Automatic driving simulation method and system

Abstract

The present invention discloses an autonomous driving simulation method and system. The method comprises: rendering virtual environment data and a vehicle dynamics model, wherein the virtual environment data includes a pre-constructed virtual simulation road, and the vehicle dynamics model is rendered on the virtual simulation road; performing autonomous driving simulation based on the virtual simulation road, and during the simulation process: obtaining first driving data of a vehicle simulation device and second driving data of a vehicle dynamics model, wherein the first driving data and the second driving data form driving data at the current moment; determining predicted driving data of the vehicle on the virtual simulation road based on the driving data at the current moment; determining vehicle control information based on the predicted driving data; controlling the vehicle simulation device to perform autonomous driving simulation based on the vehicle control information; and / or controlling the vehicle dynamics model to drive on the virtual simulation road based on the vehicle control information. This solution implements joint simulation testing, improves the accuracy of autonomous driving simulation testing, and reduces testing costs.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an autonomous driving simulation method and system. Background Art

[0002] Autonomous driving technology refers to a technology that uses computer systems and sensor equipment to achieve automatic vehicle navigation, automatic control and intelligent decision-making. Its emergence and development has brought revolutionary changes to the field of transportation.

[0003] The field of autonomous driving has very high safety requirements, but the use of real vehicle testing will lead to excessively high testing costs. The use of building a vehicle autonomous driving model for testing will lead to inaccurate testing and low efficiency. Summary of the Invention

[0004] The present invention provides an autonomous driving simulation method and system to solve the problems of high test costs, inaccurate autonomous driving tests and low efficiency in the prior art.

[0005] According to one aspect of the present invention, there is provided an autonomous driving simulation method, comprising:

[0006] Rendering virtual environment data and a vehicle dynamics model, wherein the virtual environment data includes a pre-built virtual simulation road, and the vehicle dynamics model is rendered on the virtual simulation road;

[0007] An autonomous driving simulation is performed based on a virtual simulation road. During the simulation process: first driving data of a vehicle simulation device and second driving data of a vehicle dynamics model are obtained, wherein the first driving data and the second driving data form driving data at a current moment; predicted driving data of the vehicle on the virtual simulation road is determined based on the driving data at the current moment; vehicle control information is determined based on the predicted driving data; the vehicle simulation device is controlled to perform autonomous driving simulation based on the vehicle control information; and / or the vehicle dynamics model is controlled to drive on the virtual simulation road based on the vehicle control information.

[0008] Optionally, the method for creating a virtual simulation road includes at least one of the following:

[0009] Acquire a simulation requirement configuration file, the simulation requirement configuration file including at least one road configuration information; construct a simulated road segment based on the road configuration information, and form a virtual simulated road based on the at least one simulated road segment;

[0010] In the simulation interaction page, a road construction operation is detected, wherein the road construction operation includes road configuration information; a simulated road segment is constructed based on the road configuration information, and a virtual simulated road is formed based on at least one simulated road segment;

[0011] In the simulation interaction page, a road construction operation is detected, which includes road configuration information; a target simulation road segment is matched in the constructed simulation road segment based on the road configuration information, and a virtual simulation road is formed based on the target simulation road segment;

[0012] In the simulation interaction page, in response to a road calling operation, at least one simulated road segment is called from a pre-created road library, and a virtual simulated road is formed based on the at least one simulated road segment.

[0013] Optionally, the method further includes:

[0014] A simulation path is formed based on the starting point and the end point in the virtual simulation road, and reference points and index information of the reference points are sequentially set on the simulation path;

[0015] Correspondingly, the current driving data includes the current vehicle position information, the current vehicle speed information, the current vehicle yaw angle data, the current vehicle steering wheel angle data, the index information of the nearest reference point of the vehicle position at the previous moment, and the position set of reference points in the simulation path;

[0016] The predicted driving data includes the reference path information corresponding to the predicted time step, the vehicle speed information at the next moment, the vehicle yaw angle data at the next moment, the vehicle steering wheel angle data at the next moment and the index information of the nearest reference point at the current moment.

[0017] Optionally, during the simulation, the vehicle speed information is preset average speed data, the vehicle yaw angle data includes a preset yaw angle corresponding to each reference point, and the vehicle steering wheel angle data includes preset steering wheel angle data corresponding to each reference point.

[0018] The method for determining the reference path information corresponding to the prediction time step includes: determining the reference index information corresponding to the preset time step after the index information of the nearest reference point located at the vehicle position at the previous moment, and using the reference point position information corresponding to the reference index information as the reference path information corresponding to the prediction time step.

[0019] Optionally, determining vehicle control information based on the predicted driving data includes:

[0020] The predicted driving data is simulated and processed based on the MPC algorithm to obtain vehicle control information, where the vehicle control information includes the vehicle front wheel deflection angle at the next moment, the vehicle position information at the next moment, the vehicle speed at the next moment, the vehicle yaw angle at the next moment, the steering wheel angle at the next moment, and the vehicle acceleration at the next moment.

[0021] Optionally, the method further includes:

[0022] The simulation sensors configured on the vehicle dynamics model are used to obtain environmental data of the vehicle dynamics model during its driving on the virtual simulation road, and abnormal driving detection of the vehicle dynamics model is performed based on the environmental data.

[0023] Optionally, the method further includes:

[0024] Acquire driving data of the vehicle dynamics model and driving data of the vehicle simulation device during the simulation process;

[0025] When there is a difference between the driving data of the vehicle dynamics model and the driving data of the vehicle simulation device, difference comparison data is generated based on the driving data of the vehicle dynamics model and the driving data of the vehicle simulation device, and the difference comparison data is used to optimize the vehicle dynamics model.

[0026] According to another aspect of the present invention, an autonomous driving simulation system is provided, comprising: a simulation test system, a traffic scenario server, and a vehicle simulation device; wherein the simulation test system comprises a road construction module, an autonomous driving processing module, and a vehicle dynamics model;

[0027] The traffic scene server pre-stores virtual environment data;

[0028] A road construction module, used for constructing a virtual simulation road in virtual environment data;

[0029] an autonomous driving processing module, configured to render virtual environment data and a vehicle dynamics model on a virtual simulated road, and perform autonomous driving simulation based on the virtual simulated road. During the simulation, the module: obtains first driving data from a vehicle simulation device and second driving data from the vehicle dynamics model, wherein the first driving data and the second driving data form current driving data; determines predicted driving data of the vehicle on the virtual simulated road based on the current driving data; determines vehicle control information based on the predicted driving data; transmits the vehicle control information to the vehicle simulation device; and / or controls the vehicle dynamics model to drive on the virtual simulated road based on the vehicle control information.

[0030] The vehicle simulation device is equipped with a driving response component for executing vehicle control information to perform automatic driving simulation.

[0031] Optionally, the simulation test system further includes a sensor module, which is used to obtain environmental data of the vehicle dynamics model during driving on the virtual simulation road, and send the environmental data to the automatic driving processing module;

[0032] The autonomous driving processing module performs abnormal driving detection on the vehicle dynamics model based on environmental data.

[0033] Optionally, the vehicle simulation device is configured with at least pitch, yaw and lateral freedom components.

[0034] According to another aspect of the present invention, a simulation test system is provided, the simulation test system comprising:

[0035] at least one processor; and

[0036] a memory communicatively connected to at least one processor; wherein,

[0037] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the automatic driving simulation method of any embodiment of the present invention.

[0038] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions, and the computer instructions are used to enable a processor to implement the automatic driving simulation method of any embodiment of the present invention when executed.

[0039] The technical solution of an embodiment of the present invention is to render virtual environment data and a vehicle dynamics model, wherein the virtual environment data includes a pre-constructed virtual simulation road, and the vehicle dynamics model is rendered on the virtual simulation road; and autonomous driving simulation is performed based on the virtual simulation road. During the simulation process: first driving data of a vehicle simulation device and second driving data of a vehicle dynamics model are obtained, wherein the first driving data and the second driving data form driving data at the current moment; predicted driving data of the vehicle on the virtual simulation road is determined based on the driving data at the current moment; vehicle control information is determined based on the predicted driving data; the vehicle simulation device is controlled based on the vehicle control information to perform autonomous driving simulation, and / or the vehicle dynamics model is controlled to drive on the virtual simulation road based on the vehicle control information. This realizes the construction of a test environment of a virtual simulation road, the combination of the vehicle simulation device and the autonomous driving simulation, and the realization of joint simulation testing, thereby improving the accuracy of autonomous driving simulation testing, improving development and testing efficiency, and reducing testing costs.

[0040] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 This is a flowchart of an autonomous driving simulation method provided by an embodiment of the present invention;

[0043] Figure 2 This is a schematic diagram of a test structure of a driving simulation device applicable to an embodiment of the present invention;

[0044] Figure 3 This is a schematic diagram of the structure of an autonomous driving simulation system provided by an embodiment of the present invention;

[0045] Figure 4 A schematic structural diagram of a simulation test system for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0047] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0048] Figure 1 This is a flow chart of an automatic driving simulation method provided by an embodiment of the present invention. This embodiment is applicable to the case of performing automatic driving simulation. The method can be executed by an automatic driving simulation system. The automatic driving simulation system can be implemented in the form of hardware and / or software. The automatic driving simulation system can be configured in electronic devices such as vehicle controllers, computers, and simulation devices. Figure 1 As shown, the method includes:

[0049] S110 , rendering virtual environment data and a vehicle dynamics model, where the virtual environment data includes a pre-built virtual simulation road, and the vehicle dynamics model is rendered on the virtual simulation road.

[0050] Among them, the virtual environment data can be specifically understood as relevant data that describes environmental characteristics, especially data that describes the characteristics of the vehicle's driving environment. The virtual environment data may include pre-built virtual simulation roads. The pre-built virtual simulation roads can be constructed by a pre-set creation method. The vehicle dynamics model is used to simulate the response of the vehicle itself to the control of the autonomous driving algorithm, especially the response to acceleration, braking and steering. The vehicle dynamics module generally refers to the real target vehicle and is composed of a driver model, an environmental model, a body model, a chassis model, a suspension model, a tire model, a steering model, a power model, a braking model and a control model. In this embodiment, the core of the autonomous driving algorithm module is a model predictive control (Model Predictive Control) module built based on the MWORKS.Sysplorer software platform and the Modelica language.

[0051] Specifically, the virtual environment data and vehicle dynamics model are rendered using rendering technology to obtain a corresponding visualized virtual simulated road and visualized vehicle model. For example, a high-performance computing engine can be used to render the virtual environment data and vehicle dynamics model, generating corresponding 3D images in real time, supporting 3D linkage and a rendering speed of no less than 60 frames per second.

[0052] In some embodiments, the method for creating a virtual simulated road can be by obtaining a simulation requirement configuration file, which includes at least one road configuration information; constructing a simulated road segment based on the road configuration information, and forming a virtual simulated road based on the at least one simulated road segment.

[0053] Specifically, the simulation requirements file can be understood as a file that records the relevant parameters required for constructing a virtual simulated road. The simulation requirements configuration file includes at least one piece of road configuration information. The road configuration information includes the road type and road type parameters. For example, if the road type is a straight road, the road type parameter may be the length; if the road type is an uphill road, the road type parameter may be the slope; if the road type is a bumpy road, the road type parameter may be the bump coefficient. The road type may also include a slippery road section, a curve, etc. The specific road configuration information is set according to the actual road simulation requirements.

[0054] Specifically, the corresponding simulation requirement configuration file is determined according to the actual simulation requirements, and can be stored in a server or a local storage device. When performing the corresponding simulation requirements, the corresponding simulation requirement configuration file is read from the server or the local storage device, or the simulation requirement configuration file is imported from an external device, and at least one road configuration information in the simulation requirement configuration file is further read. The corresponding simulation road segment is constructed according to the read road configuration information. If there is only one simulation road segment, it is directly used as a virtual simulation road segment. If multiple simulation road segments are constructed, the obtained multiple simulation road segments are spliced ​​to form a virtual simulation road segment.

[0055] In some embodiments, the method for creating a virtual simulated road can detect a road construction operation in a simulation interaction page, where the road construction operation includes road configuration information; construct a simulated road segment based on the road configuration information, and form a virtual simulated road based on at least one simulated road segment.

[0056] Specifically, in the simulation interaction page, there are controls for adding, deleting, modifying and checking road configuration information. When a road construction operation is detected, the system will jump to the simulation interaction page. In the simulation interaction page, the system user can edit the corresponding road configuration information in the current simulation interaction page. When the system receives the road configuration information, it constructs the corresponding simulated road segment according to the road configuration information, and forms a virtual simulated road based on at least one simulated road segment. It should be noted that the constructed virtual simulated road segment can be stored so that the constructed virtual simulated road segment can be recycled, without the need to rebuild the virtual simulated road segment each time, thereby improving the construction efficiency of the virtual simulated road segment.

[0057] In some embodiments, the method for creating a virtual simulated road can be to detect a road construction operation in a simulation interaction page, where the road construction operation includes road configuration information; match a target simulated road segment in the constructed simulated road segment based on the road configuration information, and form a virtual simulated road based on the target simulated road segment.

[0058] Specifically, in the simulation interaction page, when a road construction operation is detected, the target simulation road segment can be matched from the constructed simulation road segment according to the road configuration information edited in the simulation interaction page. If the road configuration information corresponding to the constructed simulation road segment is the same as the road configuration information edited in the simulation interaction page, it means that the match is successful. Furthermore, a virtual simulation road is formed based on the target simulation road segment, which improves the speed of virtual simulation road construction, thereby improving the speed of virtual simulation road construction.

[0059] In some embodiments, the method for creating a virtual simulated road can be to call at least one simulated road segment from a pre-created road library in response to a road call operation in a simulation interaction page, and form a virtual simulated road based on the at least one simulated road segment.

[0060] Among them, the pre-created road library can be specifically understood as being used to store simulated road segments that are pre-built based on the set road configuration information. In this process, the set road configuration information can first be obtained through demand research or analysis of the vehicle driving environment to obtain multiple road configuration information, and the corresponding simulated road segments are constructed and stored, which can meet as many vehicle driving road scenarios as possible. It should be noted that the pre-created road library can be updated according to actual needs. During the test, simulated road segments that do not exist in the road library can be added to the road library, and the simulated road segments in the road library can be continuously improved. The road call operation can be performed by setting an operation button on the interactive page, or by selecting a label or image in the road display list on the simulation interactive page, or by directly entering the road type name for search, etc., which is not limited here.

[0061] Specifically, in the simulation interaction page, when it is detected that a road call operation is initiated, in response to the road call operation, the simulation interaction page calls a simulated road segment in a pre-created road library. The required simulated road segment can be matched according to the road call operation, or at least one simulated road segment in the pre-created road library can be directly called to form a virtual simulated road through at least one simulated road segment.

[0062] It should be noted that the method for creating a virtual simulated road may include one or more of the methods described above. For example, after editing the road configuration information on the simulation interaction page, the target simulated road segment is first matched against the constructed simulated road segments based on the configuration information. If a match is not successful, a simulated road segment is further constructed based on the road configuration information, thereby forming a virtual simulated road based on at least one simulated road segment. In the case where there are two or more simulated road segments to be constructed, it is necessary to splice each simulated road segment to obtain a new simulated road segment. The splicing method can be spliced ​​sequentially according to the obtained simulated road segments, and the rationality of the spliced ​​simulated road segments can be checked. The rationality check can be set according to the simulation road requirements. For example, it is checked that the angle formed by the two simulated road segments at the splicing point of the two simulated road segments cannot be less than the preset angle value. If it is not satisfied, it means that the current splicing of the two simulated road segments is unreasonable and the splicing method needs to be readjusted. It can also be checked whether there is a dense distribution of traffic light devices on the spliced ​​simulated road. If so, it means that there is an unreasonable phenomenon in the splicing of the simulated road segments. The corresponding rationality check method can also be set according to actual needs, which is no longer limited here.

[0063] In this embodiment, by rendering virtual environment data and a vehicle dynamics model, the virtual environment data includes a pre-built virtual simulation road, and the vehicle dynamics model is rendered on the virtual simulation road, so that the user can observe the results of the autonomous driving simulation more intuitively.

[0064] S120. Performing autonomous driving simulation based on a virtual simulation road. During the simulation process: obtaining first driving data of a vehicle simulation device and second driving data of a vehicle dynamics model, wherein the first driving data and the second driving data form driving data at a current moment; determining predicted driving data of the vehicle on the virtual simulation road based on the driving data at the current moment; determining vehicle control information based on the predicted driving data; controlling the vehicle simulation device to perform autonomous driving simulation based on the vehicle control information; and / or controlling the vehicle dynamics model to drive on the virtual simulation road based on the vehicle control information.

[0065] Specifically, the vehicle simulation equipment can be understood as consisting of a simulated cockpit and a multi-degree-of-freedom motion system. The simulated cockpit features a racing-style seat with adjustable backrest and fore-and-aft position. The five major operating components are based on actual components from the simulated vehicle. The steering mechanism is constructed using a steering gear assembly with torque feedback, enabling tire torque feedback and automatic self-centering during steering. The gear shift mechanism uses real-world shift paddles, providing a realistic feel. The throttle, clutch, and brake controls are integrated into a single assembly using mechanical components from the simulated vehicle. The multi-degree-of-freedom motion system consists of four servo screws, a double-layer support platform, and a servo drive control system. The servo screw columns are mounted on a fixed base on the ground. The support platform is constructed from welded double-layer steel plates, fastened together with bolts. The servo drive control system controls the stroke of the electric cylinder to achieve the three degrees of freedom of the motion platform: vertical translation within the Cartesian coordinate system, and roll and pitch about the XY coordinate axes. The first driving data can be specifically understood as data provided by the vehicle simulation device, which is collected by the corresponding simulated mechanical components in the vehicle simulation device, and may include the steering wheel angle data of the vehicle simulation device; the second driving data can be specifically understood as data obtained through simulation of the vehicle dynamics model, which may include but is not limited to vehicle driving speed data, vehicle yaw angle data, vehicle coordinate information, etc.

[0066] Specifically, during the simulation process, the first driving data collected by the vehicle simulation device traveling on the virtual simulation road and the second driving data of the vehicle dynamics model form the driving data at the current moment. The first driving data and the second driving data are respectively configured with a timestamp, and the first driving data and the second driving data with matching timestamps are combined to obtain the driving data at the current moment. Timestamp matching can mean that the difference in timestamps is less than an error threshold. The acquired driving data at the current moment is transmitted to the autonomous driving algorithm module. The autonomous driving algorithm module determines the predicted driving data of the vehicle on the virtual simulation road based on the current driving data, i.e., the vehicle driving data at the next moment. Vehicle control information is generated based on the predicted driving data, and the vehicle control information controls the vehicle simulation device to perform autonomous driving simulation. Alternatively, the vehicle control information is input into the vehicle dynamics model to control the vehicle dynamics model to travel on the virtual simulation road according to the vehicle control information.

[0067] For example, Figure 2 The schematic diagram of a driving simulation device test structure is shown, which includes a real-time platform, a desktop computer, and a vehicle simulation device. The real-time platform is used to simulate the cockpit, allowing the driver to input virtual environment data, driving data, and other information. The real-time platform also includes a vehicle model and a vehicle output module that outputs vehicle output via CAN signals. The desktop computer also includes a device equivalent to a driving simulation server, which is used to build a virtual environment road, simulate vehicle posture, and send the constructed virtual environment data to the vehicle simulation device. The driving simulation service uses a high-level high-performance server in the industry as a carrier, on which the entire Tongyuan simulation test platform software system runs. It is deployed with a high-performance GPU and generates three-dimensional images in real time based on a high-performance computing engine. It supports three-screen linkage and a rendering speed of no less than 60 frames per second, realizing realistic simulation of various road and environmental scenarios of vehicle simulated driving. In addition, for parts of the vehicle dynamics component simulation that require high real-time performance, the high-performance real-time simulation lower computer can simulate component output close to the actual working conditions, which can meet some hardware-in-the-loop testing requirements. The vehicle simulation device is used to simulate vehicle pitch, lateral deviation, yaw, and other functions. The input information is sent to the vehicle model and the vehicle control information is output. The driving simulation server is used to build a virtual driving environment and send the built image to the vehicle simulation device.

[0068] Optionally, the method further includes: forming a simulation path based on the starting point and the end point in the virtual simulation road, sequentially setting reference points and index information of the reference points on the simulation path; accordingly, the driving data at the current moment includes the vehicle position information at the current moment, the vehicle speed information at the current moment, the vehicle yaw angle data at the current moment, the vehicle steering wheel angle data at the current moment, the index information of the nearest reference point of the vehicle position at the previous moment, and the position set of the reference points in the simulation path. Among them, the index information of the nearest reference point of the vehicle position at the previous moment can be determined based on the position set of the reference points in the simulation path and the vehicle position information at the previous moment, and the position set of the reference points in the simulation path is pre-stored, and the predicted driving data includes the reference path information corresponding to the predicted time step, the vehicle speed information at the next moment, the vehicle yaw angle data at the next moment, the vehicle steering wheel angle data at the next moment, and the index information of the nearest reference point at the current moment.

[0069] Among them, the reference point can be specifically understood as any point on the virtual simulation path. The simulation path can be segmented according to the preset segmentation rules. The connection between each segment is regarded as a node. Starting from the starting point in the virtual simulation road, each node is numbered in the order of the path as a reference point. The index information of the reference point can be specifically understood as the number of the reference point, that is, the index value. For example, the starting point in the virtual simulation road is regarded as a reference point, and the corresponding index value is set to 0. Among them, the segmentation rule can be divided according to the rule of equal spacing, or it can be segmented according to different spacings set according to the road feature information. For example, the spacing at the curve is set to be smaller than the spacing at the non-curve for segmentation. The position information of the nearest reference point can be matched with the position information of each reference point according to the vehicle position information at the current moment to determine the reference point corresponding to the nearest index value. The prediction time step can be specifically understood as the difference between the current moment and the next prediction moment, which is equivalent to a prediction control cycle and can be set according to actual needs.

[0070] Specifically, starting from the starting point of the constructed virtual simulation road and ending at the end point, the corresponding simulation path is generated by the path generation module, and each reference point in the simulation path and the index information of the reference point are set. The required driving data at the current moment include the vehicle position information at the current moment, the vehicle speed information at the current moment, the vehicle yaw angle data at the current moment, the vehicle steering wheel angle data at the current moment, the index information of the nearest reference point of the vehicle position at the previous moment, and the position set of the reference points in the simulation path. In the initial state, the index value corresponding to the index information of the nearest reference point is set to 1; the automatic driving algorithm module determines the predicted driving data of the vehicle on the virtual simulation road based on the driving data at the current moment. Accordingly, the required predicted driving data include the reference path information corresponding to the prediction time step, the vehicle speed information at the next moment, the vehicle yaw angle data at the next moment, the vehicle steering wheel angle data at the next moment and the index information of the nearest reference point at the current moment.

[0071] In some embodiments, during the simulation process, the vehicle speed information is preset average speed data, the vehicle yaw angle data includes the preset yaw angle corresponding to each reference point; the vehicle steering wheel angle data includes the preset steering wheel angle data corresponding to each reference point; the method for determining the reference path information corresponding to the prediction time step includes: determining the reference index information corresponding to the preset time step after the index information of the nearest reference point located at the vehicle position at the previous moment, and using the reference point position information corresponding to the reference index information as the reference path information corresponding to the prediction time step.

[0072] Specifically, during the simulation, the vehicle is first assumed to be traveling at a constant speed at a preset speed. The vehicle's current position information, including the x-axis and y-axis coordinates of the vehicle's current position information, is obtained. The index value of the closest coordinate point to the reference trajectory is obtained. Initially, the index value is 0. After determining the index value S of the closest coordinate point to the reference trajectory, the reference trajectory point at a preset time step T is obtained, that is, a reference estimated point with an index value between (S, S+T) is obtained. For example, if the current index value S is 1, the second, third, ..., and first + T reference trajectory coordinate points are obtained. The distances between the current vehicle position and these reference trajectory coordinate points are calculated, and the index value of the closest coordinate point to the reference trajectory is updated as the output of the path module. The reference path information, vehicle speed reference information, and vehicle control angle reference information for the next T coordinate points after the index value of the closest coordinate point to the reference trajectory are output. For example, if the current index value is 1, the reference path information of the second, third, ..., and first + T coordinate points are used as the module output.

[0073] In some embodiments, determining vehicle control information based on predicted driving data includes: simulating the predicted driving data based on an MPC algorithm to obtain vehicle control information, wherein the vehicle control information includes the vehicle front wheel deflection angle at the next moment, the vehicle position information at the next moment, the vehicle speed at the next moment, the vehicle yaw angle at the next moment, the steering wheel angle at the next moment, and the vehicle acceleration at the next moment.

[0074] Among them, MPC (Model Predictive Control) is a multivariable control strategy, which is an advanced control method for controlling the process when specific constraints are met in process control. MPC is based on the dynamic model of the process. Through the linear empirical model obtained by system identification, it predicts the corresponding changes in the dependent variable of the modeled system when the independent variable changes. The characteristic of MPC is that it optimizes the current time block each time, and then optimizes the time block again at the next time, predicts future events and performs corresponding processing. The MPC algorithm constructs a cost function based on the input vehicle status information and predicted driving data, which is used to calculate the error between the predicted control data and the reference data. It performs optimization and solution by calling the external optimization library, and finally obtains the predicted result through rolling calculation and feedback correction.

[0075] Specifically, the rolling calculation process uses the control variable information data obtained from the current vehicle state and is executed only at the current moment. The calculation is repeated again with the next sample input, yielding a new set of optimal results. The calculation process converts the system's performance requirements and constraints into the value of the objective function and the range of values ​​for the solution to the optimization problem, thereby determining the optimal sequence of control variables for the future control horizon.

[0076] Specifically, the feedback correction process simulates the predicted driving data using the MPC algorithm. Reference information from the predicted driving data is used to construct an objective function and optimize the solution. The error between the reference information and the actual model output is included as part of the objective function. By optimizing the minimum value of the objective function, the actual output is ensured to approach the reference value. The first control variable obtained from the optimization is fed back into the control system to influence the model's motion state in the next cycle. Throughout the calculation process, not only feedforward compensation based on future reference data is required, but also feedback compensation based on the current system state. Finally, the predicted control information, including the generated vehicle front wheel deflection angle, vehicle position information, vehicle speed, vehicle yaw angle, steering wheel angle, and vehicle acceleration at the next moment, is transmitted to the driver model.

[0077] Based on the above embodiment, the method further includes: obtaining environmental data of the vehicle dynamics model during driving on the virtual simulation road through a simulation sensor configured on the vehicle dynamics model, and performing abnormal driving detection on the vehicle dynamics model based on the environmental data.

[0078] The simulated sensors specifically include, but are not limited to, simulated radars and simulated cameras, which are used to detect the driving environment data of the vehicle dynamics model. The driving environment data refers to the environmental data of the vehicle dynamics model during its driving on the virtual simulated road.

[0079] Specifically, simulation sensors are configured on the vehicle dynamics model to obtain environmental data of the vehicle dynamics model during its driving on a virtual simulation road. The obtained environmental data is then identified to determine whether the vehicle dynamics model is driving in accordance with the predicted control information during driving, and to detect whether the vehicle dynamics model has any abnormalities such as crossing the line or deviating from the preset driving track.

[0080] Based on the above embodiment, the method also includes: obtaining driving data of the vehicle dynamics model and driving data of the vehicle simulation device during the simulation process; when there is a difference between the driving data of the vehicle dynamics model and the driving data of the vehicle simulation device, generating difference comparison data based on the driving data of the vehicle dynamics model and the driving data of the vehicle simulation device, and the difference comparison data is used to optimize the vehicle dynamics model.

[0081] Specifically, the vehicle control information is input as an input parameter to the vehicle dynamics model and the vehicle simulation device respectively. The vehicle dynamics model simulates driving according to the vehicle control information to obtain driving data corresponding to the vehicle dynamics model. The vehicle simulation device simulates driving according to the vehicle control information to obtain driving data corresponding to the vehicle simulation device. Further, the driving data of the obtained vehicle dynamics model and the driving data of the vehicle simulation device are compared to determine whether there is a difference. If there is a difference, difference comparison data is generated based on the driving data of the vehicle dynamics model and the driving data of the vehicle simulation device. The obtained difference comparison data is returned to the vehicle dynamics model for optimizing the vehicle dynamics model until the difference comparison data tends to be stable or meets a preset difference threshold, thereby obtaining an optimized vehicle dynamics model.

[0082] The technical solution of this embodiment is to render virtual environment data and a vehicle dynamics model, wherein the virtual environment data includes a pre-built virtual simulation road, and the vehicle dynamics model is rendered on the virtual simulation road; and perform autonomous driving simulation based on the virtual simulation road. During the simulation process: current driving data of the vehicle simulation device is obtained, predicted driving data of the vehicle on the virtual simulation road is determined based on the current driving data, vehicle control information is determined based on the predicted driving data, the vehicle simulation device is controlled based on the vehicle control information to perform autonomous driving simulation, and / or the vehicle dynamics model is controlled to travel on the virtual simulation road based on the vehicle control information. This realizes the construction of a test environment for a virtual simulation road, the combination of the vehicle simulation device for autonomous driving simulation, and the realization of joint simulation testing, thereby improving the accuracy of autonomous driving simulation testing, improving development and testing efficiency, and reducing testing costs.

[0083] Figure 3 This is a schematic diagram of the structure of an autonomous driving simulation system provided by an embodiment of the present invention. Figure 3 As shown, the system includes: a simulation test system 310, a traffic scene server 320 and a vehicle simulation device 330.

[0084] Among them, the simulation test system 310 includes a road construction module 3101, an automatic driving processing module 3102 and a vehicle dynamics model 3103; the traffic scene server 320 pre-stores virtual environment data; the road construction module 3101 is used to construct a virtual simulation road in the virtual environment data; the automatic driving processing module 3102 is used to render the virtual environment data and the vehicle dynamics model 3103 on the virtual simulation road, and perform automatic driving simulation based on the virtual simulation road. During the simulation process: first driving data of the vehicle simulation device 330 and second driving data of the vehicle dynamics model are obtained, wherein the first driving data and the second driving data form the current driving data, based on the current driving data, the predicted driving data of the vehicle on the virtual simulation road is determined, based on the predicted driving data, vehicle control information is determined, the vehicle control information is sent to the vehicle simulation device 330, and / or, based on the vehicle control information, the vehicle dynamics model 3103 is controlled to drive on the virtual simulation road; the vehicle simulation device 330 is configured with a driving response component for executing the vehicle control information to perform automatic driving simulation.

[0085] Specifically, virtual environment data is pre-stored in the traffic scene server 320 of the simulation test system 310, and a virtual simulation road is constructed in the virtual environment data through the road construction module 3101. Then, the autonomous driving processing module 3102 uses rendering technology to render the virtual environment data and the vehicle dynamics model 3103 on the virtual simulation road to obtain a visualized simulation road, so that the rendered vehicle dynamics model 3103 performs autonomous driving simulation on the virtual simulation road. During the simulation process, a data read request can be sent to the vehicle simulation device 330 to obtain the current driving data of the vehicle simulation device 330. Alternatively, a time interval can be set so that the vehicle simulation device 330 sends the current driving data to the automatic driving processing module 3102 when the preset time interval is reached. The automatic driving algorithm in the automatic driving processing module 3102 predicts the predicted driving data of the vehicle on the virtual simulation road based on the current driving data, and then determines the vehicle control information based on the predicted driving data, and sends the determined vehicle control information to the vehicle simulation device 330. The vehicle simulation device 330 performs automatic driving simulation based on the control information, or controls the driving state of the vehicle dynamics model 3103 through the determined vehicle control information so that it drives on the virtual simulation road, or, after determining the vehicle control information, directly sends the control information to the vehicle simulation device 330 and the vehicle dynamics model 3103 at the same time, thereby controlling the automatic driving simulation of the vehicle simulation device 330 and the vehicle dynamics model 3103.

[0086] It should be noted that the vehicle simulation device 330 is equipped with a driving response component for executing vehicle control information to perform automatic driving simulation. Optionally, the vehicle simulation device 330 is equipped with at least pitch, yaw and lateral freedom components.

[0087] Specifically, when the vehicle simulation device 330 receives vehicle control information, the configured driving response component performs automatic driving simulation based on the received control information. The control information can be executed by a component configured with at least pitch, yaw and lateral freedom, thereby realizing vertical translation movement in the Cartesian coordinate system, as well as control operations such as rolling and pitching around the XY coordinate axis, which are applied to the simulation analysis of the vehicle's handling stability and ride comfort.

[0088] Based on the above embodiment, the simulation test system 310 also includes a sensor module 3104, which is used to obtain environmental data of the vehicle dynamics model 3103 during its driving on the virtual simulation road, and send the environmental data to the automatic driving processing module 3102; the automatic driving processing module 3102 performs abnormal driving detection on the vehicle dynamics model 3103 based on the environmental data.

[0089] Specifically, the simulation test system 310 is further provided with a sensor module 3104. The sensor module 3104 may include a laser radar, a millimeter-wave radar, a camera, and other equipment. The sensor module 3104 is used to collect environmental data of the vehicle dynamics model 3103 while it is driving on the virtual simulation road. For example, the environmental data may be collected virtual environment image information. The acquired environmental data is sent to the autonomous driving processing module 3102. The autonomous driving processing module 3102 analyzes the environmental data and performs abnormal driving detection on the vehicle dynamics model 3103. The module detects whether the vehicle dynamics model 3103 violates any regulations or traffic rules on the virtual simulation road. For example, the module detects whether there is a compaction line problem; or detects whether the vehicle dynamics model 3103 performs operations that differ from the vehicle control information.

[0090] The technical solution of this embodiment is to propose an automatic driving simulation system, which includes a simulation test system, a traffic scene server and a vehicle simulation device; wherein the simulation test system includes a road construction module, an automatic driving processing module and a vehicle dynamics model; virtual environment data is pre-stored in the traffic scene server; the road construction module constructs a virtual simulation road in the virtual environment data; the automatic driving processing module renders the virtual environment data and the vehicle dynamics model on the virtual simulation road, and performs automatic driving simulation based on the virtual simulation road. During the simulation process: first driving data of the vehicle simulation device and second driving data of the vehicle dynamics model are obtained, wherein the first driving data and the second driving data form the driving data at the current moment, the predicted driving data of the vehicle on the virtual simulation road is determined based on the driving data at the current moment, the vehicle control information is determined based on the predicted driving data, the vehicle control information is sent to the vehicle simulation device, and / or the vehicle dynamics model is controlled to drive on the virtual simulation road based on the vehicle control information; the vehicle simulation device is configured with a driving response component for executing the vehicle control information to perform automatic driving simulation. This is achieved by building an autonomous driving anti-simulation system, using a simulation test system to conduct simulation testing, using a traffic scene server to store a variety of virtual environment data, which helps to determine a variety of virtual forms of environmental data, using a vehicle simulation device to simulate the vehicle, and configuring a driving response component in the vehicle simulation device to execute vehicle control information to perform autonomous driving simulation, so that the driving state of the vehicle simulation device is more consistent with the driving state of the actual vehicle, thereby improving the simulation efficiency of the autonomous driving simulation system, and at the same time helping to improve the efficiency of development testing and reduce test costs.

[0091] Figure 41 is a structural diagram of a simulation test system provided by an embodiment of the present invention. The simulation test system 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The simulation test system can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0092] like Figure 4 As shown, the simulation test system 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. Various programs and data required for the operation of the simulation test system 10 can also be stored in the RAM 13. The processor 11, ROM 12 and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0093] Multiple components in the simulation test system 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard and mouse; an output unit 17, such as various types of displays and speakers; a storage unit 18, such as a magnetic disk and optical disk; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the simulation test system 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0094] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the autonomous driving simulation method.

[0095] In some embodiments, the autonomous driving simulation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the simulation test system 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the autonomous driving simulation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the autonomous driving simulation method in any other appropriate manner (e.g., by means of firmware).

[0096] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0097] Computer programs for implementing the autonomous driving simulation methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that, when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0098] An embodiment of the present invention further provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a processor to execute an autonomous driving simulation method, the method comprising:

[0099] Rendering virtual environment data and a vehicle dynamics model, wherein the virtual environment data includes a pre-built virtual simulation road, and the vehicle dynamics model is rendered on the virtual simulation road;

[0100] An autonomous driving simulation is performed based on a virtual simulation road. During the simulation process: first driving data of a vehicle simulation device and second driving data of a vehicle dynamics model are obtained, wherein the first driving data and the second driving data form driving data at a current moment; predicted driving data of the vehicle on the virtual simulation road is determined based on the driving data at the current moment; vehicle control information is determined based on the predicted driving data; the vehicle simulation device is controlled to perform autonomous driving simulation based on the vehicle control information; and / or the vehicle dynamics model is controlled to drive on the virtual simulation road based on the vehicle control information.

[0101] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0102] To provide interaction with a user, the systems and techniques described herein can be implemented on a simulation test system having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the simulation test system. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0103] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0104] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within a cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0105] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0106] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. An automatic driving simulation method, characterized in that: include: Rendering virtual environment data and a vehicle dynamics model, wherein the virtual environment data includes a pre-built virtual simulation road, and the vehicle dynamics model is rendered on the virtual simulation road; Performing an autonomous driving simulation based on the virtual simulated road, during the simulation process: obtaining first driving data of a vehicle simulation device and second driving data of the vehicle dynamics model, wherein the first driving data and the second driving data form driving data at a current moment; determining predicted driving data of the vehicle on the virtual simulated road based on the driving data at the current moment; determining vehicle control information based on the predicted driving data; controlling the vehicle simulation device to perform the autonomous driving simulation based on the vehicle control information; and / or controlling the vehicle dynamics model to drive on the virtual simulated road based on the vehicle control information; The determining of vehicle control information based on the predicted driving data includes: Performing simulation processing on the predicted driving data based on an MPC algorithm to obtain the vehicle control information, wherein the vehicle control information includes a front wheel deflection angle of the vehicle at a next moment, vehicle position information at a next moment, vehicle speed at a next moment, vehicle yaw angle at a next moment, steering wheel angle at a next moment, and vehicle acceleration at a next moment; The method further comprises: Acquiring driving data of the vehicle dynamics model and driving data of the vehicle simulation device during the simulation process; When there is a difference between the driving data of the vehicle dynamics model and the driving data of the vehicle simulation device, difference comparison data is generated based on the driving data of the vehicle dynamics model and the driving data of the vehicle simulation device, and the difference comparison data is used to optimize the vehicle dynamics model.

2. The method according to claim 1, characterized in that A method for creating a virtual simulation road includes at least one of the following: Acquire a simulation requirement configuration file, wherein the simulation requirement configuration file includes at least one road configuration information; construct a simulated road segment based on the road configuration information, and form a virtual simulated road based on the at least one simulated road segment; In the simulation interaction page, detecting a road construction operation, wherein the road construction operation includes road configuration information; constructing a simulated road segment based on the road configuration information, and forming a virtual simulated road based on at least one of the simulated road segments; In the simulation interaction page, detecting a road construction operation, wherein the road construction operation includes road configuration information; matching a target simulated road segment in the constructed simulated road segment based on the road configuration information, and forming a virtual simulated road based on the target simulated road segment; In the simulation interaction page, in response to a road calling operation, at least one simulated road segment is called from a pre-created road library, and a virtual simulated road is formed based on the at least one simulated road segment.

3. The method according to claim 1, characterized in that The method further comprises: forming a simulation path based on a starting point and an end point in the virtual simulation road, and sequentially setting reference points and index information of the reference points on the simulation path; Correspondingly, the current driving data includes the vehicle position information at the current moment, the vehicle speed information at the current moment, the vehicle yaw angle data at the current moment, the vehicle steering wheel angle data at the current moment, the index information of the nearest reference point of the vehicle position at the previous moment, and the position set of the reference points in the simulation path; The predicted driving data includes reference path information corresponding to the predicted time step, vehicle speed information at the next moment, vehicle yaw angle data at the next moment, vehicle steering wheel angle data at the next moment, and index information of the nearest reference point at the current moment.

4. The method according to claim 3, characterized in that During the simulation process, the vehicle speed information is preset average speed data, the vehicle yaw angle data includes a preset yaw angle corresponding to each reference point; the vehicle steering wheel angle data includes preset steering wheel angle data corresponding to each reference point; The method for determining the reference path information corresponding to the predicted time step includes: determining the reference index information corresponding to the preset time step after the index information of the nearest reference point located at the vehicle position at the previous moment, and using the reference point position information corresponding to the reference index information as the reference path information corresponding to the predicted time step.

5. The method according to claim 1, characterized in that: The method further comprises: Environmental data of the vehicle dynamics model during its driving on the virtual simulation road is acquired through a simulation sensor configured on the vehicle dynamics model, and abnormal driving detection is performed on the vehicle dynamics model based on the environmental data.

6. An automatic driving simulation system, characterized in that: include: A simulation test system, a traffic scenario server, and a vehicle simulation device; wherein the simulation test system includes a road construction module, an autonomous driving processing module, and a vehicle dynamics model; The traffic scene server is pre-stored with virtual environment data; The road construction module is used to construct a virtual simulation road in the virtual environment data; The autonomous driving processing module is configured to render virtual environment data and a vehicle dynamics model on the virtual simulated road, and perform autonomous driving simulation based on the virtual simulated road. During the simulation, the module: obtains first driving data of a vehicle simulation device and second driving data of the vehicle dynamics model, wherein the first driving data and the second driving data form driving data at a current moment; determines predicted driving data of the vehicle on the virtual simulated road based on the driving data at the current moment; determines vehicle control information based on the predicted driving data; sends the vehicle control information to the vehicle simulation device; and / or controls the vehicle dynamics model to drive on the virtual simulated road based on the vehicle control information. The vehicle simulation device is configured with a driving response component for executing the vehicle control information to perform an autonomous driving simulation; The simulation test system further includes a sensor module, which is used to obtain environmental data of the vehicle dynamics model during driving on the virtual simulation road, and send the environmental data to the automatic driving processing module; The automatic driving processing module performs abnormal driving detection on the vehicle dynamics model based on the environmental data.

7. The system according to claim 6, characterized in that The vehicle simulation device is configured with at least pitch, yaw and lateral freedom components.

8. A simulation test system, characterized in that: The simulation test system includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the automatic driving simulation method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the automatic driving simulation method according to any one of claims 1 to 5 when executed.

Images