Self-adaptive lane keeping auxiliary control method and system and vehicle
Through real-time lane line image processing and Kalman filtering evaluation, steering zero point adjustment is performed, which solves the problem of inconsistent correction strength between different vehicles and improves the user experience of the lane keeping assist system.
Patent Information
- Application Number
- CN202411121372.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-15
- Publication Date
- 2024-11-15
AI Technical Summary
The existing lane keeping assist system (LKA) has inconsistent correction strength due to EPS zero point difference and working conditions between different vehicles, which affects the user experience.
By capturing lane line images in real time, building a Cartesian coordinate system, identifying lane line information, using cubic equation fitting to calculate the offset distance, and using Kalman filter to evaluate the working conditions. If the conditions are met, the steering zero point adjustment will be performed until the deviation distance difference is corrected Less than the preset threshold.
It effectively solves the problem of inconsistent correction of left and right deviations in LKA functions, improves the consistency of strength during vehicle deviation correction, and improves user experience.
Smart Images

Figure CN118953347A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicle technology, and in particular to an adaptive lane keeping auxiliary control method, system, electronic equipment, storage medium and vehicle. Background Art
[0002] With the continuous development of intelligent driving cars in recent years, more and more new models of automobile manufacturers are equipped with intelligent driving assistance systems. Lane keeping assist system (LKA) is an important component of advanced intelligent driving assistance system (ADAS). It is designed to send out an alarm and actively control the vehicle back to the lane when the driver unconsciously controls the vehicle to avoid traffic accidents caused by the driver.
[0003] The system mainly consists of three parts: external sensors, LKA controller, and actuator. The core is the LKA controller, which obtains lane line information and vehicle status information of the current environment through sensors, and then analyzes and calculates through the vehicle deviation warning module to determine the dangerous situation of vehicle deviation and issue a deviation warning. If the driver does not operate the vehicle to return to the original lane, the steering control actively controls the vehicle to return to the original lane.
[0004] In the prior art, such a phenomenon was found in actual development and testing: the left and right correction forces of some vehicles are inconsistent, and the functional performance consistency and adaptability of different vehicles are poor. After investigation, it was found that the reason is that the EPS zero points of different vehicles are different when they leave the factory, and there are differences in the working conditions (tire pressure, quality, etc.) of different vehicles, and the zero position deviation is different. That is, when the vehicle is traveling in a straight line, the steering wheel angle is not 0°, and a small angle is required to go in a straight line. As a result, when the LKA function is activated, the left and right correction responses are inconsistent, and the left side correction force is large and the right side force is small, which affects the user experience.
[0005] Therefore, the present application provides an adaptive lane keeping assist control method to solve the above technical problems. Summary of the invention
[0006] The purpose of the present invention is to provide an adaptive lane keeping assist control method, system, electronic device, storage medium and vehicle, so as to solve the technical problem in the prior art that there are differences in different vehicle operating conditions, resulting in inconsistent responses of left and right deviation correction when the LKA function is activated, affecting the user experience.
[0007] In order to solve the above technical problems, the present invention provides an adaptive lane keeping assist control method, comprising:
[0008] In response to the real-time captured vehicle surrounding environment, a current lane line image is acquired, and a Cartesian coordinate system centered on the front bumper of the vehicle is constructed based on the lane line image;
[0009] In response to the lane line image, identifying left and right lane line information of the current road condition, fitting the lane line information in the form of a cubic equation, and calculating an offset distance of the vehicle relative to the lane line information;
[0010] In response to the triggering result of the LKA deviation correction, evaluating whether the current operating condition meets the preset adjustment requirement range, wherein the current operating condition includes the deviation speed, and the deviation speed is calculated by Kalman filtering;
[0011] If the current working condition meets the adjustment requirement range, the steering zero point adjustment is performed based on the offset distance difference until the deviation correction distance difference is less than a preset threshold, and the zero point adjustment value is updated.
[0012] In some specific embodiments, in response to the real-time captured vehicle surrounding environment, a current lane line image is acquired, and a Cartesian coordinate system centered on the front bumper of the vehicle is constructed based on the lane line image, further comprising:
[0013] Setting a visual sensor to capture the lane line image in real time;
[0014] Convert the captured lane line image into a Cartesian coordinate system centered on the front bumper of the vehicle, wherein in the Cartesian coordinate system, the X-axis is defined as the positive direction and the Y-axis direction is defined as positive on the left and negative on the right;
[0015] The position of the vehicle in the Cartesian coordinate system is calculated and updated in real time.
[0016] In some specific embodiments, in response to the lane line image, identifying left and right lane line information of the current road condition, fitting the lane line information in the form of a cubic equation, and calculating the offset distance of the vehicle relative to the lane line information further includes:
[0017] Identify the lane line image, obtain the left and right lane line information and determine the position;
[0018] Using the cubic equation to fit the identified lane line information to obtain the shape of the lane line;
[0019] According to the fitted lane line equation, the offset distance of the vehicle at the current position relative to the lane center is calculated.
[0020] In some specific embodiments, in response to the triggering result of the LKA correction, evaluating whether the current operating condition meets the preset adjustment requirement range, wherein the current operating condition includes a deviation speed, and the deviation speed is calculated by Kalman filtering, further comprising:
[0021] Monitoring the output signal of the LKA in real time to determine whether a lane keeping correction instruction is triggered;
[0022] Obtaining current vehicle speed and lane width information, and comparing them with the adjustment requirement range;
[0023] Determining the lane line curvature and comparing it with the adjustment requirement range, including calculating the lane line curvature based on the lane line equation to determine whether the current working condition is a straight road;
[0024] The offset speed is estimated based on a Kalman filter, including constructing a prediction model, a state transfer matrix, an observation matrix, a noise matrix, an observation noise matrix and a covariance matrix, and the offset speed is estimated in real time according to a Kalman filter algorithm.
[0025] In some specific embodiments, if the current working condition meets the adjustment requirement range, the steering zero point adjustment is performed based on the offset distance difference until the deviation correction distance difference is less than a preset threshold, and the zero point adjustment value is updated, further comprising:
[0026] Record the offset distance of the current side and compare it with the offset distance of the last correction on the other side;
[0027] When the offset distance difference between the two sides exceeds the preset threshold, the direction of adjustment is determined according to the offset distance difference, and the step length of each adjustment is set;
[0028] Based on the adjustment direction and the step size, the steering wheel angle output by the LKA is fine-tuned and compensated until the difference in the offset distances on both sides of two consecutive corrections is less than the preset threshold, and the zero point adjustment is completed.
[0029] In some specific embodiments, based on the adjusted direction and the step size, fine-tuning and compensating the steering wheel angle output by the LKA further comprises:
[0030] Determining the direction of the zero point adjustment to reduce the difference in deviation distances on both sides;
[0031] Set the steering wheel angle step size to plus or minus 0.2° each time, and limit the adjustment range to plus or minus 1°;
[0032] Adjust and monitor the adjustment effect in real time until the zero point adjustment is completed.
[0033] Based on the same concept, the present invention also provides an adaptive lane keeping assist control system, comprising:
[0034] A coordinate system establishment module, configured to obtain a current lane line image in response to the real-time captured vehicle surrounding environment, and to construct a Cartesian coordinate system centered on the front bumper of the vehicle based on the lane line image;
[0035] A deviation correction distance calculation module is configured to respond to the lane line image, identify the left and right lane line information of the current road condition, fit the lane line information in the form of a cubic equation, and calculate the offset distance of the vehicle relative to the lane line information;
[0036] a current operating condition evaluation module, configured to evaluate whether the current operating condition meets a preset adjustment requirement range in response to a trigger result of the LKA deviation correction, wherein the current operating condition includes a deviation speed, and the deviation speed is calculated by a Kalman filter;
[0037] The zero point adjustment module is configured to perform a steering zero point adjustment based on the offset distance difference if the current working condition meets the adjustment requirement range, until the correction distance difference is less than a preset threshold, and update the zero point adjustment value.
[0038] Based on the same concept, the present invention also provides an electronic device, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the adaptive lane keeping assist control method.
[0039] Based on the same concept, the present invention also provides a computer-readable storage medium storing a computer program executable by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the adaptive lane keeping assist control method.
[0040] Based on the same concept, the present invention also provides a vehicle, wherein the vehicle is provided with the adaptive lane keeping assist control system as described above.
[0041] Compared with the prior art, the invention has the following beneficial effects:
[0042] The present invention discloses an adaptive lane keeping assist control method, system, electronic device, storage medium and vehicle, which can effectively solve the problem of inconsistent left and right deviation correction of LKA function caused by problems such as EPS zero point error, and re-evaluate, judge and adjust the zero point by judging the deviation distance, so that the left and right forces of the vehicle tend to be consistent in the subsequent deviation correction process, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 is a flowchart of an adaptive lane keeping assist control method of the present invention in some specific embodiments;
[0044] Figure 2 It is a flow chart of an adaptive lane keeping assist control method of the present invention in some applications;
[0045] Figure 3 It is a schematic diagram of scenarios of an adaptive lane keeping auxiliary control method of the present invention in some applications;
[0046] Figure 4 is a schematic structural diagram of an adaptive lane keeping assist control system of the present invention in some specific embodiments;
[0047] Figure 5 It is a schematic diagram of the structure of an electronic device in some specific embodiments of the present invention. DETAILED DESCRIPTION
[0048] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0049] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.
[0050] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.
[0051] It should be understood that although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.
[0052] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.
[0053] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the commodity or device including the elements.
[0054] It should be particularly noted that any symbols and / or numbers in the specification that are not marked in the accompanying drawings are not drawing marks.
[0055] Reference Figure 1 , an adaptive lane keeping assist control method, comprising:
[0056] S101, in response to the real-time captured vehicle surrounding environment, acquiring a current lane line image, and constructing a Cartesian coordinate system centered on the front bumper of the vehicle based on the lane line image;
[0057] It can be understood that capturing the lane line image in front of the vehicle and constructing a Cartesian coordinate system centered on the front bumper of the vehicle includes:
[0058] Determine the coordinate origin: Set the center point of the vehicle's front bumper as the origin of the coordinate system (0,0).
[0059] Define the coordinate axes: the vehicle's driving direction is the positive direction of the X-axis, and the direction perpendicular to the driving direction and pointing to the left side of the vehicle is the positive direction of the Y-axis.
[0060] Image conversion: Convert the captured lane line image from the pixel coordinate system to the Cartesian coordinate system constructed above.
[0061] In some of the applications, in response to the real-time capture of the vehicle's surrounding environment, a current lane line image is obtained, and a Cartesian coordinate system centered on the vehicle's front bumper is constructed based on the lane line image, and a visual sensor is set to capture the lane line image in real time; the captured lane line image is converted into a Cartesian coordinate system centered on the vehicle's front bumper, in which the X-axis is defined as the positive direction and the Y-axis direction is defined as positive on the left and negative on the right; and the vehicle's position in the Cartesian coordinate system is calculated and updated in real time.
[0062] It is understandable that a high-definition camera is selected as a visual sensor to ensure that a clear and stable lane line image can be captured. The camera is installed at an appropriate position on the front of the vehicle, such as above the front windshield or near the rearview mirror, to ensure that the camera field of view can cover the lane line in front of the vehicle. At the same time, adjust the installation angle of the camera so that its viewing angle is consistent with the direction of vehicle travel and minimize the blind spot. A two-dimensional Cartesian coordinate system is established with the center point of the front bumper of the vehicle as the coordinate origin (0,0). In this coordinate system, the vehicle travel direction is defined as the positive direction of the X axis, and the direction perpendicular to the travel direction and pointing to the left side of the vehicle is defined as the positive direction of the Y axis (i.e., positive on the left and negative on the right). The camera captures the lane line image in real time and performs preprocessing, including image denoising, contrast enhancement, color segmentation, etc., to improve the accuracy of lane line recognition. The preprocessed lane line image is converted from the pixel coordinate system to the Cartesian coordinate system centered on the front bumper of the vehicle. In the converted image, the lane line will appear as a series of discrete points or line segments, and its coordinate values represent the position of the lane line in the Cartesian coordinate system.
[0063] The position of the vehicle in the Cartesian coordinate system is calculated in real time based on the converted lane line image, including fitting the lane line (such as using polynomial fitting, Hough transform, etc.) to obtain the precise shape and position parameters of the lane line. Then, based on information such as the offset distance and angle of the vehicle relative to the lane line, the specific position of the vehicle in the coordinate system is calculated and the position information is updated in real time.
[0064] For example, the vertical distance from the center point of the front bumper of the vehicle to the ground is 1.2 meters, the camera is installed 0.5 meters above the front windshield, and the viewing angle is 60 degrees horizontally and 45 degrees vertically. The camera captures an image containing lane lines in real time, and obtains the lane line representation in the Cartesian coordinate system after preprocessing and conversion. According to the position and shape parameters of the lane lines, the current position of the vehicle in the coordinate system is calculated as (X=5, Y=-0.3), indicating that the vehicle is 5 meters in front of the coordinate origin and slightly to the right. Continuously receive new lane line images and update the vehicle's position information in the coordinate system in real time for subsequent lane keeping control.
[0065] S102, in response to the lane line image, identifying left and right lane line information of the current road condition, fitting the lane line information in the form of a cubic equation, and calculating an offset distance of the vehicle relative to the lane line information;
[0066] It is understandable that, given that the lane lines may have different curvatures, the lane lines are fitted in the form of a cubic equation.
[0067] Fitting parameter solution: The fitting parameters (i.e. coefficients of the equation) of the cubic equation are solved using the least squares method or other optimization algorithms. The parameters are dynamically adjusted according to the actual shape of the lane line to ensure the accuracy of the fitting.
[0068] Vehicle position determination: In the Cartesian coordinate system, the position of the vehicle in the current lane is determined based on the position of the center point of the vehicle's front bumper.
[0069] Offset distance calculation: Compare the vehicle position with the fitted lane line equation to calculate the offset distance of the vehicle relative to the lane line. Specifically, the shortest distance (i.e. vertical distance) from the vehicle position point to the lane line equations on both sides can be calculated as the offset of the vehicle relative to the left and right lane lines.
[0070] For example, suppose that at a certain moment, after preprocessing and recognition of the captured lane line image, the edge information of the left and right lane lines is obtained. Then, the left and right lane lines are fitted in the form of a cubic equation, and the following equation is obtained:
[0071] Left lane line: y=ax3+bx2+cx+d;
[0072] Right lane line: y=ex3+fx2+gx+nine;
[0073] Among them, a, b, c, d, e, f, g, and nine are the fitting parameters. Assuming that the position of the center point of the front bumper of the vehicle in the Cartesian coordinate system is (x0, y0), the offset distance dleft of the vehicle relative to the left lane line and the offset distance dright of the right lane line can be obtained by calculating the shortest distance from the point to the curve.
[0074] For example, for the left lane line, we can solve the equation To find the perpendicular tangent point to the point (x0, y0), and then calculate the shortest distance dleft. Similarly, dright can also be calculated.
[0075] In some of the applications, in response to a lane line image, the left and right lane line information of the current road condition is identified, the lane line information is fitted in the form of a cubic equation, and the offset distance of the vehicle relative to the lane line information is calculated. The lane line image is identified, the left and right lane line information is obtained and the position is determined; the identified lane line information is fitted using a cubic equation to obtain the shape of the lane line; and based on the fitted lane line equation, the offset distance of the vehicle at the current position relative to the center of the lane is calculated.
[0076] It can be understood that in a Cartesian coordinate system established with the center of the front bumper of the vehicle as the origin, the position of the vehicle at the current moment is determined by the on-board GPS, IMU or other sensors. Based on the fitted left and right lane line equations, the equation of the lane centerline is calculated. The lane centerline can be regarded as the average of the left and right lane line equations or a line calculated according to specific rules (such as considering the lane width). The vehicle position is compared with the lane centerline equation to calculate the offset distance of the vehicle at the current position relative to the lane centerline. The offset distance can be a distance in the horizontal direction (i.e., along the lane direction) or a distance perpendicular to the lane direction, depending on actual needs.
[0077] S103, in response to the triggering result of the LKA deviation correction, evaluating whether the current operating condition meets the preset adjustment requirement range, wherein the current operating condition includes a deviation speed, and the deviation speed is calculated by Kalman filtering;
[0078] It is understandable that when the lane keeping assist system detects that the vehicle has deviated from the lane and reaches a preset threshold, the deviation correction mechanism will be triggered. The deviation speed refers to the speed component of the vehicle relative to the lane line, reflecting the urgency and potential risk of vehicle deviation. In order to eliminate measurement noise and uncertainty, the Kalman filter algorithm is used to process the deviation speed.
[0079] The adjustment requirement range is pre-set according to vehicle performance, road conditions and safety standards, including but not limited to the maximum allowable deviation speed, deviation angle, speed limit, etc.
[0080] The deviation speed and other key parameters processed by Kalman filtering are compared and analyzed with the preset adjustment requirement range. If all parameters meet the required range, the current working condition is judged to be suitable for deviation correction; otherwise, corresponding safety strategies are adopted according to the specific situation, such as issuing a warning signal, reducing the speed or suspending the deviation correction operation.
[0081] In some of the applications, in response to the triggering result of the LKA correction, it is evaluated whether the current operating condition meets the preset adjustment requirement range, the current operating condition includes the deviation speed, and the deviation speed is calculated through the Kalman filter, and the output signal of the LKA is monitored in real time to determine whether the lane keeping correction instruction is triggered; the current vehicle speed and lane width information are obtained and compared with the adjustment requirement range; the lane line curvature is judged and compared with the adjustment requirement range, including calculating the lane line curvature based on the lane line equation to determine whether the current working condition is a straight road; the deviation speed is estimated based on the Kalman filter, including constructing a prediction model, a state transfer matrix, an observation matrix, a noise matrix, an observation noise matrix and a covariance matrix, and the deviation speed is estimated in real time according to the Kalman filter algorithm.
[0082] It is understood that the output signal of LKA is continuously monitored, including but not limited to the position deviation of the vehicle relative to the lane line, the deviation direction and the deviation trend. When it is detected that the vehicle deviates from the lane and reaches a preset threshold, it is initially determined that a lane keeping correction instruction may need to be triggered.
[0083] Obtain the current vehicle speed and lane width information in real time. Compare the obtained current vehicle speed and lane width with the preset adjustment requirement range.
[0084] For example, the preset speed range is 60-120km / h and the lane width range is 3-4 meters. If the current speed and lane width are both within the range, the next step of evaluation will be continued; otherwise, the correction operation will be adjusted or suspended according to the specific situation.
[0085] Identify lane lines, construct lane line equations, and calculate lane line curvature based on the constructed lane line equations. For straight line equations, the curvature is 0; for curve equations, the curvature can be calculated by the second-order derivative of the equation or a specific algorithm. Compare the calculated lane line curvature with the preset adjustment requirement range.
[0086] For example, if the curvature threshold of the preset straight road condition is a smaller value (such as ±0.01 / m), then when the curvature is within this range, it is judged as a straight road condition and is suitable for correction operation; if it exceeds the range, the correction strategy needs to be adjusted according to the curvature size.
[0087] According to the vehicle dynamics characteristics and sensor measurement principles, the prediction model of the Kalman filter, the state transfer matrix, the observation matrix, the noise matrix, the observation noise matrix and the initial covariance matrix are constructed.
[0088] The Kalman filter algorithm is used to estimate the vehicle's offset speed in real time based on the vehicle position, speed and other information measured by the sensor in real time, as well as the prediction model and noise parameters. During the estimation process, the Kalman filter will continuously adjust the state estimate based on the error between the predicted value and the observed value to improve the accuracy and stability of the estimate.
[0089] S104: If the current working condition meets the adjustment requirement range, a steering zero point adjustment is performed based on the offset distance difference until the deviation correction distance difference is less than a preset threshold, and the zero point adjustment value is updated.
[0090] It is understandable that the parameters such as vehicle speed, lane width, lane line curvature monitored in real time are compared with the preset adjustment requirement range. If all parameters meet the requirements, it is judged that the current working condition is suitable for steering zero point adjustment. If the current working condition meets the adjustment requirement range and there is an offset distance difference, a steering zero point adjustment instruction is sent according to the size and direction of the offset distance difference. The adjustment instruction will control the steering mechanism of the vehicle to make fine adjustments to reduce the offset distance difference. During the steering zero point adjustment process, the changes in the offset distance difference are continuously monitored, and the zero point adjustment value is updated according to the actual situation. When the offset distance difference is less than the preset threshold, the steering zero point adjustment is considered to be completed, and the current zero point adjustment value is saved as the new baseline value for subsequent lane keeping control.
[0091] In some of the applications, if the current working condition meets the adjustment requirement range, the steering zero point adjustment is performed based on the offset distance difference until the correction distance difference is less than a preset threshold, and the zero point adjustment value is updated, the offset distance of the current side is recorded, and compared with the offset distance of the last correction on the other side; when the offset distance difference on both sides exceeds the preset threshold, the direction of adjustment is determined according to the offset distance difference, and the step size of each adjustment is set; based on the adjustment direction and step size, the steering wheel angle output by the LKA is fine-tuned and compensated until the offset distance difference on both sides of two consecutive corrections is less than the preset threshold, and the zero point adjustment is completed.
[0092] It is understood that the offset distance of the current side (such as the left or right side) is recorded in real time and compared with the offset distance of the last correction of the other side (such as the right or left side). Here, "current side" and "last other side" refer to the two sides involved when the vehicle deviates from the lane twice in a row.
[0093] For example, the vehicle first deviates from the lane to the left, and the offset distance recorded at this time is 30 cm (left-side offset). Subsequently, the vehicle deviates from the lane to the right, and the offset distance recorded at this time is 45 cm (right-side offset).
[0094] The difference between the two offset distances is compared with a preset threshold. If the difference exceeds the threshold, it means there is a significant offset distance difference and a zero point adjustment is required.
[0095] For example, the preset offset distance difference threshold is 10 cm. In the above example, the difference in the offset distances on both sides is 15 cm, which exceeds the preset threshold.
[0096] The direction of adjustment (left or right) is determined according to the positive or negative difference in the offset distance, and the step size of each adjustment is set.
[0097] For example, since the right side has a larger offset than the left side, it is decided to adjust the zero point to the left. Set the step size of each adjustment to 2° (steering wheel angle).
[0098] Based on the adjustment direction and step size, the steering wheel angle output by LKA is fine-tuned and compensated. During the vehicle driving process, the change of the offset distance is continuously monitored, and the steering wheel angle is adjusted as needed until the expected adjustment effect is achieved.
[0099] For example, add 2° to the left based on the steering wheel angle output by LKA to make the first fine-tuning compensation. Then continue to monitor the offset distance and make further fine-tuning compensation as needed.
[0100] When the difference between the offset distances of two consecutive corrections is less than the preset threshold, the zero point adjustment is considered to be completed. At this time, the current zero point adjustment value is saved and the vehicle driving status continues to be monitored so that zero point adjustment can be performed again when necessary.
[0101] For example, after multiple fine-tuning compensations, if the difference in the offset distance between the two sides of the vehicle after two consecutive corrections is reduced to 5 cm (less than the preset 10 cm threshold), the zero point adjustment is considered to be completed, the current zero point adjustment value is saved, and the lane keeping function continues to be executed.
[0102] In some of these applications, the steering wheel angle output by the LKA is fine-tuned and compensated based on the direction and step size of the adjustment. The direction of the zero-point adjustment is determined to reduce the difference in the deviation distance between the two sides. The step size of the steering wheel angle for each adjustment is set to plus or minus 0.2°, and the adjustment range is limited to plus or minus 1°. The adjustment is made in real time and the adjustment effect is monitored until the zero-point adjustment is completed.
[0103] It is understandable that in order to ensure the adjustment accuracy while avoiding over-adjustment, the step size of the steering wheel angle for each adjustment is set to plus or minus 0.2°. At the same time, in order to limit the adjustment range and ensure the safety and stability of the adjustment process, the adjustment range is limited to plus or minus 1°. During each adjustment process, the maximum change in the steering wheel angle shall not exceed 1°, and fine-tuning can be performed within a step size of plus or minus 0.2° according to actual conditions.
[0104] The steering wheel angle is adjusted in real time, and the adjustment effect is continuously monitored. The difference in the deviation distance between the two sides is calculated, and the steering wheel angle is adjusted according to the size and direction of the difference. When the difference in the deviation distance between the two sides is less than the preset threshold for multiple consecutive monitorings, the zero point adjustment is considered to be completed.
[0105] Combine the following Figure 2 and Figure 3 The following describes the embodiments of the adaptive lane keeping assist control method of the present invention in some applications:
[0106] like Figure 2As shown, this embodiment uses the vehicle offset distance sensed by the visual sensor to form a closed-loop adjustment system. Under the same conditions, the larger the vehicle offset distance, the greater the correction force on the current side. The steering zero point is adjusted according to the offset distances on the left and right sides to keep the distance consistent.
[0107] 1. First, establish a Cartesian coordinate system with the front bumper of the vehicle as the center, with the vehicle's travel direction as the positive direction of the X-axis and the Y-axis direction as positive on the left and negative on the right.
[0108] 2. Obtain the left and right lane line information of the current road condition detected by the visual sensor. The lane line detected by the visual sensor is given in the form of a cubic equation: y = C 0 +C 1 x+C 2 x 2 +C 3 x 3 , C 0 It can be roughly used as the departure distance;
[0109] 3. Determine whether the vehicle triggers LKA correction.
[0110] Fourth, determine whether the current working condition meets the adjustment requirements. This embodiment constrains several dimensions: within the same speed range (60km / h to 90km / h), the same lane width range (3.4m to 3.6m), straight road conditions (based on the lane line curvature, 2*C 2 ), the same deviation speed range (0.2m / s~0.4m / s);
[0111] The deviation speed is estimated by Kalman filter C 0 The rate of change is:
[0112] Assume that the vehicle is in the process of deviation C 0 Uniform rate change, the prediction model of the Kalman filter is the uniform rate CV model;
[0113] The state variables of the system are Where v is the speed of the deviation direction, d is the deviation
[0114] The discrete state equation can be expressed as:
[0115]
[0116] The state transfer matrix A = [1T; 0 1], the input matrix B is a zero matrix, T is the algorithm operation cycle, and in this embodiment T = 0.04;
[0117] Observation matrix H = [1 0];
[0118] Noise matrix Q = [0.5 0; 0 1];
[0119] Observation noise matrix R = [0.1];
[0120] Covariance matrix P = [1 0; 0 1];
[0121] The lateral deviation velocity v is estimated according to the calculation formula of Kalman filter:
[0122]
[0123] Record the deviation distance on the current side and compare it with the last deviation correction distance on the other side to see if it exceeds the threshold (0.2m);
[0124] If the threshold is exceeded, zero-point adjustment is performed. Zero-point adjustment is to fine-tune the steering wheel angle output by the LKA controller. The step size of each adjustment should not be too large. The actual engineering application is plus or minus 0.2°. The upper and lower limits of the steering wheel angle for zero-point adjustment are plus or minus 1°.
[0125] Iterate the calculation until the difference between the left and right offset distances of two corrections is less than the threshold (0.2m), and the zero point adjustment is completed. Generally, 2 to 4 iterations are required to complete the zero point adjustment.
[0126] The final zero-point adjustment value is updated and recorded in the storage, and is read and used before the vehicle is powered on next time.
[0127] This embodiment is described below in conjunction with application scenarios:
[0128] like Figure 3 As shown in the figure, before the zero point adjustment under the same working condition, the left correction distance is greater than the right correction distance by more than the set threshold, which means that the left correction force is greater and the right correction force is smaller. The EPS zero point is adjusted to the left. After the adjustment, the left and right deviation distance errors are reduced during the next trigger. After several adjustments (2 to 4 times), the EPS zero point can converge to the zero position.
[0129] When the left LKA deviation correction function is triggered, it is first determined whether the current working condition meets the adjustment working condition range. At this time, according to the information of various vehicle sensors, it is determined that the current vehicle speed is 80km / h, the lane width is 3.670408m, and the current lane curvature is 0.000104 (the converted curve radius is 9615.4m, which is greater than 2000m and belongs to the straight road working condition). The first three items all meet the adjustment working condition restrictions. The calculation of the deviation speed needs to be estimated by the Kalman filter. During the deviation to the left, the left C 0 The value changes are as follows:
[0130] [1.991584 1.973484 1.962321 1.942568 1.9226551.912791 1.8929241.887171 1.866958] Unit: m;
[0131] It can be used as the observation value y of the Kalman filter k , taking the first value (1.991548) as the initial time X k-1 According to the five formulas of Kalman filtering, iterative calculation begins. The results of the first iteration are as follows:
[0132]
[0133]
[0134] Kalman filtering is a gradual convergence process. After multiple iterations, C 0 The change rate v is stable at about 0.4968m / s, and the deviation speed meets the requirements.
[0135] After triggering LKA, the lateral controller controlled the vehicle to the middle of the lane and recorded the deviation distance at this time as 2.01036m, which was 0.2255m different from the deviation distance of 1.78486m in the last right correction, and was greater than the threshold of 0.2m;
[0136] Trigger the zero point adjustment module, and the zero point is adjusted to the left with a step length of 0.2° each time;
[0137] Iterate the calculation until the difference between the left and right offset distances of two corrections is less than the threshold (0.2m), and the zero point adjustment is completed. Generally, the zero point adjustment can be completed after 2 to 4 iterations.
[0138] For the method steps disclosed in the above embodiments, the method steps are described as a series of action combinations for the purpose of simple description, but those skilled in the art should know that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.
[0139] like Figure 4 As shown, the present invention also provides an adaptive lane keeping assist control system, comprising:
[0140] A coordinate system establishing module 201 is configured to obtain a current lane line image in response to the real-time captured vehicle surrounding environment, and to construct a Cartesian coordinate system centered on the front bumper of the vehicle based on the lane line image;
[0141] The deviation correction distance calculation module 202 is configured to respond to the lane line image, identify the left and right lane line information of the current road condition, fit the lane line information in the form of a cubic equation, and calculate the offset distance of the vehicle relative to the lane line information;
[0142] A current operating condition evaluation module 203 is configured to evaluate whether the current operating condition meets a preset adjustment requirement range in response to a trigger result of the LKA deviation correction, wherein the current operating condition includes a deviation speed, and the deviation speed is calculated by a Kalman filter;
[0143] The zero point adjustment module 204 is configured to perform a steering zero point adjustment based on the offset distance difference if the current working condition meets the adjustment requirement range, until the deviation correction distance difference is less than a preset threshold, and update the zero point adjustment value.
[0144] It is worth noting that although only some basic functional modules are disclosed in the embodiments of the present invention, it does not mean that the composition of the present system is limited to the above basic functional modules. On the contrary, what the present embodiment wants to express is that on the basis of the above basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with the prior art to form an infinite number of embodiments or technical solutions. In other words, the present system is open rather than closed. Just because the present embodiment only discloses individual basic functional modules, it cannot be considered that the protection scope of the claims of the present invention is limited to the disclosed basic functional modules. At the same time, for the convenience of description, the above devices are described in terms of functions and are described separately in various units and modules. Of course, when implementing the present invention, the functions of each unit and module can be implemented in the same or one or more software and / or hardware.
[0145] like Figure 5 As shown, the present invention also provides an electronic device, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the adaptive lane keeping assist control method.
[0146] Figure 5 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 5 The electronic device provided in the embodiment of the present invention includes: one or more processors 710 and a storage device 720; the processor 710 in the electronic device may be one or more, Figure 5 A processor 710 is taken as an example; the storage device 720 is used to store one or more programs; the one or more programs are executed by the one or more processors 710, so that the one or more processors 710 implement the adaptive lane keeping assist control method as described in any one of the embodiments of the present invention.
[0147] The electronic device may further include: an input device 730 and an output device 740 .
[0148] The processor 710, storage device 720, input device 730 and output device 740 in the electronic device can be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.
[0149] The storage device 720 in the electronic device is a computer-readable storage medium that can be used to store one or more programs, which can be software programs, computer executable programs and modules, such as program instructions / modules corresponding to the adaptive lane keeping assist control method provided in the embodiment of the present invention. The processor 710 executes various functional applications and data processing of the electronic device by running the software programs, instructions and modules stored in the storage device 720, that is, the adaptive lane keeping assist control method in the above method embodiment is implemented.
[0150] The storage device 720 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the storage device 720 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the storage device 720 may further include a memory remotely arranged relative to the processor 710, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0151] The input device 730 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the electronic device. The output device 740 may include a display device such as a display screen.
[0152] The present invention also provides a computer-readable storage medium storing a computer program executable by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the adaptive lane keeping assist control method.
[0153] Specifically, the computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.
[0154] The present invention also provides a vehicle, wherein the vehicle is provided with the adaptive lane keeping assist control system as described above.
[0155] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. An adaptive lane keeping assist control method, characterized in that: include: In response to the real-time captured vehicle surrounding environment, a current lane line image is acquired, and a Cartesian coordinate system centered on the front bumper of the vehicle is constructed based on the lane line image; In response to the lane line image, identifying left and right lane line information of the current road condition, fitting the lane line information in the form of a cubic equation, and calculating an offset distance of the vehicle relative to the lane line information; In response to the triggering result of the LKA deviation correction, evaluating whether the current operating condition meets the preset adjustment requirement range, wherein the current operating condition includes the deviation speed, and the deviation speed is calculated by Kalman filtering; If the current working condition meets the adjustment requirement range, the steering zero point adjustment is performed based on the offset distance difference until the deviation correction distance difference is less than a preset threshold, and the zero point adjustment value is updated.
2. The adaptive lane keeping assist control method according to claim 1, characterized in that: In response to the real-time captured vehicle surrounding environment, a current lane line image is acquired, and a Cartesian coordinate system centered on the front bumper of the vehicle is constructed based on the lane line image, further comprising: Setting a visual sensor to capture the lane line image in real time; Convert the captured lane line image into a Cartesian coordinate system centered on the front bumper of the vehicle, wherein in the Cartesian coordinate system, the X-axis is defined as the positive direction and the Y-axis direction is defined as positive on the left and negative on the right; The position of the vehicle in the Cartesian coordinate system is calculated and updated in real time.
3. The adaptive lane keeping assist control method according to claim 1, characterized in that: In response to the lane line image, identifying left and right lane line information of the current road condition, fitting the lane line information in the form of a cubic equation, and calculating the offset distance of the vehicle relative to the lane line information, further comprising: Identify the lane line image, obtain the left and right lane line information and determine the position; Using the cubic equation to fit the identified lane line information to obtain the shape of the lane line; According to the fitted lane line equation, the offset distance of the vehicle at the current position relative to the lane center is calculated.
4. The adaptive lane keeping assist control method according to claim 3, characterized in that: In response to the trigger result of the LKA correction, evaluating whether the current operating condition meets the preset adjustment requirement range, wherein the current operating condition includes a deviation speed, and the deviation speed is calculated by Kalman filtering, further comprising: Monitoring the output signal of the LKA in real time to determine whether a lane keeping correction instruction is triggered; Obtaining current vehicle speed and lane width information, and comparing them with the adjustment requirement range; Determining the lane line curvature and comparing it with the adjustment requirement range, including calculating the lane line curvature based on the lane line equation to determine whether the current working condition is a straight road; The offset speed is estimated based on a Kalman filter, including constructing a prediction model, a state transfer matrix, an observation matrix, a noise matrix, an observation noise matrix and a covariance matrix, and the offset speed is estimated in real time according to a Kalman filter algorithm.
5. The adaptive lane keeping assist control method according to claim 1, characterized in that: If the current working condition meets the adjustment requirement range, the steering zero point adjustment is performed based on the offset distance difference until the deviation correction distance difference is less than a preset threshold value, and the zero point adjustment value is updated, further comprising: Record the offset distance of the current side and compare it with the offset distance of the last correction on the other side; When the offset distance difference between the two sides exceeds the preset threshold, the direction of adjustment is determined according to the offset distance difference, and the step length of each adjustment is set; Based on the adjustment direction and the step size, the steering wheel angle output by the LKA is fine-tuned and compensated until the difference in the offset distances on both sides of two consecutive corrections is less than the preset threshold, and the zero point adjustment is completed.
6. The adaptive lane keeping assist control method according to claim 5, characterized in that: Based on the adjusted direction and the step size, fine-tuning and compensating the steering wheel angle output by the LKA further comprises: Determining the direction of the zero point adjustment to reduce the difference in deviation distances on both sides; Set the steering wheel angle step size to plus or minus 0.2° each time, and limit the adjustment range to plus or minus 1°; Adjust and monitor the adjustment effect in real time until the zero point adjustment is completed.
7. An adaptive lane keeping assist control system, characterized in that: include: A coordinate system establishment module, configured to obtain a current lane line image in response to the real-time captured vehicle surrounding environment, and to construct a Cartesian coordinate system centered on the front bumper of the vehicle based on the lane line image; A deviation correction distance calculation module is configured to respond to the lane line image, identify the left and right lane line information of the current road condition, fit the lane line information in the form of a cubic equation, and calculate the offset distance of the vehicle relative to the lane line information; a current operating condition evaluation module, configured to evaluate whether the current operating condition meets a preset adjustment requirement range in response to a trigger result of the LKA deviation correction, wherein the current operating condition includes a deviation speed, and the deviation speed is calculated by a Kalman filter; The zero point adjustment module is configured to perform a steering zero point adjustment based on the offset distance difference if the current working condition meets the adjustment requirement range, until the correction distance difference is less than a preset threshold, and update the zero point adjustment value.
8. An electronic device, characterized in that: include: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the method described in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that: It stores a computer program executable by an electronic device, and when the computer program runs on the electronic device, the electronic device executes the steps of the method described in any one of claims 1 to 6.
10. A vehicle, characterized in that: The vehicle is provided with the adaptive lane keeping assist control system as claimed in claim 7.
