Real vehicle data back-injection method, electronic device, storage medium and program product

Abstract

The embodiment of the present application provides a real vehicle data re-injection method, electronic device, storage medium and program product. The method includes: when the current simulation moment belongs to a preset periodic moment, obtaining the simulated main vehicle positioning data that matches the simulation moment; based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, determining the dynamic target data in the real vehicle data through time alignment, and converting the dynamic target data into dynamic target simulation data; when the simulation moment meets the static update condition, based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, determining the static target data in the real vehicle data through position alignment, and converting the static target data into static target simulation data; injecting the static target simulation data and the dynamic target simulation data into the simulation environment to obtain a simulation environment for intelligent driving testing. This method is used to improve the accuracy of replaying perceived targets in a simulation environment.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving test technology, and in particular to a real vehicle data back-injection method, electronic equipment, storage medium and program product. Background Art

[0002] The intelligent driving reinjection test records the real vehicle data such as perception data, vehicle positioning data and vehicle driving data during driving on real roads, and injects the recorded real vehicle data into the simulation environment so that the simulation environment can reproduce the real driving scene and test the intelligent driving system in the simulation environment.

[0003] In related technologies, real vehicle data is injected back into a simulation environment in a time-aligned manner. However, the driving conditions determined by the intelligent driving system in the simulation environment may be different from the driving conditions of the vehicle on the real road, resulting in distortion of the simulation environment constructed based on the injected real vehicle data, thereby affecting the reliability of the intelligent driving injection test results. Summary of the Invention

[0004] The embodiments of the present application provide a real vehicle data reinjection method, electronic device, storage medium and program product to improve the accuracy of replaying perceived targets in a simulation environment, avoid distortion of the simulation environment, and improve the reliability of subsequent intelligent driving tests based on the simulation environment.

[0005] In a first aspect, an embodiment of the present application provides a method for re-injecting real vehicle data, comprising:

[0006] When the current simulation moment belongs to the preset cycle moment, the simulated main vehicle positioning data matching the simulation moment is obtained; based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, the dynamic target data in the real vehicle data is determined through time alignment, and the dynamic target data is converted into dynamic target simulation data; when the simulation moment meets the static update condition, based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, the static target data in the real vehicle data is determined through position alignment, and the static target data is converted into static target simulation data; the static target simulation data and the dynamic target simulation data are injected into the simulation environment to obtain the simulation environment of the intelligent driving test.

[0007] In one possible implementation, based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, the static target data in the real vehicle data is determined by position alignment, including: based on the position alignment, selecting the first target positioning data that matches the simulated main vehicle positioning data in the main vehicle positioning data of the real vehicle data; and selecting the static target data bound to the first target positioning data in the perception target data of the real vehicle data.

[0008] In one possible implementation, based on position alignment, first target positioning data that matches the simulated main vehicle positioning data is selected from the main vehicle positioning data in the actual vehicle data, including: determining the positioning difference between the main vehicle positioning data in the actual vehicle data and the simulated main vehicle positioning data; and using the main vehicle positioning data corresponding to the smallest positioning difference as the first target positioning data that matches the simulated main vehicle positioning data.

[0009] In one possible implementation, converting static target data into static target simulation data includes: determining a first conversion matrix based on simulated main vehicle positioning data and first target positioning data; and converting the static target data into a simulated main vehicle coordinate system based on the first conversion matrix to obtain static target simulation data.

[0010] In one possible implementation, the preset periodic moments include preset lane line processing moments and preset obstacle processing moments; when the simulation moment satisfies the static update condition, the static target data in the real vehicle data is determined by position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, including: when the simulation moment belongs to the preset lane line processing moment, the real vehicle lane line data in the real vehicle data is determined by position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data; when the simulation moment belongs to the preset obstacle processing moment, the real vehicle obstacle data in the real vehicle data is determined by position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data.

[0011] In one possible implementation, based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, the dynamic target data in the real vehicle data is determined by time alignment, including: in the main vehicle positioning data of the real vehicle data, selecting the second target positioning data whose timestamp is consistent with the simulated main vehicle positioning data; in the perception target data of the real vehicle data, selecting the dynamic target data bound to the second target positioning data.

[0012] In one possible implementation, converting dynamic target data into dynamic target simulation data includes: determining a second conversion matrix based on simulated main vehicle positioning data and second target positioning data; and converting the dynamic target data into a simulated main vehicle coordinate system based on the second conversion matrix to obtain dynamic target simulation data.

[0013] In one possible implementation, obtaining simulated main vehicle positioning data that matches the simulation moment includes: determining a simulation timestamp based on the simulation moment; requesting the simulated main vehicle positioning data corresponding to the simulation timestamp from a vehicle dynamics model; and the vehicle dynamics model is used to simulate the motion state of the real vehicle and output the simulated positioning data.

[0014] In a second aspect, an embodiment of the present application provides a real vehicle data re-injection device, comprising:

[0015] An acquisition module, configured to acquire the simulated main vehicle positioning data that matches the simulation moment when the current simulation moment belongs to a preset period moment;

[0016] A dynamic target alignment module is used to determine the dynamic target data in the real vehicle data by time alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, and convert the dynamic target data into dynamic target simulation data;

[0017] A static target alignment module is used to determine the static target data in the real vehicle data by position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data when the static update condition is met at the simulation moment, and convert the static target data into static target simulation data;

[0018] The backinjection module is used to inject static target simulation data and dynamic target simulation data into the simulation environment to obtain the simulation environment for intelligent driving testing.

[0019] In a third aspect, an embodiment of the present application provides an electronic device comprising: a memory, a processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, so that the processor executes the first aspect above and / or various possible implementations of the first aspect.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementation methods of the first aspect.

[0021] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0022] The real vehicle data reinjection method, electronic device, storage medium and program product provided in the embodiments of the present application obtain the simulated main vehicle positioning data matching the simulation moment when the current simulation moment belongs to the preset periodic moment, perform time alignment on the dynamic target according to the simulated main vehicle positioning data and the main vehicle positioning data to obtain dynamic target simulation data, and perform position alignment on the static target according to the simulated main vehicle positioning data and the main vehicle positioning data to obtain static target simulation data; only time alignment is performed on the dynamic target, and only position alignment is performed on the static target, which reduces the amount of data for alignment processing of the perception target and improves the data reinjection efficiency. Moreover, through time alignment, the interactive scene composed of the dynamic target simulation data at the current simulation moment is consistent with the interactive scene composed of the dynamic target data in the real driving scene. Only position alignment is performed on the static target, which eliminates the error caused by time interpolation, so that the static target simulation data at the current simulation moment is consistent with the static target data in the real driving scene, improves the accuracy of replaying the perception target in the simulation environment, avoids the distortion of the simulation environment, and thus improves the reliability of subsequent intelligent driving tests based on the simulation environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0024] Figure 1 A schematic diagram of the scenario of the real vehicle data back-injection method provided in this application;

[0025] Figure 2 A schematic diagram provided for this application to illustrate that a static target near a simulated main vehicle is not correctly identified;

[0026] Figure 3 A schematic diagram of the position alignment of lane line data provided in this application;

[0027] Figure 4 A schematic diagram of position alignment of obstacle data provided by this application;

[0028] Figure 5 A schematic diagram of time alignment of dynamic target data provided by this application;

[0029] Figure 6 This is a schematic diagram of the structure of the real vehicle data re-injection device provided in this application;

[0030] Figure 7 This is a schematic diagram of the structure of the electronic device provided in this application.

[0031] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0032] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0033] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0034] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0035] Figure 1 Schematic diagram of the process of real vehicle data back-injection method provided for this application Figure 1 ,The real vehicle data back-injection method can be applied to electronic ,devices, which can be terminals or servers; Figure 1 As shown, the real vehicle data back-injection method includes:

[0036] S101. When the current simulation time belongs to a preset period time, obtain simulation main vehicle positioning data matching the simulation time.

[0037] Among them, the current simulation moment is the moment provided by the simulation clock; the preset periodic moment includes multiple preset moments, which are pre-set moments for periodically processing the perception target. The interval between any two adjacent preset moments is equal, and the interval is the period for processing the perception target. The period can be set according to actual needs. The embodiment of the present application does not limit the preset periodic moment; as an example, the period can be set to 20ms, that is, the preset moment is reached every 20ms.

[0038] The simulated main vehicle positioning data is the current positioning data of the main vehicle in the simulation environment; the simulated main vehicle positioning data includes the position and posture of the simulated main vehicle in the simulation world coordinate system, and also includes the simulation timestamp.

[0039] Specifically, the electronic device detects the simulation time through the simulation clock and determines in real time whether the current simulation time belongs to the preset cycle time. When the current simulation time belongs to the preset cycle time, the simulation main vehicle positioning data matching the simulation time is obtained from the simulation positioning data of the simulation main vehicle.

[0040] In some embodiments, obtaining simulated main vehicle positioning data that matches the simulation moment includes: determining a simulation timestamp based on the simulation moment; requesting the simulated main vehicle positioning data corresponding to the simulation timestamp from the vehicle dynamics model; the vehicle dynamics model is used to simulate the motion state of the real vehicle and output the simulated positioning data.

[0041] Among them, the simulation timestamp is the timestamp corresponding to the simulation moment; in the intelligent driving test, the vehicle dynamics model is the core module of the simulation system. The vehicle dynamics model is a mathematical model based on multi-body dynamics and tire mechanics. It can simulate the motion state of a real vehicle in real time and provide accurate simulation positioning data for the intelligent driving test.

[0042] Specifically, the electronic device calculates the difference between the simulation moment and the preset system delay to obtain a simulation timestamp, wherein the preset system delay includes a preset virtual perception delay and a preset data transmission delay; the preset virtual perception delay and the preset data transmission delay can be set according to actual conditions, and the embodiments of the present application do not limit this.

[0043] The electronic device generates a data acquisition request according to the simulation timestamp and sends the data acquisition request to the vehicle dynamics model. The vehicle dynamics model obtains the first simulation positioning data of the previous timestamp adjacent to the simulation timestamp and the second simulation positioning data of the subsequent timestamp adjacent to the simulation timestamp according to the simulation timestamp included in the data acquisition request. An interpolation calculation is performed based on the simulation timestamp, the first simulation positioning data of the previous timestamp and the second simulation positioning data of the subsequent timestamp to obtain the simulated main vehicle positioning data corresponding to the simulation timestamp. The vehicle dynamics model returns the simulated main vehicle positioning data corresponding to the simulation timestamp to the electronic device.

[0044] In the above embodiment, by requesting the vehicle dynamics model for the simulated main vehicle positioning data that matches the simulation time, accurate simulated main vehicle positioning data can be obtained, thereby improving the accuracy of the obtained simulated main vehicle positioning data.

[0045] S102 : Based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, determine the dynamic target data in the real vehicle data through time alignment, and convert the dynamic target data into dynamic target simulation data.

[0046] It should be noted that the state of the dynamic target changes quickly and requires high-frequency processing. Therefore, every time the simulation time reaches the preset cycle time, the dynamic target is time-aligned.

[0047] Among them, real vehicle data is data collected while the vehicle is driving on a real road; real vehicle data includes main vehicle positioning data, which is positioning data collected while the vehicle is driving on a real road; main vehicle positioning data includes: the actual main vehicle's position and posture in the geographic coordinate system, and also includes the real vehicle timestamp.

[0048] Real vehicle data also includes perceived target data, which is obtained by performing target detection on sensor data collected while the vehicle is driving on a real road. Perceived target data includes dynamic target data and static target data.

[0049] Dynamic target data is data about dynamic targets detected based on sensor data collected while the vehicle is driving on a real road.

[0050] Dynamic target simulation data is the relevant data of the dynamic target in the relative coordinate system of the simulated main vehicle.

[0051] Specifically, the electronic device adopts a time alignment method to select the first target positioning data from the main vehicle positioning data included in the actual vehicle data based on the timestamp of the simulated main vehicle positioning data; in the actual vehicle data, each main vehicle positioning data has bound perception target data (including dynamic target data), so after selecting the first target positioning data, the dynamic target data bound to the first target positioning data can be obtained; the electronic device uses a conversion matrix to convert the dynamic target data in the geographic coordinate system to the relative coordinate system of the simulated main vehicle to obtain dynamic target simulation data.

[0052] During the conversion, the dynamic target data in the geographic coordinate system is first converted into the dynamic target data in the global coordinate system, and then the dynamic target data in the global coordinate system is converted into the dynamic target simulation data in the relative coordinate system of the simulation main vehicle; the global coordinate system can be a UTM coordinate system (Universal Transverse Mercator Coordinate System).

[0053] The dynamic target data in the geographic coordinate system includes: the position of the dynamic target, the absolute speed of the dynamic target, the actual main vehicle position, the actual absolute speed of the main vehicle and the actual main vehicle heading; the dynamic target data in the global coordinate system includes: the longitudinal distance, lateral distance, azimuth and relative speed of the dynamic target relative to the actual main vehicle; the dynamic target simulation data includes: the longitudinal distance, lateral distance, azimuth and relative speed of the simulated dynamic target relative to the simulated main vehicle.

[0054] It should be noted that the first target positioning data is selected through time alignment so that the timestamp of the first target positioning data is closest to the timestamp of the simulated main vehicle positioning data among all the timestamps involved in the main vehicle positioning data; through time alignment, the interactive scene composed of the dynamic target simulation data at the current simulation moment is consistent with the interactive scene composed of the dynamic target data in the real driving scene. Specifically, the relative position and speed of the dynamic target and the actual main vehicle in the real driving scene are consistent with the relative position and speed of the simulated dynamic target and the simulated main vehicle in the simulation environment.

[0055] S103. When the simulation moment satisfies the static update condition, based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, the static target data in the real vehicle data is determined by position alignment, and the static target data is converted into static target simulation data.

[0056] It should be noted that the state of the static target changes slowly, so high-frequency processing is not required. When the static update condition is met at the simulation time, the position of the static target is aligned.

[0057] Among them, the current simulation moment meets the static update condition, which can be the time length between the current simulation moment and the time when the static target was last aligned, reaching the preset time length; it can also be that the static map corresponding to the current simulation moment is different from the static map corresponding to the previous simulation moment, that is, the static map has been updated; it can also be a pre-set time for processing the static target, and the simulation moment belongs to the pre-set time for processing the static target.

[0058] Static target data is the data of static targets detected based on sensor data collected while the vehicle is driving on a real road.

[0059] Static target simulation data is the relevant data of the static target in the simulated main vehicle coordinates.

[0060] Specifically, the electronic device adopts a position alignment method to select the second target positioning data from the main vehicle positioning data included in the actual vehicle data based on the position of the simulated main vehicle positioning data; in the actual vehicle data, each main vehicle positioning data has bound perception target data (including static target data), so after the second target positioning data is selected, the static target data bound to the second target positioning data can be obtained; the electronic device uses a conversion matrix to convert the static target data in the geographic coordinate system to the relative coordinate system of the simulated main vehicle to obtain static target simulation data.

[0061] During the conversion, the static target data in the geographic coordinate system is first converted into the static target data in the global coordinate system, and then the static target data in the global coordinate system is converted into the static target simulation data in the relative coordinate system of the simulated main vehicle.

[0062] The static target data in the geographic coordinate system includes: longitude and latitude; the static target data in the global coordinate system includes: the easting coordinate, northing coordinate, length, width and yaw angle of the static target data; the static target simulation data includes: the longitudinal distance, lateral distance and azimuth of the simulated static target relative to the simulated main vehicle.

[0063] It should be noted that the second target positioning data is selected through position alignment, so that the positioning difference between the second target positioning data and the simulated main vehicle positioning data in the main vehicle positioning data is minimized; only position alignment is performed, which eliminates the error caused by time interpolation, so that the static target simulation data at the current simulation moment is consistent with the static target data in the real driving scenario, thereby improving the accuracy of reproducing static targets in the simulation environment.

[0064] S104: Inject static target simulation data and dynamic target simulation data into the simulation environment to obtain a simulation environment for intelligent driving testing.

[0065] Specifically, the electronic device generates injection instructions corresponding to static target simulation data and dynamic target simulation data through the back-injection system, and sends the injection instructions to the simulation engine. The simulation engine creates a simulated static target through the static target simulation data in the injection instructions, and creates a simulated dynamic target through the dynamic target simulation data in the injection instructions.

[0066] After injecting the static target simulation data and the dynamic target simulation data into the simulation environment, the intelligent driving system performs intelligent driving simulation based on the simulation environment and obtains the test results corresponding to the simulation moment.

[0067] It should be noted that the above steps are for the current simulation moment belonging to the preset cycle moment, to time align the dynamic target data, to position align the static target, and to inject the static target simulation data and the dynamic target simulation data into the simulation environment to obtain the simulation environment of the intelligent driving test. As the simulation clock continues to advance, when the next simulation moment belonging to the preset cycle moment is reached, the above steps are repeated.

[0068] In related technologies, when real vehicle data is back-annotated, no distinction is made between dynamic and static targets, and all targets are time-aligned and position-aligned. This alignment method will lead to conflicts in target alignment when the driving conditions of the simulated main vehicle and the real vehicle are different, thereby causing the problem of distortion of the simulation environment.

[0069] For example, at the 10th second, the real vehicle drives to the intersection. The real vehicle detects an obstacle (static target) 10 meters to the right front and a bicycle (dynamic target) on the left side of the road. The bicycle's driving path is to cross the road; the simulated main vehicle drives to the intersection at the 15th second (that is, the driving conditions of the simulated main vehicle and the real vehicle are different).

[0070] For static targets, the same obstacle can be matched according to position alignment, that is, the simulated main vehicle "sees" an obstacle 10 meters to the right front, which is consistent with the real driving scene. If time alignment is also required, it is necessary to match the static target detected by the real vehicle at the 15th second, and thus it is impossible to match the obstacle detected at the 10th second. There is a conflict, which leads to distortion of the simulation environment.

[0071] For dynamic targets, time alignment is used to determine the dynamic targets detected by the real vehicle at the 15th second. For example, at the 15th second, the real vehicle detects a bicycle driving into the middle of the road. Then, the current simulated main vehicle "sees" the bicycle driving into the middle of the road, which is consistent with the real driving scene. If position alignment is also required, the simulated main vehicle "sees" the bicycle on the side of the road, resulting in distortion of the simulation environment.

[0072] In the embodiment of the present application, only position alignment is performed on static targets, and only time alignment is performed on dynamic targets. When the driving conditions of the simulated main vehicle and the real vehicle are different, by performing position alignment on the static targets, it is ensured that the position of the static targets in the simulation environment strictly corresponds to their positions in the real world, thereby improving the accuracy of replaying static targets in the simulation environment. By performing time alignment on the dynamic targets, the interactive scene composed of the dynamic target simulation data is consistent with the interactive scene composed of the dynamic target data in the real driving scene, thereby improving the accuracy of replaying dynamic targets in the simulation environment.

[0073] The real vehicle data reinjection method provided in the embodiment of the present application obtains the simulated main vehicle positioning data matching the simulation moment when the current simulation moment belongs to the preset period moment, performs time alignment on the dynamic target according to the simulated main vehicle positioning data and the main vehicle positioning data to obtain dynamic target simulation data, and performs position alignment on the static target according to the simulated main vehicle positioning data and the main vehicle positioning data to obtain static target simulation data; only performs time alignment on the dynamic target and only performs position alignment on the static target, thereby reducing the amount of data for alignment processing of the perception target and improving the data reinjection efficiency; and through time alignment, the interactive scene composed of the dynamic target simulation data at the current simulation moment is consistent with the interactive scene composed of the dynamic target data in the real driving scene; only performs position alignment on the static target, eliminating the error caused by time interpolation, so that the static target simulation data at the current simulation moment is consistent with the static target data in the real driving scene, improving the accuracy of replaying the perception target in the simulation environment, avoiding the distortion of the simulation environment, and thus improving the reliability of subsequent intelligent driving tests based on the simulation environment.

[0074] In some embodiments, based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, the static target data in the real vehicle data is determined by position alignment, including: based on the position alignment, selecting the first target positioning data that matches the simulated main vehicle positioning data in the main vehicle positioning data of the real vehicle data; and selecting the static target data bound to the first target positioning data in the perception target data of the real vehicle data.

[0075] Specifically, the actual vehicle data includes the main vehicle positioning data; based on the position included in the simulated main vehicle positioning data and the position included in the main vehicle positioning data, the first target positioning data is determined in the main vehicle positioning data, and the first target positioning data is the main vehicle positioning data with the smallest positioning difference with the simulated main vehicle positioning data in the main vehicle positioning data; it can be understood that through the positioning difference between the main vehicle positioning data and the simulated main vehicle positioning data, the first target positioning data that matches the simulated main vehicle positioning data is selected, thereby achieving position alignment at one level.

[0076] The actual vehicle data also includes perceived target data; after obtaining the first target positioning data, static target data bound to the first target positioning data is obtained in the perceived target data; wherein the timestamp of the first target positioning data is the same as the timestamp of the static target data bound thereto.

[0077] In the above embodiment, the first target positioning data that matches the simulated main vehicle positioning data is selected from the main vehicle positioning data based on position alignment, so that the static target simulation data at the current simulation moment is consistent with the static target data in the real driving scene, thereby improving the accuracy of replaying static targets in the simulation environment.

[0078] In some embodiments, in the main vehicle positioning data of the actual vehicle data, the first target positioning data that matches the simulated main vehicle positioning data is selected, including: determining the positioning difference between the main vehicle positioning data in the actual vehicle data and the simulated main vehicle positioning data; and using the main vehicle positioning data corresponding to the smallest positioning difference as the first target positioning data that matches the simulated main vehicle positioning data.

[0079] Specifically, for each main vehicle positioning data, the main vehicle positioning data and the simulated main vehicle positioning data are converted to the same coordinate system to obtain the main vehicle positioning data to be processed and the simulated main vehicle positioning data to be processed. For example, the main vehicle positioning data is converted to the global coordinate system to obtain the main vehicle positioning data to be processed, and the simulated main vehicle positioning data is converted to the global coordinate system to obtain the simulated main vehicle positioning data to be processed. The position difference between the to-be-processed position included in the to-be-processed main vehicle positioning data and the to-be-processed simulated position included in the to-be-processed simulated main vehicle positioning data is calculated to obtain the positioning difference corresponding to the main vehicle positioning data. In this way, the positioning difference corresponding to each main vehicle positioning data can be obtained.

[0080] The minimum positioning difference is determined among the positioning differences corresponding to each main vehicle positioning data, and the main vehicle positioning data corresponding to the minimum positioning difference is used as the first target positioning data that matches the simulated main vehicle positioning data.

[0081] In the above embodiment, the positioning difference between the main vehicle positioning data and the simulated main vehicle positioning data is used for position alignment to obtain first target positioning data that matches the simulated main vehicle positioning data, so that the static target simulation data at the current simulation moment is consistent with the static target data in the real driving scene, thereby improving the accuracy of replaying static targets in the simulation environment.

[0082] In some embodiments, converting static target data into static target simulation data includes: determining a first conversion matrix based on simulated main vehicle positioning data and first target positioning data; and converting the static target data into a simulated main vehicle coordinate system based on the first conversion matrix to obtain static target simulation data.

[0083] The first transformation matrix includes a first projection transformation matrix and a first rigid body transformation matrix.

[0084] Specifically, the projection origin is determined based on the first target positioning data, the first projection transformation matrix is ​​constructed, and the first rigid body transformation matrix is ​​determined based on the simulation main vehicle positioning data; the static target data in the geographic coordinate system is converted to the global coordinate system through the first projection transformation matrix, and the static target data in the global coordinate system is converted to the simulation main vehicle coordinate system according to the first rigid body transformation matrix to obtain static target simulation data.

[0085] Among them, the static target data in the geographic coordinate system includes: longitude and latitude; the static target data in the global coordinate system includes: the easting coordinate, northing coordinate, length, width and yaw angle of the static target data; the static target simulation data includes: the longitudinal distance, lateral distance and azimuth of the simulated static target relative to the simulated main vehicle.

[0086] In the above embodiment, the static target data in the geographic coordinate system is converted to the simulated main vehicle coordinate system through the first transformation matrix, thereby achieving another level of position alignment, ensuring that the position of the static target in the simulation environment strictly corresponds to its position in the real world, and improving the accuracy of replaying the static target in the simulation environment.

[0087] In some embodiments, the preset periodic moments include preset lane line processing moments and preset obstacle processing moments; when the simulation moment meets the static update condition, the static target data in the real vehicle data is determined by position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, including: when the simulation moment belongs to the preset lane line processing moment, the real vehicle lane line data in the real vehicle data is determined by position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data; when the simulation moment belongs to the preset obstacle processing moment, the real vehicle obstacle data in the real vehicle data is determined by position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data.

[0088] Among them, the preset lane line processing time includes multiple preset lane line processing times; the preset obstacle processing time includes multiple preset obstacle processing times.

[0089] Specifically, the electronic device determines whether the simulation moment belongs to the preset lane line processing moment. If the simulation moment belongs to the preset lane line processing moment, it triggers the position alignment of the lane line; determines the positioning difference between the simulated main vehicle positioning data and the main vehicle positioning data, and uses the main vehicle positioning data corresponding to the smallest positioning difference as the first target positioning data, and obtains the real vehicle lane line data bound to the first target positioning data.

[0090] A first conversion matrix is ​​determined according to the first target positioning data and the simulated main vehicle positioning data, and the real vehicle lane line data is converted to the simulated main vehicle coordinate system through the first conversion matrix to obtain simulated lane line data.

[0091] The electronic device determines whether the simulation moment falls within the preset obstacle processing moment. If so, it triggers the position alignment of the obstacle; determines the positioning difference between the simulated main vehicle positioning data and the main vehicle positioning data, uses the main vehicle positioning data corresponding to the minimum positioning difference as the first target positioning data, and obtains the real vehicle obstacle data bound to the first target positioning data.

[0092] A first conversion matrix is ​​determined according to the first target positioning data and the simulated main vehicle positioning data, and the real vehicle obstacle data is converted into the simulated main vehicle coordinate system by the first conversion matrix to obtain simulated obstacle data.

[0093] For example, in actual applications, if the speeds of the actual host vehicle and the simulated host vehicle are different, it may lead to the problem that static targets near the simulated host vehicle are not correctly identified, such as Figure 2 As shown, at the 29th second, the actual main vehicle recognizes the cone barrel in the schematic box 210, and at the 30th second, the actual main vehicle recognizes the cone barrel in the schematic box 220; if the speed of the simulated main vehicle is different from that of the actual main vehicle, then at the 30th second, the cone barrel near the simulated main vehicle (the cone barrel in the schematic box 230) is not correctly recognized.

[0094] In this embodiment, the method of position alignment for static targets is adopted, so that the relative position between the simulated main vehicle and the simulated static target at the current simulation moment is consistent with the relative position between the actual main vehicle and the static target in the real driving scenario, thereby improving the accuracy of reproducing static targets in the simulation environment.

[0095] In the above embodiment, position alignment is performed on the actual vehicle lane line data and the actual vehicle obstacle data to reproduce the real-world actual vehicle lane line data and the actual vehicle obstacle data in the simulation environment, providing an essential simulation environment for intelligent driving testing.

[0096] In some embodiments, based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, the dynamic target data in the real vehicle data is determined by time alignment, including: in the main vehicle positioning data of the real vehicle data, selecting the second target positioning data whose timestamp is consistent with the simulated main vehicle positioning data; in the perception target data of the real vehicle data, selecting the dynamic target data bound to the second target positioning data.

[0097] Specifically, the electronic device obtains the simulation timestamp of the simulated main vehicle positioning data, and obtains the timestamp of the main vehicle positioning data for each main vehicle positioning data. In this way, the timestamps of multiple main vehicle positioning data can be obtained. A target timestamp that is consistent with the simulation timestamp is determined from the multiple timestamps, and the main vehicle positioning data corresponding to the target timestamp is used as the second target positioning data.

[0098] Optionally, if the multiple timestamps are inconsistent with the simulation timestamp, a target timestamp closest to the simulation timestamp is selected from the multiple timestamps.

[0099] The actual vehicle data also includes perceived target data. After obtaining the second target positioning data, dynamic target data bound to the second target positioning data is obtained from the perceived target data. The timestamp (target timestamp) of the second target positioning data is the same as the timestamp of the dynamic target data bound to it.

[0100] In the above embodiment, based on time alignment, the second target positioning data that matches the simulated main vehicle positioning data is selected from the main vehicle positioning data, so that the interactive scene composed of the dynamic target simulation data at the current simulation moment is consistent with the interactive scene composed of the dynamic target data in the real driving scene, thereby improving the accuracy of replaying dynamic targets in the simulation environment.

[0101] In some embodiments, converting dynamic target data into dynamic target simulation data includes: determining a second conversion matrix based on simulated main vehicle positioning data and second target positioning data; and converting the dynamic target data into a simulated main vehicle coordinate system based on the second conversion matrix to obtain dynamic target simulation data.

[0102] The second transformation matrix includes a second projection transformation matrix and a second rigid body transformation matrix.

[0103] Specifically, the projection origin is determined based on the second target positioning data, the second projection transformation matrix is ​​constructed, and the second rigid body transformation matrix is ​​determined based on the simulation main vehicle positioning data; the dynamic target data in the geographic coordinate system is converted to the global coordinate system through the second projection transformation matrix, and the dynamic target data in the global coordinate system is converted to the simulation main vehicle coordinate system according to the second rigid body transformation matrix to obtain dynamic target simulation data.

[0104] In practical applications, since the simulated main vehicle positioning data are the same, the first rigid body transformation matrix determined based on the simulated main vehicle positioning data is the same as the first rigid body transformation matrix determined based on the simulated main vehicle positioning data.

[0105] The dynamic target data in the geographic coordinate system includes: the position of the dynamic target, the absolute speed of the dynamic target, the actual main vehicle position, the actual absolute speed of the main vehicle and the actual main vehicle heading; the dynamic target data in the global coordinate system includes: the longitudinal distance, lateral distance, azimuth and relative speed of the dynamic target relative to the actual main vehicle; the dynamic target simulation data includes: the longitudinal distance, lateral distance, azimuth and relative speed of the simulated dynamic target relative to the simulated main vehicle.

[0106] In the above embodiment, the dynamic target data in the geographic coordinate system is converted to the simulated main vehicle coordinate system through the second conversion matrix, ensuring that the position of the dynamic target in the simulation environment strictly corresponds to its position in the real world, thereby improving the accuracy of replaying static targets in the simulation environment.

[0107] For example, Figure 3 As shown in FIG, position alignment of the actual vehicle lane line data includes:

[0108] The preset lane line processing moment corresponds to multiple frames of lane line data, and the multiple frames of lane line data include: the first frame lane line data, the second frame lane line data, ..., the Nth frame lane line data; when the current simulation moment belongs to the preset lane line processing moment, for example, taking the current simulation moment corresponding to the first frame lane line data as an example; request the simulated main vehicle positioning data corresponding to the simulation moment from the vehicle dynamics model, based on the position alignment method, according to the simulated main vehicle positioning data, determine the first target positioning data in the real vehicle data, and obtain the real vehicle lane line data in the real vehicle data according to the first target positioning data, convert the real vehicle lane line data into the simulated main vehicle relative coordinate system, and obtain the simulated lane line data; inject the simulated lane line data into the simulation environment through high-performance asynchronous messages, and the central command and control system (Command and Control Center) performs intelligent driving tests based on the simulation environment; whenever the simulation moment reaches the preset lane line processing moment, the real vehicle lane line data is position aligned according to the above process.

[0109] For example, Figure 4 As shown in the figure, position alignment of real vehicle obstacle data includes:

[0110] The preset obstacle processing moment corresponds to multiple frames of obstacle data, which include: the first frame of obstacle data, the second frame of obstacle data, ..., the Nth frame of obstacle data. When the current simulation moment belongs to the preset obstacle processing moment, for example, taking the current simulation moment corresponding to the first frame of obstacle data as an example, the vehicle dynamics model is requested to obtain the simulated main vehicle positioning data corresponding to the simulation moment. Based on the position alignment method, the first target positioning data is determined in the real vehicle data according to the simulated main vehicle positioning data, and the real vehicle obstacle data is obtained in the real vehicle data according to the first target positioning data. The real vehicle obstacle data is converted to the relative coordinate system of the simulated main vehicle to obtain the simulated obstacle data. The simulated obstacle data is injected into the simulation environment via high-performance asynchronous messages, and the central command and control system executes the intelligent driving test based on the simulation environment. Whenever the simulation moment reaches the preset obstacle processing moment, the real vehicle obstacle data is position aligned according to the above process.

[0111] For example, Figure 5 As shown, time alignment of dynamic target data includes:

[0112] The preset periodic moment corresponds to multiple frames of dynamic target data, and the multiple frames of dynamic target data include: the first frame of dynamic target data, the second frame of dynamic target data, ..., the Nth frame of dynamic target data; when the current simulation moment belongs to the preset periodic moment, for example, the current simulation moment corresponds to the first frame of dynamic target data; the vehicle dynamics model is requested to obtain the simulated main vehicle positioning data corresponding to the simulation moment, and based on the time alignment method, the second target positioning data is determined in the real vehicle data according to the simulated main vehicle positioning data, and the dynamic target data is obtained according to the second target positioning data; the dynamic target data is converted to the relative coordinate system of the simulated main vehicle to obtain the dynamic target simulation data; the dynamic target simulation data is injected into the simulation environment through high-performance asynchronous messages, and the central command and control system performs intelligent driving tests based on the simulation environment; whenever the simulation moment reaches the preset periodic moment, the dynamic target is time-aligned according to the above process.

[0113] The real vehicle data reinjection method provided in the embodiment of the present application obtains the simulated main vehicle positioning data that matches the simulation moment when the current simulation moment belongs to the preset periodic moment, performs time alignment on the dynamic target according to the simulated main vehicle positioning data and the main vehicle positioning data to obtain dynamic target simulation data, and performs position alignment on the static target according to the simulated main vehicle positioning data and the main vehicle positioning data to obtain static target simulation data; only performs time alignment on the dynamic target and only performs position alignment on the static target, thereby reducing the amount of data for alignment processing of the perception target and improving the data reinjection efficiency, and through time alignment, the interactive scene composed of the dynamic target simulation data at the current simulation moment is consistent with the interactive scene composed of the dynamic target data in the real driving scene, and only performs position alignment on the static target, eliminating the error caused by time interpolation, so that the static target simulation data at the current simulation moment is consistent with the static target data in the real driving scene, improving the accuracy of replaying the perception target in the simulation environment, avoiding the distortion of the simulation environment, and thus improving the reliability of subsequent intelligent driving tests based on the simulation environment.

[0114] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0115] Figure 6 This is a schematic diagram of the structure of the real vehicle data back-injection device provided in this application, as shown in Figure 6 As shown, the real vehicle data re-injection device 60 provided in this embodiment includes:

[0116] An acquisition module 610 is configured to acquire the simulated main vehicle positioning data that matches the simulation moment when the current simulation moment belongs to a preset period moment;

[0117] A dynamic target alignment module 620 is configured to determine dynamic target data in the real vehicle data by time alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, and convert the dynamic target data into dynamic target simulation data;

[0118] A static target alignment module 630 is configured to determine static target data in the real vehicle data by position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data when the static update condition is met at the simulation moment, and convert the static target data into static target simulation data;

[0119] The back-injection module 640 is used to inject static target simulation data and dynamic target simulation data into the simulation environment to obtain a simulation environment for intelligent driving testing.

[0120] In one possible implementation, the static target alignment module 630 is used to select first target positioning data that matches the simulated main vehicle positioning data from the main vehicle positioning data of the real vehicle data based on position alignment; and select static target data bound to the first target positioning data from the perceived target data of the real vehicle data.

[0121] In one possible implementation, the static target alignment module 630 is used to determine the positioning difference between the main vehicle positioning data in the real vehicle data and the simulated main vehicle positioning data; and use the main vehicle positioning data corresponding to the smallest positioning difference as the first target positioning data matched with the simulated main vehicle positioning data.

[0122] In one possible implementation, the static target alignment module 630 is used to determine a first transformation matrix based on the simulated main vehicle positioning data and the first target positioning data; based on the first transformation matrix, the static target data is transformed into the simulated main vehicle coordinate system to obtain static target simulation data.

[0123] In one possible implementation, the preset periodic moments include preset lane line processing moments and preset obstacle processing moments; the static target alignment module 630 is used to determine the actual vehicle lane line data in the actual vehicle data through position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the actual vehicle data when the simulation moment belongs to the preset lane line processing moment; and to determine the actual vehicle obstacle data in the actual vehicle data through position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the actual vehicle data when the simulation moment belongs to the preset obstacle processing moment.

[0124] In one possible implementation, the dynamic target alignment module 620 is used to select, from the main vehicle positioning data of the actual vehicle data, second target positioning data whose timestamp is consistent with the simulated main vehicle positioning data; and to select, from the perception target data of the actual vehicle data, dynamic target data bound to the second target positioning data.

[0125] In one possible implementation, the dynamic target alignment module 620 is used to determine a second transformation matrix based on the simulated main vehicle positioning data and the second target positioning data; based on the second transformation matrix, the dynamic target data is transformed into the simulated main vehicle coordinate system to obtain dynamic target simulation data.

[0126] In one possible implementation, the acquisition module 610 is used to determine a simulation timestamp based on the simulation moment; request the simulated main vehicle positioning data corresponding to the simulation timestamp from the vehicle dynamics model; the vehicle dynamics model is used to simulate the motion state of the real vehicle and output the simulated positioning data.

[0127] The real vehicle data re-injection device provided in this embodiment can execute the real vehicle data re-injection method provided in the above method embodiment. Its implementation principle and technical effects are similar, and will not be described in detail in this embodiment.

[0128] The real vehicle data reinjection device provided in the embodiment of the present application obtains the simulated main vehicle positioning data matching the simulation moment when the current simulation moment belongs to the preset periodic moment, performs time alignment on the dynamic target according to the simulated main vehicle positioning data and the main vehicle positioning data to obtain dynamic target simulation data, and performs position alignment on the static target according to the simulated main vehicle positioning data and the main vehicle positioning data to obtain static target simulation data; only performs time alignment on the dynamic target and only performs position alignment on the static target, thereby reducing the amount of data for alignment processing of the perception target and improving the data reinjection efficiency, and through time alignment, the interactive scene composed of the dynamic target simulation data at the current simulation moment is consistent with the interactive scene composed of the dynamic target data in the real driving scene, and only performs position alignment on the static target, eliminating the error caused by time interpolation, so that the static target simulation data at the current simulation moment is consistent with the static target data in the real driving scene, improving the accuracy of replaying the perception target in the simulation environment, avoiding the distortion of the simulation environment, and thus improving the reliability of subsequent intelligent driving tests based on the simulation environment.

[0129] Figure 7 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 7 As shown, the electronic device 70 provided in this embodiment includes: at least one processor 701 and a memory 702. Optionally, the device 70 further includes a communication component 703. The processor 701, the memory 702 and the communication component 703 are connected via a bus.

[0130] During the specific implementation process, at least one processor 701 executes the computer-executable instructions stored in the memory 702, so that the at least one processor 701 performs the above method.

[0131] The specific implementation process of the processor 701 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0132] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0133] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage.

[0134] A bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0135] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0136] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0137] The readable storage medium may be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0138] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0139] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0140] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0141] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0142] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0143] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0144] Finally, it should be noted that those skilled in the art will readily identify other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

Claims

1. A real vehicle data back-injection method, characterized in that: include: When the current simulation moment belongs to a preset period moment, obtaining the simulated main vehicle positioning data matching the simulation moment; Based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, determining the dynamic target data in the real vehicle data by time alignment, and converting the dynamic target data into dynamic target simulation data; When the simulation moment satisfies a static update condition, based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, static target data in the real vehicle data is determined by position alignment, and the static target data is converted into static target simulation data; The static target simulation data and the dynamic target simulation data are injected into the simulation environment to obtain a simulation environment for intelligent driving testing.

2. The method according to claim 1, characterized in that The determining of the static target data in the real vehicle data by position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data includes: Based on position alignment, selecting first target positioning data that matches the simulated main vehicle positioning data from the main vehicle positioning data of the real vehicle data; Among the perception target data of the real vehicle data, static target data bound to the first target positioning data is selected.

3. The method according to claim 2, characterized in that The selecting, based on position alignment, first target positioning data that matches the simulated main vehicle positioning data from the main vehicle positioning data of the real vehicle data includes: Determining a positioning difference between the main vehicle positioning data in the real vehicle data and the simulated main vehicle positioning data; The main vehicle positioning data corresponding to the smallest positioning difference is used as the first target positioning data that matches the simulated main vehicle positioning data.

4. The method according to claim 2, characterized in that The converting the static target data into static target simulation data comprises: Determining a first conversion matrix according to the simulated main vehicle positioning data and the first target positioning data; Based on the first conversion matrix, the static target data is converted into a simulated main vehicle coordinate system to obtain static target simulation data.

5. The method according to any one of claims 1 to 4, characterized in that The preset periodic moments include preset lane line processing moments and preset obstacle processing moments; When the simulation moment satisfies the static update condition, determining the static target data in the real vehicle data by position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data includes: When the simulation time is a preset lane line processing time, based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, determining the real vehicle lane line data in the real vehicle data by position alignment; When the simulation moment belongs to the preset obstacle processing moment, the real vehicle obstacle data in the real vehicle data is determined by position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data.

6. The method according to any one of claims 1 to 4, characterized in that The determining of the dynamic target data in the real vehicle data by time alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data includes: Selecting second target positioning data whose timestamp is consistent with the simulated main vehicle positioning data from the main vehicle positioning data of the real vehicle data; Among the perceived target data of the real vehicle data, dynamic target data bound to the second target positioning data is selected.

7. The method according to claim 6, characterized in that The converting the dynamic target data into dynamic target simulation data comprises: Determining a second conversion matrix according to the simulated main vehicle positioning data and the second target positioning data; Based on the second conversion matrix, the dynamic target data is converted into a simulated main vehicle coordinate system to obtain dynamic target simulation data.

8. The method according to any one of claims 1 to 4, characterized in that The obtaining of the simulated main vehicle positioning data matching the simulation time includes: determining a simulation timestamp based on the simulation moment; Requesting the simulated main vehicle positioning data corresponding to the simulation timestamp from the vehicle dynamics model; the vehicle dynamics model is used to simulate the motion state of the real vehicle and output the simulated positioning data.

9. A real vehicle data re-injection device, characterized in that: The device comprises: An acquisition module, configured to acquire, when the current simulation moment belongs to a preset period moment, the simulated main vehicle positioning data matching the simulation moment; A dynamic target alignment module is used to determine dynamic target data in the real vehicle data by time alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data, and convert the dynamic target data into dynamic target simulation data; a static target alignment module, configured to determine static target data in the real vehicle data by position alignment based on the simulated main vehicle positioning data and the main vehicle positioning data in the real vehicle data when the static update condition is satisfied at the simulation moment, and convert the static target data into static target simulation data; The back-injection module is used to inject the static target simulation data and the dynamic target simulation data into the simulation environment to obtain a simulation environment for intelligent driving testing.

10. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

12. A computer program product, characterized in that The method comprises computer-executable instructions, which implement the method according to any one of claims 1 to 8 when the computer-executable instructions are executed by a processor.

Images