Intelligent networked vehicle formation test method based on digital twin virtual-real combination

Abstract

The invention relates to an intelligent networked vehicle formation test method based on digital twin virtual-real combination, and belongs to the field of automatic driving test. The method comprises the following steps: collecting traffic road map data, and constructing a digital twin virtual traffic scene; constructing an intelligent networked vehicle formation model, and loading the intelligent networked vehicle formation model into a digital twin system; the virtual traffic scene is transmitted to the driver in-the-loop simulation device, and the artificial driver controls the artificial driving simulation vehicle according to the virtual traffic scene, thereby realizing simulation of the artificial driving vehicle; the intelligent network connection vehicle formation model generates a control instruction of the automatic driving simulation vehicle based on the driving track of the artificial driving simulation vehicle, and sends the control instruction to the miniature vehicle for real vehicle verification; and collecting simulation data of the digital twin system and real vehicle data of the miniature vehicle for analysis, and verifying the validity of the intelligent network connection vehicle formation model. According to the invention, the problem of difficulty in interactive simulation of a manual driving vehicle and an automatic driving vehicle is solved, and the authenticity is high.

Description

Technical Field

[0001] The present invention belongs to the field of autonomous driving testing and relates to a method for testing a formation of intelligent networked vehicles based on the combination of virtual and real aspects of digital twins. Background Art

[0002] Before self-driving cars can be truly commercialized, a large number of road tests are required to meet commercial requirements. However, traditional road tests consume a lot of manpower and material resources, which may cause vehicle damage and personal injury, and it is difficult to ensure economic efficiency and safety. With the improvement of simulation technology and software and hardware performance, self-driving simulation has gradually become a key link in testing the performance of self-driving systems. Large-scale self-driving simulation technology relies on high-performance computing platforms, with the help of scenarios and vehicle configurations provided by self-driving simulators, to complete closed-loop simulation tests of self-driving systems, making the research and development of self-driving more efficient and economical. However, due to the lack of authenticity, single simulation tests are difficult to implement commercially.

[0003] The existing virtual-reality test platform for autonomous driving vehicles places a real autonomous driving vehicle in a real road environment during the test process, injects virtual traffic targets into the autonomous driving system through the test platform, and then drives the autonomous driving vehicle to make corresponding actions, such as avoidance, acceleration and deceleration, so as to achieve virtual-reality test for autonomous driving vehicles. Compared with single real vehicle testing and simulation testing, the scenario configuration of virtual-reality test is more flexible, the scenario coverage is high, the test process is safe, and automatic testing and cloud-based accelerated testing can be realized, which is conducive to improving test efficiency and reducing test costs. In addition, based on the digital scene of digital twins, the feasibility and authenticity of test experiments are higher.

[0004] In the prior art, for example, patent application CN118212779A discloses a mixed traffic flow testing method and system based on the combination of digital twins and virtual reality, but the real human-driven vehicles involved are offline data generated through the cockpit, not online, and cannot make corresponding changes according to the actual traffic scene. Another example is patent application CN116755954A discloses an automatic driving test system and its testing method based on the combination of digital twins and virtual reality, but the virtual traffic elements it uses are generated by algorithms and cannot simulate mixed traffic scenes. In addition, the current verification of the guidance algorithm for human-driven vehicles to networked vehicles remains at the simulation verification level, and there is a lack of a virtual-reality testing method. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a smart connected vehicle formation testing method based on the combination of digital twins and virtual and real, to construct a mixed traffic scenario including human-driven vehicles and self-driving cars, and to realize the simulation and testing of self-driving algorithms in a mixed traffic environment.

[0006] To achieve the above objectives, the present invention provides, on one hand, a method for testing a platoon of intelligent connected vehicles based on a combination of digital twins and virtual reality, the method comprising:

[0007] S1. Collect traffic road map data and build digital twin virtual traffic scenes;

[0008] S2. Build an intelligent networked vehicle formation model and load it into the digital twin system. The intelligent networked vehicle formation model is used to control the autonomous driving simulation vehicles to travel in formation under the guidance of the manually driven simulation vehicles.

[0009] S3, transmitting the virtual traffic scene to the driver-in-the-loop simulation device, and the human driver taking corresponding operations in the driver-in-the-loop simulation device according to the virtual traffic scene to control the human-driven simulation vehicle, thereby simulating the human-driven vehicle;

[0010] S4. The intelligent connected vehicle platoon model generates control instructions for the autonomous driving simulation vehicle based on the driving trajectory of the manually driven simulation vehicle, and sends the control instructions to the miniature vehicle for real vehicle verification;

[0011] S5. Collect simulation data of the digital twin system and real vehicle data of the miniature vehicle for analysis to verify the effectiveness of the intelligent connected vehicle platoon model. The evaluation indicators include the stability of the platoon driving, response time, and obstacle avoidance capability.

[0012] Furthermore, in step S5, the collected simulation data of the digital twin system includes vehicle planning trajectory information and vehicle actual operation trajectory information, and the collected real vehicle data of the miniature vehicle includes control command information and miniature vehicle trajectory information.

[0013] Among them, the vehicle planning trajectory information is the trajectory planning of the autonomous driving simulation vehicle generated by the intelligent connected vehicle formation model according to the actions of the manually driven simulation vehicle; the vehicle actual operation trajectory information is the operation trajectory generated by the autonomous driving simulation vehicle running according to the planned trajectory.

[0014] Furthermore, the miniature vehicle is a WHEELTEC ROS car, which transmits and receives information through a WiFi module.

[0015] On the other hand, the present invention provides an intelligent networked vehicle formation test system based on the combination of digital twin virtual and real, the system comprising:

[0016] The digital twin scene generation module builds virtual traffic scenes based on the collected traffic road map data;

[0017] A manual driving vehicle simulation module receives and displays virtual traffic scene data, and controls the simulated vehicle according to the virtual traffic scene through a manual driver to simulate manual driving in the digital twin scene;

[0018] The intelligent connected vehicle platoon module controls the driving of the autonomous driving simulation vehicle platoon according to the driving trajectory of the manually driven simulation vehicle in the virtual traffic scene, plans the driving trajectory of the autonomous driving simulation vehicle in the virtual traffic scene and generates control instructions;

[0019] A miniature vehicle test module receives and executes control instructions generated by the intelligent connected vehicle platooning module; and

[0020] The analysis and verification module receives and analyzes the simulation data from the digital twin scenario generation module and the real vehicle data from the miniature vehicle test module to verify the effectiveness of the formation control algorithm carried by the intelligent connected vehicle formation module.

[0021] Furthermore, the miniature car test module includes multiple WHEELTEC ROS cars, each of which is equipped with a WiFi module to achieve communication connection.

[0022] The beneficial effects of the present invention are as follows: the present invention constructs a mixed traffic scenario including human-driven vehicles and self-driving cars through a driver-in-the-loop simulation device and a digital twin system, and realizes the simulation and testing of the self-driving algorithm based on human-driven vehicle guidance in a mixed traffic environment, which greatly reduces the number of drivers, saves expenses, solves the problem of difficult interaction simulation between human-driven vehicles and self-driving vehicles, and has high authenticity. The formation control algorithm tested and verified by the present invention can be applied to traffic application scenarios such as bulk logistics that have a strong demand for high-level self-driving, such as realizing a driver driving an L2 pilot vehicle to lead multiple L4 self-driving trucks, and can automatically complete operations such as teaming, leaving the team, changing lanes, etc., and can flexibly shuttle between social vehicles.

[0023] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0025] Figure 1 A schematic diagram of a flow chart of a method proposed in one embodiment of the present invention;

[0026] Figure 2 A structural block diagram of a system proposed in one embodiment of the present invention;

[0027] Figure 3 A schematic diagram of a virtual traffic scene constructed for an embodiment of the present invention;

[0028] Figure 4 This is the structural diagram of the intelligent connected vehicle platooning algorithm;

[0029] Figure 5 Schematic diagram for simulating lane changes of manually driven vehicles and autonomous driving vehicles;

[0030] Figure 6 It is the formal parameter of the miniature vehicle under the control command. DETAILED DESCRIPTION

[0031] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0032] Example 1

[0033] This embodiment proposes a method for testing a platoon of intelligent connected vehicles based on the combination of digital twins and virtual reality. Figure 1 As shown, the method mainly includes:

[0034] 1. Collect actual road scene map data and build a digital twin virtual traffic scene. Traffic participants in the scene can exhibit different behavior states, such as normal, aggressive, and conservative, which are used to simulate the diversity in actual traffic. Traffic scenes can include campuses, cities, and highways to ensure the diversity and authenticity of the scenes.

[0035] 2. Construct an intelligent connected vehicle platoon model, so that in the digital twin virtual traffic scene, the autonomous driving simulation vehicles can travel in platoons under the guidance of the manually driven simulation vehicles, and the autonomous driving simulation vehicles can dynamically adjust their driving trajectories according to the guidance of the manually driven simulation vehicles.

[0036] Among them, in order to realize simulated manual driving, this embodiment adopts a driver-in-the-loop simulation device, which can communicate data with the digital twin system, receive and display the constructed virtual traffic scene, and then manually operate the simulated vehicle in real time in the device cockpit according to the virtual traffic scene, thereby simulating manual driving of the vehicle.

[0037] 3. Load the intelligent networked vehicle formation model into the digital twin system and test the model. Specifically, based on the driving trajectory of the artificially driven simulated vehicle in the virtual traffic scene, the intelligent networked vehicle formation model generates the path planning of the autonomous driving simulated vehicle and generates the control instructions (throttle, brake, steering angle, etc.) of the autonomous driving simulated vehicle.

[0038] 4. Send the control instructions generated by the intelligent connected vehicle platoon model to the miniature vehicle for actual vehicle testing.

[0039] 5. Analyze the data obtained from the digital twin virtual traffic scene and the actual vehicle test process, and verify through data analysis whether the performance of the intelligent connected vehicle platooning algorithm meets the predetermined compliance conditions. The main evaluation indicators include the stability of the platoon driving, response time and obstacle avoidance capability.

[0040] In addition, the digital twin system and the intelligent connected vehicle formation model both run on the computer, and the computer and the miniature vehicles are connected through a WiFi module.

[0041] Example 2

[0042] This embodiment proposes an intelligent connected vehicle platoon testing system based on the combination of digital twins and virtual reality. Figure 2 As shown, it includes a digital twin scenario generation module, an intelligent networked vehicle formation module, a real vehicle test module, a manually driven vehicle simulation module, and an analysis and verification module. Among them, the digital twin scenario generation module is respectively connected to the intelligent networked vehicle formation module, the manually driven vehicle simulation module, and the intelligent networked vehicle formation module, the real vehicle test module is connected to the intelligent networked vehicle formation module, and the analysis and verification module is respectively connected to the digital twin scenario generation module and the real vehicle test module.

[0043] The digital twin scene generation module is used to collect data on real-world traffic roads and construct virtual traffic scenes. Traffic participants in the scene can exhibit different behavior states, such as normal, aggressive, and conservative, which are used to simulate the diversity in actual traffic. Traffic scenes can include campuses, cities, and highways to ensure the diversity and authenticity of the scenes.

[0044] The intelligent networked vehicle formation module is used to realize the formation of the autonomous driving simulation vehicle formation, so that the autonomous driving simulation vehicle can dynamically adjust the driving trajectory according to the guidance of the manually driven simulation vehicle. The core of this module is the formation control algorithm, which can adjust the driving decision of the formation vehicle in real time according to the state change of the leading vehicle, and generate control instructions for the autonomous driving vehicle, such as brake, throttle, steering angle, etc.

[0045] The real vehicle test module sends the control instructions generated by the intelligent networked vehicle formation module to the miniature vehicle for real vehicle testing. This module is used to verify the performance and effectiveness of the algorithm in actual traffic scenarios to ensure that the simulation results can be achieved in a real environment.

[0046] The manually driven vehicle simulation module receives and displays the virtual traffic scene generated by the digital twin scene generation module. The manual driver makes corresponding driving actions according to the virtual traffic scene to control the manually driven simulation vehicle, and feeds back the driving actions to the digital twin scene generation module.

[0047] The analysis and verification module receives data from the digital twin scenario generation module and the real vehicle test module, and verifies whether the performance of the autonomous driving algorithm meets the predetermined standard conditions through data analysis. The main evaluation indicators include the stability of platoon driving, response time, and obstacle avoidance capabilities. Among them, the collected simulation data includes vehicle planning trajectory information and vehicle actual operation trajectory information, and the collected real vehicle data includes control command information and miniature vehicle trajectory information.

[0048] Example 3

[0049] This embodiment describes the present invention in detail based on Embodiment 1 and Embodiment 2:

[0050] First, a campus road map is collected. The campus road is a three-lane straight road with a length of 500m. A digital twin virtual traffic scene is constructed based on the campus road. At the same time, a stationary vehicle is set at 100m in the middle lane in the virtual traffic scene. Figure 3 In the virtual traffic scene shown, the white vehicle is a manually driven vehicle, the red vehicle is a stationary vehicle (as a faulty vehicle), and the black vehicle is an autonomous driving vehicle. The manually driven vehicle is controlled by a driver-in-the-loop simulation device, while the autonomous driving vehicle is controlled by an intelligent connected vehicle platoon model.

[0051] Secondly, a smart connected vehicle platoon model is established to output control instructions for autonomous driving simulation vehicles. The smart connected vehicle platoon model is loaded into the digital twin system, the model is tested, and vehicle control instructions (brake, throttle, steering angle) are generated in real time based on trajectory planning data.

[0052] like Figure 4As shown in the figure, in the intelligent connected vehicle platoon model, the expected acceleration is first calculated according to the preset driving conditions and environmental factors to ensure that the vehicle receives the optimal control command in the current state. The calculated expected acceleration is compared with the actual acceleration of the vehicle, and the throttle or brake command is accurately adjusted through comparison to make the actual acceleration as close to the expected value as possible. In addition, the vehicle's position and driving trajectory are updated in real time through data from the global positioning system and other sensors, so as to calculate the appropriate steering angle to ensure that the vehicle maintains a stable driving path in complex road conditions.

[0053] Then, the control instructions generated by the intelligent connected vehicle platoon model are sent to the miniature vehicle for real vehicle testing. The miniature vehicle is a WHEELTEC ROS car that sends and receives information through a WiFi module.

[0054] Finally, collect simulation data and real vehicle data to analyze model performance. The collected simulation data includes vehicle planning trajectory information and vehicle actual running trajectory information. The vehicle planning trajectory information is the trajectory planning of the autonomous driving simulation vehicle generated by the intelligent connected vehicle formation model according to the actions of the artificial driving simulation vehicle, which is the predicted trajectory. The vehicle actual running trajectory information is the running trajectory generated by the autonomous driving simulation vehicle according to the planned trajectory. There is an error between the two. The real vehicle data includes control command information and miniature vehicle trajectory information.

[0055] The experimental results are as follows:

[0056] like Figure 5 As shown in the figure, the white vehicle is a manually driven vehicle simulated by the driver in the loop. After finding the obstacle vehicle, it immediately changes lanes. The connected autonomous driving vehicle behind it follows the white vehicle to achieve platoon lane change. Figure 6 The figure shows the driving parameters of the miniature vehicle under the control command. It can be seen that the miniature vehicle has executed the lane changing operation according to the control command.

[0057] The test results show that in the simulation scenario, the connected vehicle achieved a good following effect. In the actual vehicle test, the miniature vehicle performed lane changing operations according to the control instructions.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. A method for testing intelligent connected vehicle platooning based on digital twin virtual and real integration, characterized in that: The method includes: Collect traffic road map data and build digital twin virtual traffic scenes; Constructing an intelligent networked vehicle platoon model and loading it into the digital twin system, wherein the intelligent networked vehicle platoon model is used to control the autonomous driving simulation vehicles to travel in platoon under the guidance of the manually driven simulation vehicles; The virtual traffic scene is transmitted to the driver-in-the-loop simulation device, and the human driver takes corresponding operations in the driver-in-the-loop simulation device according to the virtual traffic scene to control the human-driven simulation vehicle, thereby simulating the human-driven vehicle; The intelligent networked vehicle formation model generates control instructions for the autonomous driving simulation vehicle based on the driving trajectory of the manually driven simulation vehicle, and sends the control instructions to the miniature vehicle for real vehicle verification; The simulation data of the digital twin system and the real vehicle data of the miniature vehicle are collected and analyzed to verify the effectiveness of the intelligent connected vehicle platoon model.

2. The method according to claim 1, characterized in that The simulation data collected for the digital twin system includes vehicle planning trajectory information and vehicle actual operation trajectory information, and the real vehicle data collected for the miniature vehicle includes control instruction information and miniature vehicle trajectory information; wherein, the vehicle planning trajectory information is the trajectory planning of the autonomous driving simulation vehicle generated by the intelligent connected vehicle formation model according to the actions of the manually driven simulation vehicle; the vehicle actual operation trajectory information is the operation trajectory generated by the autonomous driving simulation vehicle according to the planned trajectory.

3. The method according to claim 1 or 2, characterized in that: The simulation data of the digital twin system and the actual vehicle data of the miniature vehicle are analyzed to verify the effectiveness of the intelligent connected vehicle platoon model. The evaluation indicators include the stability of the platoon driving, the response time and the obstacle avoidance capability.

4. The method according to claim 1 or 2, characterized in that: The miniature vehicle is a WHEELTEC ROS car, which sends and receives information through a WiFi module.

5. An intelligent connected vehicle platoon testing system based on digital twin virtual and real integration, characterized in that: The system includes: The digital twin scene generation module builds virtual traffic scenes based on the collected traffic road map data; A manual driving vehicle simulation module receives and displays virtual traffic scene data, and controls the simulated vehicle according to the virtual traffic scene through a manual driver to simulate manual driving in the digital twin scene; The intelligent connected vehicle platoon module controls the driving of the autonomous driving simulation vehicle platoon according to the driving trajectory of the manually driven simulation vehicle in the virtual traffic scene, plans the driving trajectory of the autonomous driving simulation vehicle in the virtual traffic scene and generates control instructions; A miniature vehicle test module receives and executes control instructions generated by the intelligent connected vehicle platooning module; and The analysis and verification module receives and analyzes the simulation data from the digital twin scenario generation module and the real vehicle data from the miniature vehicle test module to verify the effectiveness of the formation control algorithm carried by the intelligent connected vehicle formation module.

6. The system according to claim 5, characterized in that The miniature car test module includes multiple WHEELTECROS cars, each of which is equipped with a WiFi module to achieve communication connection.

7. The system according to claim 5, characterized in that The simulation data of the digital twin system includes vehicle planning trajectory information and vehicle actual operation trajectory information, and the real vehicle data of the miniature vehicle includes control command information and miniature vehicle trajectory information; The vehicle planning trajectory information is the trajectory planning of the autonomous driving simulation vehicle generated by the intelligent connected vehicle formation model according to the actions of the manually driven simulation vehicle; the vehicle actual operation trajectory information is the operation trajectory generated by the autonomous driving simulation vehicle according to the planned trajectory.

8. The system according to claim 5 or 7, characterized in that: The effectiveness of the platoon control algorithm is verified by analyzing the simulation data of the digital twin system and the actual vehicle data of the miniature vehicle. The evaluation indicators include the stability of the platoon driving, the response time and the obstacle avoidance capability.

Images