]+log1(tn1~tn2))..., and analyze other logs in the same way. Finally, obtain N scene label fragments, and the test scene library is constructed.

[0083] 10. When the fusion positioning algorithm needs to be released in an iterative version, the corresponding scene label fragment is selected from the test scene library based on the scene test requirements, that is, data is downloaded from the shared memory, and the test tool is controlled to test the selected scene label fragment to verify the test results.

[0084] See also Figure 3 As shown, the embodiment of the present invention further provides a construction test system 100 for a fusion positioning test scenario library, comprising: a data acquisition module 110, a positioning accuracy time period module 120, a classification scenario time period module 130, a time period corresponding integration module 140, a test scenario construction module 150 and a test module 160;

[0085] The data acquisition module 110 is used to acquire the collected data of each unit section of the road to be tested, wherein the collected data includes the perception camera data and the fusion positioning accuracy data;

[0086] A positioning accuracy time period module 120 is in communication with the data acquisition module 110 and is configured to acquire time periods when the fused positioning accuracy data is greater than an accuracy threshold;

[0087] The classification scene time period module 130 is in communication with the data acquisition module 110 and is configured to acquire time periods of different classification scenes based on the perception camera data;

[0088] The time period corresponding integration module 140 is in communication with the positioning accuracy time period module 120 and the classification scene time period module 130, and is used to obtain the fused positioning accuracy data and classification scene corresponding to each time period according to all the time periods; and

[0089] The test scenario construction module 150 is in communication with the time period corresponding integration module 140 and is used to construct a test scenario library based on the fused positioning accuracy data and classification scenarios corresponding to each time period.

[0090] The time period corresponding integration module 140 is used to sort all the time periods according to their length, and obtain the fused positioning accuracy data and classification scenarios corresponding to each time period.

[0091] The collected data includes GPS data, IMU data, vehicle body CAN data and high-precision map data; the test scenario construction module 150 is used to generate labels for the fused positioning accuracy data corresponding to each time period and the classification scene, and to generate scene label fragments for the GPS data, IMU data, vehicle body CAN data, high-precision map data and labels corresponding to each time period; a test scenario library is constructed based on all the scene label fragments.

[0092] It also includes a test module 160 that is communicatively connected to the test scenario construction module 150, and the test module 160 is used to obtain scenario test requirements; select corresponding scenario label segments in the test scenario library according to the scenario test requirements; and control the test tool to test the selected scenario label segments.

[0093] Because current fusion positioning algorithms require extensive real-world mileage testing before commercial use in self-driving cars, which is costly and time-consuming, this invention builds a test scenario library to reduce the cost and time required for real-world mileage testing of fusion positioning algorithms before their application.

[0094] Specifically, this embodiment corresponds one-to-one to the above method embodiment, and the functions of each module have been described in detail in the corresponding method embodiment, so they will not be repeated here.

[0095] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, all or part of the method steps of the above method are implemented.

[0096] The present invention implements all or part of the process in the above method, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0097] Based on the same inventive concept, an embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program running on the processor, and when the processor executes the computer program, all or part of the method steps in the above method are implemented.

[0098] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of a computer device, connecting all parts of the entire computer device using various interfaces and lines.

[0099] The memory can be used to store computer programs and / or modules. The processor implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created based on the use of the mobile phone (such as audio data, video data, etc.). In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0100] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, servers, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage) containing computer-usable program code.

[0101] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), servers, and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0102] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0104] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for constructing a fusion positioning test scenario library, characterized in that: The following steps are involved: Acquire collected data for each unit section of the road to be tested, wherein the collected data includes perception camera data and fused positioning accuracy data; Obtaining each time period when the fused positioning accuracy data meets the preset accuracy conditions; Obtaining time periods of different classification scenes based on the perception camera data; According to all the time periods, obtain the fused positioning accuracy data and classification scenarios corresponding to each time period; A test scenario library is constructed based on the fused positioning accuracy data and classification scenarios corresponding to each time period.

2. The method for constructing a fusion positioning test scenario library according to claim 1, wherein: The step of "obtaining each time period when the fused positioning accuracy data meets the preset accuracy condition" specifically includes the following steps: Obtaining each time period when the fused positioning accuracy data is greater than an accuracy threshold; or, Obtain each time period when the fused positioning accuracy data is less than an accuracy threshold.

3. The method for constructing a fusion positioning test scenario library according to claim 1, wherein: The step of "obtaining fused positioning accuracy data and classification scenarios corresponding to each time period according to all the time periods" specifically includes the following steps: All the time periods are sorted according to their length, and the fused positioning accuracy data and classification scenarios corresponding to each time period are obtained.

4. The method for constructing a fusion positioning test scenario library according to claim 1, wherein: The step of "building a test scenario library based on the fused positioning accuracy data and classification scenarios corresponding to each time period" specifically includes the following steps: The collected data includes GPS data, IMU data, vehicle body CAN data and high-precision map data; Generate labels for the fused positioning accuracy data and classified scenes corresponding to each time period, and generate scene label fragments for the GPS data, IMU data, vehicle CAN data, high-precision map data and labels corresponding to each time period; A test scene library is constructed based on all the scene label fragments.

5. The method for constructing a fusion positioning test scenario library according to claim 4, wherein: After the step of "building a test scenario library based on the fused positioning accuracy data and classification scenarios corresponding to each time period", the following steps are specifically included: Obtain scenario testing requirements; Selecting corresponding scene label segments from the test scene library according to the scene test requirements; Control the test tool to test the selected scene label segment.

6. A construction and testing system for a fusion positioning test scenario library, characterized in that: include: A data acquisition module is used to acquire the collected data of each unit section of the road to be tested, wherein the collected data includes perception camera data and fusion positioning accuracy data; A positioning accuracy time period module, which is in communication with the data acquisition module and is used to obtain each time period when the fused positioning accuracy data is greater than an accuracy threshold; A classification scene time period module, which is in communication with the data acquisition module and is used to obtain time periods of different classification scenes based on the perception camera data; A time period corresponding integration module is in communication with both the positioning accuracy time period module and the classification scene time period module, and is used to obtain the fused positioning accuracy data and classification scene corresponding to each time period based on all the time periods; as well as, The test scenario construction module is in communication with the integration module corresponding to the time period and is used to construct a test scenario library based on the fused positioning accuracy data and classification scenarios corresponding to each time period.

7. The system for constructing a fusion positioning test scenario library according to claim 6, wherein: The time period corresponds to an integration module, which is used to sort all the time periods according to their length and obtain the fused positioning accuracy data and classification scenarios corresponding to each time period.

8. The system for constructing a fusion positioning test scenario library according to claim 6, wherein: The collected data includes GPS data, IMU data, vehicle body CAN data and high-precision map data; the test scenario construction module is used to generate labels corresponding to the fused positioning accuracy data and classification scenarios corresponding to each time period, and to generate scene label fragments corresponding to the GPS data, IMU data, vehicle body CAN data, high-precision map data and labels corresponding to each time period; a test scenario library is constructed based on all the scene label fragments.

9. The system for constructing a fusion positioning test scenario library according to claim 8, wherein: It also includes a test module that is communicatively connected to the test scenario construction module, and the test module is used to obtain scenario test requirements; select corresponding scenario label segments in the test scenario library according to the scenario test requirements; and control the test tool to test the selected scenario label segments.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for constructing a test scenario library of a fusion positioning test according to any one of claims 1 to 5 is implemented.

Images