Unmanned vehicle stability state scoring system

Through the stability status scoring system of unmanned vehicles, vehicle operation data is collected and analyzed, and time series analysis and machine learning methods are used to score, which solves the problem of equipment aging affecting vehicle safety, and improves the operation safety of unmanned vehicles and reliability.

CN118961228APending Publication Date: 2024-11-15CICHUAN KAIWU INFORMATION TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410958959.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The prior art does not consider the impact of aging or loss of unmanned vehicle equipment on vehicle operation safety and reliability, resulting in poor safety.

Method used

A stable state scoring system for unmanned vehicles is designed, including data acquisition module, feature extraction module, feature analysis module and status scoring module. By collecting and analyzing vehicle operating status data, time series analysis and machine learning methods are used to treat vehicles. The stability status is scored, and the accuracy of the scoring results is improved through the data correction and early warning modules.

Benefits of technology

It can identify potential equipment aging or loss problems, improve the operating safety and reliability of driverless vehicles, provide reference for equipment maintenance through comprehensive and scientific scoring results, and improve vehicle stability and safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118961228A_ABST
    Figure CN118961228A_ABST
Patent Text Reader

Abstract

The invention discloses a system for scoring the stability state of an unmanned vehicle. The system comprises a data acquisition module, a feature extraction module, a feature analysis module and a state scoring module, the data acquisition module acquires vehicle running state data; the feature extraction module performs feature extraction on the vehicle running state data to obtain running state feature data; the feature analysis module performs feature analysis on the running state feature data to obtain feature change trend data; and the state scoring module scores the stability state of the vehicle according to the characteristic change trend data to obtain a stability state scoring result. By collecting and analyzing the vehicle running state data and scoring the vehicle stability state, the potential vehicle equipment aging or loss problem can be recognized, reference information is provided for equipment maintenance, and therefore the running safety and reliability of the unmanned vehicle are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of vehicle operation monitoring technology, and in particular to a stability status scoring system for unmanned vehicles. Background Art

[0002] With the development of science and technology, driverless vehicles have become a hot topic in automotive research. During the operation of driverless vehicles, their key sensors and equipment may degrade in performance due to aging, wear or interference from external factors, such as reduced laser radar accuracy and blurred camera images. These problems may affect the stability and safety of the vehicle.

[0003] In the prior art, the assessment in the patent publication number CN114550442A, "A method for evaluating and warning the state of an autonomous driving vehicle based on vehicle-road collaboration", includes two parts: an evaluation of the physical comfort state of the occupants during the entire driving process of the autonomous driving vehicle, and an evaluation of the safety state of the occupants and the vehicle during the entire driving process of the autonomous driving vehicle. The driving data of the autonomous driving vehicle and the non-autonomous driving vehicle are collected on the road side, and the driving data collected by the autonomous driving vehicle side are integrated to perform data processing and feature extraction, so as to establish an objective standard for evaluating the physical comfort of the occupants of the autonomous driving vehicle, which can be used as a state constraint for path planning. By learning and training the above-mentioned large amount of data, the abnormal behavior of the autonomous driving vehicle can be predicted online. When an unsafe state of the vehicle is predicted, an early warning will be sent to the vehicle safety officer or the remote monitoring center, and the vehicle can be taken over in time to get out of the unsafe state.

[0004] However, the above-mentioned prior art does not take into account the impact of aging or wear of vehicle equipment on unmanned vehicles, and the operating safety and reliability of unmanned vehicles are poor. Summary of the invention

[0005] The present application provides an unmanned vehicle stability status scoring system to solve the problem that the prior art does not consider the impact of vehicle equipment aging or loss on the unmanned vehicle, resulting in poor operating safety and reliability of the unmanned vehicle.

[0006] On the one hand, the present application provides an unmanned vehicle stability status scoring system, including: a data acquisition module, a feature extraction module, a feature analysis module and a status scoring module.

[0007] The data acquisition module is used to collect vehicle running status data.

[0008] The feature extraction module is used to extract features from the vehicle running status data to obtain running status feature data.

[0009] The feature analysis module is used to perform feature analysis on the running status feature data to obtain feature change trend data.

[0010] The state scoring module is used to score the vehicle stability state according to the characteristic change trend data to obtain a stability state scoring result.

[0011] In a possible implementation, the data acquisition module includes: an obstacle acquisition unit, a traffic information acquisition unit, a motion information acquisition unit, and a control information acquisition unit.

[0012] The obstacle collection unit is used to collect obstacle information.

[0013] The traffic information collection unit is used to collect traffic information.

[0014] The motion information acquisition unit is used to acquire vehicle motion information.

[0015] The control information acquisition unit is used to acquire vehicle control information.

[0016] The vehicle operation status data includes the obstacle information, the traffic information, the vehicle motion information and the vehicle control information.

[0017] In a possible implementation, the feature extraction module includes: an obstacle feature extraction unit, a traffic feature extraction unit, a motion feature extraction unit, and a control feature extraction unit.

[0018] The obstacle feature extraction unit is used to extract features from the obstacle information to obtain obstacle feature data.

[0019] The traffic feature extraction unit is used to extract features from the traffic information to obtain traffic feature data.

[0020] The motion feature extraction unit is used to extract features from the vehicle motion information to obtain motion feature data.

[0021] The control feature extraction unit is used to extract features from the vehicle control information to obtain control feature data.

[0022] The operating status characteristic data includes the obstacle characteristic data, the traffic characteristic data, the motion characteristic data and the control characteristic data.

[0023] In a possible implementation, the feature analysis module uses a time series analysis method to perform feature analysis on the operating status feature data to obtain feature change trend data.

[0024] In a possible implementation, the time series analysis method includes: an autoregressive moving average model, an autoregressive integrated moving average model, an exponential smoothing method, and a time series neural network.

[0025] In a possible implementation, the state scoring module uses a machine learning method to score the vehicle stability state according to the characteristic change trend data to obtain a stability state scoring result.

[0026] In a possible implementation, the machine learning method includes: a support vector machine algorithm, a random forest algorithm, a logistic regression algorithm, a linear regression algorithm, a cluster analysis algorithm, and a Q learning algorithm.

[0027] In a possible implementation, the unmanned vehicle stability status scoring system also includes: a preprocessing module.

[0028] The preprocessing module is used to preprocess the vehicle running status data.

[0029] In a possible implementation, the unmanned vehicle stability status scoring system also includes: a data correction module.

[0030] The data correction module is used to dynamically correct the current vehicle running status data based on historical vehicle running status data and characteristic change trend data.

[0031] In a possible implementation, the unmanned vehicle stability status scoring system also includes: an early warning module.

[0032] The early warning module is used to issue a fault early warning according to the stability status scoring result.

[0033] The unmanned vehicle stability status scoring system in this application has the following advantages:

[0034] By collecting and analyzing vehicle operating status data and scoring the vehicle stability status, it is possible to identify potential vehicle equipment aging or wear problems, provide reference information for equipment maintenance, and thus improve the operating safety and reliability of unmanned vehicles.

[0035] The proposed obstacle feature extraction unit extracts features from obstacle information to obtain obstacle feature data, the traffic feature extraction unit extracts features from traffic information to obtain traffic feature data, the motion feature extraction unit extracts features from vehicle motion information to obtain motion feature data, and the control feature extraction unit extracts features from vehicle control information to obtain control feature data, thereby improving the comprehensiveness of subsequent feature analysis and status scoring.

[0036] The proposed feature analysis module uses time series analysis method to perform feature analysis on the operating status feature data, which improves the accuracy of feature change trend data.

[0037] The proposed status scoring module uses machine learning methods to score the vehicle stability status according to feature change trend data, which improves the scientific nature of the stability status scoring results.

[0038] The proposed data correction module dynamically corrects the current vehicle operating status data according to the historical vehicle operating status data and characteristic change trend data, thereby improving the accuracy of the stability status scoring results. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] 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 or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A schematic diagram of a module of a driverless vehicle stability status scoring system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0042] like Figure 1 As shown, an embodiment of the present application provides a stability status scoring system for an unmanned vehicle, including: a data acquisition module, a feature extraction module, a feature analysis module and a status scoring module.

[0043] The data acquisition module is used to collect vehicle running status data.

[0044] The feature extraction module is used to extract features from the vehicle running status data to obtain running status feature data.

[0045] The feature analysis module is used to perform feature analysis on the running status feature data to obtain feature change trend data.

[0046] The state scoring module is used to score the vehicle stability state according to the characteristic change trend data to obtain a stability state scoring result.

[0047] Specifically, in this embodiment, the feature extraction module, the feature analysis module and the state scoring module are all software modules arranged on the vehicle-mounted computer, and the data acquisition module is electrically connected to the vehicle-mounted computer.

[0048] In other possible embodiments, the feature extraction module, the feature analysis module and the state scoring module may also be arranged on a cloud server, and the data acquisition module is communicatively connected with the cloud server.

[0049] Exemplarily, the data acquisition module includes: an obstacle acquisition unit, a traffic information acquisition unit, a motion information acquisition unit and a control information acquisition unit.

[0050] The obstacle collection unit is used to collect obstacle information.

[0051] The traffic information collection unit is used to collect traffic information.

[0052] The motion information acquisition unit is used to acquire vehicle motion information.

[0053] The control information acquisition unit is used to acquire vehicle control information.

[0054] The vehicle operation status data includes the obstacle information, the traffic information, the vehicle motion information and the vehicle control information.

[0055] Specifically, in this embodiment, the obstacle collection unit uses a laser radar to collect obstacle distance and shape information.

[0056] The traffic information collection unit uses a camera to collect information on road conditions, traffic signs and environmental changes.

[0057] The motion information acquisition unit uses GPS and inertial measurement unit (IMU) to collect vehicle position, speed and acceleration information.

[0058] The control information acquisition unit adopts the vehicle control system to collect the vehicle driving status, such as steering angle, braking force and acceleration.

[0059] Exemplarily, the feature extraction module includes: an obstacle feature extraction unit, a traffic feature extraction unit, a motion feature extraction unit and a control feature extraction unit.

[0060] The obstacle feature extraction unit is used to extract features from the obstacle information to obtain obstacle feature data.

[0061] The traffic feature extraction unit is used to extract features from the traffic information to obtain traffic feature data.

[0062] The motion feature extraction unit is used to extract features from the vehicle motion information to obtain motion feature data.

[0063] The control feature extraction unit is used to extract features from the vehicle control information to obtain control feature data.

[0064] The operating status characteristic data includes the obstacle characteristic data, the traffic characteristic data, the motion characteristic data and the control characteristic data.

[0065] Specifically, in this embodiment, the obstacle feature data is the obstacle detection frequency; the traffic feature data is the traffic picture clarity index; the motion feature data is the navigation accuracy; and the control feature data is the vehicle control accuracy.

[0066] Exemplarily, the feature analysis module uses a time series analysis method to perform feature analysis on the operating status feature data to obtain feature change trend data.

[0067] Exemplarily, the time series analysis method includes: an autoregressive moving average model, an autoregressive integrated moving average model, an exponential smoothing method, and a time series neural network.

[0068] Specifically, in this embodiment, an autoregressive moving average model in a time series analysis method is used to perform feature analysis on obstacle feature data, traffic feature data, motion feature data, and control feature data, respectively.

[0069] Taking obstacle feature data as an example, the specific process of using the autoregressive moving average model to perform feature analysis on obstacle feature data is as follows:

[0070] First, historical data of obstacle feature data in the past period of time (in this embodiment, historical data of obstacle detection frequency), referred to as obstacle feature historical data, are obtained, and autocorrelation functions and partial autocorrelation functions of the obstacle feature historical data are calculated respectively. The autoregressive (AR) order of the autoregressive moving average model is obtained based on the calculation result of the autocorrelation function, and the moving average (MA) order of the autoregressive moving average model is obtained based on the calculation result of the partial autocorrelation function. The autoregressive moving average model is fitted based on the autoregressive (AR) order and the moving average (MA) order, and the obstacle feature historical data are predicted and analyzed to obtain feature change trend data of the obstacle feature data.

[0071] The process of using the autoregressive moving average model to perform feature analysis on traffic feature data, motion feature data and control feature data is similar to the feature analysis process of obstacle feature data.

[0072] Exemplarily, the state scoring module uses a machine learning method to score the vehicle stability state according to the characteristic change trend data to obtain a stability state scoring result.

[0073] Exemplarily, the machine learning method includes: a support vector machine algorithm, a random forest algorithm, a logistic regression algorithm, a linear regression algorithm, a cluster analysis algorithm and a Q learning algorithm.

[0074] Specifically, in this embodiment, a support vector machine algorithm is used to score the vehicle stability state according to the characteristic change trend data. The specific process is as follows:

[0075] A data set containing stability state scoring labels is pre-established (in this embodiment, the stability state scoring labels are set to an arithmetic progression of 0 to 100 with a tolerance of 5), each stability state scoring label corresponds to a number of data points (in this embodiment, each stability state scoring label corresponds to 10 data points, each data point includes a combination of characteristic change trend data of obstacle feature data, characteristic change trend data of traffic feature data, characteristic change trend data of motion feature data, and characteristic change trend data of control feature data); a kernel function of a support vector machine is selected (a linear kernel function is selected in this embodiment) to establish a support vector machine model; the data set is randomly divided into a training set and a test set in a ratio of 7:3, and the support vector machine model is trained and tested using the training set and the test set respectively to obtain a scoring model; the scoring model is used to score the vehicle stability state according to the actual characteristic change trend data to obtain a stability state scoring result; and the scoring model is updated regularly.

[0076] Exemplarily, the unmanned vehicle stability status scoring system also includes: a preprocessing module.

[0077] The preprocessing module is used to preprocess the vehicle running status data.

[0078] Specifically, in this embodiment, noise filtering and normalization processing are performed on the collected vehicle operation status data to improve data quality.

[0079] Exemplarily, the unmanned vehicle stability status scoring system also includes: a data correction module.

[0080] The data correction module is used to dynamically correct the current vehicle running status data based on historical vehicle running status data and characteristic change trend data.

[0081] Specifically, the current vehicle operating status theoretical data can be obtained through historical vehicle operating status data and characteristic change trend data. The current vehicle operating status data is compared with the current vehicle operating status theoretical data. If the deviation exceeds a preset deviation threshold (3% in this embodiment), the current vehicle operating status theoretical data is replaced with the current vehicle operating status theoretical data.

[0082] Exemplarily, the unmanned vehicle stability status scoring system also includes: an early warning module.

[0083] The early warning module is used to issue a fault early warning according to the stability status scoring result.

[0084] Specifically, when the stability status scoring result is lower than a preset scoring threshold, a corresponding fault warning is performed.

[0085] The embodiments of the present application collect and analyze vehicle operating status data, score the vehicle stability status, identify potential vehicle equipment aging or wear problems, and provide reference information for equipment maintenance, thereby improving the operating safety and reliability of unmanned vehicles.

[0086] The proposed obstacle feature extraction unit extracts features from obstacle information to obtain obstacle feature data, the traffic feature extraction unit extracts features from traffic information to obtain traffic feature data, the motion feature extraction unit extracts features from vehicle motion information to obtain motion feature data, and the control feature extraction unit extracts features from vehicle control information to obtain control feature data, thereby improving the comprehensiveness of subsequent feature analysis and status scoring.

[0087] The proposed feature analysis module uses time series analysis method to perform feature analysis on the operating status feature data, which improves the accuracy of feature change trend data.

[0088] The proposed status scoring module uses machine learning methods to score the vehicle stability status according to feature change trend data, which improves the scientific nature of the stability status scoring results.

[0089] The proposed data correction module dynamically corrects the current vehicle operating status data according to the historical vehicle operating status data and characteristic change trend data, thereby improving the accuracy of the stability status scoring results.

[0090] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0091] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An unmanned vehicle stability status scoring system, characterized in that: include: Data collection module, feature extraction module, feature analysis module and status scoring module; The data acquisition module is used to collect vehicle operation status data; The feature extraction module is used to extract features from the vehicle running state data to obtain running state feature data; The feature analysis module is used to perform feature analysis on the running status feature data to obtain feature change trend data; The state scoring module is used to score the vehicle stability state according to the characteristic change trend data to obtain a stability state scoring result.

2. The unmanned vehicle stability status scoring system according to claim 1, characterized in that: The data acquisition module includes: an obstacle acquisition unit, a traffic information acquisition unit, a motion information acquisition unit and a control information acquisition unit; The obstacle collection unit is used to collect obstacle information; The traffic information collection unit is used to collect traffic information; The motion information acquisition unit is used to collect vehicle motion information; The control information acquisition unit is used to collect vehicle control information; The vehicle operation status data includes the obstacle information, the traffic information, the vehicle motion information and the vehicle control information.

3. The unmanned vehicle stability status scoring system according to claim 2, characterized in that: The feature extraction module includes: an obstacle feature extraction unit, a traffic feature extraction unit, a motion feature extraction unit and a control feature extraction unit; The obstacle feature extraction unit is used to extract features from the obstacle information to obtain obstacle feature data; The traffic feature extraction unit is used to extract features from the traffic information to obtain traffic feature data; The motion feature extraction unit is used to extract features from the vehicle motion information to obtain motion feature data; The control feature extraction unit is used to extract features from the vehicle control information to obtain control feature data; The operating status characteristic data includes the obstacle characteristic data, the traffic characteristic data, the motion characteristic data and the control characteristic data.

4. The unmanned vehicle stability status scoring system according to claim 1, characterized in that: The feature analysis module uses a time series analysis method to perform feature analysis on the operating status feature data to obtain feature change trend data.

5. The unmanned vehicle stability status scoring system according to claim 4, characterized in that: The time series analysis method includes: autoregressive moving average model, autoregressive integrated sliding average model, exponential smoothing method and time series neural network.

6. The unmanned vehicle stability status scoring system according to claim 1, characterized in that: The state scoring module uses a machine learning method to score the vehicle stability state according to the characteristic change trend data to obtain a stability state scoring result.

7. The unmanned vehicle stability status scoring system according to claim 6, characterized in that: The machine learning methods include: support vector machine algorithm, random forest algorithm, logistic regression algorithm, linear regression algorithm, cluster analysis algorithm and Q learning algorithm.

8. The unmanned vehicle stability status scoring system according to claim 1, characterized in that: Also includes: Preprocessing module; The preprocessing module is used to preprocess the vehicle running status data.

9. The unmanned vehicle stability status scoring system according to claim 1, characterized in that: Also includes: Data correction module; The data correction module is used to dynamically correct the current vehicle running status data based on historical vehicle running status data and characteristic change trend data.

10. The unmanned vehicle stability status scoring system according to claim 1, characterized in that: Also includes: Early warning module; The early warning module is used to issue a fault early warning according to the stability status scoring result.