Vehicle centering travel control method, device, apparatus, medium, and product

Abstract

This application relates to a vehicle centering control method, apparatus, computer device, storage medium, and computer program product. The method includes: first, acquiring initial influence parameters; then, conducting orthogonal experiments based on the initial influence parameters; determining a target evaluation index based on the experimental results of the orthogonal experiments; the target evaluation index characterizing the degree of influence of the initial influence parameters on vehicle centering; next, determining a first target influence parameter from the initial influence parameters based on the target evaluation index; and finally, controlling vehicle centering based on the first target influence parameter. The method provided in this application determines the degree of influence of different initial influence parameters on vehicle centering based on the results of orthogonal experiments, thereby selecting a first target influence parameter that significantly affects vehicle centering, thus improving the accuracy of vehicle centering control.

Description

Technical Field

[0001] This application relates to the field of intelligent driving control technology, and in particular to a vehicle centering driving control method, device, computer equipment, storage medium and computer program product. Background Technology

[0002] Intelligent driving vehicles combine vehicle control with AI technology, enabling lateral and longitudinal control of the vehicle through a controller. Level 2 (L2) intelligent driving assistance systems provide drivers with adequate rest time, reducing the workload of long-distance driving and improving driving safety. L2 intelligent driving systems mainly consist of two parts: single-lane centering control and adaptive cruise control. Single-lane centering control identifies and fits the lane lines ahead of the vehicle to obtain the position of the lane centerline and controls the steering wheel to keep the vehicle traveling along the lane centerline.

[0003] Currently, commonly used lane centering control methods include preview control and deep reinforcement learning. Both methods control the vehicle's lane centering based on the vehicle's own parameters and the lane line fitting parameters identified by the forward-facing camera. However, both methods treat the influence of all parameters on the vehicle's centering as the same, without distinguishing the differences in the influence of different parameters on the vehicle's centering. This makes the control of the vehicle's centering not precise enough, which may affect driving safety. Summary of the Invention

[0004] Therefore, it is necessary to provide a vehicle centering control method, device, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy and safety of vehicle centering control in response to the above-mentioned technical problems.

[0005] In a first aspect, this application provides a vehicle centering driving control method, the method comprising:

[0006] Obtain the initial impact parameters;

[0007] Orthogonal experiments were conducted based on the initial influence parameters.

[0008] The target evaluation index is determined based on the test results of the orthogonal experiment. The target evaluation index is used to characterize the degree of influence of the initial influence parameter on the vehicle's centering driving.

[0009] The first target impact parameter is determined from the initial impact parameter based on the target evaluation index;

[0010] The vehicle is controlled to stay centered based on the first target influence parameter.

[0011] In one embodiment, determining the target evaluation index based on the test results of the orthogonal experiment includes:

[0012] Based on the test results, a first initial evaluation index and a second initial evaluation index are determined. The first initial evaluation index is used to characterize the degree of influence of the initial influence parameter on the steering wheel angle, and the second initial evaluation index is used to characterize the degree of influence of the initial influence parameter on the steering wheel speed.

[0013] The first initial evaluation index and the second initial evaluation index are normalized respectively to obtain the first normalized index and the second normalized index.

[0014] The target evaluation index is obtained by weighting the first normalized index and the second normalized index.

[0015] In one embodiment, controlling the vehicle to center its movement according to the first target influence parameter includes:

[0016] Based on the first target influence parameter and the test results, a first correspondence between the steering wheel angle and the target influence parameter, and a second correspondence between the steering wheel speed and the target influence parameter are determined.

[0017] Acquire the second target's influence parameters during vehicle movement;

[0018] The target steering wheel angle and target steering wheel speed are determined based on the second target influence parameters, the first correspondence, and the second correspondence.

[0019] Control the vehicle to stay centered based on the target steering wheel angle and target steering wheel speed.

[0020] In one embodiment, obtaining the second target influence parameter during vehicle movement includes:

[0021] Obtain the vehicle information and the lane information of the vehicle.

[0022] Based on the vehicle information and the lane line information, determine the lateral distance and orientation angle between the vehicle and the lane line;

[0023] The second target influence parameters are determined based on the vehicle information, the lane line information, the lateral distance, and the orientation angle.

[0024] In one embodiment, determining the target steering wheel angle and target steering wheel speed based on the second target influence parameter, the first correspondence, and the second correspondence includes:

[0025] The upper limit values ​​of the steering wheel angle and the steering wheel speed during the vehicle's driving process are obtained. The upper limit value of the steering wheel angle is linearly related to the vehicle's driving speed, and the upper limit value of the steering wheel speed is linearly related to the steering wheel angle.

[0026] The target steering wheel angle and the target steering wheel speed are determined based on the second target influence parameter, the first correspondence, the second correspondence, the upper limit of the steering wheel angle, and the upper limit of the steering wheel speed.

[0027] In one embodiment, the method further includes:

[0028] Determine the state of the vehicle during its operation;

[0029] If the state is at least one of the following: failure to acquire the second target influence parameter and a malfunction in the vehicle's centering control system, an alarm signal is issued.

[0030] Secondly, this application provides a vehicle centering driving control device, the device comprising:

[0031] The acquisition module is used to acquire initial influence parameters;

[0032] An orthogonal experiment module is used to conduct orthogonal experiments based on the initial influence parameters;

[0033] The first determining module is used to determine the target evaluation index based on the test results of the orthogonal experiment. The target evaluation index is used to characterize the degree of influence of the initial influence parameter on the vehicle's centering driving.

[0034] The second determining module is used to determine the first target impact parameter from the initial impact parameter based on the target evaluation index;

[0035] The control module is used to control the vehicle to drive in the center according to the first target influence parameter.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the methods in any of the above embodiments.

[0037] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the methods in any of the above embodiments.

[0038] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the methods in any of the above embodiments.

[0039] The aforementioned vehicle centering control method, device, computer equipment, storage medium, and computer program product first acquire initial influence parameters, then conduct orthogonal experiments based on these parameters, and determine a target evaluation index based on the experimental results. This target evaluation index characterizes the degree of influence of the initial influence parameters on vehicle centering. Next, a first target influence parameter is determined from the initial influence parameters based on the target evaluation index, and finally, vehicle centering is controlled based on the first target influence parameter. The method provided in this application determines the degree of influence of different initial influence parameters on vehicle centering based on the results of orthogonal experiments, thereby selecting a first target influence parameter that significantly affects vehicle centering, thus improving the accuracy of vehicle centering control. Attached Figure Description

[0040] Figure 1 This is an application environment diagram of the vehicle centering driving control method in one embodiment;

[0041] Figure 2 This is a flowchart illustrating a vehicle centering control method in one embodiment;

[0042] Figure 3 This is a flowchart illustrating the process of determining the second target influence parameters in one embodiment;

[0043] Figure 4 Here is a flowchart of the parameter influence analysis method in another embodiment;

[0044] Figure 5 Here is a flowchart of a vehicle centering driving control method in another embodiment;

[0045] Figure 6 This is a structural block diagram of a vehicle centering driving control device in one embodiment;

[0046] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0048] The vehicle centering control method provided in this application embodiment can be applied to, for example, Figure 1The application environment is shown in the diagram. The application environment includes the vehicle's forward-facing camera 102, the vehicle's intelligent domain controller 104, and the vehicle 106. The intelligent domain controller 104 first controls the forward-facing camera 102 to collect lane line information, then obtains lane line information from the forward-facing camera 102 and vehicle information from the vehicle 106. Finally, the intelligent domain controller 104 determines initial influence parameters based on the vehicle information and lane line information, and controls the vehicle 106 to maintain centering based on the degree of influence of the initial influence parameters on the vehicle's centering.

[0049] In one embodiment, such as Figure 2 As shown, a vehicle centering driving control method is provided, which is applied to... Figure 1 Taking the intelligent domain controller in the example, the following steps are included:

[0050] S202, Obtain initial influence parameters.

[0051] Initial influencing parameters refer to parameters that may affect the vehicle's centering control process. These parameters may include vehicle weight, vehicle speed, average road curvature, average lateral distance between the vehicle and lane lines, and average heading angle between the vehicle and lane lines. Specifically, average road curvature is the average of the road curvatures between the vehicle and the left and right lane lines; average lateral distance is the average of the lateral distances between the vehicle and the left and right lane lines; and average heading angle is the average of the heading angles between the vehicle and the left and right lane lines.

[0052] The initial influencing parameters are selected from preset value ranges based on the driver's driving experience and the development experience of intelligent driving control algorithm engineers. For example, the preset value range for vehicle weight is 10 tons to 48 tons, and the preset value range for average road curvature is 0m. -1 up to 0.004m -1 The preset range for vehicle speed is 60km / h to 120km / h, the preset range for average lateral distance between vehicle and lane line is 0m to 0.4m, and the preset range for average orientation angle between vehicle and lane line is 0° to 20°.

[0053] S204. Conduct orthogonal experiments based on the initial influence parameters.

[0054] Orthogonal experiments are an experimental method for studying multiple factors and multiple levels.

[0055] Before conducting orthogonal experiments, experimental design is required. First, the acquired initial influencing parameters are identified as multiple factors. Then, multiple level values ​​are evenly selected from the preset value range of each initial influencing parameter. The number of independent test groups is determined according to the orthogonal principle. For example, if the initial influencing parameters are vehicle weight, vehicle speed, average road curvature, average lateral distance between the vehicle and the lane line, and average orientation angle between the vehicle and the lane line, then these five initial influencing parameters are identified as five factors. Then, nine values ​​are evenly selected from the preset value range of each factor as level values. Finally, according to the orthogonal experiment principle, the number of independent test groups is determined to be 81 groups.

[0056] Specifically, the driver drives the vehicle and conducts multiple independent tests in sequence according to the design results of the orthogonal test. During the test, the vehicle is controlled to drive along the center line of the lane as much as possible. The values ​​of the initial influencing parameters, the angle of the steering wheel controlled by the driver, and the speed of the steering wheel are recorded during the test to obtain multiple test results.

[0057] Two experiments were conducted based on the same orthogonal experimental design results. The effects of the initial influence parameters on the steering wheel angle and the steering wheel speed were analyzed respectively.

[0058] S206. Determine the target evaluation index based on the test results of the orthogonal experiment. The target evaluation index is used to characterize the degree of influence of the initial influence parameters on the vehicle's centering driving.

[0059] The experimental error of each initial influence parameter in each set of experiments is determined based on multiple level values ​​and multiple values ​​recorded during the experiment. Then, the mean square sum of errors for each initial influence parameter is determined based on the multiple experimental errors and degrees of freedom of each experimental error. Next, the target ratio of the mean square sum of each initial influence parameter to the target mean square sum of errors is calculated. Finally, the target evaluation index is determined based on the target ratio corresponding to each initial influence parameter. The degrees of freedom of the experimental error are determined based on the number of independent experimental sets, and the degrees of freedom of the initial influence parameter are determined based on the number of level values.

[0060] S208. Determine the first target impact parameter from the initial impact parameters based on the target evaluation index.

[0061] The first objective influence parameter refers to the initial influence parameter that has a significant impact on the control process of centering the vehicle. The first objective influence parameter is the influence parameter that ultimately controls the vehicle to center its movement.

[0062] Specifically, the intelligent domain controller determines the magnitude of the target evaluation index and the preset index threshold for each initial influence parameter. If the target evaluation index of the initial influence parameter is greater than the preset index threshold, then the initial influence parameter is determined as the first target influence parameter. For example, through calculation, the target evaluation index for vehicle weight is 0.1, the target evaluation index for vehicle speed is 0.3, the target evaluation index for average road curvature is 0.7, and the target evaluation indices for the average lateral distance between the vehicle and the lane line and the average orientation angle between the vehicle and the lane line are both 0.9, while the preset index threshold is 0.6. Therefore, the average road curvature, the average lateral distance between the vehicle and the lane line, and the average orientation angle between the vehicle and the lane line are determined as the first target influence parameters.

[0063] S210. Control the vehicle to stay centered based on the first target influence parameters.

[0064] Based on the experimental results of the orthogonal experiment and the first target influence parameter, the relationship between steering wheel speed and target influence parameter and the relationship between steering wheel angle and target influence parameter can be determined respectively.

[0065] During vehicle operation, the intelligent domain controller acquires the current target influence parameters and determines the steering wheel speed and steering wheel angle based on the relationship between the steering wheel speed and the target influence parameters, as well as the relationship between the steering wheel angle and the target influence parameters. Finally, the vehicle is controlled to stay centered by using the steering wheel speed and steering wheel angle.

[0066] In the aforementioned vehicle centering control method, initial influence parameters are first obtained. Then, orthogonal experiments are conducted based on these parameters, and a target evaluation index is determined based on the experimental results. This target evaluation index characterizes the degree of influence of the initial influence parameters on vehicle centering. Next, a first target influence parameter is determined from the initial influence parameters based on the target evaluation index. Finally, vehicle centering is controlled based on the first target influence parameter. The method provided in this application determines the degree of influence of different initial influence parameters on vehicle centering based on the results of orthogonal experiments, thereby selecting a first target influence parameter that significantly affects vehicle centering, thus improving the accuracy of vehicle centering control.

[0067] In some embodiments, determining the target evaluation index based on the test results of orthogonal experiments includes: determining a first initial evaluation index and a second initial evaluation index based on the test results, wherein the first initial evaluation index is used to characterize the degree of influence of the initial influence parameter on the steering wheel angle, and the second initial evaluation index is used to characterize the degree of influence of the initial influence parameter on the steering wheel speed; normalizing the first initial evaluation index and the second initial evaluation index respectively to obtain a first normalized index and a second normalized index; and performing a weighted calculation on the first normalized index and the second normalized index to obtain the target evaluation index.

[0068] In this step, the target ratio of each initial influence parameter with respect to the steering wheel angle and the target ratio of each initial influence parameter with respect to the steering wheel speed can be obtained from two orthogonal experiments. Then, the first evaluation index is determined based on the target ratio of each initial influence parameter with respect to the steering wheel angle, and the second evaluation index is determined based on the target ratio of each initial influence parameter with respect to the steering wheel speed. Next, the first and second evaluation indices are normalized to obtain the first normalized index and the second normalized index. Finally, the two normalized indices are weighted to obtain the target evaluation index for each initial influence parameter.

[0069] The method provided in this step determines the target evaluation index for each initial influence parameter by normalizing and weighting the target ratio, so that initial influence parameters of different dimensions and scales can be compared together to determine their impact on the centering of the vehicle.

[0070] In some embodiments, controlling the vehicle to drive in the center according to the first target influence parameter includes: determining a first correspondence between the steering wheel angle and the target influence parameter, and a second correspondence between the steering wheel speed and the target influence parameter, based on the first target influence parameter and test results; acquiring a second target influence parameter during vehicle driving; determining a target steering wheel angle and a target steering wheel speed based on the second target influence parameter, the first correspondence, and the second correspondence; and controlling the vehicle to drive in the center according to the target steering wheel angle and the target steering wheel speed.

[0071] In this step, the first and second correspondences are determined based on the first target influence parameter and the experimental results. However, the first correspondence can be used to determine the relationship between the target steering wheel angle and the second target influence parameter, and the second correspondence can be used to determine the relationship between the target steering wheel speed and the second target influence parameter. The second target influence parameter and the first target influence parameter have the same parameter types. The first and second correspondences can be determined using fitting methods such as neural networks.

[0072] The method provided in this step controls the steering wheel angle and steering wheel speed according to the first and second correspondences, thereby controlling the vehicle to drive in the center and improving the accuracy of vehicle centering control.

[0073] In some embodiments, such as Figure 3 As shown, Figure 3In one embodiment, a method for determining a second target influence parameter includes: acquiring vehicle information and lane information of the vehicle; determining the lateral distance and azimuth angle between the vehicle and the lane based on the vehicle information and the lane information; and determining the second target influence parameter based on the vehicle information, lane information, lateral distance, and azimuth angle.

[0074] In this step, vehicle information refers to the vehicle's own parameter information, such as vehicle weight and vehicle speed; lane line information refers to the fitting parameters of the lane lines on the left and right sides of the vehicle; the lateral distance between the vehicle and the lane lines refers to the lateral distance between the vehicle's front-view camera and the lane lines on both sides; and the orientation angle between the vehicle and the lane lines refers to the orientation angle between the vehicle and the lane lines on the left and right sides.

[0075] For example, the initial influencing parameters are vehicle weight, vehicle speed, average road curvature, average lateral distance between the vehicle and the lane line, and average orientation angle between the vehicle and the lane line. The second target influencing parameter is one or more of the above initial influencing parameters. The vehicle weight can be the sum of the towing vehicle's cargo capacity and the vehicle's curb weight. The vehicle speed signal can be directly read from the vehicle's drive-by-wire chassis as the vehicle's driving speed. The average road curvature, average lateral distance, and average heading angle can be determined based on the fitting parameters in the point coordinates (x, C0+C1*x+C2*x^2+C3*x^3), where x represents the vertical distance between a point in front of the vehicle and the front of the vehicle. C0, C1, C2, and C3 are all fitting parameters. C0 represents the lateral distance between the lane line and the vehicle's forward-facing camera, C1 represents the heading angle between the lane line and the vehicle, C2 represents the lane line curvature, and C3 represents the rate of change of the lane line curvature. The average value of C2 on both sides of the vehicle is determined as the average road curvature, the average value of C0 between the lane lines on both sides and the vehicle's forward-facing camera is determined as the average lateral distance, and the average value of C1 between the lane lines on both sides and the vehicle is determined as the average heading angle.

[0076] The method provided in this step can determine the second target influence parameters during vehicle movement based on vehicle information and lane line information, thereby improving the efficiency and accuracy of the second target influence parameter determination process.

[0077] In some embodiments, determining the target steering wheel angle and target steering wheel speed based on the second target influence parameter, the first correspondence, and the second correspondence includes: obtaining the upper limit value of the steering wheel angle and the upper limit value of the steering wheel speed during vehicle driving, wherein the upper limit value of the steering wheel angle is linearly related to the vehicle driving speed and the upper limit value of the steering wheel speed is linearly related to the steering wheel angle; and determining the target steering wheel angle and target steering wheel speed based on the second target influence parameter, the first correspondence, the second correspondence, the upper limit value of the steering wheel angle, and the upper limit value of the steering wheel speed.

[0078] In this step, the upper limit of steering wheel angle refers to the maximum allowed steering wheel angle, and the upper limit of steering wheel speed refers to the maximum allowed steering wheel speed. The upper limit of steering wheel angle has a linear relationship with vehicle speed. For example, at a vehicle speed of 120 km / h, the steering wheel angle is limited to no more than 30°, and at a vehicle speed of 60 km / h, the steering wheel angle is limited to no more than 70°. The upper limit of steering wheel angle corresponding to the intermediate vehicle speed is obtained through linear interpolation. Similarly, the upper limit of steering wheel speed has a linear relationship with steering wheel angle. For example, at a steering wheel angle of 0°, the speed is limited to no more than 1 rad / s, and at a steering wheel angle of 70°, the speed is limited to no more than 0.4 rad / s. The upper limit of steering wheel speed corresponding to the intermediate steering wheel angle is obtained through linear interpolation.

[0079] The method provided in this step, by limiting the maximum steering wheel angle and the maximum steering wheel speed, can prevent frequent steering wheel rotation and ensure vehicle driving safety.

[0080] In some embodiments, the method further includes: determining the state of the vehicle during driving; and issuing an alarm signal if the state is at least one of failure to acquire the second target influence parameter and a malfunction in the vehicle's centering control system.

[0081] In this step, if the vehicle experiences any of the following situations when the vehicle centering control system is activated: the intelligent domain controller fails to acquire the second target influence parameters, or the vehicle centering control system experiences a communication or mechanical failure, the vehicle will issue an alarm signal to remind the driver to take over the steering wheel.

[0082] The method provided in this step reminds the driver to take over the steering wheel when the vehicle encounters a problem, ensuring safety while the vehicle is centered.

[0083] In one embodiment, another method for vehicle centering control is provided, such as Figure 4 and Figure 5 As shown, Figure 4 Here is a flowchart of the parameter influence analysis method in another embodiment. Figure 5 This is a flowchart of a vehicle centering control method in another embodiment. This method includes two parts: parameter influence analysis and control method.

[0084] (1) The parameter influence analysis is conducted first before the development of the control method. The main influencing parameters are selected through analysis and considered in the development of the control method. The parameter influence analysis mainly includes the determination of influencing parameters, orthogonal experimental design, experimental condition data collection, and parameter influence significance analysis.

[0085] 1) Determination of Influencing Parameters. Based on the driving experience of drivers and the development experience of intelligent driving control algorithm engineers, several parameters that may affect the lane centering control effect are initially selected. In this method, the vehicle's total weight, road curvature, vehicle speed, the lateral distance error between the L2 (Level 2 autonomous driving) forward-looking camera and the lane centerline, and the vehicle's heading angle error are selected as initial influencing parameters. Taking a heavy-duty trailer tractor as an example, the range of values ​​for the above parameters is given: the vehicle's total weight ranges from 10 to 48 tons, and the road curvature ranges from 0 to 0.004m. -1 The vehicle speed range is 60-120km / h, the lateral distance error between the L2 forward-view camera and the lane centerline ranges from 0-0.4m, and the vehicle's orientation angle error ranges from 0°-20°.

[0086] 2) Orthogonal experimental design. In order to accurately reflect the influence of parameters and provide a sufficient number of analytical samples, the above 5 initial influence parameters are used as 5 factors in the orthogonal experiment. The number of levels for each factor is 9. Nine level values ​​are evenly selected within the range of values ​​of each initial influence parameter to conduct the orthogonal experimental design. After the experimental design, 81 independent experiments need to be conducted.

[0087] 3) Test Condition Data Acquisition Section. The driver drives the vehicle and conducts 81 independent tests in sequence according to the orthogonal test design results. During the test, the driver controls the vehicle to drive along the center line of the lane as well as possible. Data such as road curvature, vehicle speed, lateral distance error between the L2 forward-looking camera and the center line of the lane, vehicle orientation angle error, and the steering wheel angle and speed signals controlled by the driver are collected. The current vehicle weight is also recorded to form 81 sets of datasets.

[0088] 4) Parameter Influence Significance Analysis. This section analyzes the impact of five initial influencing parameters—vehicle total weight, road curvature, vehicle speed, lateral distance error between the L2 forward-looking camera and the lane centerline, and vehicle orientation angle error—on the driver's control of the steering wheel angle and speed. Since the values ​​of these five initial influencing parameters vary considerably and their effects are not entirely linear, a parameter influence significance analysis is performed. For the orthogonal experimental design described above, the degrees of freedom for each initial influencing parameter are 8, and the degrees of freedom for the experimental error are 40. The F-value is calculated, and the significance of each initial influencing parameter's impact on steering wheel control is determined using the F-distribution quantile table. The F-value is defined as the ratio of the sum of the mean squares of each initial influencing parameter to the sum of the mean squares of the error. The steering wheel control evaluation comprehensively considers the driver's control of the steering wheel angle and speed. After normalizing the steering wheel angle and speed, the weight of the steering wheel angle is set to 0.7, and the weight of the speed is set to 0.3. The weighted sum of these two values ​​serves as the evaluation parameter for the driver's degree of steering wheel control. Through parameter influence significance analysis, initial influence parameters that have a significant impact on the degree of steering wheel control are selected as consideration parameters for lane centering control, while parameters with insignificant influence are not considered in single-lane centering control.

[0089] (2) The control method section mainly includes steering wheel control quantity sample fitting, parameter calculation, steering wheel control quantity solution and HMI module.

[0090] 1) Steering wheel control quantity sample fitting. 81 sets of experimental data were fitted, with the parameters that have a significant impact on the degree of steering wheel control as inputs and the steering wheel angle and speed as outputs. The fitting method was a neural network. 10% of the dataset was randomly selected as the test set, and the effect of the neural network was evaluated and verified by the relative error and coefficient of determination of the test set.

[0091] 2) Consideration parameter calculation involves real-time acquisition and calculation of significantly influential parameters during vehicle operation when lane centering control is activated. For the vehicle gross weight parameter, it is estimated based on the sum of the towing vehicle's cargo capacity and the vehicle's curb weight. This can be set by the driver via dashboard buttons and sent to the L2 controller via drive-by-wire signals. For the road curvature parameter, it is obtained from the fitting parameters of the left and right lane lines output by the L2 forward-facing camera. The fitted lane lines output by the camera are mostly cubic polynomials. At position x in front of the vehicle, the coordinates of a point on the lane line are represented as (x, C0+C1*x+C2*x^2+C3*x^3). The fitting parameters C0, C1, C2, and C3 physically represent the lane line and the camera's position along the vehicle's path, respectively. The deviation distance in the vertical direction, the lane line's direction angle relative to the vehicle, the lane line curvature, and the rate of change of the lane line curvature are all calculated by taking the average of the left and right C2 parameters as the road curvature. For the vehicle speed parameter, the vehicle speed signal is directly read from the vehicle's drive-by-wire chassis. For the lateral distance error between the L2 forward-view camera and the lane centerline, and the vehicle's direction angle error, these are obtained based on the left and right lane line fitting parameters output by the L2 forward-view camera. The average of the left and right C0 parameters is taken as the lateral distance error between the L2 forward-view camera and the lane centerline, and the average of the left and right C1 parameters is taken as the vehicle's direction angle error.

[0092] 3) Steering wheel control quantity calculation: Based on the values ​​of various considered parameters obtained from the parameter calculation section, the values ​​are input to the neural network model obtained from the steering wheel control quantity sample fitting section to obtain the required steering angle and speed control quantities. To ensure control safety and avoid frequent steering wheel rotation, limits are imposed on the steering wheel angle control quantity. The limit varies depending on the vehicle speed: at a speed of 120 km / h, the angle is limited to no more than 30°; at a speed of 60 km / h, the angle is limited to no more than 70°; the intermediate speed steering wheel angle limit is obtained through linear interpolation. The steering wheel speed limit also varies with the steering wheel angle: at a steering wheel angle of 0°, the speed is limited to no more than 1 rad / s; at a steering wheel angle of 70°, the speed is limited to no more than 0.4 rad / s; the intermediate steering wheel angle speed limit is obtained through linear interpolation.

[0093] 4) The HMI (Human Machine Interface) module is used for human-machine interaction between the lane centering control system and the driver, displaying the current status of the lane centering control system. When the lane centering control system is off, the status is 0. After adaptive cruise control is activated, the driver can turn the lane centering control system on and off via a switch. When the lane centering control system is on and functioning normally, the status is 1. When parameter calculation fails, the status is 2. When the lane centering control system experiences a communication or hardware failure, the status is 3. When the lane centering control system status is 2 or 3, an audible alarm will alert the driver to take over steering.

[0094] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0095] Based on the same inventive concept, this application also provides a vehicle centering driving control device for implementing the vehicle centering driving control method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more vehicle centering driving control device embodiments provided below can be found in the limitations of the vehicle centering driving control method described above, and will not be repeated here.

[0096] In one embodiment, such as Figure 6 As shown, a vehicle centering driving control device 600 is provided, including: an acquisition module 601, an orthogonal test module 602, a first determination module 603, a second determination module 604, and a control module 605, wherein:

[0097] The acquisition module 601 is used to acquire the initial influence parameters.

[0098] The orthogonal experiment module 602 is used to conduct orthogonal experiments based on the initial influence parameters.

[0099] The first determining module 603 is used to determine the target evaluation index based on the test results of the orthogonal experiment. The target evaluation index is used to characterize the degree of influence of the initial influence parameter on the vehicle's centering driving.

[0100] The second determining module 604 is used to determine the first target influence parameter from the initial influence parameters based on the target evaluation index.

[0101] The control module 605 is used to control the vehicle to drive in the center according to the first target influence parameter.

[0102] In some embodiments, the first determining module 603 is further configured to: determine a first initial evaluation index and a second initial evaluation index based on the test results, wherein the first initial evaluation index is used to characterize the degree of influence of the initial influence parameter on the steering wheel angle, and the second initial evaluation index is used to characterize the degree of influence of the initial influence parameter on the steering wheel speed; normalize the first initial evaluation index and the second initial evaluation index respectively to obtain a first normalized index and a second normalized index; and perform a weighted calculation on the first normalized index and the second normalized index to obtain the target evaluation index.

[0103] In some embodiments, the control module 605 includes:

[0104] The first determining unit is used to determine, based on the first target influence parameter and the test results, a first correspondence between the steering wheel angle and the target influence parameter, and a second correspondence between the steering wheel speed and the target influence parameter;

[0105] The acquisition unit is used to acquire the second target influence parameters during the vehicle's movement.

[0106] The second determining unit is used to determine the target steering wheel angle and the target steering wheel speed based on the second target influence parameters, the first correspondence, and the second correspondence.

[0107] The control unit is used to control the vehicle to stay centered based on the target steering wheel angle and the target steering wheel speed.

[0108] In some embodiments, the acquisition unit is further configured to: acquire vehicle information of the vehicle and lane information of the lane the vehicle is traveling on; determine the lateral distance and azimuth angle between the vehicle and the lane based on the vehicle information and the lane information; and determine the second target influence parameter based on the vehicle information, the lane information, the lateral distance and the azimuth angle.

[0109] In some embodiments, the second determining unit is further configured to: obtain the upper limit value of the steering wheel angle and the upper limit value of the steering wheel speed during the vehicle's driving process, wherein the upper limit value of the steering wheel angle is linearly related to the vehicle's driving speed and the upper limit value of the steering wheel speed is linearly related to the steering wheel angle; and determine the target steering wheel angle and the target steering wheel speed based on the second target influence parameter, the first correspondence, the second correspondence, the upper limit value of the steering wheel angle, and the upper limit value of the steering wheel speed.

[0110] In some embodiments, the vehicle centering driving control device 600 is specifically used to: determine the state of the vehicle during driving; and if the state is at least one of the failure to acquire the second target influence parameter and a malfunction in the vehicle's centering control system, then issue an alarm signal.

[0111] The various modules in the aforementioned vehicle centering and driving control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0112] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data related to influencing parameters. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements a vehicle centering driving control method.

[0113] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0114] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: obtaining initial influence parameters; conducting orthogonal experiments based on the initial influence parameters; determining a target evaluation index based on the experimental results of the orthogonal experiments, the target evaluation index being used to characterize the degree of influence of the initial influence parameters on the centering of the vehicle; determining a first target influence parameter from the initial influence parameters based on the target evaluation index; and controlling the vehicle to center its movement based on the first target influence parameter.

[0115] In one embodiment, the determination of a target evaluation index based on the test results of the orthogonal experiment, implemented by the processor executing the computer program, includes: determining a first initial evaluation index and a second initial evaluation index based on the test results, wherein the first initial evaluation index characterizes the degree of influence of the initial influence parameter on the steering wheel angle, and the second initial evaluation index characterizes the degree of influence of the initial influence parameter on the steering wheel speed; normalizing the first initial evaluation index and the second initial evaluation index respectively to obtain a first normalized index and a second normalized index; and performing a weighted calculation on the first normalized index and the second normalized index to obtain the target evaluation index.

[0116] In one embodiment, the control of vehicle centering based on the first target influence parameter implemented by the processor executing the computer program includes: determining a first correspondence between the steering wheel angle and the target influence parameter, and a second correspondence between the steering wheel speed and the target influence parameter, based on the first target influence parameter and the test results; acquiring a second target influence parameter during vehicle driving; determining a target steering wheel angle and a target steering wheel speed based on the second target influence parameter, the first correspondence, and the second correspondence; and controlling vehicle centering based on the target steering wheel angle and the target steering wheel speed.

[0117] In one embodiment, the acquisition of second target influence parameters during vehicle driving, implemented by the processor executing a computer program, includes: acquiring vehicle information and lane information of the vehicle; determining the lateral distance and azimuth angle between the vehicle and the lane based on the vehicle information and the lane information; and determining the second target influence parameters based on the vehicle information, the lane information, the lateral distance, and the azimuth angle.

[0118] In one embodiment, the process of determining the target steering wheel angle and target steering wheel speed based on the second target influence parameter, the first correspondence, and the second correspondence when the processor executes a computer program includes: obtaining the upper limit value of the steering wheel angle and the upper limit value of the steering wheel speed during vehicle operation, wherein the upper limit value of the steering wheel angle is linearly related to the vehicle speed and the upper limit value of the steering wheel speed is linearly related to the steering wheel angle; and determining the target steering wheel angle and target steering wheel speed based on the second target influence parameter, the first correspondence, the second correspondence, the upper limit value of the steering wheel angle, and the upper limit value of the steering wheel speed.

[0119] In one embodiment, the method implemented by the processor when executing the computer program further includes: determining the state of the vehicle during driving; and issuing an alarm signal if the state is at least one of the failure to acquire the second target influence parameter and a malfunction in the vehicle's centering control system.

[0120] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon. When executed by a processor, the computer program performs the following steps: obtaining initial influence parameters; conducting orthogonal experiments based on the initial influence parameters; determining a target evaluation index based on the experimental results of the orthogonal experiments, the target evaluation index being used to characterize the degree of influence of the initial influence parameters on the centering of the vehicle; determining a first target influence parameter from the initial influence parameters based on the target evaluation index; and controlling the vehicle to center its movement based on the first target influence parameter.

[0121] In one embodiment, the computer program, when executed by a processor, determines a target evaluation index based on the test results of the orthogonal experiment, including: determining a first initial evaluation index and a second initial evaluation index based on the test results, wherein the first initial evaluation index characterizes the degree of influence of the initial influence parameter on the steering wheel angle, and the second initial evaluation index characterizes the degree of influence of the initial influence parameter on the steering wheel speed; normalizing the first initial evaluation index and the second initial evaluation index respectively to obtain a first normalized index and a second normalized index; and performing a weighted calculation on the first normalized index and the second normalized index to obtain the target evaluation index.

[0122] In one embodiment, the computer program, when executed by a processor, controls the vehicle to drive in the center according to the first target influence parameter, including: determining a first correspondence between the steering wheel angle and the target influence parameter, and a second correspondence between the steering wheel speed and the target influence parameter, based on the first target influence parameter and the test results; acquiring a second target influence parameter during vehicle driving; determining a target steering wheel angle and a target steering wheel speed based on the second target influence parameter, the first correspondence, and the second correspondence; and controlling the vehicle to drive in the center according to the target steering wheel angle and the target steering wheel speed.

[0123] In one embodiment, the computer program, when executed by a processor, acquires second target influence parameters during vehicle operation, including: acquiring vehicle information and lane information of the vehicle; determining the lateral distance and azimuth angle between the vehicle and the lane based on the vehicle information and the lane information; and determining the second target influence parameters based on the vehicle information, the lane information, the lateral distance, and the azimuth angle.

[0124] In one embodiment, the computer program, when executed by a processor, determines the target steering wheel angle and target steering wheel speed based on the second target influence parameter, the first correspondence, and the second correspondence, including: obtaining the upper limit value of the steering wheel angle and the upper limit value of the steering wheel speed during vehicle operation, wherein the upper limit value of the steering wheel angle is linearly related to the vehicle speed and the upper limit value of the steering wheel speed is linearly related to the steering wheel angle; and determining the target steering wheel angle and target steering wheel speed based on the second target influence parameter, the first correspondence, the second correspondence, the upper limit value of the steering wheel angle, and the upper limit value of the steering wheel speed.

[0125] In one embodiment, the method implemented when the computer program is executed by the processor further includes: determining the state of the vehicle during driving; and issuing an alarm signal if the state is at least one of the failure to acquire the second target influence parameter and a malfunction in the vehicle's centering control system.

[0126] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: obtaining initial influence parameters; conducting orthogonal experiments based on the initial influence parameters; determining a target evaluation index based on the experimental results of the orthogonal experiments, the target evaluation index being used to characterize the degree of influence of the initial influence parameters on the centering of the vehicle; determining a first target influence parameter from the initial influence parameters based on the target evaluation index; and controlling the vehicle to center its movement based on the first target influence parameter.

[0127] In one embodiment, the computer program, when executed by a processor, determines a target evaluation index based on the test results of the orthogonal experiment, including: determining a first initial evaluation index and a second initial evaluation index based on the test results, wherein the first initial evaluation index characterizes the degree of influence of the initial influence parameter on the steering wheel angle, and the second initial evaluation index characterizes the degree of influence of the initial influence parameter on the steering wheel speed; normalizing the first initial evaluation index and the second initial evaluation index respectively to obtain a first normalized index and a second normalized index; and performing a weighted calculation on the first normalized index and the second normalized index to obtain the target evaluation index.

[0128] In one embodiment, the computer program, when executed by a processor, controls the vehicle to drive in the center according to the first target influence parameter, including: determining a first correspondence between the steering wheel angle and the target influence parameter, and a second correspondence between the steering wheel speed and the target influence parameter, based on the first target influence parameter and the test results; acquiring a second target influence parameter during vehicle driving; determining a target steering wheel angle and a target steering wheel speed based on the second target influence parameter, the first correspondence, and the second correspondence; and controlling the vehicle to drive in the center according to the target steering wheel angle and the target steering wheel speed.

[0129] In one embodiment, the computer program, when executed by a processor, acquires second target influence parameters during vehicle operation, including: acquiring vehicle information and lane information of the vehicle; determining the lateral distance and azimuth angle between the vehicle and the lane based on the vehicle information and the lane information; and determining the second target influence parameters based on the vehicle information, the lane information, the lateral distance, and the azimuth angle.

[0130] In one embodiment, the computer program, when executed by a processor, determines the target steering wheel angle and target steering wheel speed based on the second target influence parameter, the first correspondence, and the second correspondence, including: obtaining the upper limit value of the steering wheel angle and the upper limit value of the steering wheel speed during vehicle operation, wherein the upper limit value of the steering wheel angle is linearly related to the vehicle speed and the upper limit value of the steering wheel speed is linearly related to the steering wheel angle; and determining the target steering wheel angle and target steering wheel speed based on the second target influence parameter, the first correspondence, the second correspondence, the upper limit value of the steering wheel angle, and the upper limit value of the steering wheel speed.

[0131] In one embodiment, the method implemented when the computer program is executed by the processor further includes: determining the state of the vehicle during driving; and issuing an alarm signal if the state is at least one of the failure to acquire the second target influence parameter and a malfunction in the vehicle's centering control system.

[0132] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0133] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0134] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0135] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for controlling vehicle centering during driving, characterized in that, The method includes: Obtain initial influence parameters; the initial influence parameters include vehicle weight, vehicle speed, average road curvature, average lateral distance between the vehicle and the lane line, and average heading angle between the vehicle and the lane line; According to the pre-set orthogonal test design results and the initial influence parameters, multiple independent tests are conducted sequentially. During the test, the vehicle is controlled to drive along the center line of the lane, and the values ​​of the initial influence parameters, the steering wheel angle controlled by the driver, and the steering wheel speed are recorded to obtain the test results of each orthogonal test. The test results of the orthogonal test include the influence results of the initial influence parameters on the steering wheel angle and the steering wheel speed under the same orthogonal test design results. The target evaluation index is determined based on the test results of the orthogonal experiment. The target evaluation index is used to characterize the degree of influence of the initial influence parameter on the vehicle's centering driving. The first target impact parameter is determined from the initial impact parameter based on the target evaluation index; The vehicle is controlled to stay centered based on the first target influence parameter.

2. The method according to claim 1, characterized in that, The step of determining the target evaluation index based on the experimental results of the orthogonal experiment includes: Based on the test results, a first initial evaluation index and a second initial evaluation index are determined. The first initial evaluation index is used to characterize the degree of influence of the initial influence parameter on the steering wheel angle, and the second initial evaluation index is used to characterize the degree of influence of the initial influence parameter on the steering wheel speed. The first initial evaluation index and the second initial evaluation index are normalized respectively to obtain the first normalized index and the second normalized index. The target evaluation index is obtained by weighting the first normalized index and the second normalized index.

3. The method according to claim 1, characterized in that, The step of controlling the vehicle to drive in the center according to the first target influence parameter includes: Based on the first target influence parameter and the test results, a first correspondence between the steering wheel angle and the first target influence parameter, and a second correspondence between the steering wheel speed and the first target influence parameter are determined. Acquire the second target's influence parameters during vehicle movement; The target steering wheel angle and target steering wheel speed are determined based on the second target influence parameters, the first correspondence, and the second correspondence. Control the vehicle to stay centered based on the target steering wheel angle and target steering wheel speed.

4. The method according to claim 3, characterized in that, The acquisition of the second target influence parameters during vehicle operation includes: Obtain the vehicle information and the lane information of the vehicle. Based on the vehicle information and the lane line information, determine the lateral distance and orientation angle between the vehicle and the lane line; The second target influence parameters are determined based on the vehicle information, the lane line information, the lateral distance, and the orientation angle.

5. The method according to claim 3, characterized in that, The step of determining the target steering wheel angle and target steering wheel speed based on the second target influence parameter, the first correspondence, and the second correspondence includes: The upper limit values ​​of the steering wheel angle and the steering wheel speed during the vehicle's driving process are obtained. The upper limit value of the steering wheel angle is linearly related to the vehicle's driving speed, and the upper limit value of the steering wheel speed is linearly related to the steering wheel angle. The target steering wheel angle and the target steering wheel speed are determined based on the second target influence parameter, the first correspondence, the second correspondence, the upper limit of the steering wheel angle, and the upper limit of the steering wheel speed.

6. The method according to claim 3, characterized in that, The method further includes: Determine the state of the vehicle during its operation; If the state is at least one of the following: failure to acquire the second target influence parameter and a malfunction in the vehicle's centering control system, an alarm signal is issued.

7. A vehicle centering driving control device, characterized in that, The device includes: The acquisition module is used to acquire initial influence parameters, which include vehicle weight, vehicle speed, average road curvature, average lateral distance between the vehicle and the lane line, and average orientation angle between the vehicle and the lane line. The orthogonal test module is used to conduct multiple independent tests sequentially according to the preset orthogonal test design results and the initial influence parameters. During the test, the vehicle is controlled to drive along the center line of the lane, and the values ​​of the initial influence parameters, the steering wheel angle controlled by the driver, and the steering wheel speed are recorded to obtain the test results of each orthogonal test. The test results of the orthogonal test include the influence results of the initial influence parameters on the steering wheel angle and the influence results on the steering wheel speed under the same orthogonal test design results. The first determining module is used to determine the target evaluation index based on the test results of the orthogonal experiment. The target evaluation index is used to characterize the degree of influence of the initial influence parameter on the vehicle's centering driving. The second determining module is used to determine the first target impact parameter from the initial impact parameter based on the target evaluation index; The control module is used to control the vehicle to drive in the center according to the first target influence parameter.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images