A method for testing trajectory tracking error of unmanned vehicle fleet

By real-time monitoring and analyzing V2V communication data, adjusting the driving trajectory and speed of unmanned fleet vehicles, the problems of V2V communication delay and packet loss are solved, the coordination and safety of the fleet are improved, and the risk of collision is reduced.

CN118524414BActive Publication Date: 2024-11-05CHINA MASCH (BEIJING) VEHICLE INSPECTION ENG RES INST CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410985858.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-05
Estimated Expiration
2044-07-23

AI Technical Summary

Technical Problem

V2V communication is susceptible to environmental factors in the unmanned fleet trajectory tracking error test, resulting in delayed data transmission or packet loss, affecting the coordination and security between vehicles.

Method used

By acquiring vehicle driving data in real time, using the V2V communication module to broadcast data and monitor the reception frequency, evaluating the real-time communication, dividing it into real-time and non-real-time communication, analyzing the accuracy of non-real-time communication data, adjusting vehicle trajectory and speed to optimize tracking performance.

Benefits of technology

It significantly improves the coordination and safety of the fleet, reduces the data transmission delay and packet loss caused by wireless signal interference, improves the accuracy and timeliness of vehicle information transmission, and reduces collision risks and driving errors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118524414B_ABST
    Figure CN118524414B_ABST
Patent Text Reader

Abstract

The present invention discloses a method for testing the trajectory tracking error of an unmanned vehicle fleet, and relates to the technical field of domain name detection. The method obtains the vehicle driving data of the unmanned vehicle fleet in real time, and broadcasts it to surrounding vehicles at a fixed frequency through a V2V communication module, determines whether the data receiving frequency is abnormal, marks the vehicle with abnormal data receiving frequency as a potential fault vehicle, monitors and analyzes its network communication status, and evaluates the real-time performance of the V2V communication. The method divides the real-time communication and non-real-time communication according to the evaluation result, and classifies the corresponding data. The method analyzes the accuracy of the non-real-time communication data, identifies errors and anomalies, adjusts the vehicle driving trajectory and speed, optimizes the trajectory tracking performance of the vehicle fleet, reduces errors, improves the coordination and safety of the vehicle fleet, reduces the driving risks caused by communication delays and packet loss, ensures the efficient operation of the vehicle fleet in various environments, and significantly improves the overall efficiency and safety.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of domain name detection, and in particular to a method for testing trajectory tracking errors of an unmanned vehicle fleet. Background Art

[0002] The unmanned vehicle fleet trajectory tracking error test is carried out by setting multiple reference points on the predetermined route, and the vehicle needs to move along these reference points. During the test, the deviation between the actual driving path of the vehicle and the predetermined trajectory is recorded in real time. These deviations are tracking errors. By analyzing these error data, the accuracy and responsiveness of the vehicle control system can be evaluated to determine whether the system needs further optimization. This test is not only used for trajectory tracking of a single vehicle, but can also be applied to scenarios of multi-vehicle collaborative tracking. During the test, each vehicle in the fleet needs to move along a shared trajectory and maintain its relative position to the vehicle in front. In this process, the error of each vehicle relative to the ideal trajectory and the relative error within the fleet are monitored, so that the overall coordination and stability of the fleet can be evaluated to ensure that the unmanned vehicle fleet can travel safely and efficiently in complex road environments.

[0003] When conducting a trajectory tracking error test for an unmanned vehicle fleet, each vehicle needs to exchange position information with the vehicle in front through a wireless communication system (such as V2V communication). V2V (Vehicle-to-Vehicle) communication is a wireless communication technology that allows vehicles to directly exchange key data such as location, speed, direction, and braking status. Through V2V communication, each vehicle can receive real-time location information from the vehicle in front and surrounding vehicles, thereby adjusting its own driving path and speed, collaboratively maintaining a predetermined relative position and distance, and improving the safety and efficiency of the fleet. V2V communication relies on wireless networks (such as DSRC or C-V2X) for data transmission to ensure fast and reliable communication between vehicles.

[0004] The prior art has the following deficiencies:

[0005] V2V communication relies on wireless networks, and wireless signals may be affected by environmental factors (such as buildings, interference from other vehicles), resulting in data transmission delays or packet loss. If V2V communication data cannot be transmitted in a timely and accurate manner, the vehicle may not be able to receive the location information and dynamic data of the vehicle in front in a timely manner, which may cause it to be unable to accurately adjust its own driving trajectory and speed, thereby increasing the relative error. This delay may cause the distance between vehicles to be unstable and the coordination of the fleet to be reduced, especially in emergency situations. The inability to respond quickly will ultimately increase the risk of collision and seriously affect the safety and overall efficiency of the fleet. Summary of the invention

[0006] The purpose of the present invention is to provide a method for testing the trajectory tracking error of an unmanned vehicle fleet to overcome the deficiencies in the background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a method for testing the trajectory tracking error of an unmanned vehicle fleet, comprising the following steps:

[0008] S1: Real-time acquisition of vehicle driving data of the unmanned fleet in a number of time periods, and broadcasting the collected data to surrounding vehicles at a fixed frequency through the V2V communication module on each vehicle, and determining whether the data receiving frequency of each vehicle is abnormal;

[0009] S2: Mark vehicles with abnormal data reception frequency as potential fault vehicles, monitor and analyze the network communication status of potential fault vehicles, and evaluate the real-time performance of V2V communication between unmanned vehicle fleet vehicles based on the communication data delay and the stability of the communication range;

[0010] S3: Based on the evaluation results, the real-time performance of V2V communication between vehicles in the unmanned vehicle fleet is divided into real-time communication and non-real-time communication, and the corresponding data is divided into real-time communication data and non-real-time communication data;

[0011] S4: Analyze the accuracy of non-real-time V2V communication data between vehicles in the unmanned fleet to identify errors and anomalies in the data, and adjust the vehicle's driving trajectory and speed based on the analysis results to optimize the overall trajectory tracking performance of the fleet and reduce errors.

[0012] In a preferred real-time method, a sliding window statistical analysis is performed to determine whether the data reception frequency of each vehicle is abnormal, specifically:

[0013] Set the size and step size of the sliding window, as well as the expected receiving frequency and frequency threshold;

[0014] Record the timestamp of each received data packet in real time;

[0015] Initialize the position of the sliding window, starting from the start time of the data record;

[0016] In each window, count the number of packets received and calculate the reception frequency;

[0017] Determine whether the receiving frequency is less than the frequency threshold. If the receiving frequency is less than the frequency threshold, mark it as an abnormal window and count the number of consecutive abnormal windows.

[0018] If the number of consecutive abnormal windows is greater than or equal to the set threshold, the vehicle is marked as a potential fault vehicle and a report and notification are generated.

[0019] In a preferred real-time mode, a communication delay deviation index is generated according to the communication delay data in a fixed time period, and a method for obtaining the communication delay deviation index is as follows:

[0020] Acquire the communication delay data within a fixed time period in real time, record the sending and receiving time of each data packet, calculate the communication delay, and calculate the mean and standard deviation of all communication delay data within the fixed time period;

[0021] The control lines in the control chart are calculated based on the mean and standard deviation, including the center line CL, which is the center line of the control chart, equal to the mean of the delayed data, and the upper control limit UCL is: UCL = ; In the formula, EX is the mean of the delayed data, σ is the standard deviation of the delayed data, k is the control limit parameter; the lower control limit LCL is; UCL= ;

[0022] Draw the mean control chart and range control chart of the delay data, detect the abnormal points that are greater than or equal to the control limit through the control chart, and calculate the communication delay deviation index according to the deviation of the delay data from the mean and the control limit. The specific calculation expression is: ; Where n is the total number of delayed data points, represents the delay value of the i-th data point, is the communication delay deviation index.

[0023] In a preferred real-time method, the effective communication distance between vehicles is measured by the V2V communication module, the communication quality of the potential fault vehicle at different positions is recorded, and the communication quality distribution abnormality index is generated according to the change of the communication quality of the vehicle at different positions within the communication range. The method for obtaining the communication quality distribution abnormality index is:

[0024] The communication quality data of potential faulty vehicles at different locations are obtained, the collected communication quality data are sorted, interpolation analysis is performed, and a variation function model is constructed according to the data characteristics. The specific calculation expression of the model is: ; In the formula, The variance function value when the distance is h, Wh is the sampling logarithm of the distance h, For location The communication quality value at The communication quality value at

[0025] Define the interpolation grid in the spatial range, determine the target position of interpolation, use the Kriging interpolation method, and predict the communication quality of each position in the interpolation grid based on the known data points. The specific prediction expression is: = ; Where s is the position number, For location The difference prediction value at Kriging weight, m ​​is the total number of locations; calculate the deviation between the actual measured value and the interpolation predicted value, and calculate the communication quality distribution anomaly index based on the deviation. The specific calculation expression is: ; In the formula, is the communication quality distribution anomaly index.

[0026] In a preferred real-time method, the communication quality distribution anomaly index and the communication delay deviation index are normalized, and the real-time analysis coefficient of the V2V communication between the vehicles in the unmanned vehicle fleet is calculated by the normalized communication quality distribution anomaly index and the communication delay deviation index.

[0027] In a preferred real-time method, the acquired real-time analysis coefficient of the V2V communication between the unmanned vehicle fleet is compared with a reference threshold of the real-time analysis coefficient. If the real-time analysis coefficient of the V2V communication between the unmanned vehicle fleet is greater than or equal to the reference threshold of the real-time analysis coefficient, the real-time of the V2V communication between the unmanned vehicle fleet vehicles is classified as real-time communication, and the corresponding data is classified as real-time communication data, and a normal signal of the V2V communication between the unmanned vehicle fleet vehicles is generated at this time; if the real-time analysis coefficient of the V2V communication between the unmanned vehicle fleet vehicles is less than the reference threshold of the real-time analysis coefficient, the real-time of the V2V communication between the unmanned vehicle fleet vehicles is classified as non-real-time communication, and the corresponding data is classified as non-real-time communication data, and an abnormal signal of the V2V communication between the unmanned vehicle fleet vehicles is generated at this time.

[0028] In a preferred real-time method, when the V2V communication data between vehicles in the unmanned vehicle fleet is non-real-time communication data, that is, the real-time analysis coefficient generated within a period of time is less than the real-time analysis coefficient reference threshold, the real-time analysis coefficients generated in a subsequent period of time are collected, and a corresponding data set is established. The real-time analysis coefficients in the data set that are less than the real-time analysis coefficient reference threshold are analyzed, and the accuracy anomaly index of the non-real-time communication data is calculated.

[0029] In a preferred real-time mode, the specific calculation expression of the accuracy anomaly index of the non-real-time communication data is: ; In the formula, is the accuracy anomaly index of non-real-time communication data, Q is the number of the real-time analysis coefficient in the data set that is less than the reference threshold of the real-time analysis coefficient, is the real-time analysis coefficient in the data set that is less than the reference threshold of the real-time analysis coefficient, F is the total number of real-time analysis coefficients in the data set, It is the reference threshold of the real-time analysis coefficient.

[0030] In a preferred real-time manner, the accuracy anomaly index of the acquired non-real-time communication data is compared with a reference threshold of the accuracy anomaly index. If the accuracy anomaly index of the non-real-time communication data is greater than or equal to the reference threshold of the accuracy anomaly index, a communication data inaccurate signal is generated, and the speed of the vehicle is immediately adjusted to reduce the following distance and the response time, thereby reducing the gap between the actual driving path of the vehicle and the ideal path;

[0031] If the accuracy anomaly index of the non-real-time communication data is less than the accuracy anomaly index reference threshold, a communication data accuracy signal is generated and the vehicle control system is updated in real time, thereby optimizing the overall trajectory tracking performance of the fleet.

[0032] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0033] 1. The present invention obtains vehicle driving data in real time, and uses the V2V communication module to broadcast data at a fixed frequency, detects and marks vehicles with abnormal data reception frequency as potential faulty vehicles, monitors and analyzes their network communication status, and evaluates the real-time performance of V2V communication. According to the evaluation results, the communication data is divided into real-time communication and non-real-time communication, and the accuracy of non-real-time communication data is further analyzed to identify errors and anomalies. The vehicle driving trajectory and speed are adjusted according to the analysis results to optimize the overall trajectory tracking performance of the fleet and reduce relative errors. This method ensures the efficient operation of vehicles in various environments by continuously monitoring and analyzing communication data, and significantly improves the coordination and safety of the fleet.

[0034] 2. Through accurate anomaly detection and real-time analysis, the present invention can timely identify and process errors in communication data, reduce data transmission delays and packet loss caused by wireless signal interference, and ensure the accuracy and timeliness of information transmission between vehicles. By adjusting the driving trajectory and speed of the vehicle, the responsiveness and overall operating efficiency of the fleet in complex traffic environments are improved, the risk of collision and driving errors are reduced, and the operating safety and overall efficiency of the unmanned fleet are significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0036] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] For examples, see Figure 1 As shown, the unmanned vehicle fleet trajectory tracking error testing method described in this embodiment includes the following steps:

[0039] S1: Real-time acquisition of vehicle driving data of the unmanned fleet in a number of time periods, and broadcasting the collected data to surrounding vehicles at a fixed frequency through the V2V communication module on each vehicle, and determining whether the data receiving frequency of each vehicle is abnormal;

[0040] S2: Mark vehicles with abnormal data reception frequency as potential fault vehicles, monitor and analyze the network communication status of potential fault vehicles, and evaluate the real-time performance of V2V communication between unmanned vehicle fleet vehicles based on the communication data delay and the stability of the communication range;

[0041] S3: Based on the evaluation results, the real-time performance of V2V communication between vehicles in the unmanned vehicle fleet is divided into real-time communication and non-real-time communication, and the corresponding data is divided into real-time communication data and non-real-time communication data;

[0042] S4: Analyze the accuracy of non-real-time V2V communication data between vehicles in the unmanned fleet to identify errors and anomalies in the data, and adjust the vehicle's driving trajectory and speed based on the analysis results to optimize the overall trajectory tracking performance of the fleet and reduce errors.

[0043] Among them, in S1, the vehicle driving data of the unmanned vehicle fleet in several time periods is obtained in real time, and the collected data is broadcast to the surrounding vehicles at a fixed frequency through the V2V communication module on each vehicle, and it is determined whether the data receiving frequency of each vehicle is abnormal, mainly including:

[0044] In the unmanned vehicle fleet trajectory tracking error test, the vehicle obtains driving data in real time, including location information, speed and direction, through high-precision sensors (such as GPS and IMU) installed on each vehicle. These data are recorded in several time periods (such as every second or shorter time intervals) to ensure that the dynamic behavior of each vehicle can be continuously monitored and analyzed. Each vehicle broadcasts these real-time data to surrounding vehicles at a fixed frequency (such as every 100 milliseconds) through its V2V communication module, so that each vehicle can obtain the latest driving information of other vehicles in a timely manner, and make necessary path adjustments and speed control to achieve coordination and safe driving of the fleet.

[0045] Through sliding window statistical analysis, it is determined whether the data reception frequency of each vehicle is abnormal. Specifically:

[0046] Set the size and step size of the sliding window, as well as the expected receiving frequency and frequency threshold;

[0047] Record the timestamp of each received data packet in real time;

[0048] Initialize the position of the sliding window, starting from the start time of the data record;

[0049] In each window, count the number of packets received and calculate the reception frequency;

[0050] Determine whether the receiving frequency is less than the frequency threshold. If the receiving frequency is less than the frequency threshold, mark it as an abnormal window and count the number of consecutive abnormal windows.

[0051] If the number of consecutive abnormal windows is greater than or equal to the set threshold, the vehicle is marked as a potential fault vehicle and a report and notification are generated.

[0052] In the present invention, by using sliding window statistical analysis to determine whether the data reception frequency of each vehicle is abnormal, it is possible to promptly discover and mark potential faulty vehicles to ensure the coordination and safe driving of the unmanned vehicle fleet. By setting the sliding window size, step size, expected reception frequency and frequency threshold, the data packet reception situation is recorded and analyzed in real time, and abnormal windows and continuous abnormal situations are accurately identified. The advantage is that it can monitor the vehicle communication status in real time, timely warn and handle potential faults, avoid trajectory deviation or collision risks caused by communication abnormalities, and significantly improve the overall stability and reliability of the fleet.

[0053] S2: Mark vehicles with abnormal data reception frequency as potential faulty vehicles, monitor and analyze the network communication status of potential faulty vehicles, and evaluate the real-time performance of V2V communication between unmanned vehicle fleet vehicles based on the communication data delay and the stability of the communication range.

[0054] According to the results of the sliding window statistical analysis, vehicles whose data reception frequency is less than the set number threshold are identified. These vehicles with abnormal reception frequency are marked as potential fault vehicles to facilitate subsequent key monitoring and analysis.

[0055] The timestamp of each data packet received by the potential fault vehicle is recorded in real time and compared with the sending timestamp of the data packet to calculate the communication delay. The communication delay deviation index is generated according to the communication delay data in a fixed time period. The method for obtaining the communication delay deviation index is as follows:

[0056] Acquire the communication delay data within a fixed time period in real time, record the sending and receiving time of each data packet, calculate the communication delay, and calculate the mean and standard deviation of all communication delay data within the fixed time period;

[0057] The control lines in the control chart are calculated based on the mean and standard deviation, including the center line CL, which is the center line of the control chart, equal to the mean of the delayed data, and the upper control limit UCL is: UCL = ; In the formula, EX is the mean of the delayed data, σ is the standard deviation of the delayed data, k is the control limit parameter, usually 3, which is used to set the width of the control limit (3σ principle); the lower control limit LCL is; UCL= ;

[0058] Draw the mean control chart and range control chart of the delay data, detect the abnormal points that are greater than or equal to the control limit through the control chart, and calculate the communication delay deviation index according to the deviation of the delay data from the mean and the control limit. The specific calculation expression is: ; Where n is the total number of delayed data points, represents the delay value of the i-th data point, is the communication delay deviation index.

[0059] The communication delay deviation index reflects the volatility of communication delay by calculating the standardized deviation between the delay value of each data packet and the mean. When the deviation index is large, it indicates that the fluctuation range of the delay data is large, that is, the instability of the delay time increases. This instability means that the vehicle cannot receive the location information and control instructions of other vehicles within the expected time, thus affecting the vehicle's real-time response ability.

[0060] In an unmanned vehicle fleet, the real-time performance of V2V communication is crucial to maintaining the coordination and safety of the fleet. If the communication delay deviation index is large, it means that the communication delay time changes dramatically. Some vehicles may not be able to obtain the position information of the vehicle in front in time due to the long delay, resulting in the inability to make timely path adjustments and speed control. This situation seriously affects the synchronization and overall response speed of the fleet, and increases the risk of the fleet during driving.

[0061] Real-time communication is an important guarantee for unmanned vehicle fleets to maintain safe driving. When the deviation index is large, the instability of communication delay increases, and information transmission between vehicles may not be timely, resulting in the inability of vehicles to accurately judge the movement state of the vehicle in front, increasing the risk of collision and accidents. For example, during emergency braking or obstacle avoidance, if the rear vehicle cannot receive the braking signal of the front vehicle in time, it may cause a rear-end collision.

[0062] Detect changes in the communication range of potential faulty vehicles, and evaluate the stability of the communication range by recording and analyzing the reception of data packets at different locations. Use the V2V communication module to measure the effective communication distance between vehicles, record the communication quality of potential faulty vehicles at different locations, and generate a communication quality distribution anomaly index based on the changes in the communication quality of vehicles at different locations within the communication range. The method for obtaining the communication quality distribution anomaly index is as follows:

[0063] Obtain the communication quality data of potential faulty vehicles at different locations, including location (such as GPS coordinates) and communication quality indicators (such as signal strength and packet loss rate); organize the collected communication quality data, perform interpolation analysis, and build a variation function model based on data characteristics. The specific calculation expression of the model is: ; In the formula, The variance function value when the distance is h, Wh is the sampling logarithm of the distance h, For location The communication quality value at The communication quality value at

[0064] Define the interpolation grid in the spatial range, determine the target position of interpolation, use the Kriging interpolation method, and predict the communication quality of each position in the interpolation grid based on the known data points. The specific prediction expression is: = ; Where s is the position number, For location The difference prediction value at Kriging weight, m ​​is the total number of locations; calculate the deviation between the actual measured value and the interpolation predicted value, and calculate the communication quality distribution anomaly index based on the deviation. The specific calculation expression is: ; In the formula, is the communication quality distribution anomaly index.

[0065] When the communication quality distribution anomaly index is large, it means that the communication quality at different locations has high volatility, and there are significant differences in signal strength and packet loss rate. This means that in some locations, communication delays may increase significantly, resulting in frequent packet loss and affecting the timely exchange of information between vehicles.

[0066] A high communication quality distribution anomaly index reflects the instability and unreliability of V2V communication. The quality of information obtained by vehicles at different locations is inconsistent, and they may not be able to obtain the location information and dynamic data of surrounding vehicles in a timely manner, which affects the real-time path adjustment and speed control of the vehicles, and reduces the overall coordination and real-time response capabilities of the fleet.

[0067] Poor real-time performance of V2V communication directly affects the safety of the fleet, especially in high-density traffic environments or complex road conditions. A large communication quality distribution anomaly index may cause the vehicle to be unable to accurately predict and respond to the behavior of the vehicle in front, increasing the risk of collision and accidents. Therefore, maintaining a low communication quality distribution anomaly index is crucial to ensure the safe and efficient operation of the unmanned fleet.

[0068] The communication quality distribution anomaly index and the communication delay deviation index are normalized, and the real-time analysis coefficient of V2V communication between unmanned vehicle fleet vehicles is calculated based on the normalized communication quality distribution anomaly index and communication delay deviation index.

[0069] For example, the present invention can use the following formula to calculate the real-time analysis coefficient of V2V communication between vehicles in an unmanned vehicle fleet, and the calculation expression is: ; In the formula, is the real-time analysis coefficient of V2V communication between unmanned vehicle fleets, is the communication delay deviation index, is the communication quality distribution anomaly index, is the proportional coefficient of the communication quality distribution anomaly index and the communication delay deviation index, and 0.

[0070] S3: Based on the evaluation results, the real-time performance of V2V communication between vehicles in the unmanned vehicle fleet is divided into real-time communication and non-real-time communication, and the corresponding data is divided into real-time communication data and non-real-time communication data;

[0071] The obtained real-time analysis coefficient of the V2V communication between the unmanned vehicle fleet vehicles is compared with the reference threshold of the real-time analysis coefficient. If the real-time analysis coefficient of the V2V communication between the unmanned vehicle fleet vehicles is greater than or equal to the reference threshold of the real-time analysis coefficient, it means that the real-time performance of the V2V communication between the unmanned vehicle fleet vehicles is relatively high, and the real-time performance of the V2V communication between the unmanned vehicle fleet vehicles is divided into real-time communication, and the corresponding data is divided into real-time communication data, and a normal signal of the V2V communication between the unmanned vehicle fleet vehicles is generated at this time; if the real-time analysis coefficient of the V2V communication between the unmanned vehicle fleet vehicles is less than the reference threshold of the real-time analysis coefficient, it means that the real-time performance of the V2V communication between the unmanned vehicle fleet vehicles is relatively low, and the real-time performance of the V2V communication between the unmanned vehicle fleet vehicles is divided into non-real-time communication, and the corresponding data is divided into non-real-time communication data, and an abnormal signal of the V2V communication between the unmanned vehicle fleet vehicles is generated at this time.

[0072] S4: Analyze the accuracy of non-real-time V2V communication data between vehicles in the unmanned fleet to identify errors and anomalies in the data, and adjust the vehicle's driving trajectory and speed based on the analysis results to optimize the overall trajectory tracking performance of the fleet and reduce errors.

[0073] When the V2V communication data between vehicles in the unmanned vehicle fleet is non-real-time communication data, that is, the real-time analysis coefficient generated within a period of time is less than the real-time analysis coefficient reference threshold, the real-time analysis coefficients generated in a subsequent period of time are collected, and a corresponding data set is established. The real-time analysis coefficients in the data set that are less than the real-time analysis coefficient reference threshold are analyzed, and the accuracy anomaly index of the non-real-time communication data is calculated.

[0074] Among them, the specific calculation expression of the accuracy anomaly index of non-real-time communication data is: ; In the formula, is the accuracy anomaly index of non-real-time communication data, Q is the number of the real-time analysis coefficient in the data set that is less than the reference threshold of the real-time analysis coefficient, is the real-time analysis coefficient in the data set that is less than the reference threshold of the real-time analysis coefficient, F is the total number of real-time analysis coefficients in the data set, It is the reference threshold of the real-time analysis coefficient.

[0075] The accuracy anomaly index of the acquired non-real-time communication data is compared with the accuracy anomaly index reference threshold. If the accuracy anomaly index of the non-real-time communication data is greater than or equal to the accuracy anomaly index reference threshold, a communication data inaccurate signal is generated and the vehicle speed is immediately adjusted to reduce the following distance and response time, thereby reducing the gap between the actual driving path of the vehicle and the ideal path; if the accuracy anomaly index of the non-real-time communication data is less than the accuracy anomaly index reference threshold, a communication data accurate signal is generated and the vehicle control system is updated in real time, thereby optimizing the overall trajectory tracking performance of the fleet.

[0076] In this embodiment, by acquiring the vehicle driving data of the unmanned vehicle fleet in real time and using the V2V communication module to broadcast the data to the surrounding vehicles at a fixed frequency, it is possible to effectively monitor and determine whether the data reception frequency of each vehicle is abnormal, mark potential faulty vehicles in a timely manner, and conduct in-depth analysis of the network communication status. The real-time performance of V2V communication is evaluated based on the delay and stability of the communication data, the communication data is divided into real-time and non-real-time communication data, and the accuracy of the non-real-time communication data is analyzed to identify errors and anomalies in the data. According to the analysis results, the vehicle driving trajectory and speed are adjusted to optimize the overall trajectory tracking performance of the fleet, thereby reducing errors. The efficiency, coordination and safety of the fleet operation are ensured, and the reliability of the communication and control system is improved.

[0077] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0078] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0079] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0080] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0081] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0082] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0083] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0084] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for testing trajectory tracking error of an unmanned vehicle fleet, characterized in that: The following steps are involved: S1: Real-time acquisition of vehicle driving data of the unmanned fleet in a number of time periods, and broadcasting the collected data to surrounding vehicles at a fixed frequency through the V2V communication module on each vehicle, and determining whether the data receiving frequency of each vehicle is abnormal; S2: Mark vehicles with abnormal data reception frequency as potential fault vehicles, monitor and analyze the network communication status of potential fault vehicles, and evaluate the real-time performance of V2V communication between unmanned vehicle fleet vehicles based on the communication data delay and the stability of the communication range; Step S2 specifically includes: generating a communication delay deviation index according to the communication delay data within a fixed time period, and the method for obtaining the communication delay deviation index is: Acquire the communication delay data within a fixed time period in real time, record the sending and receiving time of each data packet, calculate the communication delay, and calculate the mean and standard deviation of all communication delay data within the fixed time period; The control lines in the control chart are calculated based on the mean and standard deviation, including the center line CL, which is the center line of the control chart, equal to the mean of the delayed data, and the upper control limit UCL is: UCL = EX + kσ; where EX is the mean of the delayed data, σ is the standard deviation of the delayed data, and k is the control limit parameter; the lower control limit LCL is; LCL = EX-kσ; Draw the mean control chart and range control chart of the delay data, detect the abnormal points that are greater than or equal to the upper control limit through the mean control chart and the range control chart, and calculate the communication delay deviation index according to the deviation of the delay data from the mean and the upper control limit. The specific calculation expression is: Where n is the total number of delayed data points, Xi represents the delay value of the i-th data point, and CDP is the communication delay deviation index; The effective communication distance between vehicles is measured by the V2V communication module, and the communication quality of potential fault vehicles at different locations is recorded. The communication quality distribution anomaly index is generated according to the change of communication quality of vehicles at different locations within the communication range. The method for obtaining the communication quality distribution anomaly index is as follows: The communication quality data of potential faulty vehicles at different locations are obtained, the collected communication quality data are sorted, interpolation analysis is performed, and a variation function model is constructed according to the data characteristics. The specific calculation expression of the model is: In the formula, Gh is the variance function value when the distance is h, Wh is the sampling logarithm of the distance h, zx s is the position x s The communication quality value at z(x s +h) is (x s +h) communication quality value; Define the interpolation grid in the spatial range, determine the target position of interpolation, use the Kriging interpolation method, and predict the communication quality of each position in the interpolation grid based on the known data points. The specific prediction expression is: Where s is the location number, zx0 is the interpolation prediction value at location x0, d is the Kriging weight, and m is the total number of locations. The deviation between the actual measured value and the interpolation prediction value is calculated, and the communication quality distribution anomaly index is calculated based on the deviation. The specific calculation expression is: Where KH is the communication quality distribution anomaly index; The communication quality distribution anomaly index and the communication delay deviation index are normalized, and the real-time analysis coefficient of the V2V communication between the unmanned vehicle fleet vehicles is calculated by the normalized communication quality distribution anomaly index and the communication delay deviation index; Calculate the real-time analysis coefficient of V2V communication between unmanned vehicle fleets. The calculation expression is: Where KM is the real-time analysis coefficient of V2V communication between unmanned vehicle fleets, CDP is the communication delay deviation index, KH is the communication quality distribution anomaly index, a1 and a2 are the proportional coefficients of the communication quality distribution anomaly index and the communication delay deviation index, and a2>a1>0; S3: Based on the evaluation results, the real-time performance of V2V communication between vehicles in the unmanned vehicle fleet is divided into real-time communication and non-real-time communication, and the corresponding data is divided into real-time communication data and non-real-time communication data; S4: Analyze the accuracy of non-real-time V2V communication data between vehicles in the unmanned fleet to identify errors and anomalies in the data, and adjust the vehicle's driving trajectory and speed based on the analysis results to optimize the overall trajectory tracking performance of the fleet and reduce errors.

2. The unmanned vehicle fleet trajectory tracking error testing method according to claim 1, characterized in that: Through sliding window statistical analysis, it is determined whether the data reception frequency of each vehicle is abnormal, specifically: Set the size and step size of the sliding window, as well as the expected receiving frequency and frequency threshold; Record the timestamp of each received data packet in real time; Initialize the position of the sliding window, starting from the start time of the data record; In each window, count the number of packets received and calculate the reception frequency; Determine whether the receiving frequency is less than the frequency threshold. If the receiving frequency is less than the frequency threshold, mark it as an abnormal window and count the number of consecutive abnormal windows. If the number of consecutive abnormal windows is greater than or equal to the set threshold, the vehicle is marked as a potential fault vehicle and a report and notification are generated.

3. The method for testing the trajectory tracking error of an unmanned vehicle fleet according to claim 1, characterized in that: The obtained real-time analysis coefficient of the V2V communication between the unmanned vehicle fleet is compared with the reference threshold of the real-time analysis coefficient. If the real-time analysis coefficient of the V2V communication between the unmanned vehicle fleet is greater than or equal to the reference threshold of the real-time analysis coefficient, the real-time of the V2V communication between the unmanned vehicle fleet vehicles is divided into real-time communication, and the corresponding data is divided into real-time communication data, and a normal signal of the V2V communication between the unmanned vehicle fleet vehicles is generated at this time; if the real-time analysis coefficient of the V2V communication between the unmanned vehicle fleet vehicles is less than the reference threshold of the real-time analysis coefficient, the real-time of the V2V communication between the unmanned vehicle fleet vehicles is divided into non-real-time communication, and the corresponding data is divided into non-real-time communication data, and an abnormal signal of the V2V communication between the unmanned vehicle fleet vehicles is generated at this time.

4. The method for testing the trajectory tracking error of an unmanned vehicle fleet according to claim 1, characterized in that: When the V2V communication data between vehicles in the unmanned vehicle fleet is non-real-time communication data, that is, the real-time analysis coefficient generated within a period of time is less than the real-time analysis coefficient reference threshold, the real-time analysis coefficients generated in a subsequent period of time are collected, and a corresponding data set is established. The real-time analysis coefficients in the data set that are less than the real-time analysis coefficient reference threshold are analyzed, and the accuracy anomaly index of the non-real-time communication data is calculated.

5. The method for testing the trajectory tracking error of an unmanned vehicle fleet according to claim 4, characterized in that: in, The specific calculation expression of the accuracy anomaly index of non-real-time communication data is: Where TX is the accuracy anomaly index of non-real-time communication data, Q is the number of the real-time analysis coefficient in the data set that is less than the reference threshold of the real-time analysis coefficient, and KM is Q is the real-time analysis coefficient in the data set that is less than the real-time analysis coefficient reference threshold, F is the total number of real-time analysis coefficients in the data set, and KW is the real-time analysis coefficient reference threshold.

6. The method for testing the trajectory tracking error of an unmanned vehicle fleet according to claim 5, characterized in that: The accuracy anomaly index of the acquired non-real-time communication data is compared with the accuracy anomaly index reference threshold. If the accuracy anomaly index of the non-real-time communication data is greater than or equal to the accuracy anomaly index reference threshold, a communication data inaccurate signal is generated, and the speed of the vehicle is immediately adjusted to reduce the following distance and response time, thereby reducing the gap between the actual driving path of the vehicle and the ideal path; If the accuracy anomaly index of the non-real-time communication data is less than the accuracy anomaly index reference threshold, a communication data accuracy signal is generated and the vehicle control system is updated in real time, thereby optimizing the overall trajectory tracking performance of the fleet.