Testing method and device for autonomous driving high-precision map software

Abstract

The present invention provides a method and device for testing high-precision map software for autonomous driving, wherein the method includes: determining a road-level driving position signal of a simulated vehicle; obtaining high-precision map data of the simulated vehicle on the road-level driving position signal; obtaining a lane-level positioning signal of the simulated vehicle based on the high-precision map data and the road-level driving position signal; inputting the lane-level positioning signal and high-precision map data into the autonomous driving high-precision map software, and obtaining real-time feedback data from the autonomous driving high-precision map software; and generating diagnostic results for the autonomous driving high-precision map software based on the real-time feedback data and / or the high-precision map data. The embodiments of the present invention solve the technical problem of low efficiency in diagnosing the use of high-precision map data in autonomous driving tests using real vehicles in related technologies. Actual high-precision map data can be obtained in the field without the need for on-site verification of high-precision map data, thus avoiding the need for extensive field testing that consumes manpower and material resources.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving testing, and in particular to a testing method and device for autonomous driving high-precision map software. Background Art

[0002] In related technologies, high-precision maps are considered a crucial component of perception in assisted / autonomous driving. High-precision maps contain highly detailed information about road features, such as the color, line type, lane connection, and distribution of lane lines, as well as surrounding elements like guide lines, traffic lights, and traffic signs. By reading high-precision maps, this priori perception information is obtained, thus compensating for information gaps in beyond-visual-range perception. Clearly, the correct loading of high-precision maps and the accuracy and stability of environmental reconstruction using high-precision map elements play a crucial role in the stability and safety of assisted / autonomous driving. Therefore, it is particularly important for autonomous driving programs to accurately and stably identify map elements while the car is driving, as well as to process elements that may appear in high-precision maps for each scenario.

[0003] In related technologies, assisted driving / autonomous driving uses high-precision map data provided by map vendors to conduct program stability tests and high-precision map tests, which are carried out through nationwide coverage tests using multiple real vehicles. However, due to the wide coverage of high-precision maps, differences in regional elements of road construction, and complex scenarios, the diagnosis and troubleshooting of problems in high-precision map applications consumes a lot of time and manpower costs. At the same time, the data feedback from real vehicle tests has shortcomings such as time difference and missing information transmission.

[0004] For the above-mentioned problems existing in related technologies, no efficient and accurate solutions have been found yet. Summary of the Invention

[0005] The present invention provides a method and device for testing high-precision map software for autonomous driving to solve technical problems in related technologies.

[0006] According to one embodiment of the present invention, a testing method for autonomous driving high-precision map software is provided, comprising: determining a road-level driving position signal of a simulated vehicle; obtaining high-precision map data of the simulated vehicle on the road-level driving position signal, wherein the high-precision map data is autonomous driving guidance data for the vehicle; obtaining a lane-level positioning signal of the simulated vehicle based on the high-precision map data and the road-level driving position signal; inputting the lane-level positioning signal and the high-precision map data into autonomous driving high-precision map software, and obtaining real-time feedback data of the autonomous driving high-precision map software; and generating a diagnostic result of the autonomous driving high-precision map software based on the real-time feedback data and / or high-precision map data.

[0007] Furthermore, determining the road-level driving position signal of the simulated vehicle includes: generating a road-level navigation path based on a geographic information system, wherein the road-level navigation path includes a set of road segment coordinate points formed by passing through several points from a departure point to a destination; obtaining preset inertial navigation parameters of the road-level navigation path, and using the preset inertial navigation parameters and the set of coordinate points to obtain a position simulation data source; based on the position simulation data source, outputting position information in sequence and at a fixed frequency to obtain the road-level driving position signal of the simulated vehicle in real time.

[0008] Furthermore, obtaining the lane-level positioning signal of the simulated vehicle based on the high-precision map data and the road-level driving position signal includes: obtaining a lane set containing the coordinate position of the road-level driving position signal from the high-precision map data; extracting a coordinate point string of the lane centerlines of all lanes in the lane set; locating the target lane centerline closest to the coordinate position of the road-level driving position signal based on the coordinate point string; and determining the lane where the target lane centerline is located as the lane-level positioning signal of the simulated vehicle.

[0009] Furthermore, locating the target lane centerline closest to the coordinate position of the road-level driving position signal based on the coordinate point string includes: calculating the perpendicular distance from the coordinate position of the road-level driving position signal to the coordinate point string for the lane centerline of each lane in the lane set; and selecting the lane centerline corresponding to the coordinate point string with the shortest perpendicular distance as the target lane centerline.

[0010] Furthermore, obtaining the lane-level positioning signal of the simulated vehicle based on the high-precision map data and the road-level driving position signal includes: reading lane change feature information from the attribute information of the lane-level positioning signal of the previous frame of the road-level driving position signal, wherein the lane change feature information is used to characterize the influencing factors of the lane change; parsing the lane change feature information to determine the changed lane of the previous frame of the lane-level positioning signal; using the lane centerline of the changed lane to calculate the projection point of the coordinate position of the road-level driving position signal to the lane centerline of the changed lane; and using the coordinates of the projection point to determine the lane-level positioning signal.

[0011] Furthermore, generating a diagnostic result of the autonomous driving high-precision map software based on the real-time feedback data includes: analyzing the degree of impact of the real-time feedback data on the business end, and analyzing the output module of the real-time feedback data; generating an abnormality level matching the degree of impact, and searching for an abnormality type matching the output module; and determining the first diagnostic result of the autonomous driving high-precision map software using the abnormality level and the abnormality type.

[0012] Furthermore, after determining the first diagnostic result of the autonomous driving high-precision map software based on the abnormality level and the abnormality type, the method also includes: associating the first diagnostic result with the lane-level positioning signal, and displaying the point information of the first diagnostic result in the reference layer according to the lane-level positioning signal; and generating a diagnostic result distribution map of the reference layer based on the point information.

[0013] Furthermore, after generating a diagnosis result distribution map of the reference layer based on the point information, the method also includes: for each diagnosis result, determining the geographical location of the diagnosis result according to the diagnosis result distribution map; generating a scene label based on the geographical location, wherein the scene label includes at least one of the following: elevated scene, tunnel scene, ramp scene, and highway interchange scene; and adding the scene label to the attribute information of the corresponding diagnosis result.

[0014] Furthermore, after adding the scene label to the attribute information of the corresponding diagnostic result, the method also includes: for each scene category, counting the total number of all diagnostic results in the corresponding scene category, and counting the first number of target abnormality levels and the second number of target abnormality types in the corresponding scene category; calculating the first abnormality ratio of the target abnormality level based on the first number and the total number, and calculating the second abnormality ratio of the target abnormality type based on the second number and the total number; and using the first abnormality ratio and the second abnormality ratio to generate the scene coverage quality of the autonomous driving high-precision map software in the corresponding scene category.

[0015] Furthermore, generating the diagnostic result of the autonomous driving high-precision map software based on the high-precision map data includes: parsing the visual display elements of the high-precision map data, wherein the visual display elements include at least one of the following: lane line markings, lane line types, operation design domain (ODD) faults, lane speed limits, lane types, and lane curvatures; overlaying the visual display elements with a reference layer in a geographic information system, and calculating the accuracy of the high-precision map data based on the matching degree between the visual display elements and the reference layer, and determining the accuracy as the second diagnostic result of the autonomous driving high-precision map software.

[0016] According to another embodiment of the present invention, a testing device for autonomous driving high-precision map software is provided, comprising: a determination module for determining a road-level driving position signal of a simulated vehicle; a first acquisition module for acquiring high-precision map data of the simulated vehicle on the road-level driving position signal, wherein the high-precision map data is autonomous driving guidance data of the vehicle; a second acquisition module for acquiring a lane-level positioning signal of the simulated vehicle based on the high-precision map data and the road-level driving position signal; a third acquisition module for inputting the lane-level positioning signal and the high-precision map data into the autonomous driving high-precision map software and acquiring real-time feedback data of the autonomous driving high-precision map software; and a generation module for generating a diagnostic result of the autonomous driving high-precision map software based on the real-time feedback data and / or high-precision map data.

[0017] Furthermore, the determination module includes: a first generation unit, used to generate a road-level navigation path based on a geographic information system, wherein the road-level navigation path includes a set of road segment coordinate points formed by passing through several points from a departure point to a destination; a processing unit, used to obtain preset inertial navigation parameters of the road-level navigation path, and use the preset inertial navigation parameters and the set of coordinate points to obtain a position simulation data source; an output unit, used to output position information in sequence and at a fixed frequency based on the position simulation data source, and obtain the road-level driving position signal of the simulated vehicle in real time.

[0018] Furthermore, the second acquisition module includes: an acquisition unit for acquiring a lane set containing the coordinate position of the road-level driving position signal from the high-precision map data; an extraction unit for extracting a coordinate point string of the lane centerlines of all lanes in the lane set; a positioning unit for locating the target lane centerline closest to the coordinate position of the road-level driving position signal based on the coordinate point string; and a first determination unit for determining the lane where the target lane centerline is located as the lane-level positioning signal of the simulated vehicle.

[0019] Furthermore, the positioning unit includes: a calculation subunit, which is used to calculate the vertical distance from the coordinate position of the road-level driving position signal to the coordinate point string of the lane centerline of each lane in the lane set; and a selection subunit, which is used to select the lane centerline corresponding to the coordinate point string with the shortest vertical distance as the target lane centerline.

[0020] Furthermore, the second acquisition module includes: a reading unit, used to read lane change feature information from the attribute information of the lane-level positioning signal of the previous frame of the road-level driving position signal, wherein the lane change feature information is used to characterize the influencing factors of the lane change; a parsing unit, used to parse the lane change feature information and determine the changed lane of the previous frame of the lane-level positioning signal; a calculation unit, used to calculate the projection point of the coordinate position of the road-level driving position signal to the lane centerline of the changed lane using the lane centerline of the changed lane; a second determination unit, used to determine the lane-level positioning signal using the coordinates of the projection point.

[0021] Furthermore, the generation module includes: a first parsing unit, used to parse the degree of impact of the real-time feedback data on the business end, and an output module for parsing the real-time feedback data; a processing unit, used to generate an abnormality level matching the degree of impact, and to search for an abnormality type matching the output module; a first determination unit, used to determine the first diagnostic result of the autonomous driving high-precision map software based on the abnormality level and the abnormality type.

[0022] Furthermore, the generation module also includes: a display unit, which is used to associate the first diagnostic result with the lane-level positioning signal after the determination unit determines the first diagnostic result of the autonomous driving high-precision map software based on the abnormality level and the abnormality type, and display the point information of the first diagnostic result in the reference layer according to the lane-level positioning signal; a generation unit, which is used to generate a diagnostic result distribution map of the reference layer based on the point information.

[0023] Furthermore, the generation module also includes: a second determination unit, which is used to determine, for each diagnosis result, the geographical location of the diagnosis result according to the diagnosis result distribution map after the generation unit generates the diagnosis result distribution map of the reference layer based on the point information; a first generation unit, which is used to generate a scene label based on the geographical location, wherein the scene label includes at least one of the following: an elevated scene, a tunnel scene, a ramp scene, and a highway interchange scene; and an adding unit, which is used to add the scene label to the attribute information of the corresponding diagnosis result.

[0024] Furthermore, the generation module also includes: a first calculation unit, which is used to count the total number of all diagnostic results in the corresponding scene category for each scene category after the adding unit adds the scene label to the attribute information of the corresponding diagnostic result, and count the first number of target abnormality levels and the second number of target abnormality types in the corresponding scene category; a second calculation unit, which is used to calculate the first abnormality ratio of the target abnormality level based on the first number and the total number, and calculate the second abnormality ratio of the target abnormality type based on the second number and the total number; a second generation unit, which is used to use the first abnormality ratio and the second abnormality ratio to generate the scene coverage quality of the autonomous driving high-precision map software in the corresponding scene category.

[0025] Furthermore, the generation module includes: a second parsing unit, used to parse the visual display elements of the high-precision map data, wherein the visual display elements include at least one of the following: lane line markings, lane line types, operational design domain (ODD) faults, lane speed limits, lane types, and lane curvatures; a third determination unit, used to overlay the visual display elements with a reference layer in a geographic information system, and calculate the accuracy of the high-precision map data based on the matching degree between the visual display elements and the reference layer, and determine the accuracy as the second diagnostic result of the autonomous driving high-precision map software.

[0026] According to another embodiment of the present invention, a testing device for autonomous driving high-precision map software is provided, including: a case management module for creating test scenario cases, managing test paths in the scenarios, marking test scenario labels, and recording case information of test cases; a scenario test path management module for managing test path data as units based on test scenario cases, and recording simulated positioning trajectory data generated by the path through the latitude and longitude coordinate space; a position simulation module for generating simulated positioning trajectory data by real-time interpolation according to a set frequency and sampling interval, and broadcasting the position data, and obtaining high-precision map data of the previous position from the autonomous driving high-precision map software; a data diagnosis module for diagnosing the output results of the autonomous driving high-precision map software using diagnostic rules, and diagnosing the diagnostic results according to the severity of the impact of the output results on the use of the business end, and dividing the diagnostic results into error levels; and diagnosing the diagnostic results according to the name of the output module. The results are classified; the classified and graded diagnostic results are associated with the spatial position of the simulated positioning to obtain the test diagnostic results with spatial position information; the map information visualization module is used to display the high-precision map according to thematic information, and obtain a qualitative judgment on the integrity of each element of the high-precision map; when the high-precision map elements are superimposed on the layer, the element difference comparison is realized, and a qualitative judgment on the accuracy of the intuitive high-precision map elements is obtained; the spatial position information test diagnostic results are displayed to obtain a distribution map of the diagnostic results; the diagnostic results are marked for scene classification based on the diagnostic result distribution map and scene information to obtain diagnostic results with scene classification labels; the statistical analysis module is used to evaluate the scene coverage quality and processed data quality of the diagnostic program according to the proportion analysis of the number of error types diagnosed in each scene and the total number of diagnostic errors in the scene, and the proportion analysis of the number of error levels diagnosed in each scene and the total number of diagnostic errors.

[0027] According to another aspect of an embodiment of the present application, a storage medium is further provided, which includes a stored program, and the above steps are executed when the program is run.

[0028] According to another aspect of an embodiment of the present application, an electronic device is also provided, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; wherein: the memory is used to store computer programs; the processor is used to execute the steps in the above method by running the program stored in the memory.

[0029] An embodiment of the present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the steps in the above method.

[0030] According to the embodiments of the present invention, a road-level driving position signal of a simulated vehicle is determined, high-precision map data of the simulated vehicle relative to the road-level driving position signal is obtained, a lane-level positioning signal of the simulated vehicle is obtained based on the high-precision map data and the road-level driving position signal, the lane-level positioning signal and the high-precision map data are input into autonomous driving high-precision map software, and real-time feedback data from the autonomous driving high-precision map software is obtained. A diagnostic result for the autonomous driving high-precision map software is generated based on the real-time feedback data and / or the high-precision map data. By determining the road-level driving position signal of the simulated vehicle and obtaining the lane-level positioning signal within which the road-level driving position signal resides, the lane-level positioning signal is input into the autonomous driving high-precision map software to obtain real-time feedback data. The real-time feedback data and / or the high-precision map data are then used to perform diagnostic testing of the autonomous driving high-precision map software. This can reflect the changing state information of the autonomous driving high-precision map software during the driving of the simulated vehicle, thereby diagnosing the applicability of back-end usage. This solves the technical problem of low efficiency in diagnosing the use of high-precision map data in autonomous driving tests using real vehicles in related technologies. This allows for acquisition of real high-precision map data in the field without the need for on-site high-precision map data verification, thus avoiding the labor and material resources consumed by extensive field testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0032] Figure 1 This is a hardware structure block diagram of a computer according to an embodiment of the present invention;

[0033] Figure 2 is a flowchart of a method for testing high-precision map software for autonomous driving according to an embodiment of the present invention;

[0034] Figure 3 is an implementation flow chart of an embodiment of the present invention;

[0035] Figure 4 This is a schematic diagram of a test device for autonomous driving high-precision map software according to an embodiment of the present invention.

[0036] Figure 5 This is a structural block diagram of a testing device for autonomous driving high-precision map software according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the present application, the technical solutions 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 only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of this application. It should be noted that, in the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] Example 1

[0040] The method embodiment provided in the first embodiment of the present application can be executed in a vehicle terminal, a server, a computer, a test device, or a similar processing device. Taking running on a computer as an example, Figure 1 This is a hardware structure diagram of a computer according to an embodiment of the present invention. Figure 1 As shown, the computer may include one or more ( Figure 1 Only one is shown in the figure) processor 102 (processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data. Optionally, the above computer may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0041] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the testing method for high-precision map software for autonomous driving in an embodiment of the present invention. The processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, thereby implementing the above-mentioned method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories may be connected to the computer via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0042] The transmission device 106 is used to receive or send data via a network. A specific example of the aforementioned network may include a wireless network provided by a computer's communications provider. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0043] In this embodiment, a method for testing high-precision map software for autonomous driving is provided. Figure 2 : is a flow chart of a method for testing high-precision map software for autonomous driving according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0044] Step S202, determining a road-level driving position signal of a simulated vehicle;

[0045] The road-level vehicle position signal of this embodiment includes the road coordinate position of the simulated vehicle in the GIS system.

[0046] Step S204, obtaining high-precision map data of a simulated vehicle's driving position signal at the road level, wherein the high-precision map data is the vehicle's automatic driving guidance data;

[0047] In one example, by inputting a road-level vehicle position signal into the high-precision map software for autonomous driving to be tested, high-precision map data based on the road-level vehicle position signal can be output.

[0048] Step S206: obtaining a lane-level positioning signal of the simulated vehicle based on the high-precision map data and the road-level vehicle position signal;

[0049] The road-level vehicle position signal of this embodiment includes the coordinate position of the lane centerline of the simulated vehicle in the GIS system.

[0050] Step S208: Inputting the lane-level positioning signal and high-precision map data into the autonomous driving high-precision map software, and obtaining real-time feedback data from the autonomous driving high-precision map software;

[0051] Optionally, the real-time feedback data of the autonomous driving high-precision map software is structured data, including the calculation results of the high-precision map element information in front of the current position, including the distance and length of the special area in front (construction area, toll station area, tunnel area), the distance to the ramp in front, the direction of the ramp and the driving position, lane-level navigation guidance information, the curvature value of the curvature distance in front, the lane change type and distance, etc.

[0052] Step S210: Generate diagnostic results of the autonomous driving high-precision map software based on real-time feedback data and / or high-precision map data.

[0053] The diagnostic results of this embodiment are used to characterize the timeliness and accuracy of the data returned by the autonomous driving high-precision map software.

[0054] Through the above steps, the road-level driving position signal of the simulated vehicle is determined, high-precision map data of the simulated vehicle with respect to the road-level driving position signal is obtained, the lane-level positioning signal of the simulated vehicle is obtained based on the high-precision map data and the road-level driving position signal, the lane-level positioning signal and the high-precision map data are input into the autonomous driving high-precision map software, and real-time feedback data from the autonomous driving high-precision map software is obtained. A diagnostic result for the autonomous driving high-precision map software is generated based on the real-time feedback data and / or the high-precision map data. By determining the road-level driving position signal of the simulated vehicle and obtaining the lane-level positioning signal where the road-level driving position signal is located, the lane-level positioning signal is input into the autonomous driving high-precision map software to obtain its real-time feedback data, and then using the real-time feedback data and / or high-precision map data to implement a diagnostic test of the autonomous driving high-precision map software. This can reflect the changing state information of the autonomous driving high-precision map software during the driving of the simulated vehicle, thereby diagnosing the applicability of back-end usage. This solves the technical problem of low efficiency in diagnosing the use of high-precision map data in autonomous driving tests using real vehicles in related technologies. This allows for acquisition of real high-precision map data in the field without the need for on-site high-precision map data verification, thus avoiding the labor and material resources consumed by extensive field testing.

[0055] In one implementation of this embodiment, determining the road-level driving position signal of the simulated vehicle includes: generating a road-level navigation path based on a geographic information system, wherein the road-level navigation path includes a set of road segment coordinate points formed from a departure point to a destination via several points to the destination; obtaining preset inertial navigation parameters of the road-level navigation path, and using the preset inertial navigation parameters and the set of coordinate points to obtain a position simulation data source; based on the position simulation data source, outputting position information in sequence and at a fixed frequency to obtain the road-level driving position signal of the simulated vehicle in real time.

[0056] First, build the map and navigation map of the autonomous driving high-precision map software Figure 1 The measurement coordinate system can be the national open GCJ02, WGS84, or other custom coordinate systems and other geographic coordinates.

[0057] Generate the road-level positioning information for the global path planning required for the test environment in this coordinate system space. In this example, the road-level position information of the vehicle refers to the point information created in the coordinate space, which is a series of test sections from the starting point A through the passing points (a1, a2, a3...) to the destination point B. This position is the road-level point information. The coordinate points are connected in sequence to form a set of coordinate points of the road-level navigation path, which serves as the spatial position data source for simulating the movement of autonomous driving vehicles. At the same time, by resampling the road node string, the sampling interval is set according to the test requirements, and the heading angle, speed and other INS (Intertial Navigation System) inertial navigation parameters are calculated. As a position simulation data source for road-level positioning, it replaces the INS signal source in the actual vehicle test.

[0058] Optionally, the generated path location simulation data source can be location information that is entirely within the road range, or some point information can be within the road range and some points outside the road range. The purpose is to test the high-precision map program's feedback on abnormal location input.

[0059] Finally, based on the position simulation data source of the simulated test path, a position signal is output in a sequence and at a fixed frequency to obtain a simulated driving position signal. According to the test requirements, the position simulation data source is simulated into a road-level driving position signal through a certain protocol and method.

[0060] In one implementation of this embodiment, obtaining a lane-level positioning signal of a simulated vehicle based on high-precision map data and a road-level vehicle position signal includes:

[0061] S11, obtaining a lane set including coordinate positions of road-level vehicle position signals from high-precision map data;

[0062] Through the road and positioning signals and the high-precision map positioning signals, more detailed environmental information is formed. Through the detailed scene information of the high-precision map, the set of lanes closest to the location of the road-level driving position signal can be obtained from each link of the autonomous driving high-precision map software.

[0063] S12, extracting the coordinate point strings of the lane centerlines of all lanes in the lane set;

[0064] S13, locating the target lane centerline closest to the coordinate position of the road-level vehicle position signal according to the coordinate point string;

[0065] In one example, locating the target lane centerline closest to the coordinate position of the road-level driving position signal based on the coordinate point string includes: calculating the perpendicular distance from the coordinate position of the road-level driving position signal to the coordinate point string for the lane centerline of each lane in the lane set; and selecting the lane centerline corresponding to the coordinate point string with the shortest perpendicular distance as the target lane centerline.

[0066] S14, determining the lane where the center line of the target lane is located as the lane-level positioning signal of the simulated vehicle.

[0067] Based on the lane set, the coordinate point string of the lane centerline of each lane is extracted, and the coordinate position of the road-level driving position signal is compared with the coordinate position of the road-level driving position signal. According to the simulation parameters, lane change feature information, etc., the target lane centerline is obtained. Through the lane set R (L1, L2...L n ), extract the center line of each lane in the lane set and form a set M (M1, M2...M n ), calculate the distance from each element in M to the coordinate point of the road-level driving position signal in turn, determine the coordinate point from M to the road-level driving position signal by sorting, and obtain the nearest target lane center line M'.

[0068] In another implementation of this embodiment, obtaining a lane-level positioning signal of a simulated vehicle based on high-precision map data and a road-level driving position signal includes: reading lane change feature information from attribute information of a lane-level positioning signal of a previous frame of the road-level driving position signal, wherein the lane change feature information is used to characterize factors affecting lane changes; parsing the lane change feature information to determine the changed lane of the previous frame of the lane-level positioning signal; using the lane centerline of the changed lane to calculate a projection point of the coordinate position of the road-level driving position signal to the lane centerline of the changed lane; and using the coordinates of the projection point to determine the lane-level positioning signal.

[0069] When simulating vehicle lane changes, the focus is no longer solely on obtaining the nearest lane centerline. Lane connectivity within high-precision map data derived from road-level vehicle position signals, along with set distance parameters to lane change feature lanes, random parameters, and lane change feature information from the previous frame. This includes, but is not limited to, lane widening and narrowing points, lane line change points, and lane attribute change points. This lane change feature information is used to adjust the lane number for lane positioning, extract and determine the lane centerline, and finally, based on the nearest lane centerline, calculate the closest point of the projection from the point to the coordinate point string to obtain the simulated vehicle's lane-level positioning signal.

[0070] In the above embodiment, the nearest lane centerline can be used to determine the lane-level position signal. Since the lane simulation positioning signal is related to the input road-level driving position signal, as a test input source, the road-level driving position signal has normal and abnormal conditions. Therefore, when the position of the road-level driving position signal is normal, it participates in the calculation to obtain the nearest lane centerline. When the position of the road-level driving position signal is used as an abnormal input, it does not participate in obtaining the centerline position, and the position of the road-level driving position signal is directly used as the lane-level positioning position.

[0071] In a diagnostic scenario of this embodiment, generating a diagnostic result of the autonomous driving high-precision map software based on real-time feedback data includes: analyzing the impact of the real-time feedback data on the business end, and analyzing the output module of the real-time feedback data; generating an abnormality level that matches the impact level, and searching for an abnormality type that matches the output module; and determining the first diagnostic result of the autonomous driving high-precision map software based on the abnormality level and abnormality type.

[0072] Obtain real-time feedback data output by the program under test (autonomous driving high-precision map software), diagnose the output results and determine the error level of the diagnosis based on the severity of its impact on back-end business usage. The levels can be divided into fatal errors, general errors, warnings, etc. (other levels can also be used). Classify the diagnostic results according to the name of the output module, and categorize the diagnostic results based on the classified and determined error levels.

[0073] In one instance, when generating an anomaly level that matches the degree of impact, the anomaly level is determined based on the response time, value range, and value validity of the values in the real-time feedback data. If the output period value exceeds expectations and the type of the output value is invalid, it is determined to be a warning; if the distance value is <0, the curvature value is >10, the length value is <0, the orientation value is >360, and the index value is -1, it is determined to be a fatal error; if the distance value exceeds the threshold and the curvature value exceeds the threshold, it is determined to be a general error.

[0074] Optionally, after determining the first diagnostic result of the autonomous driving high-precision map software based on the abnormality level and abnormality type, it also includes: associating the first diagnostic result with the lane-level positioning signal, and displaying the point information of the first diagnostic result in the reference layer according to the lane-level positioning signal; generating a diagnostic result distribution map of the reference layer based on the point information.

[0075] Optionally, the reference layers of this embodiment may include layers of a navigation road network map and a high-definition image map in a GIS system.

[0076] In one example, after generating a diagnosis result distribution map of a reference layer based on point information, the method further includes: for each diagnosis result, determining the geographical location of the diagnosis result according to the diagnosis result distribution map; generating a scene label based on the geographical location, wherein the scene label includes at least one of the following: elevated scene, tunnel scene, ramp scene, and highway interchange scene; and adding the scene label to the attribute information of the corresponding diagnosis result.

[0077] The classified and determined error-level diagnostic results are associated with lane-level positioning signals to obtain test diagnostic results with spatial location information. Based on the diagnostic results with spatial location information, the point coordinate information of the diagnostic result information is superimposed and displayed on the high-precision map and other reference layers in the GIS system to obtain a diagnostic result distribution map. Based on the diagnostic result distribution map, the scene to which the location of the diagnostic result belongs is identified. Scene classification includes but is not limited to elevated scenes, tunnel scenes, ramp scenes, highway interchange scenes, etc. The diagnostic results are marked for scene classification in the GIS system to obtain diagnostic results with scene classification labels.

[0078] Based on the above example, after adding the scene label to the attribute information of the corresponding diagnostic result, it also includes: for each scene category, counting the total number of all diagnostic results in the corresponding scene category, and counting the first number of target abnormality levels and the second number of target abnormality types in the corresponding scene category; calculating the first abnormality ratio of the target abnormality level based on the first number and the total number, and calculating the second abnormality ratio of the target abnormality type based on the second number and the total number; using the first abnormality ratio and the second abnormality ratio to generate the scene coverage quality of the autonomous driving high-precision map software in the corresponding scene category.

[0079] In this example, by counting the diagnosis results with scene classification labels, the scene coverage quality and processing data quality of the autonomous driving high-precision map software are evaluated based on the proportion of the number of error types diagnosed in each scene to the total number of diagnostic errors in the scene, and the proportion of the number of error levels diagnosed in each scene to the total number of diagnostic errors.

[0080] In another diagnostic scenario of this embodiment, generating a diagnostic result of autonomous driving high-precision map software based on high-precision map data includes: parsing the visual display elements of the high-precision map data, wherein the visual display elements include at least one of the following: lane line markings, lane line types, operational design domain (ODD) faults, lane speed limits, lane types, and lane curvatures; overlaying the visual display elements with a reference layer in a geographic information system, and calculating the accuracy of the high-precision map data based on the matching degree between the visual display elements and the reference layer, and determining the accuracy as the second diagnostic result of the autonomous driving high-precision map software.

[0081] Based on lane-level positioning signals, displaying high-precision maps in the GIS system can obtain intuitive display and reference comparison of high-precision map elements; such as rendering lane line marking topics, lane line type topics, lane anomaly topics (ODD faults), lane speed limit topics, lane type topics, lane curvature anomaly topics, etc.; obtain a qualitative judgment on the integrity of each element of the high-precision map that is intuitively displayed; in the GIS system, high-precision map elements are superimposed with layers, such as navigation road network maps, high-definition image maps, etc., and the differences between high-precision map elements and actual road conditions are compared to obtain an intuitive qualitative judgment on the accuracy of high-precision map elements.

[0082] Figure 3 This is an implementation flow chart of an embodiment of the present invention. A method for diagnosing high-precision map data and programs for autonomous driving provided in this embodiment includes:

[0083] S31. Generate a road-level navigation path based on the GIS system and obtain a location information data source for the simulated test path;

[0084] S32. Based on the position information data source of the simulated test path, output a position information in sequence and at a fixed frequency to obtain a simulated road-level driving position signal;

[0085] S33. Based on the simulated driving position signal, input the program under test, obtain the high-precision map data of the position, and then execute S34 to S37 and S38 separately;

[0086] S34. Obtaining a lane-level positioning signal of a simulated driving position using the acquired road-level driving position signal and high-precision map data;

[0087] S35. Input the lane-level positioning data and high-precision map data into the program under test to obtain an output result of the program under test;

[0088] S36. Diagnose the diagnostic result of the output result of the tested program, determine the error level and error type of the diagnostic result, associate it with the lane-level spatial position information, mark the scene information, and obtain the diagnostic result with the spatial position and scene label;

[0089] Furthermore, the output results of the tested program are obtained, and the output results are diagnosed according to the severity of the impact on back-end use, and the error level of the diagnosis results is determined, which is divided into fatal errors, general errors, and warnings. The diagnosis results are classified according to the name of the output module, and the classified and determined error level diagnosis results are associated with the road-level driving position signal to obtain the test diagnosis results with spatial position information.

[0090] Based on the test diagnosis results with spatial location information, the high-precision map, reference layers (such as navigation road network, high-definition images, etc.), and the point information of the test diagnosis results are superimposed and displayed in the GIS system to obtain the diagnosis result distribution map;

[0091] Based on the diagnosis result distribution map, the scene to which the location of the diagnosis result belongs, the scene classification includes but is not limited to elevated scenes, tunnel scenes, ramp scenes, highway interchange scenes, etc. The diagnosis results are marked with scene classification in the GIS system to obtain diagnosis results with scene classification labels.

[0092] S37. Based on the diagnosis results with spatial location and scene labels, evaluate the scene coverage quality and processed data quality of the tested program;

[0093] The diagnostic results with scene classification labels are counted, and the scene coverage quality and data processing quality of the diagnostic program are evaluated based on the proportion of the number of diagnostic error types in each scene to the total number of diagnostic errors in the scene, and the proportion of the number of diagnostic error levels in each scene to the total number of diagnostic errors.

[0094] S38. Based on high-precision map data, high-precision maps are displayed in the GIS system to obtain intuitive high-precision map element display and reference comparison;

[0095] For example, the system renders lane markings, lane type, lane anomalies, non-ODD areas, special areas, and lane types; obtaining a qualitative assessment of the integrity of each HD map element. In the GIS system, HD map elements are overlaid with reference layers of real roads, such as navigation network maps and high-definition image maps. The differences between HD map elements and real-world road conditions are compared to obtain a qualitative assessment of the accuracy of HD map elements.

[0096] The solution of this embodiment also provides a test device for autonomous driving high-precision map software. Figure 4This is a schematic diagram of a test system for autonomous driving high-precision map software according to an embodiment of the present invention, including a test device, an autonomous driving domain controller, and a navigation map controller. The system includes: a case management module, a scenario test path management module, a position simulation module, a lane-level positioning simulation module (with autonomous driving high-precision map software installed), a data diagnosis module, a map information visualization module, and a statistical analysis module.

[0097] The case management module is used to create test scenario cases, manage test paths in scenarios, label test scenarios, and record test case information.

[0098] The scenario test path management module is used to manage the test path data for the unit according to the case, and record the simulated positioning trajectory data generated by the path through the latitude and longitude coordinate space.

[0099] The position simulation module is used to generate simulated positioning trajectory data by real-time interpolation according to the set frequency and sampling interval of the test path used, broadcast the position data, and obtain high-precision map data of the previous position from the autonomous driving map program.

[0100] The lane-level positioning simulation module uses the HD map data acquired through simulated positioning and the position data broadcast by the position simulation module. By obtaining the HD map lane geometry and the coordinate information of the position data, the module uses simulation parameters and HD map data to obtain lane widening points, lane narrowing points, lane line change points, and lane attribute change points ahead of the current position to generate lane change feature information, adjust the lane positioning information coordinates, and simulate the lane change effect during driving.

[0101] The data diagnosis module uses diagnostic rules to diagnose the results of the program under test. It then classifies the diagnostic results into error levels based on the severity of their impact on back-end usage. It also categorizes the diagnostic results based on the name of the output module. The classified diagnostic results are then associated with the spatial location of the simulated positioning to obtain a test diagnostic result with spatial location information.

[0102] The map information visualization module is used to display high-precision maps for thematic information and obtain a qualitative judgment on the integrity of each element of the high-precision map; by overlaying high-precision map elements with layers, it can realize element difference comparison and obtain a qualitative judgment on the accuracy of intuitive high-precision map elements; it displays the diagnostic results of spatial location information tests and obtains a distribution map of diagnostic results; based on the diagnostic result distribution map and scene information, the diagnostic results are marked for scene classification to obtain diagnostic results with scene classification labels.

[0103] The statistical analysis module is used to evaluate the scenario coverage quality and processed data quality of the diagnostic program based on the analysis of the proportion of the number of diagnostic error types in each scenario to the total number of diagnostic errors in the scenario, and the proportion of the number of diagnostic error levels in each scenario to the total number of diagnostic errors;

[0104] Using the high-precision map data and program diagnostics provided by this embodiment, autonomous driving vehicle driving trajectory scenarios are constructed using latitude and longitude coordinate space. Real-world high-precision map data can be quickly obtained from the actual vehicle's movement. Based on the real high-precision map data and the simulated driving trajectory's road and location, lane geometry, lane characteristics, and lane change factors are obtained to simulate automatic lane changes. Lane change positioning data can be accurately simulated by adjusting the lane change factors. This data is then input into the autonomous driving map driver to calculate current map environment information (such as ramp distance, ramp length, and nearest ramp direction). The diagnostic module then uses the calculated information and map data to perform correctness checks, data integrity checks, and value range checks. The diagnostic module then classifies the error locations and levels them based on the inspection object and the inspection value range. Error location information is recorded and associated with scenario information. A visualization system is used to intuitively display the spatial distribution and correlation of errors, facilitating the identification of program weaknesses. Paths stored in the case are effectively used for scenario archiving and management, enabling long-term monitoring of the program's operating status. Diagnostic results are archived and classified into scenarios, achieving unmanned, long-term operation. This reduces the time required for manual monitoring of test data results, improves detection efficiency, and reduces the cost of field testing.

[0105] The test software constructed in this embodiment combines the autonomous driving high-precision map software and high-precision map data in the autonomous driving control domain to troubleshoot problems in the production and conversion of high-precision map data, as well as data calculation issues during software development. Therefore, this application can reflect the changing state information of high-precision maps and navigation maps during simulated vehicle driving and can determine the applicability of high-precision usage information in the back-end. It is possible to obtain real-world high-precision map data in the field without the need for on-site high-precision map data verification, avoiding the labor and material resources consumed by extensive field testing.

[0106] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0107] Example 2

[0108] In this embodiment, a testing device and system for high-precision map software for autonomous driving are also provided. The device is used to implement the above-mentioned embodiments and preferred implementations, and the details that have been described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0109] Figure 5 : is a structural block diagram of a test device for autonomous driving high-precision map software according to an embodiment of the present invention, such as Figure 5 As shown, the device includes:

[0110] A determination module 50 is used to determine a road-level driving position signal of a simulated vehicle;

[0111] A first acquisition module 52 is configured to acquire high-precision map data of the simulated vehicle's driving position signal at the road level, wherein the high-precision map data is the vehicle's automatic driving guidance data;

[0112] A second acquisition module 54 is configured to acquire a lane-level positioning signal of the simulated vehicle based on the high-precision map data and the road-level vehicle position signal;

[0113] A third acquisition module 56 is configured to input the lane-level positioning signal and the high-precision map data into the autonomous driving high-precision map software and obtain real-time feedback data from the autonomous driving high-precision map software;

[0114] The generation module 58 is used to generate the diagnostic results of the autonomous driving high-precision map software based on the real-time feedback data and / or high-precision map data.

[0115] Optionally, the determination module includes: a first generation unit, used to generate a road-level navigation path based on a geographic information system, wherein the road-level navigation path includes a set of road segment coordinate points formed by passing through several points from a departure point to a destination; a processing unit, used to obtain preset inertial navigation parameters of the road-level navigation path, and use the preset inertial navigation parameters and the set of coordinate points to obtain a position simulation data source; an output unit, used to output position information in sequence and at a fixed frequency based on the position simulation data source, and obtain the road-level driving position signal of the simulated vehicle in real time.

[0116] Optionally, the second acquisition module includes: an acquisition unit for acquiring a lane set containing the coordinate position of the road-level driving position signal from the high-precision map data; an extraction unit for extracting a coordinate point string of the lane center lines of all lanes in the lane set; a positioning unit for locating the target lane center line closest to the coordinate position of the road-level driving position signal based on the coordinate point string; and a first determination unit for determining the lane where the target lane center line is located as the lane-level positioning signal of the simulated vehicle.

[0117] Optionally, the positioning unit includes: a calculation subunit, used to calculate the vertical distance from the coordinate position of the road-level driving position signal to the coordinate point string of the lane centerline of each lane in the lane set; and a selection subunit, used to select the lane centerline corresponding to the coordinate point string with the shortest vertical distance as the target lane centerline.

[0118] Optionally, the second acquisition module includes: a reading unit, used to read lane change feature information from the attribute information of the lane-level positioning signal of the previous frame of the road-level driving position signal, wherein the lane change feature information is used to characterize the influencing factors of the lane change; a parsing unit, used to parse the lane change feature information and determine the changed lane of the previous frame of the lane-level positioning signal; a calculation unit, used to calculate the projection point of the coordinate position of the road-level driving position signal to the lane centerline of the changed lane using the lane centerline of the changed lane; a second determination unit, used to determine the lane-level positioning signal using the coordinates of the projection point.

[0119] Optionally, the generation module includes: a first parsing unit, used to parse the degree of impact of the real-time feedback data on the business end, and an output module for parsing the real-time feedback data; a processing unit, used to generate an abnormality level matching the degree of impact, and to find an abnormality type matching the output module; a first determination unit, used to determine the first diagnostic result of the autonomous driving high-precision map software based on the abnormality level and the abnormality type.

[0120] Optionally, the generation module also includes: a display unit, which is used to associate the first diagnostic result with the lane-level positioning signal after the determination unit determines the first diagnostic result of the autonomous driving high-precision map software based on the abnormality level and the abnormality type, and display the point information of the first diagnostic result in the reference layer according to the lane-level positioning signal; a generation unit, which is used to generate a diagnostic result distribution map of the reference layer based on the point information.

[0121] Optionally, the generation module also includes: a second determination unit, used to determine, for each diagnosis result, the geographical location of the diagnosis result according to the diagnosis result distribution map after the generation unit generates the diagnosis result distribution map of the reference layer based on the point information; a first generation unit, used to generate a scene label based on the geographical location, wherein the scene label includes at least one of the following: an elevated scene, a tunnel scene, a ramp scene, and a highway interchange scene; and an adding unit, used to add the scene label to the attribute information of the corresponding diagnosis result.

[0122] Optionally, the generation module also includes: a first calculation unit, which is used to count the total number of all diagnostic results in the corresponding scene category for each scene category after the adding unit adds the scene label to the attribute information of the corresponding diagnostic result, and count the first number of target abnormality levels and the second number of target abnormality types in the corresponding scene category; a second calculation unit, which is used to calculate the first abnormality ratio of the target abnormality level based on the first number and the total number, and calculate the second abnormality ratio of the target abnormality type based on the second number and the total number; a second generation unit, which is used to use the first abnormality ratio and the second abnormality ratio to generate the scene coverage quality of the autonomous driving high-precision map software in the corresponding scene category.

[0123] Optionally, the generation module includes: a second parsing unit, used to parse the visual display elements of the high-precision map data, wherein the visual display elements include at least one of the following: lane line markings, lane line types, operational design domain (ODD) faults, lane speed limits, lane types, and lane curvatures; a third determination unit, used to overlay the visual display elements with a reference layer in a geographic information system, and calculate the accuracy of the high-precision map data based on the matching degree between the visual display elements and the reference layer, and determine the accuracy as the second diagnostic result of the autonomous driving high-precision map software.

[0124] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0125] Example 3

[0126] An embodiment of the present invention further provides a storage medium storing a computer program, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0127] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0128] S1, determining the road-level driving position signal of the simulated vehicle;

[0129] S2, obtaining high-precision map data of the simulated vehicle's driving position signal at the road level, wherein the high-precision map data is the vehicle's automatic driving guidance data;

[0130] S3, obtaining a lane-level positioning signal of the simulated vehicle based on the high-precision map data and the road-level vehicle position signal;

[0131] S4, inputting the lane-level positioning signal and the high-precision map data into autonomous driving high-precision map software, and obtaining real-time feedback data from the autonomous driving high-precision map software;

[0132] S5: Generate a diagnostic result of the autonomous driving high-precision map software based on the real-time feedback data and / or high-precision map data.

[0133] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0134] An embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0135] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0136] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0137] S1, determining the road-level driving position signal of the simulated vehicle;

[0138] S2, obtaining high-precision map data of the simulated vehicle's driving position signal at the road level, wherein the high-precision map data is the vehicle's automatic driving guidance data;

[0139] S3, obtaining a lane-level positioning signal of the simulated vehicle based on the high-precision map data and the road-level vehicle position signal;

[0140] S4, inputting the lane-level positioning signal and the high-precision map data into autonomous driving high-precision map software, and obtaining real-time feedback data from the autonomous driving high-precision map software;

[0141] S5: Generate a diagnostic result of the autonomous driving high-precision map software based on the real-time feedback data and / or high-precision map data.

[0142] Optionally, specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0143] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0144] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0145] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0146] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0147] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0148] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0149] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A testing method for autonomous driving high-precision map software, characterized in that: include: Determine a road-level driving position signal of a simulated vehicle; Obtaining high-precision map data of the simulated vehicle's driving position signal at the road level, wherein the high-precision map data is the vehicle's automatic driving guidance data; Obtaining a lane-level positioning signal of the simulated vehicle based on the high-precision map data and the road-level vehicle position signal; Inputting the lane-level positioning signal and the high-precision map data into autonomous driving high-precision map software, and obtaining real-time feedback data from the autonomous driving high-precision map software; Generating a diagnostic result of the autonomous driving high-precision map software based on the real-time feedback data and the high-precision map data; Among them, determining the road-level driving position signal of the simulated vehicle includes: generating a road-level navigation path based on a geographic information system, wherein the road-level navigation path includes a set of road segment coordinate points formed from a departure point to a destination via several points to the destination; obtaining preset inertial navigation parameters of the road-level navigation path, and using the preset inertial navigation parameters and the coordinate point set to obtain a position simulation data source, wherein the preset inertial navigation parameters include a sampling interval, heading angle, and speed set according to test requirements; based on the position simulation data source, outputting position information in sequence and at a fixed frequency to obtain the road-level driving position signal of the simulated vehicle in real time.

2. The method according to claim 1, characterized in that Acquiring the lane-level positioning signal of the simulated vehicle according to the high-precision map data and the road-level driving position signal includes: Acquire a lane set including the coordinate position of the road-level vehicle position signal from the high-precision map data; Extracting a lane centerline coordinate point string of all lanes in the lane set; Locating the target lane centerline closest to the coordinate position of the road-level vehicle position signal according to the coordinate point string; The lane where the center line of the target lane is located is determined as the lane-level positioning signal of the simulated vehicle.

3. The method according to claim 2, characterized in that Locating the target lane centerline closest to the coordinate position of the road-level vehicle position signal according to the coordinate point string includes: For the coordinate point string of the lane centerline of each lane in the lane set, respectively calculate the perpendicular distance from the coordinate position of the road-level vehicle position signal to the coordinate point string; The lane centerline corresponding to the coordinate point string with the shortest vertical distance is selected as the target lane centerline.

4. The method according to claim 1, wherein Acquiring the lane-level positioning signal of the simulated vehicle according to the high-precision map data and the road-level driving position signal includes: Reading lane change feature information from attribute information of a lane-level positioning signal of a previous frame of the road-level vehicle position signal, wherein the lane change feature information is used to characterize factors affecting lane change; Analyzing the lane change feature information to determine the lane change of the previous frame lane-level positioning signal; Calculating a projection point of the coordinate position of the road-level vehicle position signal to the lane centerline of the lane being changed using the lane centerline of the lane being changed; The coordinates of the projection points are used to determine a lane-level positioning signal.

5. The method according to claim 1, wherein Generating the diagnostic results of the autonomous driving high-precision map software based on the real-time feedback data includes: An output module for analyzing the impact of the real-time feedback data on the service end, and analyzing the real-time feedback data; generating an exception level matching the impact level, and searching for an exception type matching the output module; The abnormality level and the abnormality type are used to determine a first diagnostic result of the autonomous driving high-precision map software.

6. The method according to claim 5, characterized in that After determining the first diagnosis result of the autonomous driving high-precision map software based on the abnormality level and the abnormality type, the method further includes: Associating the first diagnostic result with the lane-level positioning signal, and displaying point information of the first diagnostic result in a reference layer according to the lane-level positioning signal; A diagnosis result distribution map of the reference layer is generated based on the point information.

7. The method according to claim 6, characterized in that After generating the diagnosis result distribution map of the reference layer based on the point information, the method further includes: For each diagnosis result, determining the geographical location of the diagnosis result according to the diagnosis result distribution map; Generating a scene label based on the geographic location, wherein the scene label includes at least one of the following: an elevated scene, a tunnel scene, a ramp scene, and a high-speed interchange scene; The scene label is added to the attribute information of the corresponding diagnosis result.

8. The method according to claim 7, characterized in that After adding the scene tag to the attribute information of the corresponding diagnosis result, the method further includes: For each scenario category, counting the total number of all diagnosis results in the corresponding scenario category, as well as counting the first number of target abnormality levels and the second number of target abnormality types in the corresponding scenario category; Calculate a first abnormality ratio of the target abnormality level based on the first number and the total number, and calculate a second abnormality ratio of the target abnormality type based on the second number and the total number; The first anomaly ratio and the second anomaly ratio are used to generate the scene coverage quality of the autonomous driving high-precision map software in the corresponding scene category.

9. The method according to claim 1, characterized in that Generating the diagnostic result of the autonomous driving high-precision map software based on the high-precision map data includes: Parsing visual display elements of the high-precision map data, wherein the visual display elements include at least one of the following: lane marking, lane type, operational design domain (ODD) fault, lane speed limit, lane type, and lane curvature; The visual display elements are superimposed on a reference layer in a geographic information system, and the accuracy of the high-precision map data is calculated based on the degree of matching between the visual display elements and the reference layer, and the accuracy is determined as the second diagnostic result of the autonomous driving high-precision map software.

10. A testing device for autonomous driving high-precision map software, characterized in that: include: A determination module, for determining a road-level driving position signal of a simulated vehicle; A first acquisition module is configured to acquire high-precision map data of the simulated vehicle's driving position signal at the road level, wherein the high-precision map data is the vehicle's automatic driving guidance data; A second acquisition module is configured to acquire a lane-level positioning signal of the simulated vehicle based on the high-precision map data and the road-level vehicle position signal; a third acquisition module, configured to input the lane-level positioning signal and the high-precision map data into autonomous driving high-precision map software, and obtain real-time feedback data from the autonomous driving high-precision map software; A generation module, configured to generate a diagnostic result of the autonomous driving high-precision map software based on the real-time feedback data and the high-precision map data; Among them, the determination module includes: a first generation unit, used to generate a road-level navigation path based on a geographic information system, wherein the road-level navigation path includes a set of road segment coordinate points formed by passing through several points from the departure point to the destination; a processing unit, used to obtain the preset inertial navigation parameters of the road-level navigation path, and use the preset inertial navigation parameters and the coordinate point set to obtain a position simulation data source, wherein the preset inertial navigation parameters include a sampling interval, heading angle, and speed set according to test requirements; an output unit, used to output position information in sequence and at a fixed frequency based on the position simulation data source, and obtain the road-level driving position signal of the simulated vehicle in real time.

11. A testing device for autonomous driving high-precision map software, characterized in that: include: The case management module is used to create test scenario cases, manage test paths in scenarios, label test scenarios, and record case information of test cases; The scenario test path management module is used to manage the test path data for the unit according to the test scenario case, and record the simulated positioning trajectory data generated by the path through the longitude and latitude coordinate space; The position simulation module is used to generate simulated positioning trajectory data through real-time interpolation according to the set frequency and sampling interval, broadcast the position data, and obtain high-precision map data of the current position from the autonomous driving high-precision map software; A lane-level positioning simulation module is used to obtain lane widening points, lane narrowing points, lane line change points, and lane attribute change points ahead of the current position from the autonomous driving high-precision map software based on real high-precision map data and the simulated driving trajectory broadcast by the position simulation module, generate lane change feature information, adjust the lane positioning information coordinates, and perform automatic lane change positioning simulation; The data diagnostic module is used to diagnose the output results of the autonomous driving high-precision map software using diagnostic rules, and diagnose the severity of the output results' impact on business end usage, classifying the diagnostic results into error levels; classifying the diagnostic results according to the name of the output module; and associating the classified and graded diagnostic results with the spatial location of the simulated positioning to obtain a test diagnostic result with spatial location information; The map information visualization module is used to display high-precision maps according to thematic information, obtain a qualitative judgment on the integrity of each element of the high-precision map, and then overlay the high-precision map elements with the layer to compare the differences between the elements and obtain a qualitative judgment on the accuracy of the high-precision map elements. It displays the diagnostic results of the spatial location information test and obtains a distribution map of the diagnostic results. Based on the distribution map of the diagnostic results and the scene information, the diagnostic results are classified and labeled to obtain diagnostic results with scene classification labels. The statistical analysis module is used to evaluate the scene coverage quality and processed data quality of the autonomous driving high-precision map software based on the proportion analysis of the number of diagnostic error types in each scenario and the total number of diagnostic errors in the scenario, and the proportion analysis of the number of diagnostic error levels in each scenario and the total number of diagnostic errors.

12. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 9 when executed.

13. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 9.

Images