Test method, system, medium, apparatus, and program product for intelligent driving vehicle

Abstract

The application discloses a kind of intelligent driving vehicle test method, system, medium, equipment and program product, belong to intelligent driving test and simulation technical field.The method mainly includes: in high-precision map, selected to be measured section corresponding local high-precision map, and obtain the coordinate information corresponding to the local high-precision map corresponding to to be measured section as first coordinate;According to the size of real test field, the first coordinate is converted into real test field by coordinate conversion, and the second coordinate is obtained, and then the local high-precision map corresponding to to be measured section is converted into the high-precision map of the test section corresponding in real test field;Intelligent driving vehicle is tested on test section using the high-precision map of test section, and the test result of intelligent driving vehicle on to be measured section is obtained.The application quickly and safely verifies the function and stability of each function of intelligent driving system under various actual working conditions under the condition of guaranteeing test safety and saving test cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving test and simulation, and particularly relates to a test method and system of an intelligent driving vehicle, a storage medium, an electronic device and a computer program product. BACKGROUND

[0002] In the prior art, for a specific road scene, only relevant information of the road scene can be collected on site, and then the road scene is reconstructed in a test field by modeling, so as to realize one-to-one correspondence between the road scene and the real environment. When the intelligent driving vehicle is tested, the prior art runs the intelligent driving vehicle in the reconstructed road scene to perform real vehicle testing, and the simulation test process of the intelligent driving vehicle needs to be controlled by an operator through remote control or remote monitoring. The prior art is difficult to test complex road conditions in the actual road, cannot guarantee the safety of the test in the complex scene, and building a test scene completely corresponding to the real environment in the test field increases the test cost. SUMMARY

[0003] In view of the problems in the prior art that the intelligent driving vehicle is difficult to test complex road conditions and difficult to guarantee the safety of the test in the complex road conditions, the present application mainly provides a test method and system of an intelligent driving vehicle, a storage medium, an electronic device and a computer program product.

[0004] To achieve the above-mentioned purpose, the first technical solution adopted by the present application is to provide a test method of an intelligent driving vehicle, which comprises: in a high-precision map, selecting a local high-precision map corresponding to a to-be-tested road section, and obtaining coordinate information corresponding to the local high-precision map corresponding to the to-be-tested road section as a first coordinate; according to the size of a real test field, converting the first coordinate to the real test field by coordinate conversion to obtain a second coordinate, and then converting the local high-precision map corresponding to the to-be-tested road section into a high-precision map of a test road section corresponding to the real test field; using the high-precision map of the test road section to make the intelligent driving vehicle perform intelligent driving test on the test road section, and obtaining a test result of the intelligent driving vehicle on the to-be-tested road section.

[0005] Optionally, the local high-precision map corresponding to the to-be-tested road section is selected, and the coordinate information corresponding to the local high-precision map corresponding to the to-be-tested road section is obtained as the first coordinate, which comprises: in the high-precision map, selecting a to-be-tested high-precision map region, i.e. the local high-precision map, and selecting a to-be-tested road section in the local high-precision map, and obtaining static environment information corresponding to the to-be-tested road section, wherein the local high-precision map comprises lane line information and sign information; the coordinate information corresponding to the local high-precision map is taken as the first coordinate.

[0006] Optionally, according to the size of the real test field, the first coordinate is converted to the real test field through coordinate conversion to obtain a second coordinate, and then the local high-precision map corresponding to the to-be-tested road section is converted to a high-precision map of a test road section in the real test field, including: projecting and transforming the first coordinate into a first two-dimensional coordinate system to obtain a third coordinate; according to the size of the test field, the third coordinate is projected into a second two-dimensional coordinate system by using affine transformation to obtain a fourth coordinate and an affine transformation matrix; the fourth coordinate is inversely projected and transformed to obtain the second coordinate.

[0007] Optionally, the high-precision map of the test road section is used to make the intelligent driving vehicle perform intelligent driving test on the test road section to obtain a test result of the intelligent driving vehicle on the to-be-tested road section, including: acquiring pose information of the intelligent driving vehicle on the test road section in the test field, and converting the pose information by projection transformation to obtain converted pose information corresponding to the pose information in the to-be-tested road section; using the converted pose information to perform test of the intelligent driving vehicle on the test road section.

[0008] Optionally, the pose information of the intelligent driving vehicle on the test road section in the test field is acquired, and the pose information is converted by projection transformation to obtain converted pose information corresponding to the pose information in the to-be-tested road section, including: projecting and transforming the pose information into a third two-dimensional coordinate system to obtain first pose information; inversely affine transforming the first pose information by using an inverse affine transformation matrix to project the first pose information into a fourth two-dimensional coordinate system to obtain second pose information; inversely projecting and transforming the second pose information to obtain the converted pose information.

[0009] Optionally, the high-precision map of the test road section is used to make the intelligent driving vehicle perform intelligent driving test on the test road section to obtain a test result of the intelligent driving vehicle on the to-be-tested road section, including: generating dynamic obstacles according to the scene of the to-be-tested road section, and using the dynamic obstacles as perception information of the intelligent driving vehicle to perform test of the intelligent driving vehicle on the test road section, wherein the scene of the to-be-tested road section includes a curve and a slope.

[0010] The second technical solution adopted by the present application is to provide a test system for an intelligent driving vehicle, comprising: a high-precision map module for providing a local high-precision map of a to-be-tested road section; a coordinate information acquisition module for selecting a local high-precision map corresponding to the to-be-tested road section in the high-precision map and acquiring coordinate information corresponding to the local high-precision map as first coordinates; a conversion module for converting the first coordinates to a real test field by coordinate conversion according to the size of the real test field to obtain second coordinates, and then converting the local high-precision map corresponding to the to-be-tested road section into a high-precision map of a test road section in the real test field; a test module for enabling the intelligent driving vehicle to perform intelligent driving test on the test road section by using the high-precision map of the test road section to obtain a test result of the intelligent driving vehicle on the to-be-tested road section; and a test field for projecting and converting the local high-precision map into a real test environment and for enabling the intelligent driving vehicle to perform test according to the converted local high-precision map.

[0011] Optionally, the coordinate information acquisition module comprises: selecting a to-be-tested high-precision map region, i.e., a local high-precision map, in the high-precision map, selecting a to-be-tested road section in the local high-precision map, and acquiring static environment information corresponding to the to-be-tested road section, wherein the local high-precision map comprises lane line information and sign information; and the coordinate information corresponding to the local high-precision map is taken as the first coordinates.

[0012] Optionally, the conversion module comprises: projecting and converting the first coordinates into a first two-dimensional coordinate system to obtain third coordinates; projecting the third coordinates into a second two-dimensional coordinate system by using affine transformation according to the size of the test field to obtain fourth coordinates and an affine transformation matrix; and performing inverse projection and conversion on the fourth coordinates to obtain the second coordinates.

[0013] Optionally, the test module comprises: acquiring pose information of the intelligent driving vehicle on the test road section in the test field, and projecting and converting the pose information to obtain converted pose information corresponding to the to-be-tested road section; and performing test of the intelligent driving vehicle on the test road section by using the converted pose information.

[0014] Optionally, the test module further comprises: projecting and converting the pose information into a third two-dimensional coordinate system to obtain first pose information; performing inverse affine transformation on the first pose information by using an inverse affine transformation matrix to project the first pose information into a fourth two-dimensional coordinate system to obtain second pose information; and performing inverse projection and conversion on the second pose information to obtain the converted pose information.

[0015] Optionally, the test module comprises: generating dynamic obstacles according to the scene of the to-be-tested road section, and using the dynamic obstacles as perception information of the intelligent driving vehicle to perform test of the intelligent driving vehicle on the test road section, wherein the scene of the to-be-tested road section comprises a curve and a slope.

[0016] The third technical solution adopted by the present application is to provide a computer readable storage medium storing computer programs / instructions, which are operated to execute the test method of the intelligent driving vehicle in solution one.

[0017] The fourth technical solution adopted by the present application is to provide a computer device including a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the test method of the intelligent driving vehicle in solution one.

[0018] The fifth technical solution adopted by the present application is to provide a computer program product including computer programs / instructions, which are executed by the processor to implement the test method of the intelligent driving vehicle in solution one.

[0019] The beneficial effects achieved by the technical solutions of the present application are that the coordinates of the real road section in the high-precision map are converted to the test field through multiple projection transformations, so as to simulate the actual road conditions of the real road section in the test field, and the complex simulation scene based on the real environment can be constructed by combining the simulation perception results output by the perception module when the intelligent driving vehicle is tested in the test field, so as to facilitate the test of complex road conditions and ensure the safety and efficiency of the test process. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0021] Figure 1 is a schematic diagram of one specific embodiment of the test method of the intelligent driving vehicle of the present application;

[0022] Figure 2 is a flowchart of the conversion process of the high-precision map to the test field of the present application;

[0023] Figure 3 is a schematic diagram of selecting the to-be-tested road section in the high-precision map of the present application;

[0024] Figure 4 is a schematic diagram of the coordinate conversion of the to-be-tested road section of the present application;

[0025] Figure 5 is a flowchart of the conversion process of the test field to the high-precision map of the present application;

[0026] Figure 6This is a schematic diagram of a specific embodiment of a testing system for an intelligent driving vehicle according to this application.

[0027] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0028] The preferred embodiments of this application will now be described in detail with reference to the accompanying drawings, so that the advantages and features of this application can be more easily understood by those skilled in the art, thereby providing a clearer and more definite definition of the scope of protection of this application.

[0029] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0030] The method provided in this application is applicable to dynamic or static real-time testing under complex road conditions.

[0031] The inventive concept of this application is to project real-time GPS information onto a designated area road segment through multiple coordinate projection transformations, so that the tested system is operating in the test field, but the positioning system recognizes it as operating in the actual test road segment.

[0032] The technical solutions of this application and how they solve the aforementioned technical problems will be described in detail below with specific embodiments. The specific embodiments described below can be combined with each other to form new embodiments. The same or similar ideas or processes described in one embodiment may not be repeated in other embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0033] Figure 1 An embodiment of a testing method for an intelligent driving vehicle according to this application is shown.

[0034] Figure 1The test method of the intelligent driving vehicle shown comprises: in step S101, a local high-precision map corresponding to a to-be-tested road section is selected in a high-precision map, and coordinate information corresponding to the local high-precision map corresponding to the to-be-tested road section is obtained as first coordinates;

[0035] In step S102, the first coordinates are converted into a real test field by coordinate conversion according to the size of the real test field, second coordinates are obtained, and then the local high-precision map corresponding to the to-be-tested road section is converted into a high-precision map of a test road section in the real test field;

[0036] In step S103, the high-precision map of the test road section is used to make the intelligent driving vehicle perform intelligent driving test on the test road section, and test results of the intelligent driving vehicle on the to-be-tested road section are obtained. In the specific embodiment, the coordinates in the map are converted into the test field through multiple projection transformations, so as to simulate the actual road conditions of the real road section in the test field. When the intelligent driving vehicle performs test in the test field, a complex simulation scene based on the real environment can be constructed by cooperating with the simulation perception results output by the perception module, so as to facilitate the test of the complex road conditions, ensure the safety and efficiency of the test process, save the cost of building the test field, and better test the reliability of the intelligent driving system.

[0037] Specifically, in the test method of the prior art, the road conditions of the to-be-tested road are completely restored in the test field, and the to-be-tested intelligent driving vehicle is tested in the test field, or the to-be-tested intelligent driving vehicle is driven to the to-be-tested road section for test. The above two test methods cannot simultaneously consider safety and test cost. Although the to-be-tested road section is completely restored in the test field, the cost of building the environment is high and the built environment cannot be reused in many cases. When the to-be-tested road is tested, because the to-be-tested intelligent driving vehicle is not a mature product, unpredictable states may occur during the test process. Direct testing on the to-be-tested road cannot guarantee the safety of the test process. In addition, when some extreme conditions are tested, such as occlusion test and high-speed test, testing on the actual road is impossible. Therefore, the present application proposes a test method of an intelligent driving vehicle, which can complete the test of the intelligent driving vehicle on the to-be-tested road section at a low cost.

[0038] Figure 2 FIG. 1 is a flowchart of the process of converting the high-precision map into the test field according to the present application. As shown in FIG. 1, the process comprises the following steps: Figure 2As shown, in order to complete the test of the intelligent driving vehicle on the to-be-tested road section in another region in the test field, the application selects the road section corresponding to the to-be-tested road section in the high-precision map, and obtains the coordinate information of the to-be-tested road section in the high-precision map and the static environment information and the dynamic environment information corresponding to the to-be-tested road section as the first coordinate. The test field for selecting the intelligent driving vehicle for testing is selected according to the size of the test field, the first coordinate is converted into the test field through coordinate conversion, and the corresponding test road section of the to-be-tested road section in the test field is obtained. When the intelligent driving vehicle tests in the test road section of the test field, the vehicle positioning system of the intelligent driving vehicle obtains the real pose information corresponding to the intelligent driving vehicle, and projects and converts the pose information into the high-precision map through inverse conversion of the above-mentioned coordinate conversion. The pose information projected into the high-precision map is obtained as the information obtained by the perception system of the intelligent driving vehicle, so that the intelligent driving system to be tested will recognize that the intelligent driving vehicle runs on the to-be-tested road section. Through the above-mentioned method, the test of the intelligent driving vehicle on the real road section in the test road section of the test field can be completed, and the test result of the intelligent driving vehicle on the to-be-tested road section is obtained.

[0039] In Figure 1 In the embodiment shown, the test method of the intelligent driving vehicle comprises the step S101 of selecting a local high-precision map corresponding to a to-be-tested road section in a high-precision map, and obtaining coordinate information corresponding to the local high-precision map corresponding to the to-be-tested road section as a first coordinate. This step uses the high-precision map to obtain the related information of the to-be-tested road section, and lays a foundation for the construction and testing of the test road section in the test field according to the related information of the to-be-tested road section.

[0040] In one specific embodiment of the application, the step S101 comprises selecting a local high-precision map corresponding to a to-be-tested road section, and obtaining coordinate information corresponding to the local high-precision map corresponding to the to-be-tested road section as a first coordinate, which comprises: selecting a to-be-tested high-precision map region, i.e. a local high-precision map, in the high-precision map, selecting a to-be-tested road section in the local high-precision map, and obtaining static environment information corresponding to the to-be-tested road section, wherein the local high-precision map comprises lane line information and sign information; and taking the coordinate information corresponding to the local high-precision map as the first coordinate.

[0041] Specifically, as Figure 3 is a schematic diagram of selecting a to-be-tested road section in a high-precision map according to the application, as Figure 3 In the high-precision map, a to-be-tested region is selected, i.e. Figure 3 the part enclosed by the frame line in the map. In the to-be-tested region, a to-be-tested road section is selected, and the static environment information corresponding to the to-be-tested road section is obtained by using the high-precision map, and the to-be-tested road section is Figure 3The static environment information for Road 1 includes the location and content of signs, the location and type of traffic lights, the location of streetlights, and lane markings. Simultaneously, high-precision maps are used to obtain the coordinates of the road segment under test, facilitating a better reconstruction of its road conditions. By acquiring this static environment information, the real-world road conditions can be better recreated in the test field, enabling intelligent driving vehicles to conduct tests that are inconvenient to perform on actual roads, including occlusion tests.

[0042] exist Figure 1 In the specific embodiment shown, the testing method for intelligent driving vehicles further includes step S102, which involves transforming the first coordinates to the actual test field based on the size of the test field, obtaining the second coordinates, and then converting the local high-precision map corresponding to the road segment to be tested into a high-precision map of the corresponding test road segment within the actual test field. This step, through coordinate transformation, can obtain the correspondence between the road segment to be tested and the designated test field, reducing testing costs during the testing process, making the testing process safer, and enabling remote testing of the road segment to be tested.

[0043] Specifically, a test track for testing intelligent driving vehicles is selected, and information such as the size, location, and coordinates of the test track is obtained. Based on the first coordinate of the road segment to be tested and the relevant information of the test track, the first coordinate is transformed into the test track, and the projection transformation relationship between the road segment to be tested and the test track is calculated and saved for subsequent coordinate transformation between the road segment to be tested and the test track. Using the projection transformation relationship, the corresponding test road segment in the test track is determined.

[0044] In one specific embodiment of this application, step S102 includes: projecting the first coordinates onto a first two-dimensional coordinate system to obtain the third coordinates; projecting the third coordinates onto a second two-dimensional coordinate system using an affine transformation according to the size of the test field to obtain the fourth coordinates and the affine transformation matrix; and performing an inverse projection transformation on the fourth coordinates to obtain the second coordinates.

[0045] Specifically, such as Figure 4 This is a schematic diagram of the coordinate transformation of the road segment to be tested in this application, as shown below. Figure 4 , using Figure 3 The origin of the coordinate system is selected on Road 1 (the bold point in Figure 3). The coordinates of the road segment to be measured are transformed into the first two-dimensional coordinate system using the Gauss-Kruger transformation, as shown below. Figure 4The third coordinates are projected into the second two-dimensional coordinate system according to the size of the test field, and the fourth coordinates and an affine transformation matrix are obtained by performing rotation transformation and the like on the third coordinates. For example, the third coordinates are subjected to affine transformation to obtain the fourth coordinates as shown in Road 2. Figure 4 The fourth coordinates are projected into the test field to obtain the second coordinates by performing inverse projection transformation on the fourth coordinates (Road 2). The two-dimensional coordinate system here can be a two-dimensional local Cartesian coordinate system. The first two-dimensional coordinate system and the second two-dimensional coordinate system can be the same two-dimensional coordinate system or different two-dimensional coordinate systems, Figure 4 The example is illustrated in the same coordinate system. The coordinate conversion method described here is only exemplary, and the coordinate conversion method in actual application is not limited by the present application.

[0046] In the specific embodiment shown in Figure 1 In the specific embodiment shown in

[0047] Specifically, the positioning system of the intelligent driving vehicle obtains the real GPS information of the corresponding test section, and converts the real GPS information to the test section in the high-precision map by the projection transformation relationship between the test section and the test section that has been calculated. Among them, the pose information such as GPU or IMU can also be converted by the same conversion method, and the conversion of dynamic virtual environment information or static virtual environment information related to the position of the high-precision map including but not limited to lane lines, signs, V2X devices, environment vehicles and the like can also be performed.

[0048] In one specific embodiment of the present application, step S103 includes obtaining the pose information of the intelligent driving vehicle on the test section in the test field, and performing projection transformation on the pose information to obtain the converted pose information corresponding to the pose information in the test section; and using the converted pose information to test the intelligent driving vehicle on the test section.

[0049] Further, the pose information is projected and transformed into a third two-dimensional coordinate system to obtain first pose information; the first pose information is projected into a fourth two-dimensional coordinate system through inverse affine transformation by using an inverse affine transformation matrix to obtain second pose information; and the second pose information is inversely projected and transformed to obtain converted pose information.

[0050] Specifically, Figure 5 is a flowchart of the test field to high-precision map conversion process of the present application. As Figure 5 , the intelligent driving vehicle tests according to the test section in the test field and obtains the pose information corresponding to the test section in the test field. The pose information is converted into a third two-dimensional coordinate system through Gauss-Kruger transformation using the coordinate origin selected on the test section, to obtain first pose information; the affine transformation inverse matrix is calculated using the affine transformation matrix calculated in the process of projecting and transforming the test section in the high-precision map into the specified test field, and the first pose information is inversely transformed through the inverse affine transformation of the affine transformation inverse matrix to obtain second pose information in the fourth two-dimensional coordinate system. The second pose information is inversely projected and transformed using the inverse Gauss-Kruger transformation to obtain converted pose information. The third two-dimensional coordinate system and the fourth two-dimensional coordinate system can be the same coordinate system as the first two-dimensional coordinate system and the second two-dimensional coordinate system used in the process of projecting and transforming the test section in the high-precision map into the specified test field, or can be different coordinate systems. The intelligent driving vehicle in the test field can simulate the test situation of the intelligent driving test vehicle on the real test section through the projection and transformation of the pose information and in cooperation with other required test information.

[0051] In one specific embodiment of the present application, step S103 includes generating dynamic obstacles according to the scene of the test section, and using the dynamic obstacles as the perception information of the intelligent driving vehicle to test the intelligent driving vehicle under the condition of the test cost of the virtual test section, so that the vehicle tests various functions in the actual environment, which not only ensures real vehicle-in-the-loop testing, but also ensures test safety. When combined with high-precision map related information, the functions and stability of the system under various actual working conditions can be quickly and safely verified through dynamic generation and other methods.

[0052] Specifically, the scheme of the present application is more convenient and integrated with other simulation functions, and has less interference compared with existing integrated use methods. For example, dynamic obstacle information is calculated and generated according to the scene corresponding to the test section, and the generated dynamic obstacles are input into the perception module of the intelligent driving vehicle in real time, and the planning and decision-making function modules of the intelligent driving vehicle make decisions and other tests according to the results of the perception module.

[0053] In a specific embodiment of the present application, testing on actual roads is essential in the landing process of the intelligent driving system, and a pure virtual simulation environment is difficult to reflect various working conditions of the vehicle on the actual road and various working conditions of the actual to-be-tested hardware and software system in the vehicle-mounted environment through ViL testing (whole vehicle in loop testing). The present application projects and converts the to-be-tested road section to the test field, so that the to-be-tested vehicle can test the actual to-be-tested road section in a safe and controllable test field environment, and realize a complete ViL testing process. The ViL testing that can be realized by the present application includes lane line recognition testing in the testing process, calculation of the corresponding lane line information in the high-precision map through the positioning information of the intelligent driving vehicle, input of the lane line information in the high-precision map into the tested system, realization of the lane line recognition testing, and integration of various errors in the testing process to make the test result more accurate. On the actual to-be-tested road section, it is basically impossible to arrange V2X equipment by oneself, but the present application solves this problem. In the testing process, V2X arrangement can be realized in the test field, and the system can determine that the intelligent driving vehicle has completed the V2X test on the to-be-tested road section. Moreover, the method adopted by the present application is more friendly to the national secret positioning plug-in, and the test running process of the intelligent driving vehicle does not affect the use of the national secret positioning plug-in. The system still obtains the encrypted coordinates of the national bureau, which does not affect the test result.

[0054] Figure 6 A specific embodiment of a test system of an intelligent driving vehicle of the present application is shown.

[0055] In Figure 6 In the specific embodiment shown, the test system of the intelligent driving vehicle mainly includes: a high-precision map module 601 for providing a local high-precision map of a to-be-tested road section;

[0056] A coordinate information acquisition module 602 is configured to select a local high-precision map corresponding to the to-be-tested road section in the high-precision map, and acquire coordinate information corresponding to the local high-precision map corresponding to the to-be-tested road section as first coordinates.

[0057] A conversion module 603 is configured to convert the first coordinates to a real test field through coordinate conversion according to the size of the real test field, to obtain second coordinates, and further convert the local high-precision map corresponding to the to-be-tested road section into a high-precision map of a test road section in the real test field;

[0058] A test module 604 is configured to use the high-precision map of the test road section to make the intelligent driving vehicle perform intelligent driving testing on the test road section, and obtain a test result of the intelligent driving vehicle on the to-be-tested road section.

[0059] The test field 605 is used for projecting and converting the local high-precision map into a real test environment, and for testing the intelligent driving vehicle according to the converted local high-precision map. In this specific embodiment, the received real vehicle pose information (GPS and IMU information) is converted to the position of the road to be tested according to the configuration parameters through multiple projection and conversion, so as to deceive the intelligent driving system to be tested, and make the system recognize that the intelligent driving vehicle is in the real road section to be tested for testing, so as to complete the testing of the road section to be tested in the test field, and make the testing process safer.

[0060] In one specific embodiment of the present application, the coordinate information acquisition module includes: selecting a high-precision map region to be tested, i.e., a local high-precision map, in the high-precision map, selecting a road section to be tested in the local high-precision map, and acquiring static environment information corresponding to the road section to be tested, wherein the local high-precision map includes lane line information and sign information; and the coordinate information corresponding to the local high-precision map is taken as the first coordinate.

[0061] In one specific embodiment of the present application, the conversion module includes: projecting and converting the first coordinate into a first two-dimensional coordinate system to obtain a third coordinate; using affine transformation to project the third coordinate into a second two-dimensional coordinate system to obtain a fourth coordinate and an affine transformation matrix according to the size of the test field; and performing inverse projection and conversion on the fourth coordinate to obtain the second coordinate.

[0062] In one specific embodiment of the present application, the test module includes: acquiring pose information of the intelligent driving vehicle on the test section in the test field, and performing projection and conversion on the pose information to obtain converted pose information corresponding to the pose information in the road section to be tested; and using the converted pose information to test the intelligent driving vehicle on the test section.

[0063] In one specific embodiment of the present application, the test module further includes: projecting and converting the pose information into a third two-dimensional coordinate system to obtain first pose information; performing inverse affine transformation on the first pose information through an inverse affine transformation matrix to project the first pose information into a fourth two-dimensional coordinate system to obtain second pose information; and performing inverse projection and conversion on the second pose information to obtain the converted pose information.

[0064] In one specific embodiment of the present application, the test module includes: generating dynamic obstacles according to the scene of the road section to be tested, and using the dynamic obstacles as perception information of the intelligent driving vehicle to test the intelligent driving vehicle on the test section, wherein the scene of the road section to be tested includes a curve and a slope.

[0065] The test system of the intelligent driving vehicle provided in the present application can be used to execute the test method of the intelligent driving vehicle described in any of the above embodiments, and has similar implementation principles and technical effects, which will not be described here again.

[0066] In one embodiment of the present application, the functional modules in the test system of the intelligent driving vehicle can be directly in hardware, in a software module executed by a processor, or a combination of both.

[0067] The software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium.

[0068] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, or any combination thereof, etc. The general-purpose processor can be a microprocessor, but in the alternative, the processor can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. In the alternative, the storage medium can be integral to the processor. The processor and the storage medium can reside in an ASIC. The ASIC can reside in a user terminal. In the alternative, the processor and the storage medium can reside as discrete components in a user terminal.

[0069] In another embodiment of the present application, a computer readable storage medium stores computer programs / instructions that are operated to perform the test method of the intelligent driving vehicle described in the above embodiments.

[0070] In one embodiment of the present application, a computer device includes a memory, a processor, and a computer program stored on the memory, and the processor executes the computer program to implement the test method of the intelligent driving vehicle described in the above embodiments.

[0071] In one specific embodiment of the present application, a computer program product includes computer programs / instructions that, when executed by a processor, implement the test method of the intelligent driving vehicle described in the above embodiments.

[0072] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, apparatuses or units, and can be electrical, mechanical or other forms.

[0073] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0074] The above description is only an embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structural transformation made by using the content of the present application specification and drawings, or directly or indirectly applied to other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A test method of an intelligent driving vehicle, characterized by, The application relates to a method for testing intelligent driving of a vehicle. The method comprises the following steps: selecting a local high-precision map corresponding to a to-be-tested road section in a high-precision map, and obtaining coordinate information corresponding to the local high-precision map as first coordinates; converting the first coordinates into a real test field through coordinate conversion according to the size of the real test field, obtaining second coordinates, and then converting the local high-precision map corresponding to the to-be-tested road section into a high-precision map of a test road section in the real test field; using the high-precision map of the test road section to make the intelligent driving vehicle test intelligent driving on the test road section, and obtaining a test result of the intelligent driving vehicle on the to-be-tested road section; wherein the step of using the high-precision map of the test road section to make the intelligent driving vehicle test intelligent driving on the test road section, and obtaining a test result of the intelligent driving vehicle on the to-be-tested road section comprises the following steps: obtaining pose information of the intelligent driving vehicle on the test road section in the real test field, and performing projection conversion on the pose information to obtain converted pose information corresponding to the pose information in the to-be-tested road section; 2. The test method of an intelligent driving vehicle according to claim 1, wherein using the converted pose information to test the intelligent driving vehicle on the test road section. The step of selecting a local high-precision map corresponding to a to-be-tested road section in a high-precision map, and obtaining coordinate information corresponding to the local high-precision map as first coordinates comprises the following steps: selecting a to-be-tested high-precision map region, i.e. a local high-precision map, in a high-precision map, selecting the to-be-tested road section in the local high-precision map, and obtaining static environment information corresponding to the to-be-tested road section, wherein the local high-precision map comprises lane line information and sign information; 3. The test method of an intelligent driving vehicle according to claim 1, wherein the coordinate information corresponding to the local high-precision map is taken as the first coordinates. The step of converting the first coordinates into a real test field through coordinate conversion according to the size of the real test field, obtaining second coordinates, and then converting the local high-precision map corresponding to the to-be-tested road section into a high-precision map of a test road section in the real test field comprises the following steps: performing projection conversion on the first coordinates into a first two-dimensional coordinate system to obtain third coordinates; according to the size of the test field, performing affine conversion on the third coordinates into a second two-dimensional coordinate system to obtain fourth coordinates and an affine conversion matrix; 4. The test method of an intelligent driving vehicle according to claim 1, wherein performing inverse projection conversion on the fourth coordinates to obtain the second coordinates. The step of obtaining pose information of the intelligent driving vehicle on the test road section in the real test field, and performing projection conversion on the pose information to obtain converted pose information corresponding to the pose information in the to-be-tested road section comprises the following steps: performing projection conversion on the pose information into a third two-dimensional coordinate system to obtain first pose information; performing inverse affine conversion on the first pose information into a fourth two-dimensional coordinate system through an affine conversion inverse matrix to obtain second pose information; 5. The test method of an intelligent driving vehicle according to claim 1, wherein performing inverse projection conversion on the second pose information to obtain the converted pose information. The step of using the high-precision map of the test road section to make the intelligent driving vehicle test intelligent driving on the test road section, and obtaining a test result of the intelligent driving vehicle on the to-be-tested road section comprises the following steps: According to the scene of the to-be-tested section, a dynamic obstacle is generated, and the dynamic obstacle is used as perception information of the intelligent driving vehicle to test the intelligent driving vehicle on the test section, wherein the scene of the to-be-tested section includes a curve and a slope.

6. A test system for intelligent driver vehicles, characterized by The application comprises: a high-precision map module configured to provide a local high-precision map of a to-be-tested section; a coordinate information acquisition module configured to select a local high-precision map corresponding to the to-be-tested section in a high-precision map and acquire coordinate information corresponding to the local high-precision map corresponding to the to-be-tested section as first coordinates; a conversion module configured to convert the first coordinates to a real test field by coordinate conversion according to a size of the real test field to obtain second coordinates, and further convert the local high-precision map corresponding to the to-be-tested section into a high-precision map of a test section in the real test field; a test module configured to use the high-precision map of the test section to test the intelligent driving vehicle on the test section to obtain a test result of the intelligent driving vehicle on the to-be-tested section, wherein the test module comprises: acquiring pose information of the intelligent driving vehicle on the test section in the real test field, and projecting and transforming the pose information to obtain converted pose information of the pose information in the to-be-tested section; and using the converted pose information to test the intelligent driving vehicle on the test section; a test field configured to project and transform the local high-precision map to a real test environment, and configured to test the intelligent driving vehicle according to the transformed local high-precision map.

7. A computer readable storage medium storing computer programs / instructions, characterized in that, The computer program / instructions are operated to perform the test method of the intelligent driving vehicle according to any one of claims 1-5.

8. A computer device comprising a memory, a processor, and a computer program stored on the memory, wherein the computer program comprises instructions that, when executed by the processor, cause the processor to perform the method of any one of claims 1-7. The processor executes the computer program to implement the test method of the intelligent driving vehicle according to any one of claims 1-5.

9. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instructions are executed by the processor to implement the test method of the intelligent driving vehicle according to any one of claims 1-5.

Images