Intelligent driving system based on digital twinning

Abstract

The application provides an intelligent driving system based on digital twinning, comprising a perception module, a positioning module, a vehicle control module, a communication module and a drive-by-wire chassis; wherein the perception module is used for sensing traffic and environmental information of a road around a vehicle driving through a sensor and sending the information to the vehicle control module; the positioning module is used for determining a position of the vehicle in an environment; the vehicle control module is used for helping a user to select an automatic driving application and performing digital twinning simulation test on the automatic driving application selected by the user, and if the simulation test is passed, the vehicle enters automatic driving and sends a control signal of the vehicle to the drive-by-wire chassis; and the drive-by-wire chassis is used for controlling the vehicle according to the control signal. The application can realize that a user selects an application software of intelligent driving according to a need of the user, and ensures safety and stability through digital twinning simulation test.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of control and regulation systems for vehicles, and in particular to an intelligent driving system based on digital twinning. BACKGROUND

[0002] With the development and improvement of deep learning technology and large-scale data processing capability, integrated automatic driving solutions are gradually becoming the focus of the industry. This solution integrates multiple modules such as perception, decision-making, and planning, achieving direct mapping from raw sensor data input to driving action output, significantly improving the joint optimization capability and computational efficiency of the system.

[0003] Because different companies may have different sizes, qualities, and differences in data, or companies may use different algorithms and technical routes when developing large models for autonomous driving, such as some companies may prefer to use deep learning algorithms, while others may combine other technologies such as reinforcement learning or traditional control theory, or the research and development investment and resources of the company also affect the development of large models. Companies with more resources may be able to conduct more in-depth research and development, trying more advanced technologies and architectures, or different companies' autonomous driving application scenarios and goals may be different, some companies may focus on specific areas or scenarios such as urban traffic or highway driving, all of which will affect the training and performance of the model.

[0004] Software-defined cars are an important concept in the automotive industry, with the core idea that software technology centered on artificial intelligence will determine the future direction of car development. With the trend of intelligentization and networking, cars are transforming from simple mechanical transportation tools to new-generation mobile intelligent terminals. In the future, car users can freely choose different manufacturers' autonomous driving software according to their personal preferences, such as navigation map selection, choosing Baidu, Tencent, or Google. With the continuous maturation and evolution of technology, users can even assemble car hardware and download software for integration, and then test the real car through a digital twinning system.

[0005] The existing technical solutions for software-defined cars in the prior art, such as patent CN202211197934.X or patent CN202210159920.2, where the former only outlines the software-defined car process as five steps: demand determination, field design, service development, testing and release, and continuous expansion, but does not detail the vehicle safety testing method, and the latter describes the design of the whole car, which is more macroscopic in car design, lacking detailed explanation of how the system software defines the car. Therefore, there is an urgent need for an intelligent driving system based on digital twinning. SUMMARY

[0006] The technical problems solved by the present application are: to provide an intelligent driving system based on digital twinning, to realize that users can select application function software of intelligent driving and autonomously select automatic driving application according to their own needs, and to ensure the safety of driving through digital twinning simulation testing.

[0007] The technical solution adopted by the present application to solve the above technical problems is: an intelligent driving system based on digital twinning, comprising a perception module, a positioning module, a vehicle control module, a communication module and a drive-by-wire chassis; wherein,

[0008] The perception module is used to perceive the traffic and environmental information of the road around the vehicle driving through sensors and send it to the vehicle control module;

[0009] The positioning module is used for the vehicle to determine its position in the environment;

[0010] The vehicle control module is used to complete: identity authentication after the vehicle starts; vehicle state safety detection; when the vehicle state is judged to be safe, according to the user's input destination, screening out an automatic driving application list for the user to select; according to the user's selection, sending the vehicle's own basic state information and driving state information to the cloud through the communication module, for the cloud to perform digital twinning simulation test on the user's selected automatic driving application, and receiving the simulation test result; if the simulation test passes, enter automatic driving, send the vehicle control signal to the drive-by-wire chassis, if the simulation test does not pass, re-screen an automatic driving application list for the user to select;

[0011] The drive-by-wire chassis is used to control the vehicle according to the control signal.

[0012] Further, the vehicle control module contains application function software configured based on the user's selection before the vehicle is completed.

[0013] Further, the identity authentication method includes establishing a connection between the vehicle end and the cloud, the user sending an identity ID and password to the cloud, and the cloud receiving and matching with the database.

[0014] Further, the vehicle safety detection includes checking whether each system of the vehicle is working normally and whether the connection between the vehicle end and the cloud is stable.

[0015] Further, the screened automatic driving application list includes automatic driving applications designed to run in areas covering the user's starting point and destination, and the characteristics of each automatic driving application.

[0016] Further, if no automatic driving application designed to run in areas covering the user's starting point and destination is screened out, an automatic driving application combination is screened out for the user to select, and for the user who selects the automatic driving application combination, the automatic driving application needs to be switched during driving.

[0017] Further, for the user who needs to switch the automatic driving application during driving, it is judged whether remote driving is needed, if the remote driving is needed, the automatic driving application is switched to the remote driving mode, if the remote driving is not needed, the automatic driving application is switched at the place where the vehicle is parked.

[0018] Further, the self basic state information of the vehicle includes the length, width and height of the vehicle and the unique identification code of the vehicle, and the driving state information of the vehicle includes the position, speed and acceleration of the vehicle.

[0019] Another aspect of the application provides a digital twin test method, which is set in the cloud and is used to assist the intelligent driving system, comprising:

[0020] The self basic state information and driving state information of the vehicle end are received and analyzed, and the effective information is stored as physical vehicle data information;

[0021] According to the physical vehicle data information, a virtual twin vehicle is constructed, and a digital twin simulation test is performed on the automatic driving application selected by the user in the virtual twin vehicle.

[0022] The third aspect of the application provides a digital twin test system, which is set in the cloud and comprises an information processing module, an information storage module and a digital twin simulation module; wherein,

[0023] The information processing module is used to receive and analyze the self basic state information and driving state information of the vehicle end;

[0024] The information storage module is used to analyze the self basic state information and driving state information of the vehicle end, store the effective information as physical vehicle data information, and input the digital twin simulation module;

[0025] The digital twin simulation module is used to construct a virtual twin vehicle according to the received physical vehicle data information, and perform a digital twin simulation test on the automatic driving application selected by the user using the virtual twin vehicle.

[0026] The beneficial effects of the present application are that the intelligent driving system based on digital twinning of the present application includes a perception module, a positioning module, a vehicle control module, a communication module and a drive-by-wire chassis, wherein the vehicle control module helps the user to complete the selection of the automatic driving application, and sends the information collected by the perception module and the positioning module to the cloud through the communication module, then completes the safety test of the automatic driving application through digital twinning simulation, and finally sends the control signal to the drive-by-wire chassis to control the driving of the vehicle. The present application can meet the user's demand to define the vehicle according to the user's own needs, and the user's autonomous selection of the automatic driving application not only fully utilizes the advantages of various enterprise model algorithms, but also realizes the creation of an automatic driving model suitable for various specific user groups, wherein the digital twinning simulation test of the automatic driving application ensures the safety, reliability and stability of the intelligent driving process of the vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0027] Figure 1 FIG. 1 is a schematic diagram of an intelligent driving system based on digital twinning according to an embodiment of the present application;

[0028] Figure 2 FIG. 2 is a schematic diagram of vehicle-cloud communication according to an embodiment of the present application;

[0029] Figure 3 FIG. 3 is a schematic diagram of a digital twinning test system according to an embodiment of the present application;

[0030] Figure 4 FIG. 4 is a flowchart of a digital twinning test method according to an embodiment of the present application;

[0031] Figure 5 FIG. 5 is a flowchart of the implementation function of the vehicle control module in the intelligent driving system according to an embodiment of the present application. DETAILED DESCRIPTION

[0032] Embodiment 1

[0033] The present embodiment provides an intelligent driving system based on digital twinning, as shown in FIG. 1, which includes a perception module, a positioning module, a vehicle control module, a communication module and a drive-by-wire chassis. Figure 1

[0034] Specifically, the perception module is used to perceive the road traffic environment information around the vehicle and send it to the vehicle control module. The perception module is usually composed of several sensing modules, and the arrangement of the sensing modules needs to consider various requirements to ensure that the vehicle can accurately perceive the surrounding environment and make safe and reliable decisions, such as multi-modal sensor cooperation, high precision and high reliability, redundancy design, real-time and low delay, and flexibility and scalability.

[0035] The positioning module is used to determine the position of the vehicle in the environment, and is usually selected from GPS or inertial navigation system, or a combination of the two. ​

[0036] The vehicle control module is used to help the user select an automatic driving application, to perform digital twin simulation testing on the automatic driving application selected by the user, and to output a control signal to the drive-by-wire chassis to control the vehicle after the testing is passed. If the testing is failed, the system reselects a list of automatic driving applications for the user. The function implementation process of the vehicle control module is as shown in Figure 5 .

[0037] The drive-by-wire chassis controls the driving behavior and necessary indicator lights of the vehicle, such as driving, gear, braking, steering, parking, etc., and controls the vehicle to give correct and timely state feedback.

[0038] Further, the automatic driving application selection function of the vehicle control module includes system recommendation and user free selection. Specifically, the steps include: starting the vehicle, and establishing a connection between the vehicle end and the cloud end; after the connection between the vehicle end and the cloud end is successfully established, the user sends a unique identity ID and a password to the cloud end, the cloud end performs database matching on the received user information, and creates a session for the user after the matching is successful; and sends a signal of successful access to the vehicle end as a starting condition for the vehicle to perform a safety self-check. The safety self-check of the vehicle includes checking whether each system of the vehicle is working normally and whether the connection between the vehicle end and the cloud end is stable, that is, whether the communication quality between the vehicle end and the cloud end is good, so as to ensure the safety and stability of the intelligent driving behavior; the vehicle obtains its own position information through a positioning device such as an inertial navigation system and a GPS; the vehicle uploads its own basic state information, including the length, width, height of the vehicle and the unique identification code of the vehicle, and driving state information, including position, speed and acceleration, to the cloud end; and the communication process between the vehicle end and the cloud end is as shown in Figure 2 .

[0039] Next, according to the destination input by the user on the vehicle-mounted human-computer interaction interface and the departure place of the user, the system automatically selects an automatic driving application suitable for the user. Specifically, the system selects a set of automatic driving applications covering the starting point and the destination of the user from the automatic driving application library as a list of available automatic driving applications for selection, which is displayed on the user interface. The characteristics of each automatic driving application are also displayed on the interface to help the user select an automatic driving application suitable for his own driving style. The characteristics of the automatic driving application include driving stability, high traffic efficiency, energy saving and low traffic cost. For example, the driving model of the automatic driving application with driving stability is mostly imitated and learned from the data of stable personality drivers with less speed increase and decrease and lane change, which is suitable for users who are prone to car sickness; the driving model of the automatic driving application with high traffic efficiency is mostly imitated and learned from the data of aggressive drivers, which is suitable for users who are in a hurry.

[0040] The user selects and installs the automatic driving application according to the own demand. If the system cannot screen the automatic driving application completely covering the entire running route of the user, the system recommends a combined automatic driving application to the user for screening. That is, the running route of the user is divided into different areas, and different automatic driving applications are recommended in different areas, so that the automatic driving application needs to be switched when the driving area is changed. At this time, the user selects whether the remote driving system needs to intervene. If not, the system screens the area where the vehicle can be parked temporarily, and then switches the automatic driving application. If yes, the remote driving system intervenes to complete the conversion of the automatic driving application.

[0041] By adopting the system architecture of the application, the user can select the interior and application function software in the intelligent driving function of the vehicle according to the own preference before the vehicle is assembled and produced. The automobile manufacturer provides the corresponding hardware configuration list according to the demand list provided by the user, and completes the assembly and production of the vehicle.

[0042] To ensure the safety of driving, and also to ensure the compatibility of software and hardware and the safety, reliability and stability during the running of the vehicle, the automatic driving application selected by the user is subjected to digital twin simulation test according to the vehicle information uploaded to the cloud by the vehicle end at the beginning.

[0043] Another aspect of the embodiment provides a digital twin test method for assisting the intelligent driving system. An interface between the virtual and real domains is designed between the vehicle end and the cloud end to complete the interaction and fusion of real data and virtual data. The virtual and real interaction system based on digital twin realizes the accurate simulation of the state of the real vehicle, the experimental environment, the sensor and the function running, so as to accurately predict the state of the real vehicle, and construct a corresponding virtual twin vehicle to complete the safety and stability test of the automatic driving application selected by the user.

[0044] Specifically, the digital twin test method includes the steps of receiving the vehicle basic state information of the vehicle end, including the length, width, height of the vehicle and the unique identification code of the vehicle, and the driving state information, including the position, speed and acceleration, analyzing the vehicle information, storing the effective information in the vehicle information as physical vehicle data information, accurately predicting the state of the entity vehicle according to the physical data information, and constructing a virtual twin vehicle to perform digital twin simulation test on the automatic driving application selected by the user, as shown in Figure 4 .

[0045] A third aspect of the embodiment provides a digital twin test system, as shown in Figure 3 , for assisting the intelligent driving system, which includes an information processing module, an information storage module and a digital twin simulation module.

[0046] Specifically, the information collection module is configured to receive vehicle self basic state information of the vehicle end, including vehicle length, width, height, and vehicle unique identification code, and driving state information, including position, speed, acceleration, etc., and analyze the information;

[0047] The information processing module is configured to build a corresponding traffic flow mathematical model according to the obtained information, complete correction of the mathematical model and corresponding data analysis, store effective information in the mathematical model as physical vehicle data information, and input the digital twin simulation module;

[0048] The digital twin simulation module is configured to build a geometric and kinematic model of the physical vehicle according to the received physical vehicle data information, accurately depict and map the real-time state of the entity unmanned vehicle, further construct a corresponding virtual twin vehicle, and use the virtual twin vehicle to perform digital twin simulation testing on the selected automatic driving application.

[0049] In summary, the present application provides an intelligent driving system based on digital twinning, which meets the user's self-definition of vehicle intelligent driving application function software according to their own needs, and provides the user with the function of freely selecting automatic driving applications while setting up digital twin simulation testing to ensure the safety and stability of the user's selected automatic driving application.

[0050] It should be understood that those skilled in the art can make improvements or changes according to the above description, and all these improvements and changes shall belong to the protection scope of the appended claims of the present application.

Claims

1. An intelligent driving system based on digital twinning, arranged at a vehicle end, characterized in that, It comprises a perception module, a positioning module, a vehicle control module, a communication module and a drive-by-wire chassis. The perception module is configured to perceive traffic and environmental information of a road around the vehicle through sensors and send the information to the vehicle control module. The positioning module is configured to determine the position of the vehicle in the environment. The vehicle control module is configured to perform identity authentication after the vehicle is started, perform safety detection of the vehicle state, select an automatic driving application list for the user to select according to the destination input by the user when the vehicle state is determined to be safe, send the basic state information and the driving state information of the vehicle to the cloud through the communication module according to the user's selection, perform digital twin simulation test on the automatic driving application selected by the user, receive the simulation test result, and if the simulation test is passed, enter the automatic driving mode and send the control signal of the vehicle to the drive-by-wire chassis, and if the simulation test is not passed, reselect an automatic driving application list for the user to select. The drive-by-wire chassis is configured to control the vehicle according to the control signal.

2. The digital-twin-based intelligent driving system according to claim 1, wherein, The vehicle control module comprises application function software configured based on the user's selection before the vehicle is assembled. 3.The digital-twin-based intelligent driving system of claim 1, wherein, The identity authentication method comprises establishing a connection between the vehicle and the cloud, sending an identity ID and a password to the cloud by the user, and matching the received information with a database by the cloud. 4.The digital-twin-based intelligent driving system of claim 1, wherein, The safety detection of the vehicle comprises checking whether each system of the vehicle is working normally and whether the connection between the vehicle and the cloud is stable.

5. The digital-twin-based intelligent driving system of claim 1, wherein, The selected automatic driving application list comprises automatic driving applications designed to run in an area covering the starting point and the destination of the user, and the characteristics of each automatic driving application.

6. The digital-twin-based intelligent driving system according to claim 5, wherein, If no automatic driving application designed to run in an area covering the starting point and the destination of the user is selected, an automatic driving application combination is selected for the user to select, and the user who selects the automatic driving application combination needs to switch the automatic driving application during the driving process.

7. The digital-twin-based intelligent driving system according to claim 6, wherein For the user who needs to switch the automatic driving application during the driving process, it is determined whether remote driving is needed, if the remote driving is needed, the automatic driving application is switched to the remote driving mode, and if the remote driving is not needed, the vehicle is parked at a convenient parking place to switch the automatic driving application. 8.The digital-twin-based intelligent driving system of claim 1, wherein, The basic state information of the vehicle comprises the length, width and height of the vehicle and the unique identification code of the vehicle, and the driving state information of the vehicle comprises the position, speed and acceleration of the vehicle.

9. A digital twin testing method for assisting the intelligent driving system of any one of claims 1-8, disposed in the cloud, characterized in that, It comprises: receiving and analyzing the basic state information and the driving state information of the vehicle, and storing the effective information as physical vehicle data information; constructing a virtual twin vehicle according to the physical vehicle data information, and performing digital twin simulation test on the automatic driving application selected by the user in the virtual twin vehicle.

10. A digital twin testing system for assisting the intelligent driving system of any one of claims 1-8, disposed in the cloud, characterized in that, It comprises an information processing module, an information storage module and a digital twin simulation module. The information processing module is configured to receive and analyze the basic state information and the driving state information of the vehicle. The information storage module is configured to store the effective information in the analyzed basic state information and driving state information of the vehicle as physical vehicle data information, and input the information into the digital twin simulation module. The digital twin simulation module is configured to construct a virtual twin vehicle according to the received physical vehicle data information, and perform digital twin simulation testing on the automatic driving application selected by the user using the virtual twin vehicle.

Images