Software-in-the-loop simulation test system and method for intelligent driving

Abstract

The invention discloses a software-in-the-loop simulation test system and method for intelligent driving, and relates to the technical field of automatic driving algorithm testing. According to the scheme, a closed-loop test of an in-the-loop simulation test is realized only through an intelligent driving platform, a scene simulation software end and an initialized vehicle dynamics model group; all the components realize distributed communication through a user datagram protocol without additional hardware, so that complicated external communication configuration is not needed in a closed-loop test for realizing in-loop simulation test, multi-tool collaboration is simplified, and the complexity of a system structure is reduced. And the intelligent driving platform coordinates vehicle dynamics data according to a preset algorithm to carry out path planning and decision control, so that the interaction efficiency of software in a loop simulation test process is improved. And the vehicle dynamics model group is used for sending the RDB data packet to the scene simulation software end through the public user datagram protocol channel, that is, cross-component collaboration is realized through the public user datagram protocol channel, and the synchronism of closed-loop testing is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving algorithm testing, in particular to a software-in-the-loop simulation test system and method for intelligent driving. BACKGROUND

[0002] In the development of automatic driving technology, software-in-the-loop (SIL) testing is a key link, which is used to verify the performance of the algorithm in a simulation environment.

[0003] In the existing SIL testing method, multiple tools are involved in the test (such as simulation software and dynamic models), which requires complex external communication configuration and increases system complexity. High system complexity may limit the synchronization of SIL testing.

[0004] Therefore, how to improve the interaction efficiency and synchronization in the SIL testing process is a problem that needs to be solved urgently. SUMMARY

[0005] Therefore, the present application discloses a software-in-the-loop simulation test system and method for intelligent driving, which aims to improve the interaction efficiency and synchronization of data in the SIL testing process.

[0006] In order to achieve the above purpose, the technical solution disclosed is as follows:

[0007] The first aspect of the present application discloses a software-in-the-loop simulation test system for intelligent driving, which comprises an intelligent driving platform, a scene simulation software end and an initialized vehicle dynamics model group.

[0008] The intelligent driving platform is connected to the scene simulation software end and the vehicle dynamics model group through user datagram protocol (UDP) respectively to realize distributed communication.

[0009] The scene simulation software end is used to send the obtained simulation scene RDB data package to the vehicle dynamics model group.

[0010] The vehicle dynamics model group is used to send the RDB data package to the scene simulation software end through a common user datagram protocol (UDP) channel.

[0011] The scene simulation software end is used to generate perception data according to the RDB data and send the perception data to the intelligent driving platform.

[0012] The intelligent driving platform is used for analyzing the perception data, obtaining vehicle dynamics data of the current vehicle under passive dynamics control, performing path planning and decision control according to a preset algorithm and the vehicle dynamics data, obtaining corresponding control instructions, and interacting with the vehicle dynamics model group in real time.

[0013] The vehicle dynamics model group is used for adjusting a vehicle model state in real time according to the control instructions, so as to realize real-time closed-loop verification.

[0014] Preferably, the vehicle dynamics model group is also used for sending vehicle tire contact point coordinates to a scene simulation software end through a user datagram protocol.

[0015] The scene simulation software end is also used for generating height coordinates and adhesion coefficients of a tire contact point of the current vehicle according to the vehicle tire contact point coordinates, and sending the height coordinates and the adhesion coefficients to a vehicle dynamics model to complete initialization of the dynamics model.

[0016] Preferably, the vehicle dynamics model group is provided with a vehicle model and a driver model; the vehicle model includes a dynamics model and a tire model.

[0017] The dynamics model is used for simulating a dynamic system of a real vehicle.

[0018] The driver model is used for simulating a driver to output control instructions to control a vehicle.

[0019] The tire model is used for data interaction of vehicle tire contact point coordinates with the scene simulation software end.

[0020] Preferably, an internal sensor RDB2 interface is arranged in the scene simulation software end; the internal sensor RDB2 interface is used for setting an IP and a port to communicate with the outside.

[0021] Preferably, a Trigger sending module is arranged in the vehicle dynamics model group; the Trigger sending module is used for receiving an RDB data packet sent by the internal sensor RDB2 interface in the scene simulation software end, and sending an RDB data packet containing a vehicle state to the RDB2 interface.

[0022] Preferably, a data management forwarding Odrgateway module is arranged in the scene simulation software end; the Odrgateway module is used for receiving tire contact point coordinates of the current vehicle and outputting height coordinates and adhesion coefficients of a tire node of the current vehicle.

[0023] Preferably, the scene simulation software is provided with a plurality of sensors; the plurality of sensors are used for acquiring scene data.

[0024] Preferably, the plurality of sensors at least include a camera / lidar sensor, a millimeter wave radar sensor, and a high-definition map sensor.

[0025] The second aspect of the present application discloses a software-in-the-loop simulation test method for intelligent driving, which is applied to the intelligent driving software-in-the-loop simulation test system of any one of the first aspect, and the system comprises an intelligent driving platform, a scene simulation software end, and an initialized vehicle dynamics model group. The intelligent driving platform is connected with the scene simulation software end and the vehicle dynamics model group through a user datagram protocol respectively to realize distributed communication. The method comprises the following steps:

[0026] Obtaining a simulation scene RDB data packet through the scene simulation software end;

[0027] Sending the RDB data packet to the scene simulation software end through the vehicle dynamics model group and a public user datagram protocol channel;

[0028] Generating perception data through the scene simulation software end and the RDB data packet, and sending the perception data to the intelligent driving platform;

[0029] Analyzing the perception data through the intelligent driving platform to obtain vehicle dynamics data of a current vehicle controlled by dynamics;

[0030] Performing path planning and decision control according to a preset algorithm and the vehicle dynamics data to obtain corresponding control instructions;

[0031] Interacting the control instructions with the vehicle dynamics model group in real time;

[0032] Adjusting a vehicle model state through the vehicle dynamics model group and the control instructions in real time to realize real-time closed-loop verification.

[0033] Preferably, the method further comprises the following steps:

[0034] When the scene simulation software end is started, sending individual data to the intelligent driving platform through internal sensors RDB of the scene simulation software end and a preset sending mode; wherein the preset sending mode at least includes a transmission control protocol, a user datagram protocol, or a shared memory.

[0035] The application discloses a kind of software in loop simulation test system and method of intelligent driving, and the technical solutions are as follows: the software in loop simulation test system of intelligent driving at least includes intelligent driving platform, scene simulation software end and initialized vehicle dynamics model group, intelligent driving platform is connected with scene simulation software end and vehicle dynamics model group respectively by user datagram protocol, to realize distributed communication, scene simulation software end is used to send the simulation scene RDB data package obtained to vehicle dynamics model group, vehicle dynamics model group is used to send RDB data package to scene simulation software end by public user datagram protocol channel, scene simulation software end is used to generate perception data according to RDB data, and perception data is sent to intelligent driving platform, intelligent driving platform is used to parse perception data, obtains the vehicle dynamics data of current vehicle by dynamics control, carries out path planning and decision control according to preset algorithm and vehicle dynamics data, obtains corresponding control instruction, and control instruction is interacted with vehicle dynamics model group in real time, vehicle dynamics model group is used to adjust vehicle model state according to control instruction in real time, to realize real-time closed loop verification.

[0036] The application only needs to realize closed-loop test of in-loop simulation test through intelligent driving platform, scene simulation software end and initialized vehicle dynamics model group, without complex external communication configuration in realizing closed-loop test of in-loop simulation test, simplifies multi-tool cooperation, reduces system structure complexity. And intelligent driving platform coordinates vehicle dynamics data according to preset algorithm to carry out path planning and decision control, improves the interaction efficiency in software in loop simulation test process. And vehicle dynamics model group is used to send RDB data package to scene simulation software end by public user datagram protocol channel, i.e. cross-component cooperation is realized through public user datagram protocol channel, to ensure the synchronization of SIL closed-loop test. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute part of the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of the provided drawings.

[0038] Figure 1 The structure diagram of the software in loop simulation test system of intelligent driving disclosed by the embodiments of the present application is shown in the figure.

[0039] Figure 2 The data interaction schematic diagram of the software in loop simulation test system of intelligent driving disclosed by the embodiments of the present application is shown in the figure.

[0040] Figure 3A flowchart of a software-in-the-loop simulation test method for intelligent driving disclosed in an embodiment of the present application is shown in the figure.

[0041] Figure 4 A structural diagram of an electronic device disclosed in an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0043] In the present application, the term “comprises”, “comprising”, or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or further includes elements inherent to such a process, method, article, or device. Without more limitations, the element defined by the phrase “comprising a” does not exclude the presence of additional identical elements in the process, method, article, or device including the element.

[0044] As known from the background, the existing SIL test method involves multiple tool cooperation (such as simulation software and dynamic model) for testing, which requires complex external communication configuration, increases system complexity, and high system complexity may limit the synchronization of SIL testing. Therefore, how to improve the interaction efficiency and synchronization in the SIL testing process is a problem that needs to be solved urgently.

[0045] To solve the above problems, the present application discloses a software-in-the-loop simulation test system and method for intelligent driving. The present scheme only needs to realize closed-loop testing of in-loop simulation testing through an intelligent driving platform, a scene simulation software end, and an initialized vehicle dynamics model group. All components realize distributed communication through a user datagram protocol without additional hardware, so that complex external communication configuration is not needed in the realization of closed-loop testing of in-loop simulation testing, which simplifies the multi-tool cooperation and reduces the system structure complexity. Moreover, the intelligent driving platform coordinates vehicle dynamics data according to a preset algorithm to make path planning and decision control, which improves the interaction efficiency in the software-in-the-loop simulation testing process. Furthermore, the vehicle dynamics model group is used to send RDB data packets to the scene simulation software end through a public user datagram protocol channel, that is, cross-component cooperation is realized through the public user datagram protocol channel to ensure the synchronization of closed-loop testing. The specific implementation is described in detail in the following embodiments.

[0046] ReferenceFigure 1 As shown in FIG. 1, the intelligent driving software-in-the-loop simulation test system disclosed in the embodiments of the present application includes an intelligent driving platform (Apollo), a scene simulation software (VTD) end, and an initialized vehicle dynamics model (Trucksim) group. The Trucksim model belongs to the Vsocde software end.

[0047] The intelligent driving software-in-the-loop simulation test system supports separate data interaction logic and joint data interaction logic.

[0048] The separate data interaction logic includes the following steps.

[0049] The intelligent driving software-in-the-loop simulation test system supports modularized data flow, and ensures the stability of each component when running independently. For example, when the VTD end is started, the internal sensor RDB package is directly sent to the Apollo platform through a Transmission Control Protocol (TCP) / User Datagram Protocol (UDP) / Shared Memory (SHM) mode, avoiding external interference.

[0050] The joint data interaction logic includes the following steps.

[0051] Cross-component collaboration is achieved through a common UDP channel. Specifically, the Trucksim and the VTD end share vehicle tire contact point data (such as x / y coordinate and z coordinate adhesion coefficient), and the Apollo and the Trucksim exchange control signals (such as throttle, brake, steering wheel angle) in real time, ensuring the synchronization of the closed-loop test.

[0052] The specific data processing process between the Apollo platform, the VTD end, and the initialized Trucksim model group is shown in FIG. 2. Figure 2

[0053] Figure 2 In the process, the VTD end is responsible for scene simulation and sensor data generation. Specifically, the VTD end is used to generate the height coordinate (z) and adhesion coefficient of the current vehicle tire contact point according to the vehicle tire contact point coordinates, and send the height coordinate and adhesion coefficient to the Trucksim model group to complete the initialization of the Trucksim model group.

[0054] The VTD end is provided with an internal sensor RDB2 interface; the internal sensor RDB2 interface is used to set the IP and port for communication with the outside; the VTD is provided with a plurality of sensors; the plurality of sensors are used to obtain scene data; the plurality of sensors at least include a camera / laser radar sensor, a millimeter wave radar sensor, and a high-precision map sensor. ​

[0055] The VTD end is provided with a data management forwarding Odrgateway module; the Odrgateway module is used for receiving a tire contact point coordinate of a current vehicle and outputting a height coordinate (z) of a tire node of the current vehicle and an adhesion coefficient;

[0056] The user starts the scene simulation software simulation of the VTD end, the internal sensor of the VTD end sends scene data (such as obstacle position) to the Apollo platform, and the Trucksim model group sends the x / y coordinate of the tire contact point of the vehicle to the Odrgateway module of the VTD end through UDP. The Odrgateway module of the VTD end returns the z coordinate and the adhesion coefficient to the Trucksim vehicle dynamics model, and the dynamics model initialization is completed.

[0057] The Odrgateway module is a module in the VTD, the input of the Odrgateway module is the x coordinate and the y coordinate of the tire contact point of the current vehicle, and the Odrgateway module outputs a height z coordinate of the tire contact point of the current vehicle. Because the VTD end is a scene simulation software, the map in the software will not be a whole flat surface without height fluctuation, so if the Z coordinate of the current vehicle at a certain point on the map is not known, the vehicle posture in the simulation picture will not be an uphill posture but will directly pass through the model and walk forward. The VTD end involves vehicle data state data and external interaction through a RDB2 interface in the VTD end to set IP and port to communicate with the outside.

[0058] The Apollo platform is the core of the algorithm, receives sensor data and outputs control instructions; the Apollo platform is connected with the VTD end and the Trucksim model group through the UDP protocol to realize distributed communication. No additional hardware is needed. The main control unit is integrated in the Apollo end, and the data flow is coordinated. The main control unit is integrated in the Apollo platform, and the data flow is coordinated through the Apollo platform.

[0059] The data flow coordination of the Apollo platform is realized through a CyberRT component of the Apollo software itself, and the data communicated with the outside will pass through this component. The specific data flow coordination is realized by calling the preset algorithm. Specifically, the data to be input is given to the Apollo platform through the component, and the Apollo platform will control the vehicle through path planning and decision control according to the input data through its internal algorithm. The Apollo platform can be equivalent to a driver model (replacing the real ADAS intelligent driving domain controller);

[0060] In the TruckSim model group, a detailed dynamics model is built based on the specific vehicle model and performance requirements. Model parameters are configured, such as vehicle structure, powertrain, suspension system, braking system, etc. The dynamics model can be understood as simulating the powertrain of a real vehicle.

[0061] The Trucksim model group is used to send the coordinates of the vehicle's tire contact points to the VTD terminal via the UDP protocol.

[0062] The Trucksim model group simulates vehicle dynamics; the Trucksim model group includes vehicle models; vehicle models include driver models and tire models; the vehicle model is the entire vehicle, including dynamics models and tire models; the vehicle dynamics model group includes vehicle models and driver models; the vehicle model includes dynamics models and tire models; the dynamics model is used to simulate the power system of a real vehicle; the driver model is used to simulate the driver in the vehicle model to output control commands (such as controlling the accelerator, brake, steering wheel, etc.) to control the vehicle; the tire model is used to exchange data with the scene simulation software for the coordinates of the vehicle tire contact points.

[0063] The driver model can be understood as simulating a real human driver. Ultimately, the vehicle is controlled by the driver model outputting signals to control the accelerator, brakes, steering wheel, etc. The intelligent driving driver model used here can be understood as the vehicle control model brought into the Apollo software algorithm. Another type of driver model is the driver model built into the VTD terminal.

[0064] The Trucksim model group includes a Trigger sending module; the Trigger sending module is used to receive RDB data packets (including packets related to the current frame number, etc.) sent by the internal sensor RDB2 interface in the VTD terminal, and send RDB data packets containing vehicle status to the RDB2 interface.

[0065] The VTD terminal is used to send the acquired simulation scene RDB data packets to the Trucksim model group;

[0066] The Trucksim model group is used to send RDB data packets to the VTD end via a public UDP channel; the VTD end sends RDB data packets to the Trucksim model group, and the Trucksim end sends RDB data packets of the current vehicle status (including position, speed, acceleration, etc.) back to the VTD end;

[0067] The VTD terminal is used to generate perception data based on RDB data and send the perception data to the Apollo platform; enabling the VTD terminal to know the current position, speed and other status of the vehicle being dynamically controlled through the generated perception data;

[0068] The Apollo platform is used to analyze perception data to obtain the vehicle dynamics data of the current vehicle under dynamic control. Based on preset algorithms (including but not limited to the Apollo algorithm) and vehicle dynamics data, it performs path planning and decision control to obtain corresponding control commands (such as throttle opening), and interacts with the Trucksim model group in real time with the control commands.

[0069] The Trucksim model group is used to adjust the vehicle model state in real time according to control commands to achieve real-time closed-loop verification.

[0070] Specifically, during the closed-loop testing phase, the Apollo platform receives perception data detected by sensors in the VTD terminal; the Trucksim model group sends vehicle dynamics data (such as speed and acceleration) to the Apollo platform via the UDP protocol; the Apollo platform calculates control commands (such as throttle opening) through the Apollo algorithm and feeds them back to the Trucksim model group, which then adjusts the vehicle model state to achieve real-time closed-loop verification.

[0071] Figure 2 The system data flow diagram is shown, which describes the UDP data interaction sequence between the VTD terminal, the Trucksim model group, and the Apollo platform, including sensor data transmission, vehicle coordinate exchange, and control command loop, ensuring the continuity and efficiency of the testing process.

[0072] This solution discloses a SIL co-simulation test system based on the Apollo platform, VTD terminal, and Trucksim model group, including core components and communication architecture. The system uses the UDP protocol to achieve sensor data reception, vehicle state synchronization, and control command closed-loop, supporting individual module testing and co-simulation. The system is simple in structure, highly efficient, and reliable, making it suitable for rapid verification and safety assessment of autonomous driving algorithms.

[0073] This solution provides an innovative SIL simulation testing approach, achieving efficient and high-precision verification of autonomous driving algorithms by integrating the Apollo platform, VTD terminal, and Trucksim model set. This intelligent driving software-in-the-loop simulation testing system simplifies multi-tool collaboration, improves test coverage and real-time performance, and can be widely applied in the field of automotive intelligent driving development, significantly reducing R&D risks and costs.

[0074] This invention relates to the field of autonomous driving algorithm testing, including but not limited to, a software-in-the-loop (SIL) co-simulation testing system based on the Apollo intelligent driving platform, VTD scenario simulation software, and Trucksim vehicle dynamics model, for efficiently verifying the functionality and safety of autonomous driving algorithms.

[0075] This solution provides a novel software-in-the-loop simulation test for SIL (Software-in-the-Loop) joint intelligent driving based on the Apollo platform, VTD (Vehicle Detection and Control) terminal, and Trucksim model group, overcoming the shortcomings of existing technologies. By optimizing the data communication architecture, this system achieves real-time seamless interaction of sensor data, vehicle status, and control signals, significantly improving testing efficiency and accuracy. The main advantages of this invention include: improved test fidelity, reduced development costs, support for comprehensive safety verification, and suitability for rapid iteration of autonomous driving algorithms at Level 2 and above.

[0076] In this embodiment, the solution only requires an intelligent driving platform, a scenario simulation software, and an initialized vehicle dynamics model group to achieve closed-loop testing of in-loop simulation. All components communicate in a distributed manner via the User Datagram Protocol (UDP), requiring no additional hardware. Therefore, complex external communication configurations are unnecessary in achieving closed-loop testing of in-loop simulation, simplifying multi-tool collaboration and reducing system complexity. Furthermore, the intelligent driving platform coordinates vehicle dynamics data for path planning and decision control based on a preset algorithm, improving the interaction efficiency of the software during in-loop simulation testing. The vehicle dynamics model group is used to send RDB data packets to the scenario simulation software via a common UDP channel, achieving cross-component collaboration and ensuring the synchronization of closed-loop testing.

[0077] refer to Figure 3 The image shows a software-in-the-loop simulation testing method for intelligent driving disclosed in this application. This method is applied to the aforementioned software-in-the-loop simulation testing system for intelligent driving and mainly includes the following steps:

[0078] S301: Obtain simulation scenario RDB data packets via the VTD terminal;

[0079] S302: Send RDB packets to the VTD end via Trucksim model group and public UDP channel.

[0080] In S302, RDB packets are sent to the VTD end via the Trucksim model group in the public UDP channel.

[0081] S303: Generates sensing data through VTD terminal and RDB data packets, and sends the sensing data to Apollo platform.

[0082] S304: By parsing the perception data through the Apollo platform, the vehicle dynamics data of the current vehicle under dynamic control is obtained.

[0083] S305: Perform path planning and decision control based on preset algorithms and vehicle dynamics data to obtain corresponding control commands.

[0084] S306: Interacts with the Trucksim model group in real time with control commands.

[0085] S307: Real-time closed-loop verification is achieved by adjusting the vehicle model state in real time through Trucksim model groups and control commands.

[0086] When the VTD is started, it sends individual data to the Apollo platform through the internal sensor RDB of the VTD and the preset transmission method; the preset transmission method includes at least TCP, UDP or SHM.

[0087] The execution process and principle of S301-S307 are consistent with the execution process and principle of the software-in-the-loop simulation test system for intelligent driving mentioned above, and can be referred to accordingly. They will not be repeated here.

[0088] In this embodiment, the solution only requires an intelligent driving platform, a scenario simulation software, and an initialized vehicle dynamics model group to achieve closed-loop testing of in-loop simulation. All components communicate in a distributed manner via the User Datagram Protocol (UDP) without the need for additional hardware. Therefore, complex external communication configurations are not required in achieving closed-loop testing of in-loop simulation, simplifying multi-tool collaboration and reducing system complexity. Furthermore, the intelligent driving platform coordinates vehicle dynamics data according to a preset algorithm for path planning and decision control, improving the interaction efficiency of the software during in-loop simulation testing. The vehicle dynamics model group is used to send RDB data packets to the scenario simulation software via a common UDP channel, i.e., cross-component collaboration is achieved through the common UDP channel, ensuring the synchronization of closed-loop testing.

[0089] This application embodiment also provides a storage medium, the storage medium including stored instructions, wherein, when the instructions are executed, the device where the storage medium is located is controlled to perform a software-in-the-loop simulation test method for intelligent driving as described above.

[0090] This application also provides an electronic device, the structural schematic diagram of which is shown below. Figure 4 As shown, it specifically includes a memory 401 and one or more instructions 402, wherein one or more instructions 402 are stored in the memory 401 and configured to be executed by one or more processors 403 to perform the above-mentioned software-in-the-loop simulation test method for intelligent driving.

[0091] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0092] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0093] The steps in the methods of the various embodiments of this application can be adjusted, combined, or deleted according to actual needs.

[0094] Finally, it should be noted that in this paper, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0095] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0096] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A software-in-the-loop simulation test system for intelligent driving, characterized in that, The system comprises an intelligent driving platform, a scene simulation software end and an initialized vehicle dynamics model group; The intelligent driving platform is connected with the scene simulation software end and the vehicle dynamics model group through user datagram protocol to realize distributed communication; The scene simulation software end is used for sending the obtained simulation scene RDB data packet to the vehicle dynamics model group; The vehicle dynamics model group is used for sending the RDB data packet to the scene simulation software end through a public user datagram protocol channel; The scene simulation software end is used for generating perception data according to the RDB data and sending the perception data to the intelligent driving platform; The intelligent driving platform is used for analyzing the perception data to obtain vehicle dynamics data of the current vehicle controlled by dynamics, performing path planning and decision control according to a preset algorithm and the vehicle dynamics data, obtaining corresponding control instructions and interacting with the vehicle dynamics model group in real time; The vehicle dynamics model group is used for adjusting the vehicle model state in real time according to the control instructions to realize real-time closed-loop verification.

2. The system of claim 1, wherein, The vehicle dynamics model group is also used for sending vehicle tire contact point coordinates to the scene simulation software end through user datagram protocol; The scene simulation software end is also used for generating height coordinates and adhesion coefficients of the tire contact point of the current vehicle according to the vehicle tire contact point coordinates and sending the height coordinates and the adhesion coefficients to the vehicle dynamics model to complete initialization of the dynamics model.

3. The system of claim 1, wherein, The vehicle dynamics model group is provided with a vehicle model and a driver model; the vehicle model comprises a dynamics model and a tire model; The dynamics model is used for simulating a power system of a real vehicle; The driver model is used for simulating a driver to output control instructions to control a vehicle; The tire model is used for data interaction of vehicle tire contact point coordinates with the scene simulation software end.

4. The system of claim 1, wherein, An internal sensor RDB2 interface is arranged in the scene simulation software end; the internal sensor RDB2 interface is used for setting IP and port for communication with the outside.

5. The system of claim 4, wherein, A Trigger sending module is arranged in the vehicle dynamics model group; the Trigger sending module is used for receiving an RDB data packet sent by the internal sensor RDB2 interface in the scene simulation software end and sending an RDB data packet containing vehicle state to the RDB2 interface.

6. The system of claim 1, wherein, A data management forwarding Odrgateway module is arranged in the scene simulation software end; the Odrgateway module is used for receiving tire contact point coordinates of a current vehicle and outputting height coordinates and adhesion coefficients of the tire contact point of the current vehicle.

7. The system of claim 1, wherein, The scene simulation software is provided with a plurality of sensors; the plurality of sensors are used for obtaining scene data.

8. The system of claim 7, wherein, The plurality of sensors at least comprise a camera / laser radar sensor, a millimeter wave radar sensor and a high-precision map sensor. 9.A software-in-the-loop simulation test method for intelligent driving, characterized in that, The method is applied to the intelligent driving software-in-the-loop simulation test system in any one of claims 1 to 8, the system comprising an intelligent driving platform, a scene simulation software end and an initialized vehicle dynamics model group, the intelligent driving platform being connected with the scene simulation software end and the vehicle dynamics model group through a user datagram protocol to realize distributed communication, the method comprising: obtaining a simulation scene RDB data packet through the scene simulation software end; sending the RDB data packet to the scene simulation software end through the vehicle dynamics model group and a public user datagram protocol channel; generating perception data through the scene simulation software end and the RDB data packet, and sending the perception data to the intelligent driving platform; analyzing the perception data through the intelligent driving platform to obtain vehicle dynamics data of a current vehicle subjected to dynamics control; performing path planning and decision control according to a preset algorithm and the vehicle dynamics data to obtain corresponding control instructions; interacting the control instructions with the vehicle dynamics model group in real time; adjusting a vehicle model state in real time through the vehicle dynamics model group and the control instructions to realize real-time closed-loop verification.

10. The method of claim 9, wherein, Further comprising: when the scene simulation software end is started, sending individual data to the intelligent driving platform through internal sensors RDB of the scene simulation software end and a preset sending mode; wherein the preset sending mode at least comprises a transmission control protocol, a user datagram protocol or a shared memory.

Images