A vehicle-road collaboration application scenario testing method and system

Abstract

The present invention discloses a vehicle-road cooperative application scenario testing method and system, which relates to the field of intelligent transportation technology, including: in vehicle-road cooperative applications, multiple sensors are deployed on vehicles to collect multi-source vehicle data in real time; the multi-source vehicle data is integrated using the parallel processing capabilities of quantum computing; a virtual test environment is constructed on a high-performance computing platform based on the integrated data; testing is performed in the virtual test environment, and real-time monitoring is initiated to automatically identify abnormal situations that occur during the test through an abnormality algorithm; and an intelligent intervention and error correction mechanism is automatically initiated based on the detected abnormal results. By introducing the parallel processing capabilities of quantum computing and advanced anomaly detection algorithms, the present invention significantly improves the perception and decision-making capabilities of vehicles in complex traffic environments, and demonstrates strong advantages in practical applications.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a vehicle-road collaborative application scenario testing method and system. Background Art

[0002] Vehicle-road cooperative technology has made significant progress in recent years, especially in multi-sensor data fusion, virtual environment construction and intelligent decision-making. Traditional vehicle-road cooperative systems usually rely on multiple sensors to collect data on the vehicle's surrounding environment in real time, and generate a unified environmental perception model through data fusion algorithms. However, existing data fusion technologies have certain limitations when processing large amounts of real-time data, especially in terms of data processing speed and accuracy. In addition, although existing virtual test environments can simulate some traffic scenarios, their realism and real-time performance in complex environments still need to be improved. In addition, traditional anomaly detection algorithms are prone to false detection and missed detection when faced with complex and changeable traffic scenarios, resulting in inaccurate intelligent intervention measures.

[0003] To overcome the above-mentioned shortcomings, quantum computing technology has attracted widespread attention in recent years due to its outstanding parallel processing capabilities. Quantum computing can significantly improve data processing speed and accuracy, showing great potential in the fusion of multi-source vehicle data. In addition, quantum computing can also be used to optimize virtual environment construction and anomaly detection algorithms, thereby improving the robustness and real-time response capabilities of the system. Based on these, the present invention proposes a method for data fusion using quantum computing and, on this basis, constructing a high-precision virtual test environment, which solves the problems of slow data processing speed, inaccurate environment simulation, and inaccurate anomaly detection in the existing technology. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a vehicle-road cooperative application scenario testing method and system to solve the problem of efficient fusion of multi-source vehicle data in vehicle-road cooperative applications.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides a method for testing a vehicle-road cooperative application scenario, which includes: in a vehicle-road cooperative application, deploying multiple sensors on a vehicle to collect multi-source data of the vehicle in real time; utilizing the parallel processing capability of quantum computing to fuse the multi-source data of the vehicle; building a virtual test environment on a high-performance computing platform based on the fused data; conducting tests in the virtual test environment, and starting real-time monitoring to automatically identify abnormal situations occurring during the test through an abnormality algorithm; automatically starting an intelligent intervention and error correction mechanism based on the detected abnormal results; after completing the error correction mechanism, continuing to execute the test task, and analyzing the data during the test to make optimizations.

[0008] As a preferred solution of the vehicle-road cooperative application scenario testing method of the present invention, wherein: in the vehicle-road cooperative application, multiple sensors are deployed on the vehicle to collect multi-source data of the vehicle in real time. The specific steps are:

[0009] To achieve comprehensive perception of the vehicle's surrounding environment, multiple sensors are deployed, including millimeter-wave radar, lidar, high-definition cameras, global positioning and inertial measurement units;

[0010] Sensors are installed at different locations on the vehicle to cover a 360-degree field of view, and the sampling frequency is configured to continuously collect multi-source data from the vehicle, including obstacle location, obstacle speed, obstacle direction, traffic signal status, vehicle location, vehicle speed, vehicle direction, and vehicle acceleration.

[0011] As a preferred solution of the vehicle-road cooperative application scenario testing method of the present invention, wherein: the parallel processing capability of quantum computing is used to fuse vehicle multi-source data. The specific steps are:

[0012] Transmit the collected multi-source vehicle data to a fusion center based on quantum computing via the 5G high-speed communication network;

[0013] After receiving the multi-source vehicle data, the fusion center pre-processes the multi-source vehicle data;

[0014] Mapping the pre-processed vehicle multi-source data into quantum state data through quantum coding;

[0015] The superposition and entanglement characteristics of quantum algorithms are used to fuse quantum state data to generate a fused quantum state.

[0016] As a preferred solution of the vehicle-road cooperative application scenario testing method of the present invention, wherein: based on the fused data, a virtual test environment is constructed on a high-performance computing platform, and the specific steps are:

[0017] Obtain weather data through external meteorological services, local environmental information through roadside units in the vehicle-road cooperative infrastructure, and road characteristics through geographic information;

[0018] Integrate weather data, local environmental information, and road characteristics into an environmental parameter set through data formatting and time synchronization;

[0019] Receive the fused quantum state and environmental parameter set through the high-performance computing platform and execute the environment construction task;

[0020] The high-performance computing platform analyzes the fused quantum state through quantum measurement, extracts the dynamic and static characteristics of the quantum state, and adjusts the vehicle's dynamic behavior based on the environmental parameter set;

[0021] Through numerical simulation based on the fused quantum state and environmental parameter set, the dynamic behavior of the vehicle is simulated using the adjusted vehicle dynamic behavior to generate the interaction results between the vehicle and the environment;

[0022] The high-performance computing platform normalizes the interaction results between the vehicle and the environment, balances the contribution ratio of the fused quantum state and the environmental parameter set, and generates a virtual test environment.

[0023] As a preferred solution of the vehicle-road cooperative application scenario testing method of the present invention, the test is performed in a virtual test environment, and real-time monitoring is started to automatically identify abnormal situations that occur during the test through an abnormal algorithm. The specific steps are:

[0024] In the constructed virtual test environment, simulate real driving scenarios and test vehicle behavior responses;

[0025] Real-time monitoring is enabled, and anomalies that arise during testing are automatically identified through a machine learning-based anomaly detection algorithm, including abnormal vehicle behavior, abnormal sensor readings, environmental perception errors, communication failures, and decision logic errors.

[0026] As a preferred solution of the vehicle-road cooperative application scenario testing method of the present invention, wherein: the intelligent intervention and error correction mechanism is automatically started according to the detected abnormal results, the specific steps are:

[0027] If an abnormal situation is detected during the virtual test environment, intelligent intervention measures will be triggered, including adjusting vehicle behavior patterns, replanning driving routes, slowing down and stopping, steering avoidance, light and sound warnings, emergency communication, switching to autonomous driving mode, and activating backup sensors.

[0028] As a preferred solution of the vehicle-road cooperative application scenario testing method of the present invention, after the error correction mechanism is completed, the test task is continued to be executed, and the data during the test process is analyzed and optimized. The specific steps are:

[0029] Continue to perform the test task and define a series of performance indicators;

[0030] Use statistical methods to evaluate the stability and reliability of test results;

[0031] Apply cluster analysis to identify patterns and trends in test data;

[0032] Explore the reasons behind test results through cause-and-effect diagrams;

[0033] Generate optimization suggestions for test plans and vehicle control platforms based on analysis results;

[0034] Apply the optimization recommendations to a new test cycle, perform virtual testing again, and record the results to compare the differences before and after optimization.

[0035] In the second aspect, the present invention provides a vehicle-road cooperative application scenario testing system, including a data acquisition module, a data fusion module, a virtual environment construction module, a test monitoring module, an intelligent intervention and error correction module and an analysis and optimization module; the data acquisition module is used to deploy multiple sensors on the vehicle in the vehicle-road cooperative application to collect multi-source data of the vehicle in real time; the data fusion module is used to utilize the parallel processing capability of quantum computing to fuse multi-source data of the vehicle; the virtual environment construction module is used to build a virtual test environment on a high-performance computing platform based on the fused data; the test monitoring module is used to perform testing in the virtual test environment, and start real-time monitoring to automatically identify abnormal situations occurring during the test through an abnormality algorithm; the intelligent intervention and error correction module is used to automatically start the intelligent intervention and error correction mechanism according to the detected abnormal results; the analysis and optimization module is used to continue to execute the test task after completing the error correction mechanism, and analyze the data during the test and make optimizations.

[0036] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the vehicle-road collaborative application scenario testing method as described in the first aspect of the present invention is implemented.

[0037] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, wherein: when the computer program is executed by a processor, it implements any step of the vehicle-road cooperative application scenario testing method as described in the first aspect of the present invention.

[0038] The beneficial effects of the present invention are: by utilizing the parallel processing capabilities of quantum computing to fuse multi-source vehicle data, the speed and accuracy of data processing are significantly improved. The quantum algorithm not only speeds up the data fusion process, but also ensures the consistency and integrity of the fused data by mapping sensor data into quantum states and performing efficient calculations. This efficient quantum data fusion method reduces data processing delays, enhances the realism and dynamic response capabilities of the virtual test environment, and enables the test environment to more quickly reflect changes in the real world. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 This is a flowchart of the vehicle-road collaboration application scenario testing method in Example 1.

[0041] Figure 2 This is a flow chart for analyzing and optimizing the data during the test process in Example 1. DETAILED DESCRIPTION

[0042] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0043] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0044] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0045] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a method for testing a vehicle-road collaboration application scenario, including the following steps:

[0046] S1. In vehicle-road collaborative applications, multiple sensors are deployed on vehicles to collect multi-source vehicle data in real time.

[0047] Furthermore, to achieve comprehensive perception of the vehicle's surrounding environment, multiple sensors are deployed, including millimeter-wave radar, lidar, high-definition cameras, global positioning and inertial measurement units;

[0048] Sensors are installed at different locations on the vehicle to cover a 360-degree field of view, and the sampling frequency is configured to continuously collect multi-source data from the vehicle, including obstacle location, obstacle speed, obstacle direction, traffic signal status, vehicle location, vehicle speed, vehicle direction, and vehicle acceleration.

[0049] It should be noted that in vehicle-road collaborative applications, all-round perception of the vehicle's surrounding environment is achieved by deploying a variety of sensors including millimeter-wave radar, lidar, high-definition cameras, global positioning systems and inertial measurement units; these sensors are strategically installed in different positions of the vehicle to ensure 360-degree coverage without blind spots, and continuously collect information such as the location, speed and direction of obstacles, as well as the vehicle's own status information at a high sampling frequency; the goal of this deployment is to provide real-time, accurate and comprehensive environmental perception data, thereby supporting the vehicle to make timely and accurate decisions and enhance the safety and reliability of autonomous driving.

[0050] S2. Utilize the parallel processing capabilities of quantum computing to integrate multi-source vehicle data.

[0051] Furthermore, the collected multi-source vehicle data will be transmitted to a fusion center based on quantum computing via the 5G high-speed communication network;

[0052] Specifically, through the 5G high-speed communication network, 5G's high bandwidth (up to 10Gbps) and low latency (within 1ms) meet the real-time requirements of vehicle-road collaboration;

[0053] To ensure data integrity and security, multi-source vehicle data is protected using timestamps (recording the collection time) and encryption protocols (such as TLS or AES) to prevent tampering or loss during transmission.

[0054] Using lossless compression to reduce bandwidth usage while preserving critical information for transmission to a quantum computing-based fusion center;

[0055] After receiving the multi-source data from the vehicle, the fusion center pre-processes the multi-source data (including denoising, time synchronization, and format unification to eliminate heterogeneity and noise interference between sensors);

[0056] Specifically, filtering (such as Kalman filtering or median filtering) is used to smooth the data;

[0057] Since different sensors have different sampling frequencies (e.g., 10 frames per second for lidar and 30 frames per second for cameras), the data is unified to the same time base through interpolation algorithms (e.g., linear interpolation) or timestamp alignment.

[0058] Convert heterogeneous data (such as radar range-angle data and camera pixel data) into a unified vector representation (such as three-dimensional coordinates or velocity vectors) to facilitate subsequent quantum encoding;

[0059] Detect and remove obvious outliers (e.g., invalid data from a camera due to overexposure due to strong light) using statistical methods (e.g., Z-scores);

[0060] Mapping the pre-processed vehicle multi-source data into quantum state data through quantum coding;

[0061] By using the superposition and entanglement characteristics of quantum algorithms, the quantum state data is fused to generate a fused quantum state, which is expressed as:

[0062]

[0063] Among them, |ψ f > is the fused quantum state, which is the final quantum state after fusion processing and is used to represent the fused vehicle multi-source data. is the normalization factor, which ensures the final quantum state. Is the summation symbol, which means the sum of all i from 1 to n, w i is the weight factor of the i-th data point, i is the index of the data point, n is the total number of all sensor data involved in the fusion, which indicates how many data points are used to construct the final fusion quantum state, |D i > is the quantum state corresponding to the i-th data point, each sensor data D i is mapped into a quantum state |D i >, this quantum state contains the relevant information of the data point.

[0064] Specifically, suppose we have three quantum states derived from multiple sources of vehicle data (e.g., obstacle distance 5 meters, speed 2 meters per second, and direction 30 degrees). These are like three small boxes filled with information, representing each data point. These small boxes have been prepared by the quantum computer, each carrying its own information and ready to use at any time. Now, what needs to be done is to use the quantum computer to combine the information in these three small boxes into a large box that can simultaneously represent all the data and is more powerful than each box alone. This is the process of fusion.

[0065] Quantum computers rely on superposition and entanglement to allow them to "speak" simultaneously. Superposition is like having three radio channels, each broadcasting a different sound. Ordinary computers have to listen to each one one by one, but quantum computers can open all three channels simultaneously, allowing all the sounds to overlap and become a single sound. Quantum state fusion works the same way: the states in three small boxes are put into a quantum computer and allowed to "speak" simultaneously. However, you can't just stack them together randomly; there must be a certain degree of importance. For example, the distance of 5 meters is measured by lidar, which is very accurate, so you should listen to it more. The speed of 2 meters per second is measured by ordinary radar, which has some errors, so you should listen to it less. The speed of 30 degrees is seen by the camera and is very important, but it depends on the situation. This degree of importance is like putting a label on each box, telling the quantum computer which box should speak loudly and which should speak softly. These labels are called "weights" and are determined based on the credibility of the vehicle's multi-source data.

[0066] Then, the quantum computer gets to work, using special tools (like switches or knobs) to mix the information in the three boxes together according to their importance. Imagine three cups of water: the first one has more water, the second one has less, and the third one has the right amount. Pour them into a large cup, and the water mixes, but you can still see how much each cup contributed. The quantum computer does the same thing, superimposing the states in the three small boxes proportionally to create a new state.

[0067] Entanglement also helps in this process. It's like tying an invisible string between the three boxes, making them no longer separate entities, but friends that influence each other. For example, distance and speed are actually related. The quantum computer uses entanglement to let them chat, ensuring that the fused large box not only contains the three pieces of information but also reflects the connection between them. This way, the fused object is smarter and can help better judge the situation of obstacles.

[0068] Finally, you get a big box. This big box is the fused quantum state. On the surface, it doesn't look like an ordinary number—you can't tell whether it's 5 or 2—but inside it are shadows of all the data, like a super information packet. The quantum computer knows how to use it. To make it work well, the quantum computer automatically adjusts the size of the big box, ensuring it's neither too big nor too small, just like adjusting the volume to get the sound just right. This big box can be used for the next step, such as simulating how a vehicle will react or deciding how to drive, because it sees the whole picture at once, much more powerful than a single box.

[0069] It should be noted that by utilizing the parallel processing capabilities of quantum computing, multi-source vehicle data on the vehicle is transmitted to the quantum computing fusion center, and quantum algorithms are used for data fusion. The purpose of this step is to leverage the advantages of quantum computing to efficiently integrate information from different sensors to form a unified, high-precision quantum state, thereby improving the accuracy and real-time performance of vehicle decision-making.

[0070] S3. Based on the fused data, a virtual test environment is built on a high-performance computing platform.

[0071] Furthermore, weather data (such as rainfall intensity and wind speed) can be obtained through external meteorological services (such as the weather forecast service of the Meteorological Bureau), local environmental information (such as traffic flow and road conditions) can be obtained through roadside units in the vehicle-road cooperative infrastructure (highway V2X pilot projects), and road characteristics (such as road friction coefficient and slope) can be obtained through geographic information (such as maps).

[0072] Integrate weather data, local environmental information, and road characteristics into an environmental parameter set through data formatting and time synchronization, ensuring compatibility with the fused quantum state in time and format;

[0073] Receive the fused quantum state and environmental parameter set through the high-performance computing platform and execute the environment construction task;

[0074] Specifically, the high-performance computing platform receives the fused quantum state, which integrates the multi-source vehicle data collected by the vehicle sensors and contains a comprehensive representation of the perception information. At the same time, it receives the environmental parameter set. The high-performance computing platform couples the fused quantum state with the environmental parameter set through a calculation function, executes the environment construction task, and lays the foundation for the generation of the virtual test environment.

[0075] The high-performance computing platform analyzes the fused quantum state through quantum measurement, extracting the dynamic characteristics (such as obstacle speed and vehicle motion state) and static characteristics (such as obstacle position and traffic signals) of the quantum state. Combined with the environmental parameter set (such as road friction coefficient, rainfall intensity, and traffic flow), it adjusts the vehicle's dynamic behavior, such as braking response in slippery conditions or stability adjustment in strong winds, providing accurate input for numerical simulations.

[0076] The high-performance computing platform simulates the dynamic behavior of the vehicle through numerical simulation based on the fused quantum state and environmental parameter set, and uses the adjusted vehicle dynamic behavior to generate the interaction results between the vehicle and the environment;

[0077] Specifically, the simulation process comprehensively considers the perception information provided by the fused quantum state and the external constraints of the environmental parameter set to generate dynamic behavior data such as the vehicle's motion trajectory, acceleration changes, steering response, and a digital mapping of environmental conditions as the interaction between the vehicle and the environment;

[0078] The high-performance computing platform normalizes the interaction results between the vehicle and the environment, balances the contribution ratio of the fused quantum state and the environmental parameter set, and generates a virtual test environment.

[0079] Specifically, the processed interaction results are integrated into a virtual test environment that includes a digital mapping of the vehicle's dynamic behavior and environmental parameters, supports real-time updates, and can be used for testing vehicle-road collaborative applications.

[0080] It should be noted that by integrating multi-source environmental data and quantum state perception information, a virtual test environment is constructed, which effectively improves the test efficiency and reliability of vehicle-road collaborative applications. The formatting and time synchronization of environmental parameter sets ensure data consistency. The analysis of quantum measurements and dynamic behavior adjustment optimize the vehicle response accuracy. The numerical simulation of the high-performance computing platform makes full use of quantum states and environmental constraints to generate realistic vehicle motion trajectories and environmental mapping. Normalization processing balances the contribution of various factors to ensure environmental stability. The final generated virtual test environment supports real-time updates, covers dynamic behavior and environmental parameters, and provides reliable support for vehicle decision-making and performance evaluation in complex scenarios, significantly reducing the cost and risk of actual road testing and promoting the development of intelligent transportation.

[0081] S4. Conduct testing in a virtual test environment and start real-time monitoring to automatically identify abnormal situations that occur during the test through an abnormality algorithm.

[0082] Furthermore, in a constructed virtual test environment, real driving scenarios are simulated to test vehicle behavior and response;

[0083] Real-time monitoring is initiated and anomalies that occur during testing are automatically identified through machine learning-based anomaly detection algorithms, including abnormal vehicle behavior, abnormal sensor readings, environmental perception errors, communication failures, and decision logic errors.

[0084] The anomaly detection algorithm calculates the distance between each test instance and the training data and determines whether an anomaly occurs through a pre-set threshold;

[0085] To determine the threshold τ in the anomaly algorithm, it is necessary to define a range of normal behavior based on historical data. In this scenario, a statistical method can be used to determine a specific threshold. The specific steps are as follows:

[0086] Collect vehicle sensor data from historical datasets under normal operating conditions, including but not limited to radar data, lidar data, camera data, GPS data, etc.; preprocess the data, including data cleaning and missing value processing;

[0087] Extract meaningful features from raw data, such as distance change rate, speed change rate, direction change rate, etc. These features can help better describe vehicle behavior;

[0088] Use unsupervised learning methods (such as Isolation Forest or One-Class SVM) to train a model that can learn the distribution of normal behavior; for example, using the Isolation Forest algorithm, you can build a model that can distinguish normal data from abnormal data;

[0089] Use the trained model to score the new data point and obtain an anomaly score S; this score indicates the degree of deviation between the new data point and the normal behavior in the training set;

[0090] Based on the anomaly score distribution of the training dataset, a threshold τ is selected so that all data points with scores lower than τ are considered normal, while data points with scores higher than τ are considered anomalies. Specifically, the 99% quantile of the anomaly scores in the training set can be selected as the threshold τ, which ensures that only a very small number of extreme cases are marked as anomalies.

[0091] The specific thresholds are as follows:

[0092] Assume that the training dataset contains a large amount of normal driving data, and calculate the anomaly score S of each data point through the Isolation Forest model; if the maximum anomaly score in the training dataset is found to be 0.95;

[0093] This means that any data point with a score S>0.5S>0.5 will be considered an anomaly. Specifically, if the vehicle's behavior in the virtual test environment causes the anomaly score of its sensor data to exceed 0.50.5, the system will trigger the intelligent intervention mechanism and take appropriate corrective measures. If the score at the 99% percentile is 0.5, then τ can be set to 0.5;

[0094] When S<τ(S<0.5), the data point is considered as part of normal behavior and no special treatment is required;

[0095] When S ≥ τ (S\geq 0.5), the data point is considered to be abnormal behavior, triggering an alarm mechanism or intelligent intervention measures;

[0096] It should be noted that the specific implementation steps of the anomaly detection algorithm are:

[0097] Collect vehicle sensor data during normal operation;

[0098] Clean data and handle missing values;

[0099] Extract meaningful features from raw data, such as distance change rate, speed change rate, direction change rate, etc.;

[0100] Use unsupervised learning methods to train a model to learn the distribution of normal behaviors;

[0101] Use the trained model to score the new data point and get an anomaly score S;

[0102] Based on the anomaly score distribution of the training dataset, a threshold τ is selected so that all data points with scores lower than τ are considered normal, while data points with scores higher than τ are considered anomalies.

[0103] If the anomaly score S of a new data point is greater than or equal to the threshold τ, the data point is considered to be abnormal;

[0104] For example, when using the Isolation Forest model, the model constructs one or more decision trees to try to isolate each data point as quickly as possible; normal data points usually require more segmentation to be isolated, so their average path length is longer; conversely, abnormal data points are isolated faster and have a shorter average path length; by comparing the average path length of new data points with the average path length of normal data points, its degree of abnormality can be assessed and the threshold τ can be set accordingly.

[0105] Isolation Forest is an unsupervised learning method mainly used for anomaly detection. Its basic idea is to construct a decision tree by randomly selecting features and randomly splitting feature values ​​until all data points are isolated (that is, each node contains only one data point).

[0106] The working principle is as follows: Isolation Forest constructs a decision tree by recursively splitting the data space; each split randomly selects a feature and a random value on the feature, which can effectively distinguish outliers from normal points, because outliers often do not need too many splits to be isolated.

[0107] Measuring anomaly scores: The anomaly score of each data point is determined by the length of its path in the tree. Normal data points typically require more splits to be isolated, so their average path length is longer. Conversely, anomaly data points are isolated more quickly and have shorter average path lengths. A lower score indicates a more likely anomaly.

[0108] It should be noted that in a virtual test environment, by simulating real-life driving scenarios and initiating real-time monitoring, combined with a machine learning-based anomaly detection algorithm, the goal is to automatically identify anomalies in vehicle behavior, sensor readings, environmental perception, communication, and decision-making logic during the test. This process first extracts normal operating features from historical data, uses unsupervised learning techniques such as Isolation Forest training models to identify abnormal patterns, and sets a threshold τ to distinguish between normal and abnormal behaviors. Once an anomaly score S is detected that exceeds the threshold, the system will trigger an alarm or intelligent intervention measures to verify the stability and safety of the vehicle system and prevent potential problems in advance.

[0109] S5. Automatically start intelligent intervention and error correction mechanism based on the detected abnormal results.

[0110] Furthermore, if an abnormal situation is detected during the virtual test environment, intelligent intervention measures will be triggered, including adjusting vehicle behavior patterns, replanning driving routes, slowing down and stopping, steering avoidance, light and sound warnings, emergency communication, switching to autonomous driving mode, and activating backup sensors.

[0111] It should be noted that the vehicle behavior pattern can be adjusted: if it is detected that the vehicle deviates from the expected trajectory, the speed or direction of the vehicle can be adjusted to correct it;

[0112] Re-routing: When encountering obstacles or other dangerous situations, the system can recalculate a safer path;

[0113] Slow down and stop: When an emergency is detected ahead, the vehicle should immediately slow down or come to a complete stop;

[0114] Steering avoidance: When an obstacle appears in the driving path, the vehicle can automatically steer to avoid the obstacle;

[0115] Light and sound warning: Send warning signals to other drivers to alert them to the emergency maneuver being performed by the vehicle;

[0116] Emergency communications: Send alerts to nearby vehicles or infrastructure to notify them of potential risks;

[0117] Autonomous driving mode switching: If a situation is detected that the system cannot handle, it switches to manual driving mode or hands control over to a higher-level decision-making system;

[0118] Activate backup sensors: If the primary sensor fails or is interfered with, activate the backup sensor to maintain awareness.

[0119] It should be noted that smart interventions actually describe:

[0120] Adjust vehicle behavior: For example, if a vehicle detects a pedestrian suddenly crossing the street ahead, it will automatically slow down and change direction to avoid a collision.

[0121] Re-route: If the road ahead is closed due to an accident, the vehicle will recalculate a detour based on the latest map information;

[0122] Slow down and stop: When the sensor detects an obstacle ahead, the vehicle will automatically slow down until it comes to a complete stop;

[0123] Steering avoidance: On the highway, if a vehicle in the adjacent lane suddenly changes lanes, the autonomous car will slightly adjust the steering wheel to maintain a safe distance;

[0124] Light and sound warning: If the vehicle is about to make an emergency brake, it will turn on the brake lights and send a warning signal to other vehicles;

[0125] Emergency communication: When a vehicle encounters an emergency, it will send an emergency communication signal to other nearby vehicles to remind them to pay attention to safety;

[0126] Autonomous driving mode switching: If a system fault is detected or external conditions do not allow autonomous driving, the vehicle will prompt the driver to take over control;

[0127] Activate backup sensors: When a problem occurs with the primary sensor, the system switches to the backup sensor to ensure that the necessary environmental information continues to be obtained.

[0128] It should be noted that in the virtual test environment, once an abnormal situation is detected, the system will automatically initiate intelligent intervention and error correction mechanisms; these measures include adjusting vehicle behavior patterns, replanning driving routes, slowing down or stopping, steering to avoid, issuing light and sound warnings, initiating emergency communications, switching to autonomous driving mode, and activating backup sensors; these intervention measures are designed to respond quickly to potential risks and ensure that the vehicle can take reasonable actions in the face of emergencies to protect the safety of passengers and other road users, while maintaining the stability and reliability of the system.

[0129] S6. After completing the error correction mechanism, continue to perform the test task, analyze the data during the test process, and make optimizations.

[0130] Continue to execute the test task and define a series of performance indicators, such as vehicle response time, path planning efficiency, collision avoidance success rate, etc. Each indicator should have a clear calculation method and standard unit;

[0131] Use statistical methods to evaluate the stability and reliability of test results;

[0132] Apply cluster analysis to identify patterns and trends in test data;

[0133] Use cause-and-effect diagrams to explore the reasons behind test results, such as determining whether a sensor failure directly caused a specific type of abnormal behavior;

[0134] Generate optimization suggestions for test plans and vehicle control platforms based on analysis results;

[0135] Apply the optimization recommendations to a new test cycle, perform virtual testing again, and record the results to compare the differences before and after optimization.

[0136] It should be noted that the definitions of performance indicators: for example, "vehicle response time" can be defined as the time required from the system detecting an event to taking corresponding actions, "path planning efficiency" can be defined as the ability to plan the shortest or fastest path, and "collision avoidance success rate" refers to the proportion of successful collision avoidance.

[0137] Statistical methods are applied as follows: In order to evaluate the stability and reliability of test results, hypothesis tests (such as t-tests) can be used to determine whether there are significant differences in the results between different test groups; analysis of variance (ANOVA) can be used to compare the mean differences between multiple sample groups; and regression analysis can also be used to explore the strength of the relationship between different variables.

[0138] It should be noted that after the intelligent error correction mechanism is completed, the test tasks will continue to be executed and the test data will be analyzed in depth; by defining performance indicators such as vehicle response time and path planning efficiency, and using statistical methods to evaluate the stability and reliability of the results, the effectiveness of the test can be ensured; using cluster analysis to identify data patterns and combining cause-and-effect diagrams to explore the root causes will help understand the connection between sensor failures and abnormal behaviors; based on the analysis results, optimization suggestions will be made and implemented in the new test cycle, and the differences before and after optimization will be recorded and compared, so as to continuously improve the performance and safety of the autonomous driving system.

[0139] This embodiment also provides a vehicle-road cooperative application scenario testing system, including: a data acquisition module, a data fusion module, a virtual environment construction module, a test monitoring module, an intelligent intervention and error correction module and an analysis and optimization module; the data acquisition module, in the vehicle-road cooperative application, the vehicle deploys multiple sensors to collect multi-source data of the vehicle in real time; the data fusion module, using the parallel processing capability of quantum computing to fuse multi-source data of the vehicle; the virtual environment construction module, based on the fused data, builds a virtual test environment on a high-performance computing platform; the test monitoring module, performs testing in the virtual test environment, and starts real-time monitoring to automatically identify abnormal situations that occur during the test through an abnormality algorithm; the intelligent intervention and error correction module, automatically starts the intelligent intervention and error correction mechanism according to the detected abnormal results; the analysis and optimization module, after completing the error correction mechanism, continues to execute the test task, and analyzes the data during the test and makes optimizations.

[0140] This embodiment also provides a computer device suitable for the vehicle-road collaborative application scenario testing method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the vehicle-road collaborative application scenario testing method proposed in the above embodiment.

[0141] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0142] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by the processor, it implements the vehicle-road cooperative application scenario testing method proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, abbreviated as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, abbreviated as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, abbreviated as EPROM), programmable read-only memory (Programmable Red-Only Memory, abbreviated as PROM), read-only memory (Read-Only Memory, abbreviated as ROM), magnetic memory, flash memory, disk or optical disk.

[0143] In summary, the present invention significantly improves the speed and accuracy of data processing by utilizing the parallel processing capabilities of quantum computing to fuse multi-source vehicle data. Quantum algorithms not only accelerate the data fusion process, but also ensure the consistency and integrity of the fused data by mapping sensor data into quantum states and performing efficient calculations. This efficient quantum data fusion method reduces data processing delays, enhances the realism and dynamic response capabilities of the virtual test environment, and enables the test environment to more quickly reflect changes in the real world.

[0144] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. 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 solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A vehicle-road collaboration application scenario testing method, characterized by: include, In vehicle-road collaborative applications, multiple sensors are deployed on vehicles to collect multi-source vehicle data in real time; Leverage the parallel processing capabilities of quantum computing to fuse multi-source vehicle data; Based on the fused data, a virtual test environment is built on a high-performance computing platform; Conduct tests in a virtual test environment and enable real-time monitoring to automatically identify anomalies that occur during the test using anomaly algorithms; Automatically start intelligent intervention and error correction mechanisms based on detected abnormal results; After completing the error correction mechanism, continue to perform the test task, analyze the data during the test process, and make optimizations; The parallel processing capability of quantum computing is used to fuse vehicle multi-source data. The specific steps are: Transmit the collected multi-source vehicle data to a fusion center based on quantum computing via the 5G high-speed communication network; After receiving the multi-source vehicle data, the fusion center pre-processes the multi-source vehicle data; Mapping the pre-processed vehicle multi-source data into quantum state data through quantum coding; Using the superposition and entanglement characteristics of quantum algorithms, quantum state data is fused to generate a fused quantum state; The virtual test environment is constructed on a high-performance computing platform based on the fused data. The specific steps are: Obtain weather data through external meteorological services, local environmental information through roadside units in the vehicle-road cooperative infrastructure, and road characteristics through geographic information; Integrate weather data, local environmental information, and road characteristics into an environmental parameter set through data formatting and time synchronization; Receive the fused quantum state and environmental parameter set through the high-performance computing platform and execute the environment construction task; The high-performance computing platform analyzes the fused quantum state through quantum measurement, extracts the dynamic and static characteristics of the quantum state, and adjusts the vehicle's dynamic behavior based on the environmental parameter set; Through numerical simulation based on the fused quantum state and environmental parameter set, the dynamic behavior of the vehicle is simulated using the adjusted vehicle dynamic behavior to generate the interaction results between the vehicle and the environment; The high-performance computing platform normalizes the interaction results between the vehicle and the environment, balances the contribution ratio of the fused quantum state and the environmental parameter set, and generates a virtual test environment.

2. The vehicle-road cooperative application scenario testing method according to claim 1, characterized in that: In the vehicle-road collaborative application, multiple sensors are deployed on the vehicle to collect multi-source data in real time. The specific steps are as follows: To achieve comprehensive perception of the vehicle's surrounding environment, multiple sensors are deployed, including millimeter-wave radar, lidar, high-definition cameras, global positioning and inertial measurement units; Sensors are installed at different locations on the vehicle to cover a 360-degree field of view, and the sampling frequency is configured to continuously collect multi-source data from the vehicle, including obstacle location, obstacle speed, obstacle direction, traffic signal status, vehicle location, vehicle speed, vehicle direction, and vehicle acceleration.

3. The vehicle-road cooperative application scenario testing method according to claim 1, characterized in that: The test is conducted in a virtual test environment, and real-time monitoring is started to automatically identify abnormal situations that occur during the test through an abnormal algorithm. The specific steps are: In the constructed virtual test environment, simulate real driving scenarios and test vehicle behavior responses; Real-time monitoring is enabled, and anomalies that arise during testing are automatically identified through a machine learning-based anomaly detection algorithm, including abnormal vehicle behavior, abnormal sensor readings, environmental perception errors, communication failures, and decision logic errors.

4. The vehicle-road cooperative application scenario testing method according to claim 1, characterized in that: The intelligent intervention and error correction mechanism is automatically started according to the abnormal results detected. The specific steps are: If an abnormal situation is detected during the virtual test environment, intelligent intervention measures will be triggered, including adjusting vehicle behavior patterns, replanning driving routes, slowing down and stopping, steering avoidance, light and sound warnings, emergency communication, switching to autonomous driving mode, and activating backup sensors.

5. The vehicle-road cooperative application scenario testing method according to claim 1, characterized in that: After the error correction mechanism is completed, the test task is continued, and the data during the test is analyzed and optimized. The specific steps are: Continue to perform the test task and define a series of performance indicators; Use statistical methods to evaluate the stability and reliability of test results; Apply cluster analysis to identify patterns and trends in test data; Explore the reasons behind test results through cause-and-effect diagrams; Generate optimization suggestions for test plans and vehicle control platforms based on analysis results; Apply the optimization recommendations to a new test cycle, perform virtual testing again, and record the results to compare the differences before and after optimization.

6. A vehicle-road cooperative application scenario testing system, based on the vehicle-road cooperative application scenario testing method according to any one of claims 1 to 5, characterized in that: Including data acquisition module, data fusion module, virtual environment construction module, test monitoring module, intelligent intervention and error correction module and analysis and optimization module; The data acquisition module is used to deploy multiple sensors on a vehicle in a vehicle-road collaborative application to collect multi-source vehicle data in real time; The data fusion module is used to fuse vehicle multi-source data by utilizing the parallel processing capability of quantum computing; The virtual environment construction module is used to construct a virtual test environment on a high-performance computing platform based on the fused data; The test monitoring module is used to perform testing in a virtual test environment and start real-time monitoring to automatically identify abnormal situations that occur during the test process through an abnormality algorithm; The intelligent intervention and error correction module is used to automatically start the intelligent intervention and error correction mechanism according to the detected abnormal results; The analysis and optimization module is used to continue executing the test task after completing the error correction mechanism, and to analyze and optimize the data during the test process.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the vehicle-road cooperative application scenario testing method described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the vehicle-road cooperative application scenario testing method described in any one of claims 1 to 5 are implemented.

Images