Simulation data generation method, device and medium

Abstract

The embodiment of the application provides a simulation data generation method, device and medium, three-dimensional maps are generated according to map data; vehicle planning paths are generated from the three-dimensional maps according to population data and vehicle data; simulation vehicle driving is performed according to the three-dimensional maps, vehicle equipment information of the vehicle data and the vehicle planning paths, and simulation data between the vehicle and the map is obtained; the path planning scheme of all vehicles in a region can be automatically generated to adapt to maps of different scales and different scenes, and multi-modal simulation data related to vehicle equipment between the vehicle and the map is obtained, so that the simulation data is diversified and comprehensive, and a better simulation effect is achieved; rich map data, population data and vehicle data are used, so that the generation of simulation vehicle driving data can be realized; the amount of manual participation in the process of generating an automatic driving related data set is greatly reduced, and a high degree of freedom data set multi-dimensional customization is realized in a parameterized manner.

Description

Technical Field

[0001] The embodiments of this application relate to, but are not limited to, the field of data simulation, and particularly to simulation data generation methods, devices, and media. Background Technology

[0002] Existing simulation models and methods suffer from poor simulation results, necessitating full human involvement in the simulation data generation process to prevent the generation of unreasonable data. For example, before the simulation, it is typically necessary to manually set vehicle path planning, vehicle sensor models, simulation duration, and customized data formats based on the actual scene map. Furthermore, during the simulation, the driving status of the vehicles must be monitored and continuously adjusted to avoid generating data that deviates from the actual scene or is meaningless. Summary of the Invention

[0003] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0004] This application provides a method, device, and medium for generating simulation data.

[0005] An embodiment of the first aspect of this application provides a simulation data generation method, comprising:

[0006] Acquire map data, population data, and vehicle data;

[0007] Generate a 3D map based on the map data;

[0008] Vehicle planning routes are generated from the 3D map based on the population data and the vehicle data.

[0009] Based on the 3D map, the vehicle equipment information of the vehicle data, and the planned vehicle path, simulated vehicle driving is performed to obtain simulation data between the vehicle and the map.

[0010] In some embodiments of the first aspect of this application, the population data includes structured population data and unstructured population data, wherein the structured population data is population data related to map distribution, and the unstructured population data is population data not related to map distribution;

[0011] The step of generating vehicle planning routes from the 3D map based on the population data and the vehicle data includes:

[0012] Traffic flow distribution is obtained based on the working area, population size of the working area, residential area, and population size of the residential area in the 3D map of the population structured data.

[0013] Individual activity paths are obtained based on the aforementioned unstructured population data;

[0014] Vehicle planning routes are generated from a 3D map based on the traffic flow distribution, individual activity paths, and vehicle data.

[0015] In certain embodiments of the first aspect of this application, the work area and the residential area are divided as follows:

[0016] The location of the road intersection is obtained based on the map data;

[0017] Clustering is performed using the location of the road intersection as the center to divide the area into regions, resulting in the work area and the residential area.

[0018] In certain embodiments of the first aspect of this application, the vehicle equipment information includes communication equipment information; the step of simulating vehicle driving based on the three-dimensional map, the vehicle equipment information of the vehicle data, and the vehicle planned path to obtain simulation data between the vehicle and the map includes:

[0019] Based on the 3D map and the vehicle planning path, the vehicle trajectory points during the simulated vehicle driving process are obtained;

[0020] The first distance between vehicles and the second distance between vehicles and base stations are obtained based on the base station location information on the map, the communication equipment information, and the vehicle driving trajectory points;

[0021] Based on preset base station communication parameters, the first distance, and the second distance, a communication simulation between the vehicle and the base station is performed to obtain communication simulation data during the simulated vehicle's driving process.

[0022] In certain embodiments of the first aspect of this application, the base station communication parameters include an antenna characteristic constant, an antenna far-field distance, and a path attenuation power factor; the step of performing communication simulation between the vehicle and the base station based on preset base station communication parameters, the first distance, and the second distance to obtain communication simulation data during the simulated vehicle's driving process includes:

[0023] Based on preset base station communication parameters, the first distance, and the second distance, communication channel parameters are obtained, and the communication channel parameters include a channel fading factor.

[0024] Based on the communication channel parameters, communication simulation between the vehicle and the base station is performed to obtain communication simulation data during the simulated vehicle's driving process.

[0025] In certain embodiments of the first aspect of this application, the vehicle equipment information includes sensor equipment information; the step of simulating vehicle driving based on the 3D map, the vehicle equipment information of the vehicle data, and the vehicle planned path to obtain simulation data between the vehicle and the map includes:

[0026] Based on the 3D map and the vehicle planning path, the vehicle trajectory points during the simulated vehicle driving process are obtained;

[0027] Based on the sensor device information and the vehicle's driving trajectory points, the relative position mapping relationship between the sensor and the vehicle is obtained;

[0028] Based on the 3D map, the vehicle's trajectory points, and the relative position mapping relationship, the 3D map during the simulated vehicle's driving process and the projection data formed by the vehicle's projection under the vehicle's sensor viewpoint are obtained.

[0029] In some embodiments of the first aspect of this application, the process for setting the sampling interval of the simulation data is as follows:

[0030] The simulation step size value of the simulated vehicle driving is determined as the time quantization factor of the sampling interval;

[0031] Based on the 3D map and the vehicle planning path, the vehicle trajectory points during the simulated vehicle driving process are obtained, and the spatial quantization factor of the sampling interval is determined based on the vehicle trajectory points.

[0032] According to certain embodiments of the first aspect of this application, the simulation data generation method further includes:

[0033] The vehicle driving is simulated based on the 3D map, the vehicle equipment information of the vehicle data, and the vehicle planned path. The spatial changes of the vehicle position at adjacent time intervals are obtained through a Markov chain model. The state transition kernel function is obtained based on the spatial changes of the vehicle position at adjacent time intervals. The state transition kernel function is used to describe the state transition process of vehicle-related events.

[0034] According to a second aspect of this application, an electronic device includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for enabling communication between the processor and the memory. When the program is executed by the processor, it implements the simulation data generation method as described above.

[0035] According to a third aspect of this application, a computer-readable storage medium stores computer-executable instructions for causing a computer to perform the simulation data generation method described above.

[0036] The above-mentioned solution offers at least the following benefits: It can generate path planning schemes for all vehicles within a region from a 3D map based on population and vehicle data, adapting to maps of different scales and scenarios. Furthermore, it simulates vehicle driving based on the 3D map, vehicle equipment information from the vehicle data, and the planned vehicle paths, obtaining multimodal simulation data related to vehicle equipment and the map. This diversifies and comprehensively enhances the simulation data, resulting in better simulation performance. Additionally, through unsupervised learning algorithm design, continuous human intervention in observation and adjustment is unnecessary. The generation of simulated vehicle driving data can be achieved using only abundant map, population, and vehicle data. This significantly reduces the amount of human intervention in the generation of autonomous driving-related datasets, enabling high-degree-of-freedom, multi-dimensional customization of datasets without code modification through parameterization. Attached Figure Description

[0037] The accompanying drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0038] Figure 1 This is a flowchart illustrating the steps of the simulation data generation method provided in the embodiments of this application;

[0039] Figure 2 This is a sub-step diagram of step S300;

[0040] Figure 3 This is a diagram of the sub-steps of step S400 in communication simulation;

[0041] Figure 4 yes Figure 3 A diagram of the sub-steps of step S430 in the diagram;

[0042] Figure 5 This is a diagram of the sub-steps of step S400 in terms of sensor simulation;

[0043] Figure 6 This is a step-by-step diagram illustrating the process of setting the sampling interval for simulation data;

[0044] Figure 7 This is a step diagram of obtaining the state transition kernel function;

[0045] Figure 8 This is a structural diagram of the electronic device provided in the embodiments of this application;

[0046] Figure 9 This is a schematic diagram of the interface of the simulation data generation system provided in the embodiments of this application. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0048] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, or the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0049] The embodiments of this application will be further described below with reference to the accompanying drawings.

[0050] An embodiment of this application provides a method for generating simulation data.

[0051] Reference Figure 1 The simulation data generation method includes, but is not limited to, the following steps:

[0052] Step S100: Obtain map data, population data, and vehicle data;

[0053] Step S200: Generate a 3D map based on the map data;

[0054] Step S300: Generate vehicle planning routes from the 3D map based on population data and vehicle data;

[0055] Step S400: Simulate vehicle driving based on the vehicle equipment information and planned vehicle path of the 3D map and vehicle data to obtain simulation data between the vehicle and the map.

[0056] For step S100, acquire map data, population data, and vehicle data.

[0057] Map data is used to describe roads, buildings, and other related information.

[0058] Population data describes aspects such as population size, distribution, and individual characteristics, including age distribution, car ownership, labor force size, and working hours. Population data includes structured and unstructured data. Structured population data is related to map distribution, such as the number of residences and workplaces on each street. Unstructured population data is not related to map distribution, such as age distribution, working-age population proportion, number of residences, and car ownership rate.

[0059] Vehicle data describes information about vehicles operating in the area, such as vehicle type, shape, onboard equipment, and passenger capacity. The vehicle data uses the vtypes format defined by the open-source software CARLA, describing a collection of information about all vehicles in the area, including their type and dimensions (length, width, and height).

[0060] In step S200, a 3D map is generated based on the map data using simulation software. Specifically, the entire road network is described using an OpenDRIVE file in XML format, involving all data related to the road environment, including surrounding buildings, road geometry, logical interconnections of lanes, and signal controllers (such as intersections).

[0061] For step S300, the work area and residential area are divided as follows: the location of road intersections is obtained from the map data; clustering is performed with the location of the road intersections as the center to divide the area, thus obtaining the work area and residential area.

[0062] Specifically, let S denote the work area or residential area, and x denote the location of the road intersection. Divide the area around the road intersection location. According to the K-clustering algorithm: Where, μ i It is the center point of the i-th region. Based on historical experience, a value of 2 for K for the working region and a value of 3 for K for the residential region show good fitting results.

[0063] Reference Figure 2 Furthermore, based on population and vehicle data, vehicle planning routes are generated from the 3D map, including but not limited to the following steps:

[0064] Step S310: Based on the work area, population size of the work area, residential area, and population size of the residential area in the 3D map of the population structured data, obtain the traffic flow distribution.

[0065] Step S320: Obtain individual activity paths based on unstructured population data;

[0066] Step S330: Generate vehicle planning routes from the 3D map based on traffic flow distribution, individual activity paths, and vehicle data.

[0067] For step S310, based on the working area, population size of the working area, residential area, and population size of the residential area in the 3D map of the population structured data, and according to the number of intersections in the area, the population size is allocated proportionally to obtain the distribution of traffic flow on different streets.

[0068] For step S320, implicit daily activities (commuting to and from get off work, commuting to and from school, etc.) are extracted from unstructured population data to obtain personal activity paths, which include the starting point, the destination, and the route from the starting point to the destination.

[0069] For step S330, based on traffic flow distribution, personal activity paths, and vehicle data, the A* algorithm is used to balance the traffic flow on different roads, thereby generating vehicle planning paths from the 3D map.

[0070] Through unsupervised learning algorithms, it can adapt to maps of different sizes and scenarios, and generate path planning schemes for all vehicles in the area.

[0071] In step S400, vehicle driving is simulated based on the 3D map, vehicle equipment information from vehicle data, and the planned vehicle path, resulting in simulation data between the vehicle and the map. This simulation data is multimodal, including communication simulation data and projection data from sensors.

[0072] Reference Figure 3 The vehicle equipment information includes communication equipment information; based on the 3D map, vehicle equipment information from vehicle data, and the planned vehicle path, simulated vehicle driving is performed to obtain simulation data between the vehicle and the map, including but not limited to the following steps:

[0073] Step S410: Based on the 3D map and the vehicle planning path, obtain the vehicle trajectory points during the simulated vehicle driving process;

[0074] Step S420: Based on the base station location information, communication equipment information and vehicle driving trajectory points on the map, obtain the first distance between vehicles and the second distance between vehicles and base stations;

[0075] Step S430: Based on the preset base station communication parameters, the first distance and the second distance, perform communication simulation between the vehicle and the base station to obtain communication simulation data during the simulated vehicle's driving process.

[0076] Reference Figure 4 Specifically, for step S430, communication simulation between the vehicle and the base station is performed based on preset base station communication parameters, a first distance, and a second distance to obtain communication simulation data during the simulated vehicle's driving process, including but not limited to the following steps:

[0077] Step S431: Based on the preset base station communication parameters, the first distance, and the second distance, the communication channel parameters are obtained. The communication channel parameters include the channel fading factor. Among them, the base station communication parameters include the antenna characteristic constant, the antenna far-field region distance, and the path attenuation power factor.

[0078] Step S432: Based on the communication channel parameters, perform communication simulation between the vehicle and the base station to obtain communication simulation data during the simulated vehicle's driving process.

[0079] During vehicle operation, the distance between vehicles and the distance between a vehicle and a base station are constantly changing. Based on this, it is necessary to conduct communication simulation between the vehicle and the base station to obtain communication simulation data during the simulated vehicle operation.

[0080] Based on the travel trajectory points of vehicle A and vehicle B, the first distance between vehicle A and vehicle B can be obtained. Based on the travel trajectory points of vehicle A and the location information of base station a, the second distance between vehicle A and base station a can be obtained.

[0081] During the simulated vehicle's movement, global communication channel parameters are obtained based on preset base station communication parameters, a first distance, and a second distance. For example, using a general path fading model based on statistical channels, the distance at time t can be calculated as d. t The channel fading factor at that time can be expressed as: In the formula, K is the antenna characteristic constant, σ is the antenna far-field distance, and ∈ is the path attenuation power factor. Base station communication parameters can be selected based on statistical characteristics in an open environment. Based on the description of the communication channel, and with additional settings for the communication frequency band, transmit power, and communication bandwidth, the simulated global communication rate can be obtained using Shannon's formula.

[0082] Furthermore, based on the 3D map model, a more accurate channel fading factor is obtained through a 3D path tracing-based method. Specifically, at time t, considering the obstruction of the line-of-sight channel by buildings and other environmental factors, and considering other 3D environments calculated using ray tracing, a more accurate real-time channel fading factor is obtained by superimposing these factors. The ray tracing method can be achieved by reusing the ray tracing built into the 3D image engine and adding an additional constant attenuation factor.

[0083] Based on the communication channel parameters, communication simulation between the vehicle and the base station is performed to obtain communication simulation data during the simulated vehicle's driving process.

[0084] Reference Figure 5 On the other hand, regarding the acquisition of sensor projection data, vehicle driving is simulated based on the 3D map, vehicle equipment information from vehicle data, and the vehicle's planned path to obtain simulation data between the vehicle and the map, including but not limited to the following steps:

[0085] Step S440: Based on the 3D map and the vehicle planning path, obtain the vehicle trajectory points during the simulated vehicle driving process;

[0086] Step S450: Based on the sensor device information and the vehicle's driving trajectory points, obtain the relative position mapping relationship between the sensor and the vehicle;

[0087] Step S460: Based on the 3D map, vehicle trajectory points, and relative position mapping relationship, obtain the 3D map during the simulated vehicle driving process and the projection data formed by the vehicle's projection under the vehicle sensor's view.

[0088] Based on a 3D map, rendering with a 3D image engine yields a series of 2D and 3D images, along with statistical information from within them. Vehicle equipment information includes sensor information, specifying sensor types and their installation locations on the vehicle. Sensor types can include RGB cameras, depth cameras, LiDAR, millimeter-wave radar, etc. Based on the sensor information and the vehicle's trajectory points, the relative positional mapping between the sensors and the vehicle is obtained. This mapping is parameterized using simple geometric relationships and can be automated.

[0089] Through basic 3D model graphics operations, based on the 3D map, vehicle trajectory points, and relative position mapping relationships, the system obtains 3D map data of the simulated vehicle's movement and projection data formed by the vehicle's projection from the vehicle's sensor perspective. The projection data is semantically segmented data, i.e., data labels corresponding to the original sensor data. Furthermore, the projection data supports various common dataset types, such as exporting from training dataset formats like KITTI and Lyft.

[0090] Furthermore, due to the detailed 3D models and related operations, the aforementioned communication simulation and multimodal dataset acquisition processes involve significant computational resource overhead. A reasonable sampling interval needs to be defined to balance overall simulation time and simulation accuracy.

[0091] Specifically, the dataset is downsampled during or after simulation by using quantization methods on both the time and spatial scales, i.e., by employing time quantization factors and spatial quantization factors.

[0092] Reference Figure 6 The process for setting the sampling interval for simulation data is as follows:

[0093] Step S471: Determine the simulation step size value of the simulated vehicle driving as the time quantization factor of the sampling interval;

[0094] Step S472: Obtain the vehicle trajectory points during the simulated vehicle driving process based on the 3D map and the vehicle planning path, and determine the spatial quantization factor of the sampling interval based on the vehicle trajectory points; for example, selecting l1 distance (Manhattan distance) as the quantization condition in spatial quantization can obtain a "chessboard" spatial quantization effect; or selecting l2 distance (Euclidean distance) as the quantization condition in spatial quantization can obtain a "honeycomb" spatial quantization effect.

[0095] In some embodiments of this application, a low-precision large-scale simulation process with the same parameter settings can be quickly reproduced by generating a probability transfer kernel function.

[0096] Reference Figure 7 The simulation data generation method also includes the step of obtaining the state transition kernel function, which is used to describe the state transition process of vehicle-related events.

[0097] But not limited to the following steps:

[0098] Step S480: Simulate vehicle driving based on the vehicle equipment information and vehicle planning path of the 3D map and vehicle data. Obtain the spatial changes of vehicle position in adjacent time periods through the Markov chain model, and obtain the state transition kernel function based on the spatial changes of vehicle position in adjacent time periods.

[0099] Specifically, based on spatiotemporal quantization, the temporal statistical characteristics of the simulation process with given parameters can be obtained, that is, the spatial changes of vehicle positions at adjacent times can be obtained through Markov chain models.

[0100] First, based on the Markov property, the stationary transition probability description of the time series is obtained through a smoothing window, as shown below: In the formula, x t Let be the data point at time t, and SW be the size of the sliding window.

[0101] The state transition kernel function is derived from the spatial changes in vehicle positions at adjacent time points. This kernel function describes the state transition process of vehicle-related events using a sparse matrix. Specifically, the state transition kernel function can be expressed as: In the formula, N[A] represents the number of times event A occurs.

[0102] In this embodiment, a path planning scheme for all vehicles in a region can be generated from a 3D map based on population data and vehicle data to adapt to maps of different scales and scenarios. The vehicle driving is simulated based on the 3D map, vehicle equipment information from vehicle data, and planned vehicle paths, resulting in multimodal simulation data related to vehicle equipment between vehicles and the map. This makes the simulation data more diverse and comprehensive, achieving better simulation results.

[0103] Furthermore, through the design of unsupervised learning algorithms, continuous human intervention in observation and adjustment is unnecessary. The generation of simulated vehicle driving data can be achieved simply by utilizing abundant map data, population data, and vehicle data. This significantly reduces the amount of human intervention in the generation of autonomous driving-related datasets and enables multi-dimensional customization of high-degree-of-freedom datasets without code modification through parameterization.

[0104] An embodiment of this application provides a simulation data generation system.

[0105] The simulation data generation system uses the simulation data generation method described above. (Refer to...) Figure 9 , Figure 9 This is a schematic diagram of the interface of the simulation data generation system provided in this application embodiment. In the figure, the upper left corner is a bird's-eye view of the 3D map; the upper right corner is a schematic diagram of the vehicle planning path; and the bottom is a graphical display of the simulation data.

[0106] The simulation data generation system includes a data input module, a map generation module, a path planning module, and a simulation module.

[0107] The data input module is used to acquire map data, population data, and vehicle data; the map generation module is used to generate a 3D map based on the map data; the route planning module is used to generate planned vehicle routes from the 3D map based on the population data and vehicle data; and the simulation module is used to simulate vehicle driving based on the 3D map, vehicle equipment information from the vehicle data, and the planned vehicle routes, thereby obtaining simulation data between the vehicle and the map.

[0108] An embodiment of this application provides an electronic device. (Refer to...) Figure 8 The electronic device includes a memory 620, a processor 610, a program stored in the memory 620 and executable on the processor 610, and a data bus 630 for connecting and communicating between the processor 610 and the memory 620. When the program is executed by the processor 610, it implements the simulation data generation method as described above.

[0109] This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0110] In general, for the hardware structure of electronic devices, the processor 610 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor 610, application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., to execute relevant programs in order to implement the technical solutions provided in the embodiments of this application.

[0111] The memory 620 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 620 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 620 and is called and executed by the processor 610.

[0112] Input / output interfaces are used to implement information input and output.

[0113] The communication interface is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0114] Bus 630 transmits information between various components of the device, such as processor 610, memory 620, input / output interfaces, and communication interfaces. Processor 610, memory 620, input / output interfaces, and communication interfaces communicate with each other within the device via bus 630.

[0115] Embodiments of this application provide a computer-readable storage medium. The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the simulation data generation method described above.

[0116] It should be understood that the method steps in the embodiments of the present invention can be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable storage medium. The method can use standard programming techniques. Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with the computer system. However, if necessary, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. Furthermore, for this purpose, the program can run on a programmed application-specific integrated circuit (ASIC).

[0117] Furthermore, the procedures described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by the context. The procedures described herein (or variations and / or combinations thereof) may be executed under the control of one or more computer systems configured with executable instructions, and may be implemented by hardware or a combination thereof as code (e.g., executable instructions, one or more computer programs, or one or more applications) that commonly executes on one or more processors. The computer program comprises a plurality of instructions executable by one or more processors.

[0118] Furthermore, the method can be implemented in any suitable type of computing platform, including but not limited to personal computers, smartphones, mainframes, workstations, networked or distributed computing environments, standalone or integrated computer platforms, or in communication with charged particle tools or other imaging devices. Aspects of the invention can be implemented as machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and / or write storage medium, RAM, ROM, etc., such that it is readable by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the processes described herein. Furthermore, the machine-readable code, or portions thereof, can be transmitted via wired or wireless networks. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media comprises instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. When programmed according to the methods and techniques described in the invention, the invention also includes the computer itself.

[0119] A computer program can be applied to input data to perform the functions described herein, thereby transforming the input data to generate output data stored in non-volatile memory. The output information can also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including specific visual depictions of physical and tangible objects generated on the display.

[0120] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

[0121] The above is a detailed description of the preferred embodiments of this application, but this application is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for generating simulation data, characterized by, The method comprises: acquiring map data, population data and vehicle data; generating a three-dimensional map according to the map data; generating a vehicle planning path from the three-dimensional map according to the population data and the vehicle data; performing simulation vehicle driving according to the three-dimensional map, vehicle equipment information of the vehicle data and the vehicle planning path to obtain simulation data between the vehicle and the map; wherein the population data comprises population structured data and population unstructured data, the population structured data is population data related to map distribution, and the population unstructured data is population data unrelated to map distribution; the generation of the vehicle planning path from the three-dimensional map according to the population data and the vehicle data comprises: obtaining traffic flow distribution according to a working area of the three-dimensional map, a population quantity of the working area, a residential area of the three-dimensional map and a population quantity of the residential area in the population structured data; obtaining a personal activity path according to the population unstructured data; generating a vehicle planning path from the three-dimensional map according to the traffic flow distribution, the personal activity path and the vehicle data; the vehicle equipment information comprises communication equipment information; the simulation vehicle driving according to the three-dimensional map, the vehicle equipment information of the vehicle data and the vehicle planning path to obtain simulation data between the vehicle and the map comprises: obtaining vehicle driving track points in the simulation vehicle driving process according to the three-dimensional map and the vehicle planning path; obtaining a first distance between vehicles and a second distance between the vehicle and a base station according to base station position information of the map, the communication equipment information and the vehicle driving track points; performing communication simulation between the vehicle and the base station according to preset base station communication parameters, the first distance and the second distance to obtain communication simulation data in the simulation vehicle driving process; the vehicle equipment information comprises sensor equipment information; the simulation vehicle driving according to the three-dimensional map, the vehicle equipment information of the vehicle data and the vehicle planning path to obtain simulation data between the vehicle and the map comprises: obtaining vehicle driving track points in the simulation vehicle driving process according to the three-dimensional map and the vehicle planning path; obtaining a relative position mapping relationship between a sensor and the vehicle according to the sensor equipment information and the vehicle driving track points; obtaining projection data formed by projection of the three-dimensional map and the vehicle in a vehicle sensor visual angle in the simulation vehicle driving process according to the three-dimensional map, the vehicle driving track points and the relative position mapping relationship.

2. The method of claim 1, wherein, the working area and the residential area are obtained by division in the following manner: obtaining road intersection positions according to the map data; performing clustering with the road intersection positions as the center to divide areas to obtain the working area and the residential area.

3. The method of claim 1, wherein, the base station communication parameters comprise an antenna characteristic constant, an antenna far-field area distance and a path attenuation power factor; the communication simulation between the vehicle and the base station according to the preset base station communication parameters, the first distance and the second distance to obtain communication simulation data in the simulation vehicle driving process comprises: According to the preset base station communication parameter, the first distance and the second distance, a communication channel parameter is obtained, and the communication channel parameter comprises a channel fading factor; According to the communication channel parameter, communication simulation between the vehicle and the base station is performed to obtain communication simulation data in a simulation vehicle driving process.

4. The method of claim 1 or 3, wherein, The setting process of the sampling interval of the simulation data is as follows: A simulation step value of the simulation vehicle driving is determined as a time quantization factor of the sampling interval; According to the three-dimensional map and the vehicle planning path, a vehicle driving track point in the simulation vehicle driving process is obtained, and a space quantization factor of the sampling interval is determined according to the vehicle driving track point.

5. The method of claim 4, wherein, The simulation data generation method further comprises: According to the three-dimensional map, vehicle equipment information of the vehicle data and the vehicle planning path, the simulation vehicle driving is performed, a spatial change of vehicle positions at adjacent times is obtained through a Markov chain model, a state transition kernel function is obtained according to the spatial change of the vehicle positions at the adjacent times, and the state transition kernel function is used to describe a state transition process of a vehicle related event.

6. An electronic device, comprising: The electronic device comprises a memory, a processor, a program stored on the memory and executable on the processor, and a data bus for realizing connection communication between the processor and the memory, and the program is executed by the processor to realize the simulation data generation method in any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions for causing a computer to execute the simulation data generation method in any one of claims 1 to 5.

Images