Vehicle driving simulation method, system and device and storage medium

Abstract

The embodiment of the invention discloses a vehicle driving simulation method, system and device and a storage medium, and the method comprises the steps: a driving simulation module obtains the driving image information of a preset vehicle model in a preset simulation scene driving process, and transmits the driving image information to a vehicle control module; the vehicle control module generates a corresponding vehicle control instruction according to the driving image information and sends the vehicle control instruction to the parameter updating module; the parameter updating module generates corresponding driving control parameters according to the vehicle control instruction and sends the driving control parameters to the driving simulation module, so that the driving simulation module adjusts the driving state of a preset vehicle model according to the driving control parameters; wherein the driving simulation module, the vehicle control module and the parameter updating module are constructed based on the same language. According to the technical scheme, simulation modules can be constructed based on the same language, interface protocols between different simulation modules are unified, and data delay and data deviation are reduced.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of vehicle simulation, and in particular, to a vehicle driving simulation method, system, device, and storage medium. Background Art

[0002] There are bottlenecks in the development of current assisted driving systems: In the traditional development process, vehicle dynamics models (such as CarSim / Simulink) and control algorithms (such as Python / C++) are developed on heterogeneous platforms, resulting in complex interface protocols and data delays as high as 50 - 100 ms. Existing digital twin systems are difficult to synchronize the physical model and the virtual environment state. Especially in scenarios where obstacles change dynamically, the position deviation can reach more than 0.5 m. Traditional obstacle avoidance algorithms (such as the dynamic window method) take more than 200 ms for path replanning when sudden obstacles appear, and cannot meet the safety requirements of high-speed scenarios (>60 km / h). Summary of the Invention

[0003] The embodiments of the present invention provide a vehicle driving simulation method, system, device, and storage medium, which can unify the interface protocols between different simulation modules and reduce data latency and data deviation.

[0004] In a first aspect, the embodiments of the present invention provide a vehicle driving simulation method, which includes:

[0005] The driving simulation module acquires driving image information during the driving process of a preset vehicle model in a preset simulation scene, and sends the driving image information to the vehicle control module; the vehicle control module generates a corresponding vehicle control instruction according to the driving image information, and sends the vehicle control instruction to the parameter update module; the parameter update module generates corresponding driving control parameters according to the vehicle control instruction, and sends the driving control parameters to the driving simulation module, so that the driving simulation module adjusts the driving state of the preset vehicle model according to the driving control parameters; wherein, the driving simulation module, the vehicle control module, and the parameter update module are built based on the same language.

[0006] In a second aspect, the embodiments of the present invention provide a vehicle driving simulation system, which includes:

[0007] A driving simulation module, configured to obtain driving image information during the driving process of a preset vehicle model in a preset simulation scenario, and send the driving image information to the vehicle control module; a vehicle control module, configured to generate a corresponding vehicle control instruction according to the driving image information, and send the vehicle control instruction to the parameter update module; a parameter update module, configured to generate corresponding driving control parameters according to the vehicle control instruction, and send the driving control parameters to the driving simulation module, so that the driving simulation module adjusts the driving state of the preset vehicle model according to the driving control parameters; wherein, the driving simulation module, the vehicle control module and the parameter update module are built based on the same language.

[0008] In a third aspect, an embodiment of the present invention provides a computer device, which includes:

[0009] One or more processors;

[0010] A memory for storing one or more programs;

[0011] When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle driving simulation method described in any embodiment.

[0012] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the vehicle driving simulation method described in any embodiment.

[0013] The technical solution provided by the embodiment of the present invention is as follows: the driving simulation module obtains driving image information during the driving process of a preset vehicle model in a preset simulation scenario, and sends the driving image information to the vehicle control module; the vehicle control module generates a corresponding vehicle control instruction according to the driving image information, and sends the vehicle control instruction to the parameter update module; the parameter update module generates corresponding driving control parameters according to the vehicle control instruction, and sends the driving control parameters to the driving simulation module, so that the driving simulation module adjusts the driving state of the preset vehicle model according to the driving control parameters; wherein, the driving simulation module, the vehicle control module and the parameter update module are built based on the same language. The technical solution of the embodiment of the present invention solves the problems in the existing vehicle simulation technology that the simulation system is developed based on heterogeneous platforms, which is prone to complex interface protocols, high data latency and large data deviation. It can build each module of the simulation system based on the same language, and then complete the vehicle simulation process based on the mutual cooperation between multiple modules, unify the interface protocols between different modules, and reduce data latency and data deviation. Description of the Drawings

[0014] Figure 1 It is a flowchart of a vehicle driving simulation method provided by an embodiment of the present invention;

[0015] Figure 2 It is another flowchart of a vehicle driving simulation method provided by an embodiment of the present invention;

[0016] Figure 3 It is a work flowchart of performing vehicle driving simulation provided by an embodiment of the present invention;

[0017] Figure 4 It is another work flowchart of performing vehicle driving simulation provided by an embodiment of the present invention;

[0018] Figure 5 It is a schematic structural diagram of a vehicle driving simulation system provided by an embodiment of the present invention;

[0019] Figure 6 It is a schematic structural diagram of a computer device provided by an embodiment of the present invention. Detailed implementation manners

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0021] Figure 1 It is a flowchart of a vehicle driving simulation method provided by an embodiment of the present invention. The embodiments of the present invention are applicable to scenarios of simulating vehicle driving. This method can be executed by a vehicle driving simulation system, and this system can be implemented in a software and / or hardware manner.

[0022] As Figure 1 shown, the vehicle driving simulation method includes the following steps:

[0023] S110. The driving simulation module obtains driving image information during the driving process of a preset vehicle model in a preset simulation scenario, and sends the driving image information to the vehicle control module.

[0024] Among them, the preset vehicle model can be a preset simulation model of the target vehicle. Specifically, the preset vehicle model can be a three-dimensional model obtained by reducing the target vehicle by a certain proportion. The technical solution of the embodiment of the present invention can automatically drive based on the preset vehicle model in the preset simulation scenario, and continuously adjust the driving state of the preset vehicle model based on the environmental information around the preset vehicle model to realize the vehicle driving simulation process. The preset simulation scenario can be a preset simulation scenario for vehicle driving. The driving image information can be the image information of the surrounding environment during the driving process of the preset vehicle model. Specifically, the driving image information can be obtained by the camera device on the preset vehicle model taking pictures of the surrounding environment.

[0025] S120. The vehicle control module generates a corresponding vehicle control instruction according to the driving image information and sends the vehicle control instruction to the parameter update module.

[0026] Among them, the vehicle control instruction can be an instruction for controlling the driving state of the preset vehicle model. Specifically, the vehicle control module can generate a vehicle control instruction corresponding to the preset adjustment condition when the driving image information meets the preset adjustment condition.

[0027] Optionally, the vehicle control module can input the driving image information into the target control decision model to obtain the vehicle control instruction; among them, the target control decision model includes a pre-trained neural network model.

[0028] Exemplarily, the vehicle control module is written based on the machine learning toolbox and the image processing toolbox, adopts a multi-modal sensor fusion architecture, and realizes high-precision environment modeling through the collaborative perception of the camera and the lidar. The camera completes the semantic segmentation and target detection of the RGB image based on the deep learning model (such as YOLOv7+), and outputs the lane lines, traffic signs and the 2D bounding boxes of obstacles in real time; the radar extracts the boundary features and motion features of the obstacles through point cloud clustering, senses the positions of the obstacles, and enables the vehicle to avoid the obstacles and drive smoothly.

[0029] S130. The parameter update module generates corresponding driving control parameters according to the vehicle control instruction and sends the driving control parameters to the driving simulation module, so that the driving simulation module adjusts the driving state of the preset vehicle model according to the driving control parameters.

[0030] Among them, the driving control parameters can be parameters for controlling the driving state of a preset vehicle model. Specifically, the driving control parameters can be dynamic parameters. Exemplarily, the driving control parameters can include: heading angle, roll angle, pitch angle, speed, acceleration, wheel deflection angle and other parameters. The parameter update module can establish a dynamic model corresponding to the preset vehicle model, and can determine the dynamic parameters corresponding to the vehicle control instruction based on the dynamic model, and then obtain the driving control parameters. Further, the driving simulation module adaptively adjusts the driving state of the preset vehicle model according to the driving control parameters.

[0031] Among them, the driving simulation module, the vehicle control module and the parameter update module can be built based on the same language. By building the modules in the vehicle simulation system with the same language, the four goals of virtual scene construction, intelligent perception, intelligent control, and controlled object model construction are achieved, avoiding algorithm control and data communication across platforms and software, unifying the interface protocols between different simulation modules, reducing data latency and data deviation, and effectively reducing development costs.

[0032] Exemplarily, the three modules can be built based on the Modelica language. The driving simulation module can be built based on the MWORKs.Syslab software; the vehicle control module can be built based on the MWORKs.sysplorer software; the parameter update module can be built based on the MWORKS.PostEngineer software. This system establishes a high-precision vehicle dynamics model in MWORKS.Sysplorer, develops an intelligent algorithm for reinforcement learning in MWORKS.Syslab, and uses MWORKS.PostEngineer to achieve real-time interactive verification in a three-dimensional virtual environment, finally forming a "modeling-control-verification" closed-loop framework. This solution is particularly suitable for real-time obstacle avoidance control of assisted driving in complex urban road scenarios, and is used to realize real-time obstacle avoidance decision-making and control of assisted driving vehicles in complex environments.

[0033] The technical solution provided by the embodiment of the present invention obtains the driving image information of a preset vehicle model during the driving process in a preset simulation scenario through a driving simulation module, and sends the driving image information to a vehicle control module; the vehicle control module generates a corresponding vehicle control instruction according to the driving image information, and sends the vehicle control instruction to a parameter update module; the parameter update module generates a corresponding driving control parameter according to the vehicle control instruction, and sends the driving control parameter to the driving simulation module, so that the driving simulation module adjusts the driving state of the preset vehicle model according to the driving control parameter; wherein, the driving simulation module, the vehicle control module and the parameter update module are built based on the same language. The technical solution of the embodiment of the present invention solves the problems in the existing vehicle simulation technology that the simulation system is developed based on heterogeneous platforms, which are prone to complex interface protocols, high data latency and large data deviation. Each module of the simulation system can be built based on the same language, and then the vehicle simulation process can be completed based on the mutual cooperation between multiple modules, unifying the interface protocols between different modules, and reducing data latency and data deviation.

[0034] Figure 2 It is a flowchart of another vehicle driving simulation method provided by the embodiment of the present invention. The embodiment of the present invention is applicable to scenarios of simulating vehicle driving. On the basis of the above embodiment, it further illustrates how to obtain the driving image information of a preset vehicle model during the driving process in a preset simulation scenario; how to generate a corresponding vehicle control instruction according to the driving image information; and how to adjust the driving state of the preset vehicle model according to the driving control parameter. The system can be implemented in a software and / or hardware manner and integrated in a computer device with application development functions.

[0035] As Figure 2 shown, the vehicle driving simulation method includes the following steps:

[0036] S210. The driving simulation module obtains road images of at least one angle of the preset vehicle model at every preset period, and determines the driving image information according to the road images.

[0037] Among them, the preset vehicle model can be a simulation model of the target vehicle. Specifically, the preset vehicle model can be a three-dimensional model obtained by reducing the target vehicle by a certain proportion. The technical solution of the embodiment of the present invention can automatically drive based on the preset vehicle model in the preset simulation scenario, and continuously adjust the driving state of the preset vehicle model based on the environmental information around the preset vehicle model to realize the vehicle driving simulation process. The road image can be an image of the road around the preset vehicle model taken from a preset angle. Specifically, a plurality of cameras can be installed around the prediction vehicle model, and each camera takes pictures of the road from a preset angle at intervals of a preset period to obtain road images. The driving image information can be the image information of the surrounding environment during the driving process of the preset vehicle model. Specifically, for each preset period, a plurality of road images taken within the preset period can be combined to obtain the driving image information corresponding to the preset period, and then the driving state can be adjusted based on the driving image information corresponding to the preset period to realize the periodic adjustment of the driving state of the preset vehicle model.

[0038] S220. The vehicle control module determines vehicle position information and obstacle information according to the driving image information.

[0039] Among them, the vehicle position information is used to represent the relative position between the preset vehicle model and the lane line. Specifically, image processing such as gray scale, binaryzation, edge detection, masking, and Hough transform can be performed on the road image to extract the lane line features, and then the vehicle position information can be determined.

[0040] Among them, image gray scale processing is the process of converting a color image into a gray scale image. By simplifying the color information of each pixel into a single brightness value (usually between 0 and 255), the image presents different gray levels from black to white, reducing the amount of calculation. In this process, gray scale is mainly used for preprocessing the road surface image so that the lane line features can be extracted subsequently.

[0041] Image binaryzation processing is the process of converting a gray scale image into a binary image that only contains two pixel values of black and white (usually 0 and 255). By setting a threshold, the pixel points are divided into two categories: foreground and background. Through binaryzation, the image information of the route can be extracted more accurately.

[0042] Image edge detection is a key step in image processing to extract the image contour and significant structure. By identifying the regions where the pixel values change drastically (i.e., the edges), the image is converted from gray scale information to geometric features. The road line appears as a line segment with a certain width in the image, and edge detection can extract the edge information of the line segment and then obtain the boundary data of the route.

[0043] Image mask processing is a technique that selectively retains or masks specific regions of the original image by creating a binary image (mask). White pixels (255) in the mask represent the retained regions, and black pixels (0) represent the masked regions. Processing the mask can remove the environmental content in the captured image and only retain the image of the lane lines.

[0044] Image Hough Transform is a classic algorithm used to detect geometric shapes (such as lines, circles, ellipses, etc.) in an image. Its core idea is to map local features (such as edge points) in the image space to the parameter space and identify the global structure through a voting mechanism. After obtaining a relatively pure road line image, to know the coordinate positions of the road lines in the image, the coordinate points of the road lines can be extracted through the Hough Transform to confirm the specific coordinates of the road segments.

[0045] Furthermore, the obstacle information can be the attribute information of the obstacles around the preset vehicle model. Specifically, the obstacle information can include the size information of the obstacles themselves and the relative position information between the preset vehicle model and the obstacles. Exemplarily, obstacles on the road can be recognized based on the road image. Once an obstacle is recognized, the on-vehicle radar on the preset vehicle model can be used to sense the position of the obstacle, and then by performing SVD feature extraction, DBSCAN algorithm clustering, and RANSAC algorithm for noise point filtering on the three-dimensional point cloud data, the point cloud data features of the obstacles can be extracted, and thus the obstacle information can be determined.

[0046] Among them, SVD (Singular Value Decomposition) is a linear algebra method widely used for data dimensionality reduction, feature extraction, and noise suppression. In image processing, SVD extracts the core features of an image by decomposing the image matrix into a low-rank approximation. Noise in the image can be filtered through SVD, and the effective information data can be purified.

[0047] DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a density-based clustering algorithm that does not require specifying the number of clusters in advance and can discover clusters of any shape and identify noise points. Through the DBSCAN algorithm, the obstacle point cloud data in the radar point cloud can be extracted and classified.

[0048] RANSAC (RANdom SAmple Consensus) is an iterative algorithm for estimating the parameters of a mathematical model from observation data containing noise. Its core idea is to fit a model by randomly sampling a subset of the data (assumed to be inliers), and to use the model to verify the consistency of other data points, thereby gradually screening out the optimal model. The RANSAC algorithm can further process the point cloud data extracted by the DBSCAN algorithm to remove outliers and obtain more accurate obstacle point cloud data.

[0049] S230. Generate a corresponding vehicle control instruction according to the vehicle position information and the obstacle information.

[0050] Among them, the vehicle control instruction can be an instruction for controlling the driving state of a preset vehicle model. Specifically, the vehicle control module can analyze the vehicle position information and the obstacle information, and generate a vehicle control instruction corresponding to the preset adjustment condition when the preset adjustment condition is met.

[0051] Exemplarily, when it is determined according to the obstacle information that there is an obstacle in front of the preset vehicle model, a corresponding obstacle avoidance instruction can be generated according to the obstacle information and the current vehicle driving state of the preset vehicle model; when it is determined according to the vehicle position information that the offset distance between the preset vehicle model and the lane line is greater than the preset offset threshold, a corresponding lane centering control instruction can be generated.

[0052] Among them, the current vehicle driving state can be the current driving state of the preset vehicle model. The obstacle avoidance instruction can be an instruction for controlling the preset vehicle model to avoid obstacles. Specifically, the vehicle control module can combine the obstacle information and the current vehicle driving state of the preset vehicle model to determine the corresponding path for avoiding obstacles, and generate a corresponding obstacle avoidance instruction based on the avoidance path.

[0053] Furthermore, the preset offset threshold can be a reference threshold for determining the degree of deviation of the preset vehicle model from the lane line. The lane centering control instruction can be an instruction for controlling the preset vehicle model to maintain driving at the center of the lane. When the offset distance between the preset vehicle model and the lane line is greater than the preset offset threshold, it indicates that the degree of deviation between the two is too large, and at this time, a corresponding lane centering control instruction can be generated to enable the preset vehicle model to perform the corresponding lane centering action.

[0054] Optionally, an obstacle avoidance instruction is generated according to the obstacle information and the current vehicle driving state of the preset vehicle model, including: the vehicle control module determines the state information of the obstacle according to the obstacle information, and the relative position information between the preset vehicle model and the obstacle; an obstacle avoidance plan is determined according to the state information, the current vehicle driving state and the relative position information, and an obstacle avoidance instruction corresponding to the obstacle avoidance plan is generated.

[0055] Among them, the state information includes the size information and the motion state information of the obstacle. The relative position information includes the relative azimuth angle and the relative distance between the preset vehicle model and the obstacle. The obstacle avoidance plan can be an action plan for controlling the preset vehicle model to avoid obstacles. Specifically, the relative motion state between the two (i.e., the preset vehicle model and the obstacle) can be determined according to the motion state information of the obstacle and the current vehicle driving state, and then the obstacle avoidance plan can be determined based on the relative motion state, the relative position information and the size information of the obstacle.

[0056] S240. The parameter update module generates corresponding driving control parameters according to the vehicle control instruction, and sends the driving control parameters to the driving simulation module.

[0057] Among them, the driving control parameters can be parameters for controlling the driving state of the preset vehicle model. Exemplarily, the driving control parameters can include: heading angle, roll angle, pitch angle, speed, acceleration, wheel deflection angle and other parameters.

[0058] S250. The driving simulation module determines the driving state parameters corresponding to the driving control parameters based on the preset variable mapping table, and adjusts the driving state of the preset vehicle model based on the driving state parameters.

[0059] Among them, the driving state parameters can be parameters for representing the driving state of the preset vehicle model. Exemplarily, the driving state parameters can include parameters such as the vehicle body rigid body, wheel rigid body, instrument data, and steering wheel angle in the preset vehicle model. Among them, the conversion from the driving control parameters to the driving state parameters can be understood as converting the dynamic parameters into the state parameters of the preset vehicle model in the simulation environment. Further, the preset variable mapping table is used to represent the mapping relationship between the driving control parameters and the driving state parameters. The driving state parameters corresponding to the driving control parameters can be determined based on the mapping relationship in the preset variable mapping table, and the driving state of the preset vehicle model can be adjusted based on the driving state parameters.

[0060] Exemplarily, Figure 3 is a flowchart of a method for vehicle driving simulation provided by an embodiment of the present invention. As Figure 3 shown, the workflow of vehicle driving simulation includes the following steps:

[0061] 1. Build a vehicle dynamics module, establish a vehicle model in MWORKS.Sysplorer and connect the corresponding sensor interfaces.

[0062] 2. Write an environmental perception algorithm in MWORKS.Syslab, sense environmental information through cameras and radars, extract features, and summarize the feature information and transfer it to the intelligent control module.

[0063] 3. Write an embodied intelligent control algorithm in MWORKS.Syslab. Based on the two-way integration of MWORKS.Sysplorer and MWORKS.Syslab, obtain vehicle state data from MWORKS.Sysplorer and transfer it to the intelligent algorithm. The intelligent algorithm outputs control signals to the controlled components of the vehicle model.

[0064] 4. Build a scenario and a vehicle model in the virtual environment of MWORKS.PostEngineer.

[0065] 5. Build a communication module, transfer data such as the vehicle model speed in MWORKS.Sysplorer to MWORKS.PostEngineer, and display the driving state of the vehicle in the virtual environment of MWORKS.PostEngineer.

[0066] Exemplarily, for a better understanding of the technical solution provided by the present invention, the following is an introduction to specific embodiments: Figure 4 It is another workflow diagram for vehicle driving simulation provided by the embodiments of the present invention. As Figure 4 shown, the workflow for vehicle driving simulation includes the following steps:

[0067] (1) The vehicle will drive in the virtual scenario of MWORKS.PostEngineer. During the driving process of the vehicle, if no obstacle is detected in front of the vehicle, then the vehicle will activate the lane keeping function and the vehicle will drive forward at a constant speed. The lane keeping function mainly uses the perception function of the on-vehicle camera, and the image information obtained in MWORKS.PostEngineer will be transferred to MWORKS.Syslab for step 1.1 to process the image information.

[0068] (1.1) The on-vehicle camera senses and captures the road image in front of the vehicle to sense the vehicle position. By performing gray-scale, binarization, edge detection, masking, and Hough transform on the road image, the lane line features are extracted to determine the position of the vehicle on the road. If the vehicle position is offset, the driving direction of the vehicle is adjusted so that the vehicle always drives in the center of the lane.

[0069] (2) In the scenario of MWORKS.PostEngineer, if an obstacle is detected during vehicle driving, the perception function of the on-vehicle radar will be used to identify the obstacle and avoid it. The lidar information obtained in MWORKS.PostEngineer will be transmitted to MWORKS.Syslab for the steps in 2.1 to process the radar point cloud information.

[0070] (2.1) First, the obstacle data information detected by the radar needs to be processed. After the lidar perceives the position of the obstacle, by performing SVD feature extraction on the three-dimensional point cloud data, DBSCAN algorithm clustering, and RANSAC algorithm for noise point filtering, the point cloud data features of the obstacle are extracted.

[0071] (3) After the obstacle is identified and the position information of the obstacle is perceived, the perception module will transmit the information to the embodied intelligent control module. The embodied intelligent control module has the ability of self-decision-making and can adaptively avoid obstacles during driving in different scenarios. After the obstacle avoidance is completed, it can return to the original vehicle lane and continue driving. The embodied intelligent control module is built in MWORKS.Syslab based on the reinforcement learning toolbox and the machine learning toolbox. After encapsulating the embodied intelligent algorithm into a module, through the bidirectional fusion function of MWORKS.Syslab and MWORKS.Sysplorer, this module can be directly applied in MWORKS.Sysplorer to realize the application of the vehicle controlled object model.

[0072] (4) The embodied intelligent control module will output the throttle pedal opening signal of the vehicle and the steering wheel deflection amount to the vehicle model in MWORKS.Sysplorer. After receiving the input signal, the vehicle model will calculate the vehicle speed and yaw angle to realize the change of the vehicle state.

[0073] (5) The vehicle speed and yaw angle of MWORKS.Sysplorer are transmitted to MWORKS.PostEngineer through the communication interface, and in the virtual environment, the change of the vehicle state can be more intuitively seen.

[0074] In MWORKS.PostEngineer, radar point cloud data and camera captured image data are acquired. These data are classified as hardware data and transmitted to MWORKS.Syslab. The machine learning toolbox, basic mathematical tool types, and image processing toolbox of MWORKS.Syslab are applied to process these hardware data information to achieve intelligent perception. Intelligent perception extracts effective information in the environment, such as obstacle positions and road position information, which are key information. Embodied intelligent control is implemented based on the reinforcement learning toolbox and machine learning toolbox of MWORKS.Syslab. It receives the key information in the environment and the vehicle state data in MWORKS.Sysplorer. After comprehensive processing, it transmits the relevant control signals to MWORKS.Sysplorer to achieve embodied intelligent control. After receiving the control signals, MWORKS.Sysplorer calculates the updated state of the vehicle. These updated states are transmitted to MWORKS.PostEngineer through the communication interface, where the change in the vehicle state can be more intuitively seen in MWORKS.PostEngineer, realizing the closed-loop of the solution.

[0075] In the technical solution provided by the embodiment of the present invention, the driving simulation module acquires road images at at least one angle of a preset vehicle model every preset period, and determines driving image information according to the road images; the vehicle control module determines vehicle position information and obstacle information according to the driving image information; generates corresponding vehicle control instructions according to the vehicle position information and obstacle information; the parameter update module generates corresponding driving control parameters according to the vehicle control instructions and sends the driving control parameters to the driving simulation module; the driving simulation module determines the driving state parameters corresponding to the driving control parameters based on a preset variable mapping table, and adjusts the driving state of the preset vehicle model based on the driving state parameters. The technical solution of the embodiment of the present invention solves the problems in the existing vehicle simulation technology that the simulation system is developed based on heterogeneous platforms, which is prone to complex interface protocols, high data latency, and large data deviation. Each module of the simulation system can be constructed based on the same language, and then the vehicle simulation process is completed based on the mutual cooperation between multiple modules, unifying the interface protocols between different modules, and reducing data latency and data deviation.

[0076] Figure 5 It is a schematic structural diagram of a vehicle driving simulation system provided by an embodiment of the present invention. The embodiment of the present invention is applicable to scenarios where vehicle driving simulation is carried out. The system can be implemented in software and / or hardware and integrated in a computer device with application development functions.

[0077] Such as Figure 5As shown in the figure, the vehicle driving simulation system includes: a driving simulation module 310, a vehicle control module 320, and a parameter update module 330.

[0078] Among them, the driving simulation module 310 is used to obtain the driving image information of a preset vehicle model during driving in a preset simulation scenario, and send the driving image information to the vehicle control module; the vehicle control module 320 is used to generate a corresponding vehicle control instruction according to the driving image information, and send the vehicle control instruction to the parameter update module; the parameter update module 330 is used to generate a corresponding driving control parameter according to the vehicle control instruction, and send the driving control parameter to the driving simulation module, so that the driving simulation module adjusts the driving state of the preset vehicle model according to the driving control parameter; among them, the driving simulation module, the vehicle control module, and the parameter update module are built based on the same language.

[0079] The technical solution provided by the embodiment of the present invention is as follows: the driving simulation module obtains the driving image information of a preset vehicle model during driving in a preset simulation scenario, and sends the driving image information to the vehicle control module; the vehicle control module generates a corresponding vehicle control instruction according to the driving image information, and sends the vehicle control instruction to the parameter update module; the parameter update module generates a corresponding driving control parameter according to the vehicle control instruction, and sends the driving control parameter to the driving simulation module, so that the driving simulation module adjusts the driving state of the preset vehicle model according to the driving control parameter; among them, the driving simulation module, the vehicle control module, and the parameter update module are built based on the same language. The technical solution of the embodiment of the present invention solves the problems in the existing vehicle simulation technology that the simulation system is developed based on heterogeneous platforms, which is prone to complex interface protocols, high data latency, and large data deviation. It is possible to build each module of the simulation system based on the same language, and then complete the vehicle simulation process based on the mutual cooperation between multiple modules, unify the interface protocols between different modules, and reduce data latency and data deviation.

[0080] In an optional implementation manner, the driving simulation module 310 is specifically used to: obtain road images of at least one angle of the preset vehicle model at intervals of a preset period, and determine the driving image information according to the road images.

[0081] In an optional implementation manner, the vehicle control module 320 is specifically used to: determine vehicle position information and obstacle information according to the driving image information; generate a corresponding vehicle control instruction according to the vehicle position information and the obstacle information; where the vehicle position information is used to represent the relative position between the preset vehicle model and the lane line.

[0082] In an alternative embodiment, the vehicle control module 320 includes: an information analysis unit configured to: when it is determined, based on the obstacle information, that there is an obstacle in front of the preset vehicle model, generate a corresponding obstacle avoidance instruction according to the obstacle information and the current vehicle driving state of the preset vehicle model; and when it is determined, based on the vehicle position information, that the offset distance between the preset vehicle model and the lane line is greater than a preset offset threshold, generate a corresponding lane centering control instruction.

[0083] In an alternative embodiment, the information analysis unit includes: an avoidance instruction generation sub-unit configured to: determine the state information of the obstacle according to the obstacle information, and the relative position information between the preset vehicle model and the obstacle; wherein the state information includes the body size information and the motion state information of the obstacle; the relative position information includes the relative azimuth angle and the relative distance between the preset vehicle model and the obstacle; determine an obstacle avoidance plan according to the state information, the current vehicle driving state and the relative position information, and generate an obstacle avoidance instruction corresponding to the obstacle avoidance plan.

[0084] In an alternative embodiment, the driving simulation module 330 is specifically configured to: determine the driving state parameters corresponding to the driving control parameters based on a preset variable mapping table, and adjust the driving state of the preset vehicle model based on the driving state parameters; wherein the preset variable mapping table is used to represent the mapping relationship between the driving control parameters and the driving state parameters.

[0085] In an alternative embodiment, the vehicle control module 320 may also be configured to: input the driving image information into a target control decision model to obtain the vehicle control instruction; wherein the target control decision model includes a pre-trained neural network model.

[0086] The vehicle driving simulation system provided by the embodiments of the present invention can execute the vehicle driving simulation method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0087] Figure 6 It is a schematic structural diagram of a computer device provided by an embodiment of the present invention. Figure 6 It shows a block diagram of an exemplary computer device 12 suitable for implementing the embodiments of the present invention. Figure 6 The shown computer device 12 is only an example, and should not impose any limitation on the functions and usage scope of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capabilities, and can be configured in a vehicle driving simulation device.

[0088] Such as Figure 6As shown, computer device 12 is presented in the form of a general-purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects different system components (including system memory 28 and processing unit 16).

[0089] Bus 18 can be one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus structures. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0090] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0091] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 can be used for reading and writing on non-removable, non-volatile magnetic media ( Figure 6 not shown, commonly referred to as a "hard disk drive"). Although Figure 6 not shown in the figure, a disk drive for reading and writing on removable non-volatile disks (such as a "floppy disk"), and an optical disk drive for reading and writing on removable non-volatile optical disks (such as a CD-ROM, DVD-ROM, or other optical media) can be provided. In these cases, each drive can be connected to bus 18 through one or more data media interfaces. System memory 28 may include at least one program product having a set (such as at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0092] A program / utility 40 having a set (at least one) of program modules 42 can be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. Program modules 42 generally perform the functions and / or methods described in the embodiments of the present invention.

[0093] The computer device 12 can also communicate with one or more external devices 14 (such as a keyboard, a pointing device, a display 24, etc.), and can also communicate with one or more devices that enable a user to interact with the computer device 12, and / or communicate with any device that enables the computer device 12 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 22. Moreover, the computer device 12 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 20. As Figure 6 shown, the network adapter 20 communicates with other modules of the computer device 12 through the bus 18. It should be understood that although Figure 6 not shown in the figure, other hardware and / or software modules can be used in combination with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0094] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing the vehicle driving simulation method provided by the embodiments of the present invention. The method includes:

[0095] The driving simulation module obtains the driving image information during the driving process of a preset vehicle model in a preset simulation scenario, and sends the driving image information to the vehicle control module; the vehicle control module generates a corresponding vehicle control instruction according to the driving image information, and sends the vehicle control instruction to the parameter update module; the parameter update module generates a corresponding driving control parameter according to the vehicle control instruction, and sends the driving control parameter to the driving simulation module, so that the driving simulation module adjusts the driving state of the preset vehicle model according to the driving control parameter; wherein, the driving simulation module, the vehicle control module, and the parameter update module are constructed based on the same language.

[0096] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the vehicle driving simulation method provided by any embodiment of the present invention, including:

[0097] The driving simulation module obtains driving image information during the driving process of a preset vehicle model in a preset simulation scenario, and sends the driving image information to the vehicle control module; the vehicle control module generates corresponding vehicle control instructions according to the driving image information, and sends the vehicle control instructions to the parameter update module; the parameter update module generates corresponding driving control parameters according to the vehicle control instructions, and sends the driving control parameters to the driving simulation module, so that the driving simulation module adjusts the driving state of the preset vehicle model according to the driving control parameters; wherein, the driving simulation module, the vehicle control module, and the parameter update module are constructed based on the same language.

[0098] The computer storage medium of the embodiments of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0099] The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0100] The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0101] Computer program code for performing the operations of the present invention may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as C, Java, Smalltalk, C++, C#, and Python, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0102] Those of ordinary skill in the art should understand that the above-mentioned modules or steps of the present invention can be implemented with a general-purpose computing system. They can be concentrated on a single computing system or distributed over a network composed of multiple computing systems. Optionally, they can be implemented with program code executable by a computer system, so that they can be stored in a storage system and executed by the computing system, or they can be made into individual integrated circuit modules respectively, or multiple modules or steps among them can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0103] Note that the above is only the preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will understand that the present invention is not limited to the specific embodiments here. Various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, more other equivalent embodiments can be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A vehicle driving simulation method, applied to a vehicle driving simulation system, wherein, The vehicle driving simulation system includes: a driving simulation module, a vehicle control module, and a parameter update module, and is characterized in that the method includes: The driving simulation module acquires driving image information during the driving process of a preset vehicle model in a preset simulation scenario, and sends the driving image information to the vehicle control module; The vehicle control module generates a corresponding vehicle control instruction according to the driving image information, and sends the vehicle control instruction to the parameter update module; The parameter update module generates corresponding driving control parameters according to the vehicle control instruction, and sends the driving control parameters to the driving simulation module, so that the driving simulation module adjusts the driving state of the preset vehicle model according to the driving control parameters; Wherein, the driving simulation module, the vehicle control module, and the parameter update module are built based on the same language.

2. The method according to claim 1, characterized in that The driving simulation module acquiring driving image information during the driving process of a preset vehicle model in a preset simulation scenario includes: The driving simulation module acquires road images of at least one angle of the preset vehicle model at every preset period, and determines the driving image information according to the road images.

3. The method according to claim 1, wherein The vehicle control module generating a corresponding vehicle control instruction according to the driving image information includes: The vehicle control module determines vehicle position information and obstacle information according to the driving image information; Generates a corresponding vehicle control instruction according to the vehicle position information and the obstacle information; Wherein, the vehicle position information is used to represent the relative position between the preset vehicle model and the lane line.

4. The method according to claim 3, characterized in that The vehicle control module generating a corresponding vehicle control instruction according to the vehicle position information and the obstacle information includes: In the case where it is determined according to the obstacle information that there is an obstacle in front of the preset vehicle model, an obstacle avoidance instruction corresponding to the obstacle information and the current vehicle driving state of the preset vehicle model is generated; In the case where it is determined according to the vehicle position information that the offset distance between the preset vehicle model and the lane line is greater than a preset offset threshold, a corresponding lane centering control instruction is generated.

5. The method according to claim 4, wherein The generating an obstacle avoidance instruction corresponding to the obstacle information and the current vehicle driving state of the preset vehicle model includes: The vehicle control module determines the state information of the obstacle and the relative position information between the preset vehicle model and the obstacle according to the obstacle information; wherein, the state information includes the body size information and the motion state information of the obstacle; the relative position information includes the relative azimuth angle and the relative distance between the preset vehicle model and the obstacle; Determines an obstacle avoidance plan according to the state information, the current vehicle driving state, and the relative position information, and generates an obstacle avoidance instruction corresponding to the obstacle avoidance plan.

6. The method according to claim 1, wherein The driving simulation module adjusting the driving state of the preset vehicle model according to the driving control parameters includes: The driving simulation module determines the driving state parameters corresponding to the driving control parameters based on a preset variable mapping table, and adjusts the driving state of the preset vehicle model based on the driving state parameters; Among them, the preset variable mapping table is used to represent the mapping relationship between driving control parameters and driving state parameters.

7. The method according to claim 1, wherein The vehicle control module generates corresponding vehicle control instructions according to the driving image information, including: The vehicle control module inputs the driving image information into the target control decision-making model to obtain the vehicle control instructions; among them, the target control decision-making model includes a pre-trained neural network model.

8. A vehicle driving simulation system, characterized in that, The system includes: A driving simulation module, configured to obtain driving image information during the driving process of a preset vehicle model in a preset simulation scenario, and send the driving image information to the vehicle control module; A vehicle control module, configured to generate corresponding vehicle control instructions according to the driving image information, and send the vehicle control instructions to the parameter update module; A parameter update module, configured to generate corresponding driving control parameters according to the vehicle control instructions, and send the driving control parameters to the driving simulation module, so that the driving simulation module adjusts the driving state of the preset vehicle model according to the driving control parameters; Among them, the driving simulation module, the vehicle control module, and the parameter update module are built based on the same language.

9. A computer device, characterized in that, The computer device includes: One or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle driving simulation method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the vehicle driving simulation method according to any one of claims 1-7.

Images