Vehicle testing method and device, processor, vehicle and storage medium

Abstract

The invention discloses a vehicle testing method and device, a processor, a vehicle and a storage medium. The method comprises the steps that original scene information of a to-be-tested vehicle is acquired; the original scene information is reconstructed to obtain first reconstructed scene information, and the first reconstructed scene information is used for representing virtual video data of the reconstructed real driving scene; based on original driving information of the to-be-tested vehicle, the first reconstructed scene information is adjusted to obtain second reconstructed scene information, and the original driving information is used for representing driving parameters of the to-be-tested vehicle driving in the real driving scene; and testing the to-be-tested vehicle driving according to the original driving information by using the second reconstructed scene information to obtain a test result of the to-be-tested vehicle. The technical problem that the safety test efficiency of the vehicle in the intelligent driving mode is low is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of vehicles, in particular to a vehicle testing method, device, processor, vehicle and storage medium. BACKGROUND

[0002] With the development of intelligent driving systems, the testing of intelligent driving functions of vehicles is becoming increasingly important. However, the traditional simulation testing of intelligent driving functions mainly relies on a pre-set static scene library, which can include fixed weather conditions, fixed obstacle positions, pre-set target vehicles, and pre-set driving trajectories, etc. Therefore, the traditional testing method is difficult to meet the simulation of dynamic scenes, resulting in the technical problem of low efficiency of safety testing of vehicles in the intelligent driving mode.

[0003] At present, there is no effective solution to the technical problem of low efficiency of safety testing of vehicles in the intelligent driving mode. SUMMARY

[0004] The embodiments of the present application provide a vehicle testing method, device, processor, vehicle and storage medium to at least solve the technical problem of low efficiency of safety testing of vehicles in the intelligent driving mode.

[0005] According to an aspect of an embodiment of the present application, a vehicle testing method is provided, which includes: obtaining original scene information of a vehicle to be tested, wherein the original scene information is used to represent virtual video data recording a real driving scene in which the vehicle to be tested is located, and the virtual video data is used to simulate a virtual driving scene corresponding to the real driving scene; reconstructing the original scene information to obtain first reconstructed scene information, wherein the first reconstructed scene information is used to represent virtual video data of the reconstructed real driving scene; adjusting the first reconstructed scene information based on original driving information of the vehicle to be tested to obtain second reconstructed scene information, wherein the original driving information is used to represent driving parameters of the vehicle to be tested driving in the real driving scene; and testing the vehicle to be tested driving according to the original driving information using the second reconstructed scene information to obtain a testing result of the vehicle to be tested.

[0006] Optionally, reconstructing the original scene information to obtain the first reconstructed scene information includes: determining a first timestamp of the original scene information and a second timestamp of the original driving information; determining a first difference between the first timestamp and the second timestamp; and reconstructing the original scene information based on the first difference to obtain the first reconstructed scene information.

[0007] Optionally, the original scene information is reconstructed based on the first difference to obtain first reconstructed scene information, including: in response to the first difference being greater than the target difference, adjusting the original scene information, wherein a second difference between a third time stamp of the adjusted original scene information and the second time stamp is less than or equal to the target difference; performing object insertion on a virtual driving scene corresponding to the adjusted original scene information, and performing environment rendering on the virtual driving scene corresponding to the adjusted original scene information to obtain the first reconstructed scene information.

[0008] Optionally, the original scene information is reconstructed based on the first difference to obtain first reconstructed scene information, including: in response to the first difference being less than or equal to the target difference, performing object insertion on a virtual driving scene corresponding to the original scene information, and performing environment rendering on the virtual driving scene corresponding to the original scene information to obtain the first reconstructed scene information.

[0009] Optionally, the original scene information is reconstructed based on the first difference to obtain first reconstructed scene information, including: in response to the first difference being less than or equal to the target difference, performing object insertion on a virtual driving scene corresponding to the original scene information, and performing environment rendering on the virtual driving scene corresponding to the original scene information to obtain the first reconstructed scene information.

[0010] Optionally, the target driving trajectory of the virtual object is determined based on the target driving information, including: inputting the first state information and the target driving information into a trajectory prediction model for prediction to obtain the target driving trajectory, wherein the trajectory prediction model includes a mapping relationship between the first state information, the target driving information and the target driving trajectory.

[0011] According to an aspect of an embodiment of the present application, a testing device of a vehicle is provided. The device can include an acquisition unit configured to acquire original scene information of a vehicle to be tested, wherein the original scene information is used to represent virtual video data of a real driving scene in which the vehicle to be tested is located, and the virtual video data is used to simulate a virtual driving scene corresponding to the real driving scene; a reconstruction unit configured to reconstruct the original scene information to obtain first reconstructed scene information, wherein the first reconstructed scene information is used to represent virtual video data of the real driving scene after reconstruction; an adjustment unit configured to adjust the first reconstructed scene information based on original driving information of the vehicle to be tested to obtain second reconstructed scene information, wherein the original driving information is used to represent driving parameters of the vehicle to be tested driving in the real driving scene; and a testing unit configured to test the vehicle to be tested driving according to the original driving information by using the second reconstructed scene information to obtain a testing result of the vehicle to be tested.

[0012] According to another aspect of an embodiment of the present application, a processor is provided. The processor is configured to run a program, wherein the program, when run by the processor, performs the testing method of the vehicle in the embodiments of the present application.

[0013] According to another aspect of an embodiment of the present application, a vehicle is provided. The vehicle includes a memory storing an executable program, and a processor configured to run the program, wherein the program, when run, performs the testing method of the vehicle in the embodiments of the present application.

[0014] According to another aspect of an embodiment of the present application, a computer readable storage medium is provided. The computer readable storage medium includes a stored program, wherein the program, when run, controls a device in which the computer readable storage medium is located to perform the testing method of the vehicle in the embodiments of the present application.

[0015] According to another aspect of an embodiment of the present application, a computer program product is provided. The computer program product includes a computer program, wherein the computer program, when executed by a processor, implements the testing method of the vehicle in the embodiments of the present application.

[0016] According to another aspect of an embodiment of the present application, a computer program product is provided. The computer program product includes a non-volatile computer readable storage medium configured to store a computer program, wherein the computer program, when executed by a processor, implements the testing method of the vehicle in the embodiments of the present application.

[0017] According to another aspect of an embodiment of the present application, a computer program is provided. The computer program, when executed by a processor, implements the testing method of the vehicle in the embodiments of the present application.

[0018] In the embodiment of the present application, when the vehicle in the intelligent driving mode is tested, the original scene information of the vehicle to be tested can be obtained. The original scene information obtained is reconstructed to obtain the first reconstructed scene information, that is, the virtual video data of the reconstructed real driving scene; the first reconstructed scene information is adjusted according to the original driving information of the vehicle to be tested to obtain the second reconstructed scene information, and the vehicle to be tested is tested according to the second reconstructed scene information to obtain the test result of the vehicle to be tested, thereby achieving the purpose of simulating the dynamic scene, solving the technical problem of low efficiency of the safety test of the vehicle in the intelligent driving mode, and further realizing the technical effect of improving the efficiency of the safety test of the vehicle in the intelligent driving mode. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings, which are included to provide a further understanding of the present application and constitute a part of this application, illustrate embodiments of the present application and together with the description serve to explain the present application. In the drawings:

[0020] Figure 1 is a flowchart of a test method of a vehicle according to an embodiment of the present application;

[0021] FIG. 2(a) is a schematic diagram of an intelligent driving simulation test system based on dynamic video injection according to an embodiment of the present application;

[0022] FIG. 2(b) is a schematic diagram of a video injection module according to an embodiment of the present application;

[0023] FIG. 2(c) is a flowchart of a dynamic video generation method according to an embodiment of the present application;

[0024] FIG. 2(d) is a flowchart of a space-time synchronization method according to an embodiment of the present application;

[0025] Figure 3 is a schematic diagram of a test device of a vehicle according to an embodiment of the present application;

[0026] Figure 4 is a schematic diagram of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application in order to make the persons skilled in the art better understand the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by the persons skilled in the art without creative work should belong to the protection scope of the present application.

[0028] It should be noted that the terms "first", "second" and the like in the description and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, 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 "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to include those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0029] According to the embodiments of the present application, a test method of a vehicle is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0030] Figure 1 is a flowchart of a test method of a vehicle according to the embodiments of the present application, as shown in Figure 1 The method can include the following steps:

[0031] Step S101, obtaining original scene information of a vehicle to be tested.

[0032] In the technical solution provided in the step S101 of the present application, the original scene information can be used to represent virtual video data of a real driving scene in which the vehicle under test is located, and the virtual video data can be used to simulate a virtual driving scene corresponding to the real driving scene. For example, the original scene information can be an original simulation video of a real driving scene in which the vehicle under test is located. The real driving scene can include a city road driving scene, a highway driving scene, a town road driving scene, etc. If the real driving scene is a city road driving scene, the virtual driving scene can be a virtual city road driving scene corresponding to the city road driving scene. If the real driving scene is a highway driving scene, the virtual driving scene can be a virtual highway driving scene corresponding to the highway driving scene. If the real driving scene is a town road driving scene, the virtual driving scene can be a virtual town road driving scene corresponding to the town road driving scene. This is only an example and is not limited in a specific manner.

[0033] In this embodiment, the original scene information of the vehicle under test is obtained. Optionally, the embodiment uses a scene simulation software to simulate a real driving scene in which the vehicle under test is located, and the original scene information of the vehicle under test can be obtained, i.e., virtual video data used to simulate a virtual driving scene corresponding to the real driving scene can be obtained.

[0034] For example, if the real driving scene in which the vehicle under test is located is a city road driving scene, the scene simulation software is used to simulate the real driving scene of the city road driving scene, and virtual video data used to simulate a virtual city road driving scene corresponding to the city road driving scene can be obtained. This is only an example and is not limited in a specific manner.

[0035] In step S102, the original scene information is reconstructed to obtain first reconstructed scene information.

[0036] In the technical solution provided in the step S102 of the present application, the first reconstructed scene information can be used to represent virtual video data of a reconstructed real driving scene, and the reconstruction operation is only an example and is not limited in a specific manner.

[0037] In this embodiment, after the original scene information of the vehicle under test is obtained, the original scene information is reconstructed to obtain first reconstructed scene information. Optionally, the embodiment adjusts the obtained original scene information on the basis of the obtained original scene information of the vehicle under test, and then reconstructs the adjusted original scene information to obtain the first reconstructed scene information, i.e., virtual video data of a reconstructed real driving scene can be obtained.

[0038] In this embodiment, the obtained frame information of the original scene information is adjusted according to the original driving information of the vehicle to be tested, then the original scene information after adjustment is subjected to object insertion, and the virtual driving scene corresponding to the original scene information after adjustment is subjected to environment rendering, so that the virtual video data of the reconstructed real driving scene can be obtained.

[0039] In step S103, the first reconstructed scene information is adjusted based on the original driving information of the vehicle to be tested to obtain second reconstructed scene information.

[0040] In the technical solution provided by step S103 of the present application, the original driving information can be used to represent the driving parameters of the vehicle to be tested in the real driving scene, wherein the driving parameters can include speed information, position information and attitude information of the vehicle to be tested in the real driving scene, etc., the speed information can include driving speed, acceleration and yaw rate of the vehicle to be tested, etc., the position information can include position coordinates and position orientation of the vehicle to be tested, etc., and the attitude information can include vehicle head attitude, vehicle body attitude and vehicle tail attitude, etc., which are only exemplified and not specifically limited.

[0041] In this embodiment, after the original scene information is reconstructed to obtain the first reconstructed scene information, the first reconstructed scene information is adjusted based on the original driving information of the vehicle to be tested to obtain the second reconstructed scene information. Alternatively, based on the first reconstructed scene information, the original driving information of the vehicle to be tested can be obtained, and the characteristics of the virtual objects included in the virtual driving scene corresponding to the first reconstructed scene information are adjusted according to the obtained original driving information, so that the second reconstructed scene information can be obtained, that is, the virtual video data of the adjusted real driving scene can be obtained.

[0042] Alternatively, the original characteristics of the virtual objects included in the virtual driving scene corresponding to the first reconstructed scene information are adjusted according to the obtained original driving information, so that the target characteristics can be obtained. Then, in the virtual driving scene corresponding to the first reconstructed scene information, the virtual objects with original characteristics are replaced by virtual objects with target characteristics, so that the second reconstructed scene information is obtained, which is only exemplified and not specifically limited.

[0043] Alternatively, the original characteristics of the virtual objects included in the virtual driving scene corresponding to the first reconstructed scene information are adjusted according to the obtained original driving information, so that the target characteristics can be obtained. Then, in the virtual driving scene corresponding to the first reconstructed scene information, the original characteristics of the virtual objects are replaced by the target characteristics obtained by adjustment, so that the second reconstructed scene information is obtained, which is only exemplified and not specifically limited.

[0044] It should be noted that the virtual object can include at least one of a virtual pedestrian, a virtual vehicle, a virtual roadblock, and the like, which are only illustrative and not specifically limited.

[0045] In step S104, the test vehicle is tested according to the original driving information based on the second reconstructed scene information, and a test result of the test vehicle is obtained.

[0046] In the technical solution provided in step S104, the test of the test vehicle according to the original driving information can be intelligent driving simulation testing.

[0047] In this embodiment, the test result can be used to indicate whether the test vehicle according to the original driving information collides with the virtual object. For example, the test result can be that the test vehicle according to the original driving information collides with the virtual object, or that the test vehicle according to the original driving information does not collide with the virtual object, which are only illustrative and not specifically limited.

[0048] In this embodiment, after the first reconstructed scene information is adjusted based on the original driving information of the test vehicle to obtain the second reconstructed scene information, the test vehicle is tested according to the original driving information based on the second reconstructed scene information, and a test result of the test vehicle is obtained. Alternatively, based on the second reconstructed scene information obtained by adjustment, the test vehicle in the intelligent driving mode is controlled to drive according to the original driving information in the virtual driving scene corresponding to the second reconstructed scene information, and the test vehicle is tested according to the original driving information during driving, and a test result can be obtained, that is, whether the test vehicle according to the original driving information collides with the virtual object.

[0049] It should be noted that the test method of the vehicle in the present application can be applied not only to specific types of vehicles (such as school buses and fire trucks), but also to other types of vehicles including but not limited to trucks, buses, and sedans. That is, as long as the safety test of the vehicle is involved, no matter what type of vehicle, the intelligent driving simulation test of the vehicle can be performed by the test method of the vehicle in the present application.

[0050] The above steps S101 to S104 of the application can obtain the original scene information of the vehicle to be tested when the vehicle in the intelligent driving mode is tested. The original scene information obtained is reconstructed to obtain the first reconstructed scene information, that is, the virtual video data of the reconstructed real driving scene. The first reconstructed scene information obtained by reconstruction is adjusted according to the original driving information of the vehicle to be tested to obtain the second reconstructed scene information. The vehicle to be tested is tested according to the original driving information by using the second reconstructed scene information obtained by adjustment to obtain the test result of the vehicle to be tested. Thus, the purpose of simulating dynamic scenes is achieved, thereby solving the technical problem of low efficiency of safety testing of vehicles in the intelligent driving mode, and further achieving the technical effect of improving the efficiency of safety testing of vehicles in the intelligent driving mode.

[0051] The above method of the embodiment will be further described below.

[0052] As an optional embodiment, in step S102, the original scene information is reconstructed to obtain the first reconstructed scene information, including: determining a first timestamp of the original scene information and a second timestamp of the original driving information; determining a first difference between the first timestamp and the second timestamp; and reconstructing the original scene information based on the first difference to obtain the first reconstructed scene information.

[0053] In the embodiment, the first timestamp can be used to represent the time mark of each frame of image data in the virtual video data corresponding to the original scene information. For example, the first timestamp can be represented by T_video, which is only illustrative and not limited.

[0054] In the embodiment, the second timestamp can be used to represent the time mark of each original driving information in the plurality of original driving information. For example, the second timestamp can be represented by T_phys, which is only illustrative and not limited.

[0055] In the embodiment, after obtaining the original scene information of the vehicle to be tested, the first timestamp of the original scene information and the second timestamp of the original driving information are determined. Optionally, based on the obtained original scene information of the vehicle to be tested, the time mark of each frame of image data in the virtual video data corresponding to the original scene information is recorded to obtain the first timestamp, and the time mark of each original driving information in the plurality of original driving information is recorded to obtain the second timestamp. The first timestamp and the second timestamp obtained are calculated to obtain the first difference between the first timestamp and the second timestamp, thereby achieving the purpose of calculating the time difference.

[0056] Optionally, a first difference between the first timestamp and the second timestamp can be obtained by calculating the difference between the first timestamp and the second timestamp, which can be achieved by the following formula (1):

[0057] Δt = |T phys-T video | (1)

[0058] In this embodiment, after determining the first difference between the first timestamp and the second timestamp, the original scene information is reconstructed based on the first difference to obtain the first reconstructed scene information. Optionally, based on the first difference between the first timestamp and the second timestamp, the original scene information obtained is adjusted according to the relationship between the first difference and a target difference, and then the adjusted original scene information is reconstructed to obtain the first reconstructed scene information, thereby achieving the purpose of determining the virtual video data of the reconstructed real driving scene, and realizing the technical effect of improving the simulation accuracy of the real driving scene.

[0059] The step of reconstructing the original scene information based on the first difference to obtain the first reconstructed scene information in this embodiment will be further introduced below.

[0060] As an optional embodiment, reconstructing the original scene information based on the first difference to obtain the first reconstructed scene information includes: adjusting the original scene information in response to the first difference being greater than the target difference; inserting an object into a virtual driving scene corresponding to the adjusted original scene information, and rendering an environment of the virtual driving scene corresponding to the adjusted original scene information to obtain the first reconstructed scene information.

[0061] In this embodiment, a second difference between a third timestamp of the adjusted original scene information and the second timestamp can be less than or equal to the target difference. The third timestamp can be used to represent a time mark of each frame of image data in the virtual video data corresponding to the adjusted original scene information.

[0062] In this embodiment, the target difference can be used to determine whether to adjust the original scene information. For example, the target difference can be 9 ms and 10 ms, and the values herein are only used as examples and are not limited specifically.

[0063] In this embodiment, the adjustment operation can be an operation of adjusting the playback frame rate of the virtual video data corresponding to the original scene information, or an operation of inserting a video frame or an operation of deleting a video frame.

[0064] In this embodiment, after determining the first difference between the first timestamp and the second timestamp, the original scene information is adjusted in response to the first difference being greater than the target difference. Optionally, the embodiment determines the relationship between the obtained first difference and the target difference on the basis of the obtained first difference between the first timestamp and the second timestamp, and if it is determined that the obtained first difference is greater than the target difference, the obtained original scene information is adjusted, thereby achieving the purpose of being able to adjust the original scene information.

[0065] In this embodiment, the environment rendering operation can be used to superimpose weather effects on the virtual driving scene corresponding to the adjusted original scene information, for example, the weather effects can include any one or a combination of the following: rain and snow effects, haze effects, and light change effects, etc., which are only illustrative and not limited.

[0066] In this embodiment, after adjusting the original scene information in response to the first difference being greater than the target difference, the virtual driving scene corresponding to the adjusted original scene information is subjected to object insertion, and the virtual driving scene corresponding to the adjusted original scene information is subjected to environment rendering to obtain first reconstructed scene information. Optionally, the embodiment can obtain first reconstructed scene information by, on the basis of adjusting the original scene information, subjecting the virtual driving scene corresponding to the adjusted original scene information to object insertion, and subjecting the virtual driving scene corresponding to the adjusted original scene information to environment rendering, thereby achieving the purpose of being able to reconstruct the original scene information, and thus achieving the technical effect of being able to improve the simulation accuracy of the real driving scene.

[0067] For example, in the case of a real driving scene being a highway driving scene, the virtual driving scene corresponding to the adjusted original scene information is an adjusted virtual highway driving scene, the adjusted virtual highway driving scene is subjected to virtual pedestrian insertion, and the adjusted virtual highway driving scene is superimposed with haze effects, which are only illustrative and not limited.

[0068] For another example, in the case of a real driving scene being an urban road driving scene, the virtual driving scene corresponding to the adjusted original scene information is an adjusted virtual urban road driving scene, the adjusted virtual urban road driving scene is subjected to virtual roadblock insertion, and the adjusted virtual urban road driving scene is superimposed with rain and snow effects, which are only illustrative and not limited.

[0069] The above step of reconstructing the original scene information on the basis of the first difference to obtain first reconstructed scene information of this embodiment will be further introduced below.

[0070] As an optional embodiment, the first reconstructed scene information is obtained by reconstructing the original scene information based on the first difference, comprising: in response to the first difference being less than or equal to the target difference, performing object insertion on the virtual driving scene corresponding to the original scene information, and performing environment rendering on the virtual driving scene corresponding to the original scene information to obtain the first reconstructed scene information.

[0071] In this embodiment, after determining the first difference between the first timestamp and the second timestamp, in response to the first difference being less than or equal to the target difference, object insertion is performed on the virtual driving scene corresponding to the original scene information, and environment rendering is performed on the virtual driving scene corresponding to the original scene information to obtain the first reconstructed scene information. Optionally, this embodiment determines the relationship between the obtained first difference and the target difference based on the obtained first difference between the first timestamp and the second timestamp. If it is determined that the obtained first difference is less than or equal to the target difference, object insertion is performed on the virtual driving scene corresponding to the original scene information, and environment rendering is performed on the virtual driving scene corresponding to the original scene information to obtain the first reconstructed scene information. Thus, the original scene information can be reconstructed, thereby achieving the technical effect of improving the simulation accuracy of the real driving scene.

[0072] For example, in the case of a real driving scene being a highway driving scene, the virtual driving scene corresponding to the original scene information is a virtual highway driving scene, virtual roadblock insertion is performed on the virtual highway driving scene, and rain and snow special effects are superimposed on the virtual highway driving scene. This is only an example and is not limited.

[0073] For example, in the case of a real driving scene being a city road driving scene, the virtual driving scene corresponding to the original scene information is a virtual city road driving scene, virtual pedestrian insertion is performed on the virtual city road driving scene, and lighting change special effects are superimposed on the virtual city road driving scene. This is only an example and is not limited.

[0074] The following further introduces the step of adjusting the first reconstructed scene information based on the original driving information of the to-be-tested vehicle to obtain the second reconstructed scene information.

[0075] As an optional embodiment, in step S103, the first reconstructed scene information is adjusted based on the original driving information of the to-be-tested vehicle to obtain second reconstructed scene information, including: mapping the original driving information from an initial coordinate system in which the original driving information is located to a target coordinate system in which the first reconstructed scene information is located to obtain target driving information of the to-be-tested vehicle; determining a target driving track of the virtual object based on the target driving information; and adjusting first state information in the first reconstructed scene information according to the target driving track to obtain second state information in the second reconstructed scene information.

[0076] In this embodiment, the initial coordinate system can be used to represent a world coordinate system of a vehicle dynamics model, and the target coordinate system can be used to represent a video frame pixel coordinate system.

[0077] In this embodiment, after the original scene information is reconstructed to obtain the first reconstructed scene information, the original driving information is mapped from an initial coordinate system in which the original driving information is located to a target coordinate system in which the first reconstructed scene information is located to obtain target driving information of the to-be-tested vehicle. Alternatively, on the basis of the first reconstructed scene information, the original driving information of the to-be-tested vehicle can be obtained, and the obtained original driving information is mapped from an initial coordinate system in which the original driving information is located to a target coordinate system in which the first reconstructed scene information is located, so that the target driving information of the to-be-tested vehicle is obtained, thereby achieving the purpose of converting the original driving information.

[0078] In this embodiment, the virtual object can exist in a virtual driving scene corresponding to the first reconstructed scene information. The target driving track can be used to represent a simulation track of a collision between the virtual object and the to-be-tested vehicle.

[0079] In this embodiment, after the original driving information is mapped from an initial coordinate system in which the original driving information is located to a target coordinate system in which the first reconstructed scene information is located to obtain target driving information of the to-be-tested vehicle, the target driving track of the virtual object is determined based on the target driving information. Alternatively, on the basis of the target driving information of the to-be-tested vehicle, at least the obtained target driving information is used to control a track prediction model to output the target driving track of the virtual object, thereby achieving the purpose of predicting a simulation track of a collision between the virtual object and the to-be-tested vehicle.

[0080] In this embodiment, the first state information can be used to represent a motion condition of the virtual object included in the virtual driving scene corresponding to the first reconstructed scene information, where the motion condition can include each position to which the virtual object moves and a motion state of the virtual object when moving to each position. For example, the first state information can be represented by original features of the virtual object.

[0081] In this embodiment, the second state information described above can be used to represent the motion condition of the virtual object included in the virtual driving scene corresponding to the second reconstructed scene information. For example, the second state information described above can be represented by the target feature of the virtual object.

[0082] In this embodiment, after determining the target driving trajectory of the virtual object based on the target driving information, the first state information in the first reconstructed scene information is adjusted according to the target driving trajectory, so as to obtain the second state information in the second reconstructed scene information. Alternatively, based on the determination of the target driving trajectory of the virtual object, the first state information in the first reconstructed scene information is adjusted according to the target driving trajectory determined above, so as to obtain the second state information in the second reconstructed scene information, thereby achieving the purpose of reconstructing the original scene information, thereby realizing the technical effect of improving the simulation accuracy of the real driving scene.

[0083] Alternatively, the first state information in the first reconstructed scene information is adjusted according to the target driving trajectory determined above, so as to obtain the second state information in the second reconstructed scene information. For example, the original feature of the virtual object included in the virtual driving scene corresponding to the first reconstructed scene information is adjusted according to the target driving trajectory determined above, so as to obtain the target feature. Then, in the virtual driving scene corresponding to the first reconstructed scene information, the virtual object with the original feature is replaced by the virtual object with the target feature, thereby realizing the adjustment of the first state information, so as to obtain the second reconstructed scene information, which is only exemplified here and is not limited specifically.

[0084] Alternatively, the first state information in the first reconstructed scene information is adjusted according to the target driving trajectory determined above, so as to obtain the second state information in the second reconstructed scene information. For example, the original feature of the virtual object included in the virtual driving scene corresponding to the first reconstructed scene information is adjusted according to the target driving trajectory determined above, so as to obtain the target feature. Then, in the virtual driving scene corresponding to the first reconstructed scene information, the original feature of the virtual object is replaced by the target feature obtained by adjustment, thereby realizing the adjustment of the first state information, so as to obtain the second reconstructed scene information, which is only exemplified here and is not limited specifically.

[0085] The step of determining the target driving trajectory of the virtual object based on the target driving information in this embodiment will be further introduced below.

[0086] As an optional embodiment, determining the target driving trajectory of the virtual object based on the target driving information comprises: inputting the first state information and the target driving information into a trajectory prediction model for prediction to obtain the target driving trajectory.

[0087] In this embodiment, the trajectory prediction model can include a mapping relationship between the first state information, the target driving information, and the target driving trajectory. For example, the trajectory prediction model can be, but is not limited to, a prediction model constructed based on a vehicle dynamics model.

[0088] In this embodiment, after the original driving information is mapped from an initial coordinate system in which the original driving information is located to a target coordinate system in which the first reconstructed scene information is located to obtain the target driving information of the vehicle under test, the first state information and the target driving information are input into the trajectory prediction model for prediction to obtain the target driving trajectory. Alternatively, based on the target driving information of the vehicle under test, the first state information and the target driving information are input into the trajectory prediction model for trajectory prediction to obtain the target driving trajectory, that is, the first state information and the target driving information are used to control the trajectory prediction model to output the target driving trajectory, thereby achieving the purpose of predicting the simulation trajectory of the collision between the virtual object and the vehicle under test, and further achieving the technical effect of improving the efficiency of safety testing of the vehicle in the intelligent driving mode.

[0089] In the embodiment of the present application, when testing the vehicle in the intelligent driving mode, the original scene information of the vehicle under test can be obtained. The original scene information obtained can be reconstructed to obtain the first reconstructed scene information, that is, the virtual video data of the reconstructed real driving scene can be obtained; the first reconstructed scene information obtained by reconstruction can be adjusted according to the original driving information of the vehicle under test to obtain the second reconstructed scene information, and the vehicle under test driving according to the original driving information can be tested using the second reconstructed scene information obtained by adjustment to obtain the test result of the vehicle under test, thereby achieving the purpose of meeting the simulation of dynamic scenes, thereby solving the technical problem of low efficiency of safety testing of the vehicle in the intelligent driving mode, and further achieving the technical effect of improving the efficiency of safety testing of the vehicle in the intelligent driving mode.

[0090] The technical solutions of the embodiments of the present application will be illustrated below in conjunction with preferred embodiments.

[0091] With the development of intelligent driving systems, the testing of intelligent driving functions of vehicles is becoming increasingly important. However, the traditional simulation testing of intelligent driving functions mainly relies on a pre-set static scene library, which can include fixed weather conditions, fixed obstacle positions, pre-set target vehicles, and pre-set driving trajectories, etc. Therefore, the traditional testing method is difficult to meet the simulation of dynamic scenes, thereby leading to the technical problem of low efficiency of safety testing of the vehicle in the intelligent driving mode.

[0092] To solve the above technical problems, the embodiment of the present application proposes a test method of a vehicle, when a vehicle in an intelligent driving mode is tested, the obtained original scene information is reconstructed to obtain first reconstructed scene information, the first reconstructed scene information is adjusted according to the original driving information of the vehicle to be tested to obtain second reconstructed scene information, and the second reconstructed scene information is used to test the vehicle to be tested according to the original driving information, and the test result of the vehicle to be tested is obtained, thereby achieving the purpose of meeting the simulation of dynamic scenes, thereby solving the technical problem of low efficiency of safety testing of the vehicle in the intelligent driving mode, and further realizing the technical effect of improving the efficiency of safety testing of the vehicle in the intelligent driving mode.

[0093] In this embodiment, the intelligent driving simulation test system based on dynamic video injection is used, the first reconstructed scene information is adjusted according to the original driving information of the vehicle to be tested to obtain the second reconstructed scene information, and the second reconstructed scene information is used to test the vehicle to be tested according to the original driving information, and the test result of the vehicle to be tested is obtained. For example, FIG. 2(a) is a schematic diagram of an intelligent driving simulation test system based on dynamic video injection according to an embodiment of the present application, as shown in FIG. 2(a), the system 200 can include: a scene simulation module 201, a dynamic video reconstruction module 202, a video injection module 203, a simulation driving module 204, a space-time synchronization module 205, a real-time processor 206 and a control unit to be tested 207.

[0094] In this embodiment, the scene simulation module 201 can be used to generate an original simulation video, wherein the original simulation video can be used for virtual simulation testing. The dynamic video reconstruction module 202 can be used to generate a video stream with a dynamic driving environment. The video injection module 203 can be used to inject the generated video stream into the real-time processor 206. The simulation driving module 204 can be used to simulate the dynamic behavior of the vehicle and output the original driving information of the vehicle to be tested, which can be vehicle dynamics data. The space-time synchronization module 205 can be used to ensure that the video stream and the vehicle dynamics data are synchronized. The real-time processor 206 can be used to send the video stream and the vehicle dynamics data to the control unit to be tested 207 for simulation and testing, and collect the control information feedback of the control unit to be tested 207 to the simulation driving module 204 for closed-loop control.

[0095] For example, the video injection module can be as shown in FIG. 2(b). FIG. 2(b) is a schematic diagram of a video injection module according to an embodiment of the present application. The video injection module 203 can include a shared memory 2031, cameras 20321-2032n, deserializing modules 20331-2033n, a video processing module 2034, and serializing modules 20351-2035n. The shared memory 2031 can be configured to receive the spatiotemporal synchronization video stream sent by the spatiotemporal synchronization module 205. The deserializing modules 20331-2033n can be configured to respectively receive the video data collected by the cameras 20321-2032n, and deserialize the received video data to obtain deserialized video data. The deserialized video data can include check data and real image data, and can be presented through a video signal corresponding to the video data. The video processing module 2034 can be configured to receive the video signal corresponding to the video data, and adjust the received video signal. The serializing modules 20351-2035n can be configured to serialize the adjusted video signal to obtain serialized video data, and send the serialized video data to the real-time processor 206.

[0096] In this embodiment, by performing the dynamic video generation method, the first reconstructed scene information can be adjusted to obtain second reconstructed scene information according to the original driving information of the vehicle to be tested, and the vehicle to be tested can be tested according to the original driving information by using the adjusted second reconstructed scene information, so that the test result of the vehicle to be tested can be obtained. FIG. 2(c) is a flowchart of a dynamic video generation method according to an embodiment of the present application. As shown in FIG. 2(c), the dynamic video generation method can include the following steps:

[0097] In step S211, an original virtual simulation scene video is collected.

[0098] After the original virtual simulation scene video is collected, step S212 is entered, in which the road structure and environmental parameters in the virtual simulation scene video are analyzed, and the editable feature points in the video are extracted. The road structure can include lane lines and obstacle positions, and the environmental parameters can include light intensity and weather types.

[0099] After analyzing the road structure and environmental parameters in the virtual simulation scene video and extracting editable feature points in the video, step S213 is entered, and a dynamic object is generated according to a test requirement by using a generative adversarial network (GAN) model, and a motion trajectory of the dynamic object is calculated. The dynamic object can include a vehicle suddenly cutting in and / or a pedestrian crossing, and the motion trajectory can be related to a cutting-in angle and a speed of the dynamic object in a collision warning scene.

[0100] After the motion trajectory of the dynamic object is calculated, step S214 is entered, a diffusion model is applied, a weather special effect is superimposed in a video stream according to a preset weather parameter, and a camera parameter is adjusted to simulate a real perception condition. The camera parameter can include exposure and focal length.

[0101] After the real perception condition is simulated, step S215 is entered, and a standard format video stream is generated, so as to adapt to different vehicle-mounted camera interfaces. The format of the standard format video stream can include a format supporting a high-definition multimedia interface (HDMI), a format supporting low-voltage differential signaling (LVDS), and a format supporting a mobile industry processor interface alliance (MIPI).

[0102] In this embodiment, by performing the space-time synchronization method, the original scene information can be adjusted, and FIG. 2(d) is a flowchart of a space-time synchronization method according to an embodiment of the present application. As shown in FIG. 2(d), the space-time synchronization method can include the following steps:

[0103] Step S221, vehicle dynamics data is acquired.

[0104] In the technical solution provided in the above step S221 of the present application, when the test device of the vehicle triggers a space-time synchronization request, the vehicle dynamics data can be received through an interface of a vehicle dynamics model, and a timestamp of the vehicle dynamics data can be recorded as T_phys. The vehicle dynamics data can include but is not limited to the position, speed, and acceleration of the vehicle.

[0105] After the vehicle dynamics data is acquired, step S222 is entered, and a timestamp of the video stream is analyzed.

[0106] In the technical solution provided in the above step S222 of the present application, the timestamp of each frame of image data in the video stream is extracted and recorded as T video.

[0107] After analyzing the timestamp of the video stream, step S223 is entered to calculate the time difference.

[0108] In the technical solution provided in the above step S223 of the present application, the first difference between T phys and T video can be calculated according to formula (1).

[0109] After calculating the time difference, step S224 is entered to determine whether the time difference is greater than the synchronization threshold, which can be but is not limited to 9ms and 10ms.

[0110] If it is determined that the time difference is greater than the synchronization threshold, step S225 is entered to adjust the playing speed of the video stream.

[0111] In the technical solution provided in the above step S225 of the present application, the timestamp alignment algorithm is applied to calculate the time difference between the vehicle dynamics data and the video frame, and by adjusting the frame rate of the video player or inserting / dropping the video frame, the time difference is converged within the synchronization threshold.

[0112] In the technical solution provided in the above step S226 of the present application, the original driving information is mapped from the world coordinate system of the vehicle dynamics model to the pixel coordinate system of the video frame, so as to ensure that the position of the virtual object is consistent with the movement of the vehicle to be tested. For example, in the world coordinate system, the position of the vehicle to be tested can be represented by (x, y, z).

[0113] If it is determined that the time difference is less than or equal to the synchronization threshold, step S226 is entered to perform coordinate mapping calculation.

[0114] After the coordinate mapping calculation is performed, step S227 is entered to generate a synchronization control signal. The synchronization control signal can be used to reflect the synchronization mark and the coordinate calibration parameter.

[0115] In the technical solution provided in the above step S227 of the present application, the synchronization mark and the coordinate calibration parameter are output to drive the video injection module to adjust the position of the virtual object.

[0116] After the synchronization control signal is generated, step S228 is entered to send the synchronized video stream to the video injection module.

[0117] In this embodiment, when a vehicle in an intelligent driving mode is tested, original scene information of the vehicle to be tested can be acquired. The original scene information acquired above is reconstructed to obtain first reconstructed scene information, that is, virtual video data of a reconstructed real driving scene; the first reconstructed scene information obtained by reconstruction is adjusted according to original driving information of the vehicle to be tested to obtain second reconstructed scene information, and the vehicle to be tested that travels according to the original driving information is tested by using the second reconstructed scene information obtained by adjustment to obtain a test result of the vehicle to be tested, thereby achieving the purpose of meeting the simulation of dynamic scenes, thereby solving the technical problem of low efficiency of safety testing of the vehicle in the intelligent driving mode, and further achieving the technical effect of improving the efficiency of safety testing of the vehicle in the intelligent driving mode.

[0118] According to the embodiments of the present application, a vehicle testing device is also provided. It should be noted that the vehicle testing device can be used to execute the vehicle testing method in the embodiments.

[0119] Figure 3 is a schematic diagram of a vehicle testing device according to an embodiment of the present application. As shown in Figure 3 the vehicle testing device 300 can include an acquisition unit 301, a reconstruction unit 302, an adjustment unit 303 and a testing unit 304.

[0120] The acquisition unit 301 is configured to acquire original scene information of a vehicle to be tested, wherein the original scene information is used to represent virtual video data recording a real driving scene in which the vehicle to be tested is located, and the virtual video data is used to simulate a virtual driving scene corresponding to the real driving scene.

[0121] The reconstruction unit 302 is configured to reconstruct the original scene information to obtain first reconstructed scene information, wherein the first reconstructed scene information is used to represent virtual video data of a reconstructed real driving scene.

[0122] The adjustment unit 303 is configured to adjust the first reconstructed scene information based on original driving information of the vehicle to be tested to obtain second reconstructed scene information, wherein the original driving information is used to represent a driving parameter of the vehicle to be tested traveling in the real driving scene.

[0123] The testing unit 304 is configured to test the vehicle to be tested traveling according to the original driving information by using the second reconstructed scene information to obtain a test result of the vehicle to be tested.

[0124] Optionally, the reconstruction unit 302 can include: a first determination module configured to determine a first timestamp of the original scene information and a second timestamp of the original driving information; a second determination module configured to determine a first difference between the first timestamp and the second timestamp; and a reconstruction module configured to reconstruct the original scene information based on the first difference to obtain the first reconstructed scene information.

[0125] Optionally, the reconstruction module can include: a first adjustment module configured to, in response to the first difference being greater than the target difference, adjust the original scene information, wherein a second difference between a third timestamp of the adjusted original scene information and the second timestamp is less than or equal to the target difference; and a first insertion and rendering module configured to insert an object into a virtual driving scene corresponding to the adjusted original scene information and render an environment of the virtual driving scene corresponding to the adjusted original scene information to obtain the first reconstructed scene information.

[0126] Optionally, the reconstruction module can include: a second insertion and rendering module configured to, in response to the first difference being less than or equal to the target difference, insert an object into a virtual driving scene corresponding to the original scene information and render an environment of the virtual driving scene corresponding to the original scene information to obtain the first reconstructed scene information.

[0127] Optionally, the adjustment unit 303 can include: a mapping module configured to map the original driving information from an initial coordinate system in which the original driving information is located to a target coordinate system in which the first reconstructed scene information is located to obtain target driving information of the vehicle under test; a third determination module configured to determine a target driving trajectory of a virtual object based on the target driving information, wherein the virtual object exists in a virtual driving scene corresponding to the first reconstructed scene information, and the target driving trajectory is used to represent a simulation trajectory of a collision between the virtual object and the vehicle under test; and a second adjustment module configured to adjust first state information in the first reconstructed scene information according to the target driving trajectory to obtain second state information in the second reconstructed scene information, wherein the first state information is used to represent a motion condition of a virtual object included in the virtual driving scene corresponding to the first reconstructed scene information, and the second state information is used to represent a motion condition of a virtual object included in the virtual driving scene corresponding to the second reconstructed scene information.

[0128] Optionally, the third determination module can include: a prediction submodule configured to input the first state information and the target driving information into a trajectory prediction model to obtain the target driving trajectory, wherein the trajectory prediction model includes a mapping relationship between the first state information, the target driving information, and the target driving trajectory.

[0129] In this embodiment, the acquisition unit is configured to acquire original scene information of the vehicle to be tested, wherein the original scene information is used to represent virtual video data of a real driving scene in which the vehicle to be tested is located, and the virtual video data is used to simulate a virtual driving scene corresponding to the real driving scene; the reconstruction unit is configured to reconstruct the original scene information to obtain first reconstructed scene information, wherein the first reconstructed scene information is used to represent virtual video data of the reconstructed real driving scene; the adjustment unit is configured to adjust the first reconstructed scene information based on original driving information of the vehicle to be tested to obtain second reconstructed scene information, wherein the original driving information is used to represent a driving parameter of the vehicle to be tested driving in the real driving scene; and the test unit is configured to test the vehicle to be tested driving according to the original driving information by using the second reconstructed scene information to obtain a test result of the vehicle to be tested. Thus, the simulation of the dynamic scene can be achieved, and the technical problem of low efficiency of the safety test of the vehicle in the intelligent driving mode is solved, and the technical effect of improving the efficiency of the safety test of the vehicle in the intelligent driving mode is achieved.

[0130] According to the embodiments of the present application, a processor is also provided, which is used to run a program, wherein the program is run by the processor to execute the test method of the vehicle in the embodiments.

[0131] According to the embodiments of the present application, a vehicle is also provided. Figure 4 is a schematic diagram of a vehicle according to the embodiments of the present application, as Figure 4 shown, the vehicle 400 can include a memory 410 and a processor 420, wherein the memory 410 is used to store a computer program; and the processor 420 is used to run the program stored in the memory 410 to implement the test method of the vehicle.

[0132] In the present application, a plurality of refers to two or more than two.

[0133] In the present application, unless otherwise explicitly limited, the terms "mounting", "connecting", "connecting" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium, or it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0134] The terms "first", "second", "third", "fourth" and the like (if any) in the present application are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0135] The term "and / or", within the context of the present application, is used to associate associated objects, and means that three relationships can exist, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in the present application generally means that the front and rear associated objects are in an "or" relationship.

[0136] If not specifically stated, all steps in the present application can be performed sequentially or randomly. For example, the vehicle testing method of the present application can include step S101 and step S102, indicating that the vehicle testing method of the present application can include sequentially performed step S101 and step S102, or sequentially performed step S102 and step S101.

[0137] For example, the vehicle testing method of the present application can further include step S103, indicating that step S103 can be added to the method in any order, for example, the vehicle harness modeling method of the present application can include step S101, step S102 and step S103, or step S101, step S103 and step S102, or step S103, step S101 and step S102, etc. This is only an example and is not specifically limited.

[0138] For example, the vehicle testing method of the present application can further include step S104, indicating that step S104 can be added to the method in any order, for example, the vehicle testing method of the present application can include step S101, step S102, step S103 and step S104, or step S101, step S103, step S102 and step S104, or step S104, step S103, step S101 and step S102, etc. This is only an example and is not specifically limited.

[0139] According to another aspect of the embodiments of the present application, a computer readable storage medium is also provided. The computer readable storage medium includes a stored program, wherein the program controls the device where the computer readable storage medium is located to perform the vehicle testing method in the embodiments when the program is running.

[0140] The computer readable storage medium can also be referred to as computer storage medium. It can include a data signal propagating in a baseband or as a carrier wave in a propagated data signal, which bears the readable program code. Such a propagated data signal can take various forms, including but not limited to electro-magnetic signal, optical signal or any suitable combination thereof. The computer readable storage medium can send, propagate or transmit the program for use by or in connection with an instruction execution system, apparatus or device.

[0141] The program code contained in the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, radio frequency, and the like, or any suitable combination thereof.

[0142] According to an embodiment of the present application, a computer program product is also provided, which comprises a computer program, wherein the computer program, when executed by a processor, implements the test method of the vehicle in the embodiment.

[0143] According to an embodiment of the present application, a computer program product is also provided, which comprises a non-volatile computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the test method of the vehicle in the embodiment.

[0144] According to an embodiment of the present application, a computer program is also provided, wherein the computer program, when executed by a processor, implements the test method of the vehicle in the embodiment.

[0145] Optionally, the computer program, when executed by the processor, implements program code for the following steps: obtaining original scene information of the vehicle to be tested, wherein the original scene information is used to represent virtual video data recording a real driving scene in which the vehicle to be tested is located, and the virtual video data is used to simulate a virtual driving scene corresponding to the real driving scene; reconstructing the original scene information to obtain first reconstructed scene information, wherein the first reconstructed scene information is used to represent virtual video data of the reconstructed real driving scene; adjusting the first reconstructed scene information based on original driving information of the vehicle to be tested, wherein the original driving information is used to represent a driving parameter of the vehicle to be tested driving in the real driving scene; and testing the vehicle to be tested driving according to the original driving information by using the second reconstructed scene information to obtain a test result of the vehicle to be tested.

[0146] Optionally, the computer program, when executed by the processor, implements program code for the following steps: determining a first timestamp of the original scene information and a second timestamp of the original driving information; determining a first difference between the first timestamp and the second timestamp; and reconstructing the original scene information based on the first difference to obtain the first reconstructed scene information.

[0147] Optionally, the computer program, when executed by the processor, implements program code for the following steps: adjusting the original scene information in response to the first difference being greater than a target difference, wherein a second difference between a third timestamp of the adjusted original scene information and the second timestamp is less than or equal to the target difference; inserting an object into a virtual driving scene corresponding to the adjusted original scene information, and rendering an environment of the virtual driving scene corresponding to the adjusted original scene information to obtain the first reconstructed scene information.

[0148] Optionally, the computer program is executed by the processor to realize program codes of the following steps: in response to the first difference being less than or equal to the target difference, performing object insertion on the virtual driving scene corresponding to the original scene information, and performing environment rendering on the virtual driving scene corresponding to the original scene information, to obtain the first reconstructed scene information.

[0149] Optionally, the computer program is executed by the processor to realize program codes of the following steps: mapping the original driving information from an initial coordinate system in which the original driving information is located to a target coordinate system in which the first reconstructed scene information is located, to obtain target driving information of the vehicle to be tested; determining a target driving trajectory of the virtual object based on the target driving information, wherein the virtual object exists in the virtual driving scene corresponding to the first reconstructed scene information, and the target driving trajectory is used to represent a simulation trajectory of the collision between the virtual object and the vehicle to be tested; and adjusting first state information in the first reconstructed scene information according to the target driving trajectory, to obtain second state information in the second reconstructed scene information, wherein the first state information is used to represent a motion condition of the virtual object included in the virtual driving scene corresponding to the first reconstructed scene information, and the second state information is used to represent a motion condition of the virtual object included in the virtual driving scene corresponding to the second reconstructed scene information.

[0150] Optionally, the computer program is executed by the processor to realize program codes of the following steps: inputting the first state information and the target driving information into a trajectory prediction model for prediction, to obtain the target driving trajectory, wherein the trajectory prediction model includes a mapping relationship between the first state information, the target driving information and the target driving trajectory.

[0151] The above-mentioned sequence numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0152] In the above-mentioned embodiments of the present application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0153] In several embodiments provided in the present application, it should be understood that the disclosed technical contents can be implemented by other ways. Among them, the above-mentioned device embodiments are only schematic, for example, the division of units can be a logical function division, and actual implementation can have another division way, 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 displayed or discussed each other can be through some interface, indirect coupling or communication connection between units or modules, which can be electrical or other forms.

[0154] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed to multiple units. Part or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

[0155] In addition, each functional unit in various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0156] If the integrated unit is realized 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 solutions of the present application or the part that contributes to the related art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing 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 various embodiment methods of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, referred to as Read-Only Memory), a random access memory (RAM, referred to as Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0157] The above is only the preferred embodiment of the present application. It should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A vehicle testing method, characterized in that: include: Acquiring original scene information of the vehicle to be tested, wherein the original scene information is used to represent virtual video data recording a real driving scene in which the vehicle to be tested is located, and the virtual video data is used to simulate a virtual driving scene corresponding to the real driving scene; Reconstructing the original scene information to obtain first reconstructed scene information, wherein the first reconstructed scene information is used to represent reconstructed virtual video data of the real driving scene; Adjusting the first reconstructed scene information based on original driving information of the vehicle to be tested to obtain second reconstructed scene information, wherein the original driving information is used to represent driving parameters of the vehicle to be tested traveling in the real driving scene; The second reconstructed scene information is used to test the vehicle to be tested that is traveling according to the original driving information to obtain a test result of the vehicle to be tested.

2. The method according to claim 1, characterized in that Reconstructing the original scene information to obtain first reconstructed scene information includes: Determining a first timestamp of the original scene information and a second timestamp of the original driving information; determining a first difference between the first timestamp and the second timestamp; Based on the first difference, the original scene information is reconstructed to obtain the first reconstructed scene information.

3. The method according to claim 2, characterized in that Reconstructing the original scene information based on the first difference to obtain the first reconstructed scene information includes: In response to the first difference being greater than a target difference, adjusting the original scene information, wherein a second difference between a third timestamp and the second timestamp of the adjusted original scene information is less than or equal to the target difference; Object insertion is performed on the virtual driving scene corresponding to the adjusted original scene information, and environment rendering is performed on the virtual driving scene corresponding to the adjusted original scene information to obtain the first reconstructed scene information.

4. The method according to claim 2, characterized in that Reconstructing the original scene information based on the first difference to obtain the first reconstructed scene information includes: In response to the first difference being less than or equal to the target difference, object insertion is performed on the virtual driving scene corresponding to the original scene information, and environment rendering is performed on the virtual driving scene corresponding to the original scene information to obtain the first reconstructed scene information.

5. The method according to claim 1, wherein Adjusting the first reconstructed scene information based on the original driving information of the vehicle to be tested to obtain second reconstructed scene information includes: Mapping the original driving information from an initial coordinate system where the original driving information is located to a target coordinate system where the first reconstructed scene information is located, to obtain target driving information of the vehicle to be tested; determining a target driving trajectory of a virtual object based on the target driving information, wherein the virtual object exists in the virtual driving scene corresponding to the first reconstructed scene information, and the target driving trajectory is used to represent a simulated trajectory of a collision between the virtual object and the vehicle to be tested; According to the target driving trajectory, the first state information in the first reconstructed scene information is adjusted to obtain the second state information in the second reconstructed scene information, wherein the first state information is used to represent the movement of the virtual object included in the virtual driving scene corresponding to the first reconstructed scene information, and the second state information is used to represent the movement of the virtual object included in the virtual driving scene corresponding to the second reconstructed scene information.

6. The method according to claim 5, characterized in that Determining a target driving trajectory of the virtual object based on the target driving information includes: The first state information and the target driving information are input into a trajectory prediction model for prediction to obtain the target driving trajectory, wherein the trajectory prediction model includes a mapping relationship between the first state information, the target driving information and the target driving trajectory.

7. A vehicle testing device, characterized in that: include: an acquisition unit, configured to acquire original scene information of the vehicle to be tested, wherein the original scene information is used to represent virtual video data recording a real driving scene in which the vehicle to be tested is located, and the virtual video data is used to simulate a virtual driving scene corresponding to the real driving scene; a reconstruction unit, configured to reconstruct the original scene information to obtain first reconstructed scene information, wherein the first reconstructed scene information is used to represent virtual video data of the reconstructed real driving scene; an adjusting unit, configured to adjust the first reconstructed scene information based on original driving information of the vehicle to be tested to obtain second reconstructed scene information, wherein the original driving information is used to represent driving parameters of the vehicle to be tested traveling in the real driving scene; A testing unit is configured to use the second reconstructed scene information to test the vehicle to be tested that is traveling according to the original driving information, and obtain a test result of the vehicle to be tested.

8. A processor, characterized in that: The processor is configured to run a program, wherein the program, when run by the processor, executes the vehicle testing method according to any one of claims 1 to 6.

9. A vehicle, characterized in that: include: a memory storing an executable program; A processor is configured to run the program, wherein the program, when running, executes the vehicle testing method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the storage medium is located is controlled to execute the vehicle testing method according to any one of claims 1 to 6.

Images