Test data generation method and device, equipment and medium

Abstract

The invention relates to the technical field of simulation, in particular to a test data generation method and device, equipment and a medium, and the method comprises the steps: obtaining road scene parameters and vehicle behavior parameters of a target vehicle; determining lane-level road data of the target vehicle from pre-generated high-precision map data based on the road scene parameters; based on the lane-level road data of the target vehicle, the set dead reckoning frequency and the vehicle behavior parameters, obtaining lane-level simulation trajectory data of the target vehicle; and at least writing the lane-level simulation track of the target vehicle into a test playback file. According to the scheme, it can be ensured that the lane-level simulation track in the test playback file can cover a road scene concerned by a tester, the performance of the intelligent driving system on a road can be comprehensively tested based on the test playback file, and the credibility of a test result is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of simulation technology, and in particular to a method, device, equipment and medium for generating test data. Background Art

[0002] In the process of developing intelligent driving systems, manufacturers need to test the intelligent driving systems to ensure that the intelligent driving systems can provide safe and reliable services. In order to improve the efficiency and coverage of the test and reduce the test cost, the existing technology usually uses simulated navigation to generate the vehicle's driving trajectory and tests the intelligent driving system through the driving trajectory. However, simulated navigation is through the set starting point and end point, and the navigation route calculation service plans the navigation route from the starting point to the end point, and then simulates the vehicle driving along the navigation route to generate the vehicle's driving trajectory. However, since the tester cannot finely control the roads actually covered by the navigation route calculated by the navigation route calculation service, the driving trajectory generated based on the simulated navigation has the problem of not being able to cover the road scenes that the tester is concerned about, resulting in the inability to test the performance of the intelligent driving system on some roads, affecting the credibility of the test results. Summary of the invention

[0003] In order to solve the problems in the related art, the embodiments of the present disclosure provide a method, apparatus, device and medium for generating test data.

[0004] In a first aspect, an embodiment of the present disclosure provides a method for generating test data, comprising: Obtaining road scene parameters and vehicle behavior parameters of the target vehicle; Based on the road scene parameters, the lane-level road data of the target vehicle is determined from the pre-generated high-precision map data; Based on the lane-level road data of the target vehicle, the set dead reckoning frequency and the vehicle behavior parameters, the lane-level simulated trajectory data of the target vehicle is obtained; At least the lane-level simulation trajectory of the target vehicle is written to the test playback file.

[0005] In one embodiment of the present disclosure, the method further comprises: Obtaining following strategy parameters that match the road scene parameters; According to the lane-level simulated trajectory data and the following strategy parameters, the simulated trajectory data of other moving objects whose distances from the target vehicle meet a preset distance threshold are obtained; Write the simulated trajectory data of other moving objects to the test playback file.

[0006] In one embodiment of the present disclosure, based on the road scene parameters, the lane-level road data of the target vehicle is determined from the pre-generated high-precision map data. The road scene parameters are matched with the road information of at least one road and the lane information of at least one lane recorded in the pre-generated high-precision map data to obtain lane-level road data matching the road scene parameters as the lane-level road data of the target vehicle, wherein the lane-level road data includes at least one of road attributes, road connectivity, road longitude and latitude, and road altitude, and the lane information includes at least one of lane attributes, lane connectivity, lane longitude and latitude, and lane altitude.

[0007] In one embodiment of the present disclosure, the road scene parameter is used to indicate at least one of a bridge, an viaduct, a tunnel, a toll booth, a checkpoint, and a traffic light intersection.

[0008] In one embodiment of the present disclosure, based on the lane-level road data of the target vehicle, the set dead reckoning frequency and the vehicle behavior parameters, the lane-level simulated trajectory data of the target vehicle is obtained, including: According to the lane-level road data of the target vehicle, a lane-level route trajectory is obtained, and the lane-level route trajectory passes through an area defined by the road scene parameters; According to the lane-level route trajectory, vehicle behavior parameters and the set dead reckoning frequency, the lane-level simulated trajectory data of the target vehicle is obtained.

[0009] In one embodiment of the present disclosure, the vehicle behavior parameter is used to indicate at least: lane change, acceleration, deceleration, overtaking, and following.

[0010] In one embodiment of the present disclosure, other moving objects include a preceding vehicle in the same lane and a pedestrian crossing the road; The following strategy parameters include at least one of the corresponding relationship between the distance from the vehicle to the preceding vehicle in the same lane and the moving speed of the vehicle, and the corresponding relationship between the moving speed of a pedestrian crossing the road and the distance from the pedestrian to the vehicle in the crossed road.

[0011] In a second aspect, an embodiment of the present disclosure provides a device for generating test data, which includes: A scene parameter acquisition module is configured to acquire road scene parameters and vehicle behavior parameters of a target vehicle; A road data acquisition module is configured to determine lane-level road data of a target vehicle from pre-generated high-precision map data based on road scene parameters; a trajectory data acquisition module configured to acquire lane-level simulated trajectory data of the target vehicle based on lane-level road data of the target vehicle, a set dead reckoning frequency, and a vehicle behavior parameter; The test file writing module is configured to write at least the lane-level simulation trajectory of the target vehicle into a test playback file. In a third aspect, an embodiment of the present disclosure provides an electronic device, including a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method as described in the first aspect or any one of the first aspects.

[0012] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium on which computer instructions are stored. When the computer instructions are executed by a processor, the method as described in the first aspect or the first aspect is implemented.

[0013] According to the technical solution provided by the embodiment of the present disclosure, by obtaining road scene parameters and vehicle behavior parameters of the target vehicle, wherein the road scene parameters can be understood as parameters describing the road scene on which the tester requires the target vehicle to travel, and the vehicle behavior parameters can be understood as describing the driving behavior that the target vehicle needs to simulate during driving; based on the road scene parameters, the lane-level road data on which the tester requires the target vehicle to travel can be determined from the pre-generated high-precision map data; based on the lane-level road data of the target vehicle, the set dead reckoning frequency and the vehicle behavior parameters, the lane-level simulated trajectory data of the target vehicle is obtained, and the lane-level simulated trajectory data describes the lane-level driving trajectory generated by the target vehicle simulating the corresponding vehicle behavior parameters when the target vehicle passes through the road on which the tester requires the target vehicle to travel; by writing at least the lane-level simulated trajectory of the target vehicle into the test playback file, it can be ensured that the lane-level simulated trajectory in the test playback file can cover the road scene that the tester is concerned about, and based on the test playback file, the performance of the intelligent driving system on the road can be comprehensively tested, thereby improving the credibility of the test results.

[0014] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Other features, objectives and advantages of the present disclosure will become more apparent through the following detailed description of non-limiting embodiments in conjunction with the accompanying drawings. In the accompanying drawings:

[0016] FIG. 1 shows a flow chart of a method for generating test data according to an embodiment of the present disclosure.

[0017] FIG. 2 shows a structural block diagram of a device for generating test data according to an embodiment of the present disclosure.

[0018] Figure 3 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0019] FIG. 4 shows a schematic diagram of the structure of a computer system suitable for implementing the method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts not related to the description of the exemplary embodiments are omitted in the accompanying drawings.

[0021] In the present disclosure, it should be understood that terms such as "include" or "have" are intended to indicate the presence of features, numbers, steps, behaviors, components, parts, or a combination thereof disclosed in the present specification, and are not intended to exclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or a combination thereof exist or are added.

[0022] It should also be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] In the present disclosure, if it involves operations of obtaining user information or user data or displaying user information or user data to others, the operations are all authorized and confirmed by the user, or actively selected by the user.

[0024] The applicant found that in the related technology, the navigation route calculation service can plan the navigation route from the starting point to the end point by setting the starting point and the end point, and then simulate the vehicle driving along the navigation route to generate the vehicle's driving trajectory. However, since the tester cannot finely control the roads actually covered by the navigation route calculated by the navigation route calculation service, the driving trajectory generated based on the simulated navigation has the problem of not being able to cover the road scenes that the tester is concerned about, resulting in the inability to test the performance of the intelligent driving system on some roads, affecting the credibility of the test results.

[0025] In order to solve the above problems, the embodiments of the present disclosure provide a method, apparatus, device and medium for generating test data.

[0026] According to the technical solution provided by the embodiment of the present disclosure, by obtaining road scene parameters and vehicle behavior parameters of the target vehicle, wherein the road scene parameters can be understood as parameters describing the road scene on which the tester requires the target vehicle to travel, and the vehicle behavior parameters can be understood as describing the driving behavior that the target vehicle needs to simulate during driving; based on the road scene parameters, the lane-level road data on which the tester requires the target vehicle to travel can be determined from the pre-generated high-precision map data; based on the lane-level road data of the target vehicle, the set dead reckoning frequency and the vehicle behavior parameters, the lane-level simulated trajectory data of the target vehicle is obtained, and the lane-level simulated trajectory data describes the lane-level driving trajectory generated by the target vehicle simulating the corresponding vehicle behavior parameters when the target vehicle passes through the road on which the tester requires the target vehicle to travel; by writing at least the lane-level simulated trajectory of the target vehicle into the test playback file, it can be ensured that the lane-level simulated trajectory in the test playback file can cover the road scene that the tester is concerned about, and based on the test playback file, the performance of the intelligent driving system on the road can be comprehensively tested, thereby improving the credibility of the test results.

[0027] FIG1 is a flow chart of a method for generating test data according to an embodiment of the present disclosure. As shown in FIG1 , the method for generating test data includes the following steps S101 - S104:

[0028] In step S101, road scene parameters and vehicle behavior parameters of the target vehicle are obtained; In step S102, based on the road scene parameters, lane-level road data of the target vehicle is determined from pre-generated high-precision map data; In step S103, based on the lane-level road data of the target vehicle, the set dead reckoning frequency and the vehicle behavior parameters, the lane-level simulated trajectory data of the target vehicle is obtained; In step S104, at least the lane-level simulation trajectory of the target vehicle is written into a test playback file.

[0029] In one implementation of the present disclosure, the road scene parameters may be used to describe the road scene that the tester is concerned about, and when the vehicle is traveling in the road scene, the intelligent driving function requirements for the vehicle may be high.

[0030] In one embodiment of the present disclosure, the road scene parameter is used to indicate at least one of a bridge, an overpass, a tunnel, a toll booth, a checkpoint, and a traffic light intersection. The road scene parameter may also include: a geographical area parameter, such as Chaoyang District, Beijing.

[0031] Furthermore, the road scene parameters can also be used to indicate roads with a high number of traffic accidents, roads near specific buildings (such as office buildings, conference centers, educational institutions, shopping centers, etc.), etc. The road scene parameters are related to the function to be tested. The examples of road scene parameters in this disclosure are only for illustrating the disclosed solution and should not be used as a limitation on the applicability of the disclosed solution.

[0032] In one implementation of the present disclosure, the vehicle behavior parameters of the target vehicle are used to describe the driving behavior that needs to be simulated when the target vehicle is driving. If required by the function to be tested, the vehicle behavior parameters may also include parameters used to describe the probability of occurrence of corresponding driving behaviors in different road scenarios.

[0033] In one embodiment of the present disclosure, the vehicle behavior parameter is used to indicate at least: changing lanes, accelerating, decelerating, overtaking, following, etc.

[0034] In one implementation of the present disclosure, obtaining road scene parameters and vehicle behavior parameters of the target vehicle can be understood as obtaining road scene parameters and vehicle behavior parameters input by a tester through a human-computer interaction interface, and can also be understood as reading and writing pre-stored road scene parameters and vehicle behavior parameters.

[0035] In one implementation of the present disclosure, based on road scene parameters, lane-level road data of a target vehicle is determined from pre-generated high-precision map data. This can be understood as determining data corresponding to a road including a road scene that satisfies the description of the road scene parameters from the pre-generated high-precision map data.

[0036] Exemplarily, if the road scene described by the road scene parameters includes: an intersection with traffic lights and a tunnel entrance, then the lane-level road data of the target vehicle should be: the lane-level road data of the road passing through the intersection with traffic lights and the tunnel entrance.

[0037] In one implementation of the present disclosure, based on the lane-level road data of the target vehicle, the set dead reckoning frequency and the vehicle behavior parameters, the lane-level simulated trajectory data of the target vehicle is obtained, which can be understood as: According to the lane-level road data of the target vehicle, a lane-level route trajectory is obtained, and the lane-level route trajectory passes through the lane-level road area defined by the road scene parameters, that is, the area satisfies the description of the road scene concerned by the tester by the road scene parameters; According to the lane-level road data, vehicle behavior parameters and the set dead reckoning frequency, the lane-level simulated trajectory data of the target vehicle is obtained, that is, based on the position coordinates and altitude data of the position points on the lane centerline recorded in the lane-level road data, the speed of the target vehicle when the behavior described by the vehicle behavior parameters occurs when the target vehicle is traveling along the corresponding lane line is obtained based on the vehicle behavior parameters, and according to the set dead reckoning frequency (that is, the signal frequency of the simulated positioning engine) and the vehicle speed, the trajectory data with heading and speed are fitted, that is, the lane-level simulated trajectory data of the target vehicle, wherein the lane-level simulated trajectory data includes continuous trajectory frame information. Exemplarily, continuous trajectory frame information can be generated at a dead reckoning frequency of 15 Hz, that is, 15 trajectory frames are output per second.

[0038] The technical solution provided by the embodiment of the present disclosure obtains road scene parameters and vehicle behavior parameters of the target vehicle, wherein the road scene parameters can be understood as parameters describing the road scene on which the tester requires the target vehicle to travel, and the vehicle behavior parameters can be understood as describing the driving behavior that the target vehicle needs to simulate during driving; based on the road scene parameters, the lane-level road data on which the tester requires the target vehicle to travel can be determined from the pre-generated high-precision map data; based on the lane-level road data of the target vehicle, the set dead reckoning frequency and the vehicle behavior parameters, the lane-level simulated trajectory data of the target vehicle is obtained, and the lane-level simulated trajectory data describes the lane-level driving trajectory generated when the target vehicle simulates the corresponding vehicle behavior parameters when the target vehicle passes through the road on which the tester requires the target vehicle to travel; by writing at least the lane-level simulated trajectory of the target vehicle into a test playback file, it can be ensured that the lane-level simulated trajectory in the test playback file can cover the road scene that the tester is concerned about, and based on the test playback file, the performance of the intelligent driving system on the road can be comprehensively tested, thereby improving the credibility of the test results.

[0039] In one embodiment of the present disclosure, the method further comprises: Obtaining following strategy parameters that match the road scene parameters; According to the lane-level simulated trajectory data and the following strategy parameters, the simulated trajectory data of other moving objects whose distances from the target vehicle meet a preset distance threshold are obtained; Write the simulated trajectory data of other moving objects to the test playback file.

[0040] In an implementation of the present disclosure, obtaining following strategy parameters that match road scene parameters can be understood as determining following strategy parameters that match the road scene parameters based on a pre-generated correspondence between the road scene parameters and the following strategy parameters.

[0041] The following strategy parameters matched with the road scene parameters may be understood as being used to indicate the driving behavior of the target vehicle when following other vehicles, and / or the moving behavior of other moving objects when following the target vehicle, in the road scene that the tester is concerned about.

[0042] According to the lane-level simulated trajectory data and the following strategy parameters, the simulated trajectory data of other moving objects whose distance from the target vehicle meets the preset distance threshold are obtained, which can be understood as: Based on the heading and speed of the target vehicle in the lane-level simulated trajectory data, the moving speed of other moving objects whose distance from the target vehicle meets the preset distance threshold when moving in the corresponding lane and performing the moving behavior described by the following strategy parameters is calculated, and according to the set dead reckoning frequency and the moving speed of other moving objects obtained by the above calculation, the trajectory data with heading and moving speed are fitted, that is, the simulated trajectory data of other moving objects. Among them, the simulated trajectory data of other moving objects includes continuous trajectory frame information. Exemplarily, continuous trajectory frame information can be generated at a dead reckoning frequency of 15 Hz, that is, 15 trajectory frames are output per second.

[0043] In the above technical scheme, by obtaining following strategy parameters that match the road scene parameters, and obtaining simulated trajectory data of other moving objects whose distance from the target vehicle meets the preset distance threshold based on the lane-level simulated trajectory data and the following strategy parameters, the trajectory of other moving objects that are closer to the target vehicle can be simulated, and by writing the simulated trajectory data of other moving objects into the test playback file, it can be further ensured that the lane-level simulated trajectory in the test playback file can not only cover the road scene that the tester is concerned about, but also describe the trajectory of other moving targets that will be affected by the driving behavior of the target vehicle in the road scene. Based on the test playback file, the performance of the intelligent driving system on the road can be tested more comprehensively, further improving the credibility of the test results.

[0044] In one embodiment of the present disclosure, based on the road scene parameters, determining the lane-level road data of the target vehicle from the pre-generated high-precision map data includes: Matching the road scene parameters with the road information of at least one road and the lane information of at least one lane recorded in the pre-generated high-precision map data, and obtaining lane-level road data matching the road scene parameters as the lane-level road data of the target vehicle; Among them, the road information includes at least one of road attributes, road connectivity, and road longitude and latitude, and the lane information includes at least one of lane attributes, lane connectivity, lane longitude and latitude, and altitude. The lane longitude and latitude may include the longitude and latitude of a position point on the center line of the lane. It can be understood that when a vehicle moves along a lane, it usually moves along the center of the lane. Therefore, the high-precision map data may pre-store the longitude and latitude of the position point on the center line of the lane. If the longitude and latitude of the center line are not stored in the high-precision map data, but the longitude and latitude of the lane line are stored, the longitude and latitude of the position point on the center line of the lane may be generated based on the longitude and latitude of the lane line.

[0045] In an implementation of the present disclosure, road attributes may include road grade (e.g., expressway, national highway, provincial highway, etc.), road composition (e.g., whether it includes auxiliary roads, exits, entrances, etc.), road form (e.g., whether it is a tunnel, bridge, or overpass), road direction (e.g., bidirectional or unidirectional), etc. The road connectivity relationship may be understood as indicating the road connected to the starting point of the corresponding road and the road connected to the end point of the corresponding road. The longitude and latitude of the road may be understood as indicating the longitude and latitude of at least one sampling point in the corresponding road. The road altitude may be understood as indicating the altitude of at least one sampling point in the corresponding road.

[0046] In an implementation of the present disclosure, lane attributes may include lane composition (e.g., whether it is located in a secondary road, road exit, or road entrance), lane shape (e.g., whether it is a lane of a road located in a tunnel, bridge, or overpass), lane direction, etc. Lane connectivity may be understood as other lanes that are connected to the corresponding lane. Lane longitude and latitude may be understood as longitude and latitude that indicate at least one sampling point in the corresponding lane. Lane altitude may be understood as altitude that indicates at least one sampling point in the corresponding lane.

[0047] For example, if the road scene parameters are Chaoyang District, Beijing, tunnels, toll booths, roads with right-turn lanes and traffic lights, then from the pre-generated high-precision map data, the data belonging to Chaoyang District, Beijing, search for roads with tunnels, roads with road facilities including toll booths, roads with traffic lights, and roads with lanes including right-turn lanes, and then obtain the lane-level road data corresponding to these roads. Subsequently, based on the position coordinates and altitude data of the position points on the lane centerline recorded in the lane-level road data of these roads, based on the vehicle behavior parameters, the speed of the target vehicle when the behavior described by the vehicle behavior parameters occurs when driving in the corresponding lane is obtained, and according to the set dead reckoning frequency (i.e., the signal frequency of the simulated positioning engine) and the vehicle speed, the trajectory data with heading and speed is fitted, i.e., the lane-level simulated trajectory data of the target vehicle.

[0048] In the above technical solution, by matching the road scene parameters with the road information of at least one road and the lane information of at least one lane recorded in the pre-generated high-precision map data, lane-level road data matching the road scene parameters are obtained as the lane-level road data of the target vehicle. This ensures that the road corresponding to the lane-level road data of the target vehicle passes through the road scene described by the road scene parameters, thereby improving the reliability of the lane-level road data of the target vehicle.

[0049] In one embodiment of the present disclosure, based on the lane-level road data of the target vehicle, the set dead reckoning frequency and the vehicle behavior parameters, the lane-level simulated trajectory data of the target vehicle is obtained, including: According to the lane-level road data of the target vehicle, a lane-level route trajectory is obtained, and the lane-level route trajectory passes through an area defined by the road scene parameters; According to the lane-level route trajectory, vehicle behavior parameters and the set dead reckoning frequency, the lane-level simulated trajectory data of the target vehicle is obtained.

[0050] In one embodiment of the present disclosure, other moving objects include a preceding vehicle in the same lane and a pedestrian crossing the road; The following strategy parameters include at least one of the corresponding relationship between the distance from the vehicle to the preceding vehicle in the same lane and the moving speed of the vehicle, and the corresponding relationship between the moving speed of a pedestrian crossing the road and the distance from the pedestrian to the vehicle in the crossed road.

[0051] In the above technical scheme, by limiting other moving objects to include the leading vehicle in the same lane and pedestrians crossing the road, the following strategy parameters include at least one of the correspondence between the distance from the vehicle to the leading vehicle in the same lane and the vehicle's moving speed, and the correspondence between the moving speed of pedestrians crossing the road and the distance from the pedestrian to the vehicle in the crossed road. This can improve the authenticity of the simulated trajectory data of other moving objects obtained, help to more comprehensively test the performance of the intelligent driving system on the road based on the test playback file in which the simulated trajectory data of other moving objects is written, and further improve the credibility of the test results.

[0052] Fig. 2 shows a structural block diagram of a device for generating test data according to an embodiment of the present disclosure, wherein the device can be implemented as part or all of an electronic device through software, hardware, or a combination of both.

[0053] As shown in FIG. 2 , the test data generating device 200 includes: A scene parameter acquisition module 201 is configured to acquire road scene parameters and vehicle behavior parameters of a target vehicle; The road data acquisition module 202 is configured to determine lane-level road data of the target vehicle from pre-generated high-precision map data based on road scene parameters; The trajectory data acquisition module 203 is configured to acquire lane-level simulated trajectory data of the target vehicle based on the lane-level road data of the target vehicle, the set dead reckoning frequency and the vehicle behavior parameters; The test file writing module 204 is configured to write at least the lane-level simulation trajectory of the target vehicle into a test playback file.

[0054] The present disclosure also discloses an electronic device, Figure 3 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0055] like Figure 3 As shown, the electronic device includes a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method according to an embodiment of the present disclosure.

[0056] The present disclosure provides a method for generating test data, including: Obtaining road scene parameters and vehicle behavior parameters of the target vehicle; Based on the road scene parameters, the lane-level road data of the target vehicle is determined from the pre-generated high-precision map data; Based on the lane-level road data of the target vehicle, the set dead reckoning frequency and the vehicle behavior parameters, the lane-level simulated trajectory data of the target vehicle is obtained; At least the lane-level simulation trajectory of the target vehicle is written to the test playback file.

[0057] In one embodiment of the present disclosure, the method further comprises: Obtaining following strategy parameters that match the road scene parameters; According to the lane-level simulated trajectory data and the following strategy parameters, the simulated trajectory data of other moving objects whose distances from the target vehicle meet a preset distance threshold are obtained; Write the simulated trajectory data of other moving objects to the test playback file.

[0058] In one embodiment of the present disclosure, based on the road scene parameters, the lane-level road data of the target vehicle is determined from the pre-generated high-precision map data. The road scene parameters are matched with the road information of at least one road and the lane information of at least one lane recorded in the pre-generated high-precision map data to obtain lane-level road data matching the road scene parameters as the lane-level road data of the target vehicle, wherein the lane-level road data includes at least one of road attributes, road connectivity, road longitude and latitude, and road altitude, and the lane information includes at least one of lane attributes, lane connectivity, lane longitude and latitude, and lane altitude.

[0059] In one embodiment of the present disclosure, the road scene parameter is used to indicate at least one of a bridge, an viaduct, a tunnel, a toll booth, a checkpoint, and a traffic light intersection.

[0060] In one embodiment of the present disclosure, based on the lane-level road data of the target vehicle, the set dead reckoning frequency and the vehicle behavior parameters, the lane-level simulated trajectory data of the target vehicle is obtained, including: According to the lane-level road data of the target vehicle, a lane-level route trajectory is obtained, and the lane-level route trajectory passes through an area defined by the road scene parameters; According to the lane-level route trajectory, vehicle behavior parameters and the set dead reckoning frequency, the lane-level simulated trajectory data of the target vehicle is obtained.

[0061] In one embodiment of the present disclosure, the vehicle behavior parameter is used to indicate at least: lane change, acceleration, deceleration, overtaking, and following.

[0062] In one embodiment of the present disclosure, other moving objects include a preceding vehicle in the same lane and a pedestrian crossing the road; The following strategy parameters include at least one of the corresponding relationship between the distance from the vehicle to the preceding vehicle in the same lane and the moving speed of the vehicle, and the corresponding relationship between the moving speed of a pedestrian crossing the road and the distance from the pedestrian to the vehicle in the crossed road.

[0063] FIG. 4 shows a schematic diagram of the structure of a computer system suitable for implementing the method according to an embodiment of the present disclosure.

[0064] As shown in Figure 4, the computer system includes a processing unit, which can execute various methods in the above-mentioned embodiments according to a program stored in a read-only memory (ROM) or a program loaded from a storage part into a random access memory (RAM). In the RAM, various programs and data required for the operation of the computer system are also stored. The processing unit, ROM and RAM are connected to each other through a bus. An input / output (I / O) interface is also connected to the bus.

[0065] The following components are connected to the I / O interface: an input part including a keyboard, a mouse, etc.; an output part including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage part including a hard disk, etc.; and a communication part including a network interface card such as a LAN card, a modem, etc. The communication part performs a communication process via a network such as the Internet. The drive is also connected to the I / O interface as needed. Removable media, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on the drive as needed so that the computer program read therefrom can be installed into the storage part as needed. Among them, the processing unit can be implemented as a processing unit such as a CPU, a GPU, a TPU, an FPGA, an NPU, etc.

[0066] In particular, according to an embodiment of the present disclosure, the method described above can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes a program code for executing the above method. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium.

[0067] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0068] The units or modules involved in the embodiments described in the present disclosure may be implemented by software or programmable hardware. The units or modules described may also be set in a processor, and the names of these units or modules do not constitute limitations on the units or modules themselves in some cases.

[0069] As another aspect, the present disclosure further provides a computer-readable storage medium, which may be a computer-readable storage medium included in the electronic device or computer system in the above embodiment; or a computer-readable storage medium that exists independently and is not assembled into a device. The computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the method described in the present disclosure.

[0070] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present disclosure is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other.

Claims

1. A method for generating test data, wherein: include: Obtaining road scene parameters and vehicle behavior parameters of the target vehicle; Based on the road scene parameters, determining lane-level road data of the target vehicle from pre-generated high-precision map data; Acquiring lane-level simulated trajectory data of the target vehicle based on the lane-level road data of the target vehicle, the set dead reckoning frequency, and the vehicle behavior parameter; At least the lane-level simulation trajectory of the target vehicle is written into a test playback file.

2. The method according to claim 1, wherein: The method further comprises: Acquire following strategy parameters that match the road scene parameters; Acquire simulated trajectory data of other moving objects whose distances from the target vehicle meet a preset distance threshold according to the lane-level simulated trajectory data and the following strategy parameters; The simulation trajectory data of the other moving objects are written into the test playback file.

3. The method according to claim 1 or 2, wherein: The determining, based on the road scene parameters, lane-level road data of the target vehicle from pre-generated high-precision map data includes: The road scene parameters are matched with the road information of at least one road and the lane information of at least one lane recorded in the pre-generated high-precision map data to obtain lane-level road data matching the road scene parameters as the lane-level road data of the target vehicle, wherein the lane-level road data includes at least one of road attributes, road connectivity, road longitude and latitude, and road altitude, and the lane information includes at least one of lane attributes, lane connectivity, lane longitude and latitude, and lane altitude.

4. The method according to claim 3, wherein: The road scene parameter is used to indicate at least one of a bridge, an viaduct, a tunnel, a toll booth, a checkpoint, and a traffic light intersection.

5. The method according to claim 3, wherein: The acquiring lane-level simulated trajectory data of the target vehicle based on the lane-level road data of the target vehicle, the set dead reckoning frequency and the vehicle behavior parameter includes: Acquire a lane-level route trajectory according to the lane-level road data of the target vehicle, wherein the lane-level route trajectory passes through an area defined by the road scene parameters; The lane-level simulated trajectory data of the target vehicle is obtained according to the lane-level route trajectory, vehicle behavior parameters and a set dead reckoning frequency.

6. The method according to claim 5, wherein: The vehicle behavior parameter is used to indicate at least: lane change, acceleration, deceleration, overtaking, and following.

7. The method according to claim 2, wherein: The other moving objects include the vehicle ahead in the same lane and pedestrians crossing the road; The following strategy parameters include at least one of a corresponding relationship between a distance from the vehicle to a preceding vehicle in the same lane and a moving speed of the vehicle, and a corresponding relationship between a moving speed of a pedestrian crossing the road and a distance from the pedestrian to the target vehicle.

8. A device for generating test data, wherein: include: A scene parameter acquisition module is configured to acquire road scene parameters and vehicle behavior parameters of a target vehicle; A road data acquisition module is configured to determine lane-level road data of the target vehicle from pre-generated high-precision map data based on the road scene parameters; a trajectory data acquisition module configured to acquire lane-level simulated trajectory data of the target vehicle based on the lane-level road data of the target vehicle, a set dead reckoning frequency and the vehicle behavior parameter; The test file writing module is configured to write at least the lane-level simulation trajectory of the target vehicle into a test playback file.

9. An electronic device comprising a memory and a processor; wherein: The memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method steps of any one of claims 1-7.

10. A computer-readable storage medium having computer instructions stored thereon, wherein: When the computer instructions are executed by a processor, the method steps of any one of claims 1 to 7 are implemented.

Images