Intelligent driving system based on digital twinning

Abstract

The invention provides an intelligent driving system based on digital twinning. The intelligent driving system comprises a sensing module, a positioning module, a vehicle control module, a communication module and a drive-by-wire chassis. Wherein the sensing module is used for sensing traffic and environment information of a surrounding road where a vehicle runs through a sensor and sending the traffic and environment information to the vehicle control module; the positioning module is used for determining the position of the vehicle in the environment; the vehicle control module is used for helping a user to select an automatic driving application, performing a digital twin simulation test on the automatic driving application selected by the user, if the simulation test is passed, entering automatic driving, and sending a control signal of a vehicle to the drive-by-wire chassis; and the drive-by-wire chassis is used for controlling the vehicle according to the control signal. According to the invention, the user can select the application software for intelligent driving according to own needs, and the safety and stability are ensured through the digital twinborn simulation test.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control and regulation systems, and in particular to an intelligent driving system based on digital twins. Background Art

[0002] With the development and improvement of deep learning technology and large-scale data processing capabilities, integrated autonomous driving solutions are gradually becoming the focus of the industry. By integrating multiple modules such as perception, decision-making and planning, this solution realizes the direct mapping from raw sensor data input to driving action output, significantly improving the system's joint optimization capabilities and computing efficiency.

[0003] Different companies may have data of different sizes, qualities, and differences, or they may use different algorithms and technical routes when developing large autonomous driving models. For example, 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 company's R&D investment and resources may also have an impact on the development of large models. Companies with more resources may be able to conduct more in-depth research and development, try more advanced technologies and architectures, or different companies may have different autonomous driving application scenarios and goals. Some companies may focus on specific areas or scenarios, such as urban transportation or highway driving. All of the above will affect the training and performance of the model.

[0004] Software-defined cars are an important concept in the automotive industry. The core idea is that software technology with artificial intelligence as the core determines the future direction of automobile development. With the trend of intelligentization and networking, cars are transforming from simple mechanical means of transportation to a new generation of mobile smart terminals. In the future, car users can freely choose autonomous driving software from different manufacturers according to their personal preferences. For example, for navigation maps, they can choose Baidu, Tencent or Google. As technology continues to mature and evolve, users can even assemble car hardware and download and integrate software according to their preferences, and then conduct real car testing through the digital twin system.

[0005] The existing technical solutions for software-defined cars in the prior art include patent CN202211197934.X or patent CN202210159920.2. The former only outlines the software-defined car process into five steps: demand determination, domain design, service development, test release, and continuous expansion, but does not elaborate on the vehicle safety testing method. The latter describes the design of the entire vehicle, which is more inclined to macro-car design, and lacks an explanation of how detailed system software defines the car. Therefore, there is an urgent need for an intelligent driving system based on digital twins. Summary of the invention

[0006] The technical problem to be solved by the present invention is: to provide an intelligent driving system based on digital twins, so that users can select application function software for intelligent driving and autonomous driving applications according to their own needs, and ensure driving safety through digital twin simulation tests.

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

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

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

[0010] The vehicle control module is used to complete: identity authentication after the vehicle is started; vehicle status safety detection; when the vehicle status is determined to be safe, a list of autonomous driving applications for the user to select is screened out according to the destination input by the user; according to the user's selection, the vehicle's own basic status information and driving status information are sent to the cloud through the communication module, so that the cloud can perform digital twin simulation tests on the autonomous driving application selected by the user and receive the simulation test results; if the simulation test passes, the autonomous driving is entered, and the vehicle control signal is sent to the wire-controlled chassis; if the simulation test fails, the list of autonomous driving applications for the user to select is screened out again;

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

[0012] Furthermore, the vehicle control module includes application function software that is configured based on user selection before the vehicle is fully assembled.

[0013] Furthermore, the identity authentication method includes establishing a connection between the vehicle and the cloud, the user sends an identity ID and password to the cloud, and the cloud receives and matches with the database.

[0014] Furthermore, the safety inspection of the vehicle includes checking whether each system of the vehicle is working properly and whether the connection between the vehicle and the cloud is stable.

[0015] Furthermore, the screened list of autonomous driving applications includes autonomous driving applications whose designed operating areas cover the user's starting point and destination, and the characteristics of each autonomous driving application.

[0016] Furthermore, if no autonomous driving application whose design operating area covers the user's starting point and destination is screened out, an autonomous driving application combination is screened out for the user to choose from. For users who choose the autonomous driving application combination, it is necessary to switch the autonomous driving application during driving.

[0017] Furthermore, for users who need to switch the autonomous driving application during driving, it is determined whether remote driving is required. If remote driving is required, the user switches to the remote driving mode to switch the autonomous driving application. If remote driving is not required, the user stops the vehicle at a convenient parking location to switch the autonomous driving application.

[0018] Furthermore, the basic status information of the vehicle itself includes the length, width, height and unique identification code of the vehicle, and the driving status information of the vehicle includes the position, speed and acceleration of the vehicle.

[0019] Another aspect of the present invention provides a digital twin testing method, which is set in the cloud and is used to assist the above-mentioned intelligent driving system, including:

[0020] Receive and parse the basic status information and driving status information of the vehicle, and store the valid information as physical vehicle data information;

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

[0022] A third aspect of the present invention provides a digital twin test system, which is arranged in the cloud and includes an information processing module, an information storage module and a digital twin simulation module; wherein:

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

[0024] The information storage module is used to analyze the basic status information and driving status information of the vehicle after analysis, store the valid information therein as physical vehicle data information, and input it into the digital twin simulation module;

[0025] The digital twin simulation module is used to build a virtual twin vehicle based on the received physical vehicle data information, and use the virtual twin vehicle to perform digital twin simulation testing on the autonomous driving application selected by the user.

[0026] The beneficial effects of the present invention are as follows: the intelligent driving system based on digital twins of the present invention includes a perception module, a positioning module, a vehicle control module, a communication module and a wire-controlled chassis, wherein the vehicle control module helps users complete the selection of autonomous driving applications, and sends the information collected by the perception module and the positioning module to the cloud through the communication module, and then completes the safety test of the autonomous driving application through digital twin simulation, and finally sends the control signal to the wire-controlled chassis to control the driving of the vehicle. The present invention can satisfy users to define vehicles according to their own needs. At the same time, users' independent selection of autonomous driving applications not only gives full play to the advantages of each enterprise's model algorithm, but also realizes the creation of autonomous driving models suitable for various specific user groups. The digital twin simulation test of the autonomous driving application ensures the safety, reliability and stability of the vehicle's intelligent driving process. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 Schematic diagram of an intelligent driving system based on digital twins according to an embodiment of the present invention;

[0028] Figure 2 A schematic diagram of communication between a vehicle and a cloud according to an embodiment of the present invention;

[0029] Figure 3 Schematic diagram of a digital twin testing system according to an embodiment of the present invention;

[0030] Figure 4 This is a flow chart of a digital twin testing method according to an embodiment of the present invention;

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

[0032] Example 1

[0033] This embodiment provides an intelligent driving system based on digital twins, the structure of which is as follows: Figure 1 As shown, it includes a perception module, a positioning module, a vehicle control module, a communication module and a wire-controlled chassis.

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

[0035] The positioning module is used by the car to determine its own position in the environment, usually using GPS or inertial navigation system, or a combination of the two.

[0036] The vehicle control module is used to help users select autonomous driving applications and conduct digital twin simulation tests on the autonomous driving applications selected by users. After the test passes, the control signal is output to the wire-controlled chassis to control the vehicle; if the test fails, the system will re-screen the list of autonomous driving applications for the user. The function implementation process of the vehicle control module is as follows: Figure 5 shown.

[0037] The drive-by-wire chassis controls the vehicle's driving, gear, braking, steering, parking and other driving behaviors and necessary indicator lights through the CAN bus, and controls the vehicle to give correct and timely status feedback.

[0038] Furthermore, the automatic driving application selection function of the vehicle control module includes system recommendation and user free selection. Specifically, the following steps are included: the vehicle is started, and the vehicle side applies to establish a connection with the cloud; after the connection between the vehicle side and the cloud side is successfully established, the user sends a unique identity ID and password to the cloud side, and the cloud side matches the received user information with the database, and creates the user's session after the match is successful; a successful access signal is sent to the vehicle side as a starting condition for the vehicle to perform a safety self-inspection. The vehicle safety self-inspection includes checking whether the vehicle systems are working normally and whether the connection between the vehicle side and the cloud side is stable, that is, whether the communication quality between the vehicle side and the cloud side is good, so as to ensure the safety and stability of intelligent driving behavior; the vehicle obtains its own location information through the inertial navigation, GPS and other positioning devices carried by it; the vehicle uploads its basic status information, including vehicle length, width, height, vehicle unique identification code and other information, and driving status information, including location, speed and acceleration and other information, to the cloud side, and the communication process between the vehicle side and the cloud side is as follows: Figure 2 shown.

[0039] Next, based on the destination entered by the user on the vehicle human-computer interaction interface and the user's starting point, the system automatically selects the autopilot application suitable for the user. Specifically, the system selects the autopilot application set that covers the user's starting point and destination from the autopilot application library, and displays it on the user human-computer interface as a list of available autopilot applications for selection. The interface also displays the characteristics of each autopilot application, so that the user can select the autopilot application that suits his or her driving style. The characteristics of the autopilot application include stable driving, high traffic efficiency, energy saving and low traffic cost. For example, the driving model of the autopilot application with stable driving is mostly imitated and learned from the data of drivers with stable driving, slow speed increase and decrease, and few lane changes, which is suitable for users whose passengers are prone to motion sickness; the driving model of the autopilot application with high traffic efficiency is mostly imitated and learned from the data of drivers who drive aggressively, which is suitable for users who are in urgent need of time.

[0040] Users select the autonomous driving application according to their own needs and then install it. If the system cannot filter out the autonomous driving application that completely covers the user's entire operating route, it will recommend a combination of autonomous driving applications for the user to filter. That is, the user's operating route is divided into different areas, and different autonomous driving applications are recommended in different areas. Therefore, when changing the driving area, it is necessary to switch the autonomous driving application. At this time, the user chooses whether the remote driving system needs to be intervened. If not, the system will select an area that is convenient for parking, temporarily park, and then switch the autonomous driving application. If necessary, the remote driving system will be intervened to complete the conversion of the autonomous driving application.

[0041] By adopting the system architecture of the present invention, users can choose the application function software of the interior and intelligent driving function of their own vehicles according to their preferences before the assembly and production of the vehicles. The automobile manufacturer provides a corresponding hardware configuration list based on the requirement list provided by the user to complete the assembly and production of the vehicles.

[0042] To ensure driving safety, as well as the compatibility of software and hardware and the safety, reliability and stability of the vehicle during operation, the autonomous driving applications selected by users will undergo digital twin simulation testing based on the vehicle information initially uploaded to the cloud by the vehicle.

[0043] Another aspect of this embodiment provides a digital twin testing method for assisting the above-mentioned intelligent driving system. An interface between the virtual and real domains is designed between the vehicle side and the cloud to complete the interaction and fusion of real data and virtual data. Based on the virtual-real interaction system of the digital twin, the state of the real vehicle, the experimental environment, the sensor, and the function operation are accurately simulated, so as to accurately predict the state of the real vehicle and build a corresponding virtual twin vehicle to complete the safety and stability test of the user's selected autonomous driving application.

[0044] Specifically, the digital twin testing method includes the following steps: receiving basic status information of the vehicle itself, including the length, width, height and unique identification code of the vehicle, and driving status information, including position, speed and acceleration, etc., parsing the vehicle information, storing the valid information therein as physical vehicle data information, accurately predicting the status of the physical vehicle according to the physical data information, thereby constructing a virtual twin vehicle, and performing digital twin simulation testing on the autonomous driving application selected by the user, such as Figure 4 shown.

[0045] A third aspect of this embodiment provides a digital twin test system, such as Figure 3 As shown, the intelligent driving system used to assist the above-mentioned driving includes an information processing module, an information storage module and a digital twin simulation module.

[0046] Specifically, the information collection module is used to receive the basic status information of the vehicle itself, including the length, width, height and unique identification code of the vehicle, and the driving status information, including the position, speed and acceleration, and analyze the information;

[0047] The information processing module is used to build the corresponding traffic flow mathematical model based on the acquired information, complete the modification of the mathematical model and the corresponding data analysis, store the effective information as physical vehicle data information, and input it into the digital twin simulation module;

[0048] The digital twin simulation module is used to establish geometric and kinematic models of the physical vehicle based on the received physical vehicle data information, accurately characterize and map the real-time status of the physical unmanned vehicle, and then build the corresponding virtual twin vehicle. The virtual twin vehicle is used to perform digital twin simulation tests on the selected autonomous driving application.

[0049] In summary, the present invention provides an intelligent driving system based on digital twins, which meets the needs of users to customize the vehicle intelligent driving application function software according to their own needs. While providing users with the function of freely choosing autonomous driving applications, digital twin simulation tests are set up to ensure the safety and stability of the autonomous driving applications selected by users.

[0050] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all these improvements and changes should fall within the scope of protection of the appended claims of the present invention.

Claims

1. An intelligent driving system based on digital twins, arranged on the vehicle side, characterized in that: It includes a perception module, a positioning module, a vehicle control module, a communication module and a wire-controlled chassis; among which, The sensing module is used to sense the traffic and environmental information of the road around the vehicle through sensors and send it to the vehicle control module; The positioning module is used by the vehicle to determine its own position in the environment; The vehicle control module is used to complete: identity authentication after the vehicle is started; vehicle status safety detection; when the vehicle status is determined to be safe, a list of autonomous driving applications for the user to select is screened out according to the destination input by the user; according to the user's selection, the vehicle's own basic status information and driving status information are sent to the cloud through the communication module, so that the cloud can perform digital twin simulation tests on the autonomous driving application selected by the user and receive the simulation test results; if the simulation test passes, the autonomous driving is entered, and the vehicle control signal is sent to the wire-controlled chassis; if the simulation test fails, the list of autonomous driving applications for the user to select is screened out again; The control-by-wire chassis is used to control the vehicle according to the control signal.

2. The digital twin-based intelligent driving system according to claim 1, characterized in that: The vehicle control module includes application function software that is configured based on user selections before the vehicle is fully assembled.

3. The digital twin-based intelligent driving system according to claim 1, characterized in that: The identity authentication method includes establishing a connection between the vehicle and the cloud, the user sending an identity ID and password to the cloud, and the cloud matching with the database after receiving.

4. The digital twin-based intelligent driving system according to claim 1, characterized in that: The vehicle safety inspection includes checking whether the vehicle systems are working properly and whether the connection between the vehicle and the cloud is stable.

5. The digital twin-based intelligent driving system according to claim 1, characterized in that: The screened list of autonomous driving applications includes autonomous driving applications whose designed operating areas cover the user's starting point and destination, and the characteristics of each autonomous driving application.

6. The digital twin-based intelligent driving system according to claim 5, characterized in that: If no autonomous driving application whose design operating area covers the user's starting point and destination is screened out, a combination of autonomous driving applications will be screened out for the user to choose from. For users who choose the combination of autonomous driving applications, they need to switch autonomous driving applications during driving.

7. The digital twin-based intelligent driving system according to claim 6, characterized in that: For users who need to switch to the autonomous driving application during driving, determine whether remote driving is required. If remote driving is required, switch to the remote driving mode to switch to the autonomous driving application. If remote driving is not required, stop the car at a convenient parking location to switch to the autonomous driving application.

8. The digital twin-based intelligent driving system according to claim 1, characterized in that: The basic status information of the vehicle includes the length, width, height and unique identification code of the vehicle, and the driving status information of the vehicle includes the position, speed and acceleration of the vehicle.

9. A digital twin testing method for assisting the intelligent driving system according to any one of claims 1 to 8, arranged in the cloud, characterized in that: include: Receive and parse the basic status information and driving status information of the vehicle, and store the valid information as physical vehicle data information; A virtual twin vehicle is constructed based on the physical vehicle data information, and a digital twin simulation test is performed on the autonomous driving application selected by the user in the virtual twin vehicle.

10. A digital twin test system for assisting the intelligent driving system according to any one of claims 1 to 8, arranged in the cloud, characterized in that: It includes information processing module, information storage module and digital twin simulation module; among which, The information processing module is used to receive the basic status information and driving status information of the vehicle end and analyze them; The information storage module is used to analyze the basic status information and driving status information of the vehicle after analysis, store the valid information therein as physical vehicle data information, and input it into the digital twin simulation module; The digital twin simulation module is used to construct a virtual twin vehicle based on the received physical vehicle data information, and use the virtual twin vehicle to perform a digital twin simulation test on the autonomous driving application selected by the user.

Images