Steering wheel control method of vehicle, vehicle and computer readable storage medium

Abstract

The embodiment of the invention provides a vehicle steering wheel control method, a vehicle and a computer readable storage medium, and the method comprises the steps: in a vehicle driving process, obtaining target driving parameters and a current driving position of the vehicle, and lane line information of a plurality of lane lines in a current driving road where the vehicle is located; determining the lane line curvature of the virtual lane line based on the current driving position and the lane line information; determining a predicted distance of the vehicle based on the current driving parameter and the lane line curvature; and controlling a steering wheel based on the predicted distance and the target driving parameter so that the vehicle travels on the virtual lane line. The technical problem that the control effect of the steering wheel of the vehicle is poor is solved.

Description

Technical Field

[0001] This application relates to the field of vehicle system control, and more specifically, to a vehicle steering wheel control method, a vehicle, and a computer-readable storage medium. Background Technology

[0002] In intelligent driving systems, the precision of steering wheel angle control is crucial for vehicle stability and safety. However, during vehicle production, the steering wheel's zero-position is learned. This process is implemented by the production line equipment and the Electric Power Steering System (EPS). This zero-position is written to the EPS as a reference for the actual steering wheel angle. Due to vehicle variations and aging, the EPS steering wheel angle zero-position can deviate. Some vehicles with significant variations exhibit control deviations, resulting in poor steering wheel control.

[0003] There is currently no good solution to the above problems. Summary of the Invention

[0004] This application provides a vehicle steering wheel control method, a vehicle, and a computer-readable storage medium, which at least solves the technical problem of poor vehicle steering wheel control performance.

[0005] According to one aspect of the embodiments of this application, a steering wheel control method for a vehicle, a vehicle, and a computer-readable storage medium are provided, comprising: during vehicle operation, acquiring target driving parameters of the vehicle, current driving position, and lane line information of multiple lane lines in the current driving road where the vehicle is located, wherein different lane lines are located at different positions in the current driving road; determining the lane line curvature of a virtual lane line based on the current driving position and lane line information, wherein the virtual lane line passes through a preset driving position of the vehicle in the current driving road and is parallel to the multiple lane lines; determining a predicted distance of the vehicle based on the target driving parameters and lane line curvature, wherein the predicted distance is used to represent the distance between the target driving position and the current driving position of the vehicle, and the target driving position is the predicted driving position that the vehicle is to reach; and controlling the steering wheel based on the predicted distance and target driving parameters so that the vehicle drives on the virtual lane line.

[0006] Furthermore, based on the predicted distance, target driving parameters, and lane control mode, the steering wheel is controlled to ensure the vehicle travels on the virtual lane line. This includes: determining the target steering wheel angle compensation value based on the predicted distance, target driving parameters, and lane control mode, wherein the target steering wheel angle compensation value is used to adjust the current steering wheel angle of the vehicle, and the lane control mode is used to represent the mode for controlling the vehicle's driving area; compensating the current steering wheel angle based on the target steering wheel angle compensation value to generate the target steering wheel angle; and controlling the steering wheel based on the target steering wheel angle to ensure the vehicle travels on the virtual lane line.

[0007] Further, the current steering wheel angle is compensated based on the target steering wheel angle compensation value to generate the target steering wheel angle. This includes: determining whether the vehicle meets the steering wheel angle compensation value update conditions based on the predicted distance, target driving parameters, and lane control mode. The steering wheel angle compensation value update conditions represent the conditions for updating the vehicle's current steering wheel angle compensation value. If the vehicle meets the steering wheel angle compensation value update conditions, the current steering wheel angle compensation value is updated based on the vehicle's current steering wheel angle and a preset coefficient to obtain the target steering wheel angle compensation value. If the vehicle does not meet the steering wheel angle compensation value update conditions, the current steering wheel angle compensation value is determined to be the target steering wheel angle compensation value.

[0008] Furthermore, based on the predicted distance, target driving parameters, and lane control mode, it is determined whether the vehicle meets the steering wheel angle compensation value update conditions, including: determining the lane radius of the virtual lane line based on the predicted distance, wherein the lane radius is used to quantify the curvature of the virtual lane line at the current driving position; determining the current driving speed of the vehicle based on the target driving parameters; and determining whether the vehicle meets the steering wheel angle compensation value update conditions based on the lane radius, current driving speed, and lane control mode.

[0009] Furthermore, based on the lane radius, current driving speed, and lane control mode, it is determined whether the vehicle meets the steering wheel angle compensation value update conditions, including: if the lane radius is within a preset radius range, the current driving speed is within a preset speed range, and the lane control mode is a preset control mode, the vehicle is determined to meet the steering wheel angle compensation value update conditions, wherein the preset control mode is used to indicate the control mode that controls the vehicle to be in the virtual lane line; if the lane radius is not within the preset radius range, or the current driving speed is not within the preset speed range, or the lane control mode is not a preset control mode, the vehicle is determined not to meet the steering wheel angle compensation value update conditions.

[0010] Further, determining the lane radius of the virtual lane line based on the predicted distance includes: determining the predicted curvature of the target driving position based on the predicted distance; and determining the reciprocal of the predicted curvature as the lane radius.

[0011] Furthermore, the multiple lane lines include: a first lane line and a second lane line. The lane line information includes: first sub-lane line information of the first lane line and second sub-lane line information of the second lane line. Based on the current driving position and the lane line information, the lane line curvature of the virtual lane line is determined, including: determining the first curve equation of the first lane line based on the first sub-lane line information; determining the second curve equation of the second lane line based on the second sub-lane line information; determining the third curve equation of the virtual lane line based on the first curve equation and the second curve equation; and determining the lane line curvature based on the current driving position and the third curve equation.

[0012] Further, based on the target driving parameters and lane curvature, the predicted distance of the vehicle is determined, including: obtaining a preset curvature correction coefficient corresponding to the lane curvature; obtaining an initial predicted distance based on the vehicle's current driving speed and prediction time in the target driving parameters, wherein the prediction time is used to represent the predicted time for the vehicle to reach the target driving position; and determining the predicted distance based on the initial predicted distance and the preset curvature correction coefficient.

[0013] According to another aspect of the embodiments of this application, a vehicle is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of this application when it runs.

[0014] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0015] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0016] According to another aspect of the embodiments of this application, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the methods in various embodiments of this application.

[0017] According to another aspect of the embodiments of this application, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of this application.

[0018] In this embodiment, during vehicle operation, the target driving parameters, current driving position, and lane information of multiple lane lines in the current driving road are acquired, wherein different lane lines are located at different positions in the current driving road. Based on the current driving position and lane line information, the lane line curvature of a virtual lane line is determined, wherein the virtual lane line passes through a preset driving position of the vehicle in the current driving road and is parallel to multiple lane lines. Based on the target driving parameters and lane line curvature, the predicted distance of the vehicle is determined, wherein the predicted distance represents the distance between the target driving position and the current driving position of the vehicle, and the target driving position is the predicted driving position that the vehicle is to reach. Based on the predicted distance and target driving parameters, the steering wheel is controlled so that the vehicle drives on the virtual lane line. Virtual lane lines can be dynamically generated based on real-time driving parameters, location, and lane information. These virtual lane lines can then be used as a reference for autonomous driving. The curvature of the virtual lane lines can be determined using the current driving position and lane line information. By using the target driving parameters and lane line curvature, the predicted distance between the vehicle and the desired driving position can be predicted. The steering wheel can be controlled by calculating the predicted distance to ensure that the vehicle travels on the virtual lane lines. This improves the vehicle's driving stability between different lane lines, enhances driving stability and safety, and solves the technical problem of poor steering wheel control in related technologies. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 This is a schematic diagram of a vehicle steering wheel control method according to an embodiment of this application;

[0021] Figure 2 This is a system structure diagram of an optional vehicle steering wheel control method according to an embodiment of this application;

[0022] Figure 3 This is a schematic flowchart of an optional vehicle steering wheel control method according to an embodiment of this application;

[0023] Figure 4 This is a schematic diagram of lane lines and predicted distance for an optional vehicle steering wheel control method according to an embodiment of this application;

[0024] Figure 5 This is a block diagram of a predicted distance calculation method for an optional vehicle steering wheel control method according to an embodiment of this application;

[0025] Figure 6This is a block diagram of self-learning value calculation for an optional vehicle steering wheel control method according to an embodiment of this application;

[0026] Figure 7 This is a schematic diagram of a vehicle steering wheel control device according to an embodiment of this application. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] According to an embodiment of this application, a method for controlling the steering wheel of a vehicle is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] This embodiment provides a method for controlling the steering wheel of a vehicle. Figure 1 This is a schematic diagram of a vehicle steering wheel control method according to an embodiment of this application, as shown below. Figure 1 As shown, the process includes the following steps:

[0031] Step S102: During the vehicle's driving process, acquire the vehicle's target driving parameters, current driving position, and lane line information of multiple lane lines in the current driving road where the vehicle is located.

[0032] The different lane lines are located at different positions on the current driving road.

[0033] The aforementioned target driving parameters can refer to real-time dynamic data of the vehicle during driving, including but not limited to vehicle speed, acceleration, yaw rate, and actual steering wheel angle. These parameters are the basis for vehicle control decisions in the intelligent driving system, and the aforementioned target driving parameters can reflect the real-time motion state of the vehicle.

[0034] Yaw rate refers to the speed at which a vehicle rotates about its axis perpendicular to the ground. It represents the change in angular velocity around a vertical axis when a vehicle turns on a horizontal plane and is a crucial parameter for measuring the speed of a vehicle's rotation or steering. In the fields of intelligent driving and vehicle dynamics control, yaw rate helps the system understand the vehicle's real-time steering status. Actual steering wheel angle refers to the angle of deflection of the steering wheel relative to its initial or neutral position when the driver turns it. The actual steering wheel angle is measured by a steering angle sensor installed in the steering column or electronic power steering system. This sensor provides steering wheel rotation angle data, helping the system understand the driver's steering intentions and the vehicle's steering execution.

[0035] The aforementioned current driving location refers to the vehicle's specific location on the road, which is usually determined by an onboard positioning system or a high-precision map combined with sensor data. The onboard positioning system can be a global positioning system (GPS), BeiDou, or other satellite positioning systems.

[0036] The aforementioned current driving road can refer to the vehicle's current driving environment, which may be a specific road or road segment. The aforementioned multiple lane lines can refer to the boundary lines of lanes existing on the current driving road. The aforementioned lane line information may include the specific location, shape (straight or curved), lane width, and lane line type (such as solid line, dashed line, double yellow line), etc.

[0037] The different lane lines mentioned above being located at different positions on the current driving road can mean that there are multiple lanes on the current driving road, and the lane lines are located at corresponding positions on the road depending on the position of the lane.

[0038] In one optional embodiment, the intelligent driving system first captures road images in real time using a camera at the front of the vehicle. The data acquisition period can be preset (e.g., 10 seconds), and this preset period can be adjusted according to the scenario. Then, the left and right boundary lines of the current lane are identified and parsed to obtain first and second sub-lane line information for the left and right lane lines, including position coordinates and geometric attributes. Simultaneously, onboard sensors monitor real-time driving parameters of the vehicle, such as chassis speed, yaw rate, and current steering wheel angle, and the acquisition period can also be preset according to the scenario requirements.

[0039] In another optional embodiment, map data and vehicle location information can be combined to further obtain vehicle and lane information. For example, before a vehicle enters a known straight section such as a highway, the system can predict the characteristics of the road ahead through the map and obtain the target driving parameters and current driving position through positioning. At the same time, by using GPS or other positioning technologies to determine the vehicle's position on the map, the system can accurately predict the vehicle's driving status, improving the stability of intelligent driving and the user experience.

[0040] In another alternative embodiment, the user can actively send a command to request the vehicle's target driving parameters, current driving position, and lane line information of multiple lane lines in the current driving road where the vehicle is located.

[0041] Step S104: Determine the lane curvature of the virtual lane line based on the current driving position and lane line information.

[0042] The virtual lane lines pass through the vehicle's preset driving position in the current driving road and are parallel to multiple lane lines.

[0043] The aforementioned lane markings can refer to the left and right lane markings within a lane. These lane markings are used to indicate the direction of traffic within the lanes.

[0044] The aforementioned virtual lane lines can refer to the center position where vehicles should maintain stable driving, i.e., the geometric center of the lane.

[0045] Virtual lane lines can be determined based on a preset driving position of the vehicle in the current driving road. The virtual lane lines cross this preset driving position, indicating a match with the vehicle's stable driving path. Furthermore, on straight roads and curves with small curvatures, the virtual lane lines remain parallel to the actual first lane line (left lane line) and second lane line (right lane line). This method of setting virtual lane lines ensures that the intelligent driving system can use the vehicle's stable driving path as a reference.

[0046] The aforementioned virtual lane lines can be centered lane lines.

[0047] The lane line information mentioned above includes the data required to define virtual lane lines, including the first sub-lane line information of the first lane line and the second sub-lane line information of the second lane line, as well as the geometric attributes of these two lane lines, such as position coordinates, slope, and curvature. Based on the lane line information, the intelligent driving system can build a road model and calculate the specific location and shape of the virtual lane lines.

[0048] The lane curvature mentioned above refers to the degree of bending of the virtual lane line at different locations, calculated mathematically. The lane curvature is calculated based on the vehicle's current position and the geometric properties of the virtual lane line, reflecting the curvature characteristics of the road along the vehicle's path. Lane curvature is used in intelligent driving systems to assess road conditions, predict vehicle driving trends, and adjust lateral control strategies.

[0049] In one optional embodiment, cubic equations for the first lane line (left lane line) and the second lane line (right lane line) can be obtained based on the current driving position and lane line information. The coefficients of the left and right lane line equations are then weighted and averaged to obtain the virtual lane line equation. Subsequently, the lane line curvature equation of the virtual lane line is obtained by taking the second derivative of the obtained virtual lane line equation.

[0050] In another alternative embodiment, a camera at the front of the vehicle captures road images, identifies the left and right lane lines, and then converts this image information into a series of pixel coordinates, representing the positions of the lane lines on the image. Next, the intelligent driving system can use the least squares method or other curve fitting techniques to construct a mathematical model based on these coordinates, fitting the curve equations of the left and right lane lines respectively. Subsequently, by analyzing the curve equation of the left lane line... The curve equation of the right lane line To obtain the virtual lane line equation, a weighted average is used. The curvature of the virtual lane line can be determined by the second derivative of the virtual lane line equation. with the first derivative The curvature of the virtual lane line is obtained. The calculation is as follows:

[0051]

[0052] in, The second derivative of the virtual lane line equation, The first derivative of the virtual lane line equation, The virtual lane line curvature is used. By calculating the lane line curvature of the virtual lane lines, the intelligent driving system can perform road analysis and vehicle control. The setting of virtual lane lines and the calculation of lane line curvature solve the problems of discontinuity and uncertainty of physical lane lines in complex road environments, providing the intelligent driving system with a continuous and stable lane centerline model.

[0053] Step S106: Based on the target driving parameters and lane curvature, determine the predicted distance of the vehicle, wherein the predicted distance is used to represent the distance between the target driving position and the current driving position of the vehicle, and the target driving position is the predicted driving position that the vehicle is to reach.

[0054] The target driving parameters mentioned above include various dynamic information of the vehicle, such as vehicle speed, acceleration, and yaw rate. These parameters are the basis for describing and predicting vehicle driving behavior.

[0055] The predicted distance mentioned above can be the aiming distance, which refers to the distance between the target's current driving position and the vehicle's current driving position. The target driving position can be the future driving position predicted by a mathematical model based on the vehicle's current driving state and road conditions. Specifically, the predicted distance is calculated by multiplying the vehicle speed by the prediction time, and then by the curvature correction factor. The prediction time is determined by the current vehicle speed. The curvature correction factor is determined by the calculated current curvature.

[0056] The target driving position can refer to the point on the road that the vehicle is expected to reach at a specific time. This point is calculated by a prediction algorithm that combines the vehicle's current state (such as speed, acceleration, etc.) and road conditions (such as curvature, cross slope, road surface features, etc.).

[0057] Determining the vehicle's predicted distance based on target driving parameters and lane curvature involves analyzing the vehicle's dynamic performance and road geometry to calculate the expected distance the vehicle will travel over a future period. This predicted distance is used to anticipate the vehicle's path and provide a basis for lane-keeping control.

[0058] The process of determining the predicted distance based on target driving parameters and lane curvature enables the prediction of the vehicle's future driving path. In straight-line driving situations, the calculation of the predicted distance helps the intelligent driving system accurately determine whether the vehicle meets the straight-line driving conditions, thereby deciding whether to initiate steering wheel angle compensation value calculation, ensuring the effectiveness and accuracy of the steering wheel angle compensation value calculation process. Simultaneously, setting the predicted distance also helps the vehicle adjust its lateral control strategy in advance in curves with small curvature, reducing instability factors when driving in curves, improving the overall performance of lane-keeping control, and enhancing driving comfort and safety.

[0059] Step S108: Based on the predicted distance and target driving parameters, control the steering wheel so that the vehicle travels on the virtual lane line.

[0060] In one alternative embodiment, the required steering wheel angle can be calculated using a mathematical model and control strategy based on the predicted distance and target driving parameters. The system then sends this steering angle command to the EPS (Electric Power Steering). Upon receiving the command, the EPS adjusts the electric power steering of the steering wheel to achieve the desired angle, thereby guiding the vehicle to travel along the predicted path and remain centered on the virtual lane lines.

[0061] In another alternative embodiment, the intelligent driving system not only relies on lane curvature and predicted distance for control but also integrates a deep learning model of road features and a vehicle dynamics model. The system constructs a neural network model capable of predicting steering wheel control strategies under specific road conditions by learning from historical driving data. When the vehicle is traveling on complex or unknown road sections, the system analyzes road conditions (such as cross slope and road surface material) in real time and combines this with the vehicle's current driving parameters (vehicle speed, acceleration, etc.), inputting these parameters into the deep learning model. The model outputs a steering wheel angle adjustment strategy that comprehensively considers vehicle dynamics and road characteristics, accurately controlling the steering wheel angle to adapt to changing driving conditions and improve the vehicle's tracking accuracy on straightaways and curves.

[0062] In this embodiment, during vehicle operation, the target driving parameters, current driving position, and lane information of multiple lane lines in the current driving road are acquired, wherein different lane lines are located at different positions in the current driving road. Based on the current driving position and lane line information, the lane line curvature of a virtual lane line is determined, wherein the virtual lane line is used to represent a position between any two lane lines among multiple lane lines. Based on the target driving parameters and lane line curvature, the predicted distance of the vehicle is determined, wherein the predicted distance is used to represent the distance between the target driving position and the current driving position of the vehicle, and the target driving position is the predicted driving position that the vehicle wants to reach. Based on the predicted distance and target driving parameters, the steering wheel is controlled so that the vehicle drives on the virtual lane line. Virtual lane lines can be dynamically generated based on real-time driving parameters, location, and lane information. These virtual lane lines can then be used as a reference for autonomous driving. The curvature of the virtual lane lines can be determined using the current driving position and lane line information. By using the target driving parameters and lane line curvature, the predicted distance between the vehicle and the desired driving position can be predicted. The steering wheel can be controlled by calculating the predicted distance to ensure that the vehicle travels on the virtual lane lines. This improves the vehicle's driving stability between different lane lines, enhances driving stability and safety, and solves the technical problem of poor steering wheel control in related technologies.

[0063] Optionally, the steering wheel is controlled based on the predicted distance and target driving parameters to make the vehicle travel on the virtual lane line, including: determining the target steering wheel angle compensation value of the vehicle based on the predicted distance, target driving parameters and lane control mode, wherein the target steering wheel angle compensation value is used to adjust the current steering wheel angle of the vehicle, and the lane control mode is used to represent the mode of controlling the vehicle's driving area; compensating the current steering wheel angle based on the target steering wheel angle compensation value to generate the target steering wheel angle; and controlling the steering wheel based on the target steering wheel angle to make the vehicle travel on the virtual lane line.

[0064] The aforementioned target steering wheel angle compensation value is an adjustment calculated by the intelligent driving system to ensure the vehicle accurately stays on the virtual lane line, correcting the deviation between the vehicle's current steering wheel angle and the ideal steering state. The target steering wheel angle compensation value can be obtained by combining predicted distance, target driving parameters, and lane control mode. This value improves the vehicle's centering control on straight roads and curves with small curvatures, reducing control inaccuracies caused by sensor calibration deviations.

[0065] For example, the actual steering wheel angle is multiplied by the program execution cycle (typically 20ms), and then multiplied by the self-learning coefficient to obtain the self-learning value per unit cycle. The self-learning coefficient is an important calibration parameter that determines the learning speed. The self-learning process can take several hours or longer, and this parameter needs to be calibrated on a real vehicle; a typical value is 0.0003.

[0066] The self-learning value within a unit period is accumulated and then added to the self-learning value at the next moment to obtain the self-learning zero-position integral value.

[0067] The self-learning zero-position integral value needs to undergo integral anti-saturation processing. This is achieved by setting upper and lower limits for the self-learning accumulated value, typically with an upper limit of 3 degrees and a lower limit of -3 degrees. The output after this processing is the steering wheel angle zero-position self-learning value. This value is stored in an electrically erasable programmable read-only memory (EEPROM) after power-off. It can be used directly the next time the vehicle is powered on; that is, the system will automatically remember the previously learned steering wheel position when the car is started again, without requiring recalibration or adjustment.

[0068] The current steering wheel angle is compensated based on the target steering wheel angle compensation value to generate the target steering wheel angle. The calculated compensation value is then applied to the current steering wheel angle using the intelligent driving system's algorithm to correct the vehicle's directional deviation and ensure it travels along the virtual lane lines. The compensation process requires calculation to achieve stable vehicle control under various driving conditions (such as straight roads and tight curves).

[0069] The steering wheel is controlled based on a target steering wheel angle to keep the vehicle traveling along a virtual lane. This is achieved by sending the generated target steering wheel angle command to the vehicle's EPS (Electrical Power Control) system. Upon receiving the command, the EPS adjusts the steering wheel angle to ensure the vehicle's actual driving path aligns with the virtual lane lines, thus achieving stable and centered driving.

[0070] This application's embodiments determine the target steering wheel angle compensation value based on predicted distance, target driving parameters, and lane control mode. This not only compensates for steering wheel angle errors caused by sensor calibration deviations but also enhances the vehicle's centering control capability on straight roads and curves with small curvatures, ensuring the vehicle stays within the virtual lane. This technology improves driving comfort and safety, especially in multi-lane situations, where the system can more intelligently adjust the vehicle's path, ensuring the vehicle remains stably within the virtual lane, thereby improving the overall performance and user experience of the intelligent driving system. Through dynamic compensation calculations, it effectively solves the problem of inaccurate control caused by sensor calibration deviations, improving the vehicle's adaptability and stability under complex road conditions.

[0071] Optionally, the current steering wheel angle of the vehicle is compensated based on the target steering wheel angle compensation value to generate the target steering wheel angle. This includes: determining whether the vehicle meets the steering wheel angle compensation value update conditions based on the predicted distance, target driving parameters, and lane control mode, wherein the steering wheel angle compensation value update conditions are used to represent the conditions for updating the current steering wheel angle compensation value of the vehicle; if the vehicle meets the steering wheel angle compensation value update conditions, the current steering wheel angle compensation value is updated based on the vehicle's current steering wheel angle and a preset coefficient to obtain the target steering wheel angle compensation value; if the vehicle does not meet the steering wheel angle compensation value update conditions, the current steering wheel angle compensation value is determined to be the target steering wheel angle compensation value.

[0072] By comprehensively analyzing predicted distance, target driving parameters, and lane control mode, it is determined whether the vehicle meets the steering wheel angle compensation value update conditions. These conditions are used to determine when to adjust the vehicle's current steering wheel angle compensation value to better adapt to changes in the vehicle's driving state.

[0073] If the vehicle meets the steering wheel angle compensation value update conditions, this embodiment updates the current steering wheel angle compensation value based on the vehicle's current steering wheel angle and a preset coefficient. A new target steering wheel angle compensation value is calculated by combining the current steering wheel angle with the preset coefficient. The preset coefficient is a parameter calibrated according to vehicle characteristics and driving environment, used to adjust the magnitude of the compensation value to ensure that the updated compensation value can eliminate the influence of steering wheel zero-position deviation while maintaining vehicle stability and responsiveness. If the vehicle does not meet the steering wheel angle compensation value update conditions, this embodiment determines the current steering wheel angle compensation value as the target steering wheel angle compensation value, ensuring that excessive adjustment of the steering wheel angle compensation value is avoided when the update conditions are not met, thereby maintaining the stability and consistency of the vehicle's driving state and avoiding control instability caused by frequent compensation value updates.

[0074] The embodiments of this application can control the steering wheel angle of a vehicle. Under driving conditions on straight roads and curves with small curvature, by updating the steering wheel angle compensation value, it can not only compensate for the deviation of the vehicle's steering wheel zero position, but also maintain the vehicle's stable and centered driving in complex road environments, thereby improving driving comfort and safety.

[0075] Optionally, based on the predicted distance, target driving parameters, and lane control mode, it is determined whether the vehicle meets the steering wheel angle compensation value update conditions, including: determining the lane radius of the virtual lane line based on the predicted distance, wherein the lane radius is used to quantify the curvature of the virtual lane line at the current driving position; determining the current driving speed of the vehicle based on the target driving parameters; and determining whether the vehicle meets the steering wheel angle compensation value update conditions based on the lane radius, current driving speed, and lane control mode.

[0076] In this embodiment, the lane radius can be determined by predicting the distance, and the lane radius can quantify the curvature of the virtual lane line at the current driving position. By combining the vehicle's real-time driving information and road conditions, the steering needs of the vehicle under different conditions can be dynamically reflected, providing an important basis for calculating steering wheel angle compensation. The lane radius is the virtual lane radius. Substituting the predicted distance into the second derivative of the virtual lane equation, the lane curvature of the virtual lane is obtained, and the reciprocal of the lane curvature of the virtual lane is the radius of the virtual lane.

[0077] The target driving parameters mentioned above cover real-time dynamic indicators of the vehicle, such as vehicle length, acceleration, and yaw rate. Among them, the current driving speed is directly determined based on the target driving parameters and reflects the actual speed of the vehicle on the road.

[0078] In one optional embodiment, when the lane centering control function is activated and the vehicle is traveling on a straight road segment, the intelligent driving system first substitutes the calculated predicted distance into the second derivative equation of the cubic equation of the virtual lane line to obtain the predicted curvature of the virtual lane line, which is used to assess the curvature of the road. Simultaneously, the vehicle's speed can be obtained through sensors. When the virtual lane radius exceeds a set threshold (indicating the vehicle is traveling in a straight line), the vehicle speed is within a preset range (which can be set based on safe driving or different driving scenarios, for example, 20 to 100 km / h), and the lane centering control (LCC) function is currently activated, the system considers the conditions for updating the steering wheel angle compensation value met and begins the compensation value calculation process to adjust the steering wheel angle.

[0079] Based on the lane radius of the virtual lane lines, the current driving speed, and the lane control mode, the system determines whether the vehicle meets the conditions for updating the steering wheel angle compensation value. This process comprehensively analyzes the vehicle's dynamic characteristics, road conditions, and driving mode. By setting specific update criteria, it determines when to update the steering wheel angle compensation value. Through intelligent recognition and adaptation to different driving environments, it ensures that the steering wheel angle compensation value is adjusted at the appropriate time, avoiding frequent updates and effectively improving the vehicle's driving stability and control precision under complex road conditions.

[0080] This application's embodiments determine the lane radius of the virtual lane line based on predicted distance and, combined with the current driving speed and lane control mode in the target driving parameters, dynamically determine the update conditions for the steering wheel angle compensation value, thus achieving intelligent control of the vehicle's steering wheel angle. This technology directly improves the vehicle's lane centering performance on straight roads and curves with small curvatures, reduces driving deviations caused by steering wheel zero-position deviation, and enhances the driver's driving experience and safety. Especially in autonomous driving or assisted driving modes, it helps to achieve smooth and safe intelligent driving.

[0081] Optionally, based on the lane radius, current driving speed, and lane control mode, it is determined whether the vehicle meets the steering wheel angle compensation value update conditions, including: if the lane radius is within a preset radius range, the current driving speed is within a preset speed range, and the lane control mode is a preset control mode, the vehicle is determined to meet the steering wheel angle compensation value update conditions, wherein the preset control mode is used to indicate the control mode that controls the vehicle to be in the virtual lane line; if the lane radius is not within the preset radius range, or the current driving speed is not within the preset speed range, or the lane control mode is not a preset control mode, the vehicle is determined not to meet the steering wheel angle compensation value update conditions.

[0082] The lane control mode mentioned above refers to the operating mode in a vehicle's intelligent driving system that controls the vehicle to stay near the center line of the lane. A preset control mode can refer to a mode used to control the vehicle's movement along a virtual lane. Determining the preset control mode ensures that the compensation value is updated only when the system is performing lane keeping control, avoiding frequent updates in non-controlled states or specific driving tasks.

[0083] Furthermore, the vehicle meets the steering wheel angle compensation value update conditions if all three of the following conditions are met simultaneously: 1) The lane radius is greater than the straight-line threshold (this threshold is a calibrated value, typically 5000 meters); 2) The vehicle speed is within the specified range (typically greater than 20 kph and less than 100 kph); 3) Lane centering control is activated. If any of the above three conditions is not met, the vehicle does not meet the steering wheel angle compensation value update conditions.

[0084] In one optional embodiment, if the lane radius is within a preset radius range, the current driving speed is within a preset speed range, and the lane control mode is a preset control mode (i.e., the vehicle is in a stable driving state on a straight road or a small-curve curve), and the intelligent driving system is performing lane centering control, then the vehicle is determined to meet the steering wheel angle compensation value update conditions. The system can safely and effectively adjust the steering wheel angle compensation value to eliminate zero-position deviation caused by factors such as dispersion and vehicle aging, thereby improving the vehicle's lateral control performance.

[0085] In another optional embodiment, if the lane radius is not within a preset radius range, or the current driving speed is not within a preset speed range, or the lane control mode is not a preset control mode (i.e., the vehicle is driving on a sharp curve, at too high or too low speed, or the lane control function is not activated), then it is determined that the vehicle does not meet the steering wheel angle compensation value update conditions. In the above situations, updating the compensation value introduces instability or affects driving safety; therefore, the system will not update it to maintain the vehicle's stable driving state under the current conditions.

[0086] This application embodiment intelligently determines whether the vehicle meets the steering wheel angle compensation value update conditions by setting preset radius range, preset speed range, and preset control mode, thus achieving dynamic and timely updates of the compensation value. This technical solution avoids compensation adjustments under unsuitable driving conditions, ensuring the vehicle's stability and centering control performance on straight roads and curves with small curvatures. It also improves the adaptability of the intelligent driving system and the user's driving experience, especially in driving scenarios requiring long-term or high-frequency lane centering, enhancing the vehicle's lateral control accuracy and safety.

[0087] Optionally, determining the lane radius of the virtual lane line based on the predicted distance includes: determining the predicted curvature of the target driving position based on the predicted distance; and determining the reciprocal of the predicted curvature as the lane radius.

[0088] In this embodiment, determining the predicted curvature of the target driving position based on the predicted distance refers to mathematically differentiating the virtual lane function to obtain its rate of change at a specific point. This rate of change is the curvature of the predicted distance in the road environment, i.e., the curvature of the target driving position. The curvature of the predicted distance reflects the degree of curvature of the vehicle's future driving path. The calculation of the curvature of the target driving position is based on road model and vehicle state data. By analyzing the vehicle's driving direction and path, the curvature of the future position path is derived, which is the basis for the intelligent driving system to predict and adjust its control strategy.

[0089] The reciprocal of the curvature of the predicted distance, as described above, is the lane radius. By calculating the lane radius from the reciprocal of the curvature of the predicted distance, the conversion of the road's curvature change at the target driving position to a specific radius value is quantified. The lane radius of the virtual lane affects the vehicle's steering control and centering ability. Calculating the lane radius further guides the vehicle's lateral control strategy, particularly influencing the adjustment of the steering wheel angle, ensuring that the vehicle can accurately travel along the virtual lane line.

[0090] By differentiating the virtual lane in this embodiment and substituting the predicted distance into the predicted curvature of the target driving position, the reciprocal of the predicted curvature is determined as the lane radius, thus quantifying the curvature of the vehicle's future driving path. This not only provides the intelligent driving system with the ability to predict vehicle driving trends but also enables the system to dynamically adjust the steering wheel angle based on lane radius information, improving lane centering control performance.

[0091] Optionally, the multiple lane lines include: a first lane line and a second lane line. The lane line information includes: first sub-lane line information of the first lane line and second sub-lane line information of the second lane line. Based on the current driving position and the lane line information, the lane line curvature of the virtual lane line is determined, including: determining a first curve equation of the first lane line based on the first sub-lane line information; determining a second curve equation of the second lane line based on the second sub-lane line information; determining a third curve equation of the virtual lane line based on the first curve equation and the second curve equation; and determining the lane line curvature based on the current driving position and the third curve equation.

[0092] In this embodiment, the first lane line and the second lane line refer to the virtual road lines on the left and right sides of the vehicle's direction of travel, respectively. These lines are identified and information is provided by the perception system to define the lane boundaries for vehicle travel. The lane line information includes data defining the position, shape, and dynamic changes of the first and second lane lines, including but not limited to the lane line's position coordinates, slope, curvature, and the rate of change of these parameters over time. The first sub-lane line information of the first lane line and the second sub-lane line information of the second lane line describe the attributes of the left and right lane lines, respectively, and are the basic data for calculating the curvature of the virtual lane lines.

[0093] The aforementioned determination of the first curve equation for the first lane line based on the first sub-lane line information involves converting the information of the first lane line into a mathematical expression through mathematical modeling. This equation describes the geometry of the first lane line and its characteristics as it changes with the vehicle's driving position. Similarly, the determination of the second curve equation for the second lane line based on the second sub-lane line information is used to mathematically express the geometric characteristics of the second lane line.

[0094] The aforementioned determination of the third curve equation for the virtual lane line based on the first and second curve equations refers to the intelligent driving system calculating a mathematical equation representing the lane centerline by weighted averaging of the mathematical models of the first and second lane lines. This virtual lane line serves as the reference line for the intelligent driving system's lane centering control, and its curvature calculation is fundamental to determining whether the vehicle meets the conditions for straight-line driving.

[0095] The aforementioned determination of lane curvature based on the current driving position and the third curve equation refers to the system deriving a numerical index reflecting the degree of curvature of the lane line at the current point, namely, lane curvature, based on the vehicle's current actual position and the aforementioned calculated virtual lane line mathematical model.

[0096] In one optional embodiment, firstly, a vision sensor captures and analyzes the features of the first and second lane lines on both sides of the road to form first and second sub-lane line information. Next, through polynomial fitting, mathematical models of the two lane lines are constructed, namely the first and second curve equations. Subsequently, the system uses a weighted average method to synthesize the two curve equations to generate a virtual lane line equation reflecting the ideal driving path of the vehicle, namely the third curve equation. Finally, based on the vehicle's current driving position, the second derivative of the third curve equation is calculated to determine the curvature of the virtual lane line at that point, providing crucial data support for the vehicle to maintain centering.

[0097] The mathematical modeling in this embodiment converts the information of the first sub-lane line of the first lane line and the second sub-lane line of the second lane line into the first curve equation of the first lane line and the second curve equation of the second lane line, and then calculates the third curve equation of the virtual lane line, ultimately determining the lane line curvature. This process quantifies the vehicle's driving environment, providing accurate lane boundary information and road curvature judgment basis for the intelligent driving system. Especially when driving straight, based on the determination of lane line curvature, the lane situation of the vehicle can be identified, providing conditions for subsequent steering wheel compensation value calculation, ensuring the accurate execution of the self-learning method under straight driving conditions, thereby improving lane centering control performance and driving experience.

[0098] Optionally, the predicted distance of the vehicle is determined based on the target driving parameters and the lane curvature, including: obtaining an initial predicted distance based on the vehicle's current driving speed and prediction time in the target driving parameters, wherein the prediction time is used to represent the predicted time for the vehicle to reach the target driving position; and determining the predicted distance based on the initial predicted distance and a preset curvature correction coefficient.

[0099] The initial predicted distance is obtained based on the vehicle's current speed and prediction time from the target driving parameters. These parameters include real-time dynamic information such as vehicle speed, acceleration, and yaw rate, with vehicle speed being the direct indicator of the vehicle's movement. The prediction time is a pre-set time parameter representing the expected timeframe for the intelligent driving system to acquire the target location. The initial predicted distance is calculated by multiplying the vehicle's current speed by the prediction time, reflecting the projected distance the vehicle can travel after the predicted time, based on its current speed.

[0100] Based on the initial predicted distance and the preset curvature correction coefficient, the predicted distance is determined, further improving prediction accuracy. The preset curvature correction coefficient is a parameter calibrated according to road curvature and vehicle performance, used to adjust the initial predicted distance to ensure that the predicted distance more closely reflects actual road conditions. By combining the initial predicted distance with road characteristics and vehicle dynamic performance, and through correction, the predicted distance value is obtained, which is an important basis for subsequently determining whether the vehicle is traveling in a straight line.

[0101] The initial predicted distance calculation and predicted distance correction steps in this embodiment enable accurate prediction of the vehicle's future driving position. Based on a comprehensive analysis of the vehicle's current speed and predicted time in the target driving parameters, and the introduction of a preset curvature correction coefficient, the predicted distance can be ensured to be closer to the actual road conditions, providing a reliable basis for accurately judging straight-line driving and calculating the curvature of the virtual lane line.

[0102] Figure 2 This is a system structure diagram of an optional vehicle steering wheel control method according to an embodiment of this application, such as... Figure 2 As shown, the lane centering control system includes a sensing camera 201, a lane centering control unit 202, a steering wheel angle controller 203, and a vehicle 204.

[0103] The perception camera 201 obtains the cubic equation of the lane line through the visual image processing unit and transmits it to the lane centering control unit 202.

[0104] Information such as the vehicle speed, yaw rate, and actual steering wheel angle of vehicle 204 is transmitted to the lane centering control unit 202 via the Controller Area Network (CAN).

[0105] The lane centering control 202 calculates the target steering wheel angle based on the cubic equation of the perceived lane lines, vehicle speed, yaw rate, and actual steering wheel angle, and sends this information to the steering wheel angle controller via CAN. The lane centering control 202 algorithm includes an algorithm for zero-compensation value of the steering wheel angle.

[0106] The steering wheel angle controller 203 controls the electronically controlled steering wheel to move according to the target steering wheel angle based on the lane centering control 202. This steering wheel angle control ensures that the vehicle 204 stays centered within the desired lane.

[0107] Figure 3 This is a flowchart illustrating an optional vehicle steering wheel control method according to an embodiment of this application, as shown below. Figure 3 As shown, the specific process is as follows:

[0108] Step 301: Obtain the lane line equation perceived by the camera and relevant vehicle parameters, including chassis speed, yaw rate, and actual steering wheel angle.

[0109] Step 302: Calculate the lane curvature at the current point by taking the second derivative of the perceived lane line equation.

[0110] Figure 4 This is a schematic diagram of lane lines and predicted distances for an optional vehicle steering wheel control method according to an embodiment of this application, such as... Figure 4 As shown, a coordinate system is constructed with x-axis and y-axis. The road includes left lane lines, right lane lines, and virtual lane lines. The predicted distance of the vehicle can be calculated based on the vehicle's current position coordinates in the coordinate system.

[0111] The sensing camera provides the cubic equations of the left and right lane lines. The lane centering control unit then uses a weighted average of the coefficients of these cubic equations to obtain the cubic equations of the virtual lane lines. The specific calculation process is as follows:

[0112] The equation for the left lane line can be expressed as follows:

[0113] ;

[0114] in, The constant term of the polynomial represents when The value of the function at that time. The coefficient of the linear term, and Direct multiplication affects the curve. Slope in direction, The calculated representation of the left lane line, You can substitute it into the predicted distance. The coefficient of the quadratic term, and Multiplication primarily affects the curvature and direction of the curve. It is the coefficient of the cubic term, and Multiplication has a more complex effect on the shape of a curve, altering its inflection points and causing it to accelerate its ascent or descent in certain regions, thus producing more complex shapes.

[0115] The equation for the right lane line can be expressed as follows:

[0116] ;

[0117] in, For the constant term of the polynomial, The coefficient of the linear term, The coefficient of the quadratic term, It is the coefficient of the cubic term. This is a representation of the calculated equation for the right lane line. You can substitute it into the predicted distance.

[0118] By weighted averaging the coefficients of the left and right lane line equations, the virtual lane line equations are obtained:

[0119] ;

[0120] in, For the constant term of the polynomial, The coefficients of the linear terms, The coefficient of the quadratic term. It is the coefficient of the cubic term. The representation of the calculated virtual lane line equation, You can substitute it into the predicted distance.

[0121] Taking the second derivative of the virtual lane line equation, we obtain the following equation:

[0122] ;

[0123] in, The coefficient of the quadratic term. It is the coefficient of the cubic term. The second derivative of the calculated virtual lane line equation is then performed. You can substitute it into the predicted distance.

[0124] Substituting x as 0, we obtain the curvature of the current point. :

[0125] ;

[0126] in, is the coefficient of the quadratic term. Let be the curvature at the current point.

[0127] Step 303: Calculate the predicted distance by multiplying the vehicle speed by the predicted time and then by the predicted curvature correction factor.

[0128] Figure 5 This is a block diagram illustrating the predicted distance calculation of an optional vehicle steering wheel control method according to an embodiment of this application, such as... Figure 5 As shown, the predicted time can be obtained by looking up the table based on the vehicle speed, the initial predicted distance can be obtained by multiplying the predicted time by the vehicle speed, the predicted curvature correction coefficient can be obtained based on the lane curvature, and the predicted distance can be obtained by multiplying the initial predicted distance and the predicted curvature correction coefficient.

[0129] The predicted time mentioned above is obtained by looking up a one-dimensional table based on vehicle speed correction. Multiplying the vehicle speed by the predicted time yields the initial predicted distance. The predicted curvature correction coefficient is obtained by looking up a one-dimensional table based on curvature correction. Multiplying the initial predicted distance by the predicted curvature correction coefficient yields the final predicted distance. .

[0130] Step 304: Substitute the predicted distance into the second derivative equation of the lane line to obtain the predicted curvature and lane radius. The specific calculation process is as follows:

[0131] 1) Predict the distance Substituting the second derivative equation of the lane line, we obtain the predicted curvature. :

[0132] ;

[0133] 2) Lane radius for:

[0134] ;

[0135] Step 305: Determine whether to enter the self-learning mode based on whether the lane radius is greater than the straight-line threshold. The self-learning mode is entered when all three of the following conditions are met: 1) The lane radius is greater than the straight-line threshold (this threshold is a calibrated value, typically 5000 meters); 2) The vehicle speed is within the range (typically greater than 20 kph and less than 100 kph); 3) Lane centering control is activated. If any of the above three conditions is not met, the non-self-learning mode is entered.

[0136] Step 306, Non-self-learning operating mode, self-learning value is maintained. In non-self-learning operating mode, the steering wheel angle zero-position self-learning value remains unchanged, that is, the zero position does not perform self-learning.

[0137] Step 307, self-learning operating mode, the self-learning value is obtained by integrating the actual steering wheel angle.

[0138] Figure 6This is a block diagram illustrating the self-learning value calculation of a vehicle steering wheel control method according to an embodiment of this application. As shown, the actual steering wheel angle is multiplied by the program execution cycle (calculation cycle, typically 20ms), and then multiplied by the self-learning coefficient to obtain the self-learning value per unit cycle. The self-learning coefficient is a calibration parameter that determines the learning speed. The self-learning process can take several hours or longer, and this parameter needs to be calibrated on a real vehicle; a typical value is 0.0003. The self-learning value within a unit cycle is accumulated by adding the self-learning value from the previous moment to obtain the self-learning zero-position integral value. The self-learning zero-position integral value needs to undergo integral anti-saturation processing. An upper and lower limit processing method is used to adjust the accumulated self-learning value, typically with an upper limit of 3 degrees and a lower limit of -3 degrees. After processing the self-learning integral upper and lower limits, the output is the steering wheel angle zero-position self-learning value. This self-learning value is stored in an electrically erasable programmable read-only memory (EEPROM) after power-off and can be used directly upon the next vehicle power-on.

[0139] The zero-point self-learning value of the steering wheel angle is used for lane centering control. The desired steering wheel angle calculated by the LCC is subtracted from the zero-point self-learning value to obtain the final target steering wheel angle, which is then sent to the EPS controller.

[0140] 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. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0141] According to an embodiment of this application, a device for controlling the steering wheel of a vehicle is provided. It should be noted that the device can be used to execute the aforementioned method for controlling the steering wheel of a vehicle. Figure 7 This is a schematic diagram of a vehicle steering wheel control device according to an embodiment of this application, as shown below. Figure 7 As shown, the device 700 includes: a first acquisition module 702, a first determination module 704, a second determination module 706, and a first control module 708.

[0142] The system comprises the following modules: a first acquisition module, used to acquire the vehicle's target driving parameters, current driving position, and lane information of multiple lane lines in the current driving road during vehicle operation; a first determination module, used to determine the lane curvature of a virtual lane line based on the current driving position and lane information; a second determination module, used to determine the predicted distance of the vehicle based on the target driving parameters and lane curvature; and a first control module, used to control the steering wheel based on the predicted distance and target driving parameters to ensure the vehicle travels on the virtual lane line.

[0143] The first control module is further configured to determine a target steering wheel angle compensation value for the vehicle based on the predicted distance, target driving parameters, and lane control mode. The target steering wheel angle compensation value is used to adjust the current steering wheel angle of the vehicle, and the lane control mode is used to represent the mode for controlling the vehicle's driving area. The current steering wheel angle is compensated based on the target steering wheel angle compensation value to generate a target steering wheel angle. The steering wheel is controlled based on the target steering wheel angle so that the vehicle travels on the virtual lane line.

[0144] The first control module is further configured to determine whether the vehicle meets the steering wheel angle compensation value update conditions based on the predicted distance, target driving parameters, and lane control mode. The steering wheel angle compensation value update conditions represent the conditions for updating the vehicle's current steering wheel angle compensation value. If the vehicle meets the steering wheel angle compensation value update conditions, the current steering wheel angle compensation value is updated based on the vehicle's current steering wheel angle and a preset coefficient to obtain the target steering wheel angle compensation value. If the vehicle does not meet the steering wheel angle compensation value update conditions, the current steering wheel angle compensation value is determined to be the target steering wheel angle compensation value.

[0145] The first control module is also used to determine the lane radius of the virtual lane line based on the predicted distance, wherein the lane radius is used to quantify the curvature of the virtual lane line at the current driving position; determine the current driving speed of the vehicle based on the target driving parameters; and determine whether the vehicle meets the steering wheel angle compensation value update conditions based on the lane radius, the current driving speed, and the lane control mode.

[0146] The first control module is further configured to determine that the vehicle meets the steering wheel angle compensation value update conditions if the lane radius is within a preset radius range, the current driving speed is within a preset speed range, and the lane control mode is a preset control mode. The preset control mode is used to indicate the control mode in which the vehicle is in a virtual lane line. If the lane radius is not within the preset radius range, or the current driving speed is not within the preset speed range, or the lane control mode is not a preset control mode, the vehicle does not meet the steering wheel angle compensation value update conditions.

[0147] The first control module is also used to determine the predicted curvature of the target driving position based on the predicted distance; and to determine the reciprocal of the predicted curvature as the lane radius.

[0148] The first acquisition module is further configured to handle the first lane line and the second lane line. The lane line information includes: first sub-lane line information of the first lane line and second sub-lane line information of the second lane line. Based on the current driving position and the lane line information, the module determines the lane line curvature of the virtual lane line, including: determining the first curve equation of the first lane line based on the first sub-lane line information; determining the second curve equation of the second lane line based on the second sub-lane line information; determining the third curve equation of the virtual lane line based on the first curve equation and the second curve equation; and determining the lane line curvature based on the current driving position and the third curve equation.

[0149] The second determining module is further configured to obtain an initial predicted distance based on the vehicle's current driving speed and predicted time in the target driving parameters, wherein the predicted time is used to represent the predicted time for the vehicle to reach the target driving position; and to determine the predicted distance based on the initial predicted distance and a preset curvature correction coefficient.

[0150] Embodiments of this application also provide a vehicle, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods described in various embodiments of this application when it runs.

[0151] Embodiments of this application also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0152] Embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0153] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods in various embodiments of this application.

[0154] Embodiments of this application also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of this application.

[0155] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0156] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0157] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0158] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0159] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0160] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for controlling a vehicle's steering wheel, characterized in that, include: During the vehicle's operation, the target driving parameters, current driving position, and lane line information of multiple lane lines in the current driving road are acquired, wherein different lane lines are located at different positions in the current driving road. Based on the current driving position and the lane line information, the lane line curvature of the virtual lane line is determined, wherein the virtual lane line passes through the preset driving position of the vehicle in the current driving road and is parallel to the plurality of lane lines; Based on the target driving parameters and the lane curvature, the predicted distance of the vehicle is determined, wherein the predicted distance is used to represent the distance between the target driving position and the current driving position of the vehicle, and the target driving position is the predicted driving position that the vehicle is to reach. Based on the predicted distance and the target driving parameters, the steering wheel is controlled so that the vehicle travels on the virtual lane.

2. The method according to claim 1, characterized in that, Based on the predicted distance and the target driving parameters, the steering wheel is controlled to make the vehicle travel on the virtual lane line, including: Based on the predicted distance, the target driving parameters, and the lane control mode, a target steering wheel angle compensation value for the vehicle is determined, wherein the target steering wheel angle compensation value is used to adjust the current steering wheel angle of the vehicle, and the lane control mode is used to represent the mode for controlling the driving area of ​​the vehicle. The current steering wheel angle is compensated based on the target steering wheel angle compensation value to generate the target steering wheel angle; The steering wheel is controlled based on the target steering wheel angle so that the vehicle travels on the virtual lane line.

3. The method according to claim 2, characterized in that, The current steering wheel angle of the vehicle is compensated based on the target steering wheel angle compensation value to generate a target steering wheel angle, including: Based on the predicted distance, the target driving parameters, and the lane control mode, it is determined whether the vehicle meets the steering wheel angle compensation value update condition, wherein the steering wheel angle compensation value update condition is used to represent the condition for updating the current steering wheel angle compensation value of the vehicle. If the vehicle meets the steering wheel angle compensation value update condition, the current steering wheel angle compensation value is updated based on the vehicle's current steering wheel angle and a preset coefficient to obtain the target steering wheel angle compensation value. If the vehicle does not meet the steering wheel angle compensation value update condition, the current steering wheel angle compensation value is determined to be the target steering wheel angle compensation value.

4. The method according to claim 3, characterized in that, Based on the predicted distance, the target driving parameters, and the lane control mode, determining whether the vehicle meets the steering wheel angle compensation value update conditions includes: The lane radius of the virtual lane line is determined based on the predicted distance, wherein the lane radius is used to quantify the curvature of the virtual lane line at the current driving position; The current speed of the vehicle is determined based on the target driving parameters; Based on the lane radius, the current driving speed, and the lane control mode, determine whether the vehicle meets the steering wheel angle compensation value update conditions.

5. The method according to claim 4, characterized in that, Based on the lane radius, the current driving speed, and the lane control mode, determine whether the vehicle meets the steering wheel angle compensation value update conditions, including: If the lane radius is within a preset radius range, the current driving speed is within a preset speed range, and the lane control mode is a preset control mode, it is determined that the vehicle meets the steering wheel angle compensation value update condition, wherein the preset control mode is used to represent the control mode for controlling the vehicle to be in the virtual lane line; If the lane radius is not within the preset radius range, or the current driving speed is not within the preset speed range, or the lane control mode is not the preset control mode, it is determined that the vehicle does not meet the steering wheel angle compensation value update condition.

6. The method according to claim 4, characterized in that, Determining the lane radius of the virtual lane line based on the predicted distance includes: Based on the predicted distance, the predicted curvature of the target driving position is determined; The reciprocal of the predicted curvature is determined as the lane radius.

7. The method according to claim 1, characterized in that, The plurality of lane lines includes: a first lane line and a second lane line. The lane line information includes: first sub-lane line information of the first lane line and second sub-lane line information of the second lane line. Based on the current driving position and the lane line information, the lane line curvature of the virtual lane line is determined, including: Based on the first sub-lane line information, determine the first curve equation of the first lane line; Based on the second sub-lane line information, determine the second curve equation of the second lane line; Based on the first curve equation and the second curve equation, determine the third curve equation of the virtual lane line; The lane curvature is determined based on the current driving position and the equation of the third curve.

8. The method according to claim 1, characterized in that, Based on the target driving parameters and the lane curvature, the predicted distance of the vehicle is determined, including: Obtain the preset curvature correction coefficient corresponding to the lane line curvature; Based on the vehicle's current speed and predicted time in the target driving parameters, an initial predicted distance is obtained, wherein the predicted time is used to represent the predicted time for the vehicle to reach the target driving position; The predicted distance is determined based on the initial predicted distance and the preset curvature correction coefficient.

9. A vehicle, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the method according to any one of claims 1 to 8.

Images