Lane keeping method, device, apparatus and storage medium

Abstract

The present disclosure relates to a lane keeping method. The method comprises: acquiring real-time driving data of a vehicle, the real-time driving data comprising a real-time position and a reference position corresponding to the real-time position; calculating a vehicle steering curvature corresponding to the real-time position based on a position deviation between the real-time position and the reference position; calculating a target steering wheel angle corresponding to the vehicle steering curvature; and controlling the vehicle to keep lanes according to the target steering wheel angle. The present disclosure also relates to a lane keeping device, equipment and storage medium. According to the embodiments of the present disclosure, the lane keeping system can accurately control the vehicle to keep driving in a certain lane based on the target steering wheel angle, thereby improving the comfort and reliability of lane keeping, and further meeting the demand for comfortable and reliable lane cruising.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle control technology, and in particular to a lane keeping method, device, equipment and storage medium. Background Technology

[0002] Lane keeping assist systems help vehicles stay in a designated lane, preventing them from deviating from the lane.

[0003] During lane keeping, if the lane keeping system detects that the vehicle has deviated from the designated lane, it needs to adjust the steering wheel angle to bring the vehicle back into the designated lane. However, current lane keeping systems cannot accurately calculate the steering wheel angle, resulting in the system's inability to precisely control the vehicle to stay in the designated lane based on the less accurate steering wheel angle. This leads to poor comfort and reliability in lane keeping, making it difficult to meet the needs of comfortable and reliable lane cruise control. Summary of the Invention

[0004] In order to solve the above-mentioned technical problems, or at least partially solve the above-mentioned technical problems, this disclosure provides a lane keeping method, apparatus, device and storage medium.

[0005] In a first aspect, this disclosure provides a lane-keeping method, the method comprising:

[0006] Acquire real-time driving data of the vehicle, including real-time location and the corresponding reference location;

[0007] Calculate the vehicle steering curvature corresponding to the real-time position based on the positional deviation between the real-time position and the reference position.

[0008] Calculate the target steering wheel angle corresponding to the vehicle's steering curvature;

[0009] Control the vehicle to maintain lane position based on the target steering wheel angle.

[0010] In a second aspect, this disclosure provides a lane keeping device, the device comprising:

[0011] The data acquisition module is used to acquire real-time driving data of the vehicle, which includes the real-time location and the reference location corresponding to the real-time location.

[0012] The calculation module is used to calculate the vehicle steering curvature corresponding to the real-time position based on the positional deviation between the real-time position and the reference position, and to calculate the target steering wheel angle corresponding to the vehicle steering curvature.

[0013] The lane keeping module is used to control the vehicle to keep in the lane based on the target steering wheel angle.

[0014] Thirdly, embodiments of this disclosure also provide a lane keeping device, including:

[0015] processor;

[0016] Memory, used to store executable instructions;

[0017] The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the lane keeping method described in the first aspect above.

[0018] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to implement the lane-keeping method described in the first aspect.

[0019] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0020] This disclosure discloses a lane-keeping method, apparatus, device, and storage medium that can acquire the real-time position of a vehicle and a corresponding reference position. Based on the positional deviation between the real-time and reference positions, it calculates the vehicle's steering curvature corresponding to the real-time position, then calculates the target steering wheel angle corresponding to the curvature, and finally controls the vehicle to maintain its lane based on the target steering wheel angle. Since the positional deviation between the real-time and reference positions can include both lateral and longitudinal positional deviations, the vehicle's steering curvature can be accurately calculated based on the distance between the real-time and reference positions in the perpendicular direction of the vehicle's travel direction and the distance in the vehicle's travel direction. This allows for accurate calculation of the target steering wheel angle, improving the accuracy of the target steering wheel angle calculation. Consequently, the lane-keeping system can precisely control the vehicle to remain in a designated lane based on the target steering wheel angle, enhancing the comfort and reliability of lane-keeping and meeting the requirements for comfortable and reliable lane-keeping cruise. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0022] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1A schematic flowchart of a lane keeping method provided in an embodiment of this disclosure;

[0024] Figure 2 A schematic diagram illustrating the principle of calculating vehicle steering curvature as provided in this embodiment of the disclosure;

[0025] Figure 3 A schematic flowchart illustrating another lane-keeping method provided in this embodiment of the present disclosure;

[0026] Figure 4 A schematic diagram illustrating the principle of a lane keeping method provided in this embodiment of the disclosure;

[0027] Figure 5 A schematic flowchart illustrating yet another lane-keeping method provided in this disclosure embodiment;

[0028] Figure 6 A schematic flowchart illustrating another lane keeping method provided in an embodiment of this disclosure;

[0029] Figure 7 This is a schematic diagram of the structure of a lane keeping device provided in an embodiment of the present disclosure;

[0030] Figure 8 This is a schematic diagram of the structure of a lane keeping device provided in an embodiment of this disclosure. Detailed Implementation

[0031] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0032] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0033] This disclosure provides a lane keeping method, apparatus, device, and storage medium that can accurately calculate the target steering wheel angle, enabling the lane keeping system to precisely control the vehicle to stay in a designated lane based on the target steering wheel angle. This improves the comfort and reliability of lane keeping, thereby meeting the needs for comfortable and reliable lane cruise.

[0034] The following is a combination of... Figures 1 to 6 The lane keeping method provided in the embodiments of this disclosure will be described.

[0035] Figure 1 A schematic flowchart of a lane keeping method provided in an embodiment of this disclosure is shown.

[0036] In some embodiments of this disclosure, Figure 1 The lane keeping method shown can be executed by a lane keeping device. This lane keeping device can be a controller within a lane keeping system.

[0037] like Figure 1 As shown, the lane keeping method may include the following steps.

[0038] S110, Obtain real-time driving data of the vehicle.

[0039] In this embodiment of the disclosure, the lane keeping device can collect real-time driving data of the vehicle during the driving process.

[0040] In this embodiment of the disclosure, real-time driving data may include: real-time location and reference location corresponding to the real-time location.

[0041] The real-time location can be the vehicle's actual location on the road, while the reference location can be the vehicle's planned location on the road. Specifically, the planned location can be the navigation trajectory point that the lane-keeping device plans for the vehicle to reach at the corresponding time based on its real-time location.

[0042] Specifically, lane keeping devices can acquire data from navigation systems, positioning systems, and vehicle sensors, and after processing the acquired data, obtain the vehicle's real-time position and reference position.

[0043] S120. Based on the positional deviation between the real-time position and the reference position, calculate the vehicle steering curvature corresponding to the real-time position.

[0044] In this embodiment of the disclosure, after obtaining the real-time position and reference position of the vehicle, the lane keeping device can calculate the position deviation between the real-time position and the reference position, and then calculate the vehicle steering curvature corresponding to the real-time position based on the position deviation.

[0045] The positional deviation can include lateral and longitudinal positional deviations between the real-time position and the reference position. The lateral positional deviation can be the distance between the real-time position and the reference position in the direction perpendicular to the vehicle's travel direction. The longitudinal positional deviation can be the distance between the real-time position and the reference position in the vehicle's travel direction.

[0046] In this embodiment of the disclosure, the vehicle steering curvature corresponding to the real-time position can be the vehicle steering curvature calculated by the lane keeping device at the real-time position, so as to further calculate the target steering wheel angle based on the vehicle steering curvature corresponding to the real-time position.

[0047] Optionally, in this embodiment of the disclosure, the lane keeping device can first calculate the angle between the straight line formed by connecting the real-time position and the reference position and the vehicle's driving direction based on the lateral position deviation, longitudinal position deviation and vehicle turning radius in the position deviation, and if the angle is less than a preset angle, calculate the vehicle steering curvature corresponding to the real-time position based on the lateral position deviation and longitudinal position deviation.

[0048] The preset angle can be a pre-set angle. Furthermore, the preset angle can be the maximum angle of the vehicle steering curvature corresponding to the real-time position calculated based on the lateral position deviation and the longitudinal position deviation. Thus, when the calculated included angle is small enough, the vehicle steering curvature corresponding to the real-time position can be calculated based on the lateral position deviation and the longitudinal position deviation.

[0049] S130, Calculate the target steering wheel angle corresponding to the vehicle's steering curvature.

[0050] In this embodiment of the disclosure, after calculating the vehicle steering curvature, the lane keeping device can calculate the target steering wheel angle corresponding to the vehicle steering curvature.

[0051] In this embodiment of the disclosure, the target steering wheel angle may be the steering wheel angle used to control the vehicle to maintain its lane.

[0052] Specifically, after the lane keeping system calculates the vehicle's steering curvature, it inputs the vehicle's steering curvature into the vehicle dynamics model to calculate the target steering wheel angle corresponding to the vehicle's steering curvature based on parameters such as curvature, vehicle turning radius, and vehicle length.

[0053] Among them, the vehicle dynamics model can be a dynamic model established to calculate the steering wheel angle corresponding to the curvature.

[0054] S140. Control the vehicle to maintain lane position based on the target steering wheel angle.

[0055] In this embodiment of the disclosure, after the lane keeping device calculates the target steering wheel angle, it can control the vehicle to maintain the lane based on the target steering wheel angle.

[0056] In some embodiments of this disclosure, the lane keeping device can directly control the vehicle to keep in the lane using the steering wheel angle.

[0057] Specifically, the lane keeping device can calculate the target steering force corresponding to the target steering angle based on the mapping relationship between the steering wheel angle and the steering force, and control the vehicle's steering wheel rotation according to the target steering force to keep the vehicle in the lane.

[0058] In other embodiments of this disclosure, the lane keeping device can calculate torque using the steering wheel angle and then control the vehicle to keep in the lane based on the torque.

[0059] Specifically, the lane keeping device can calculate the target torque corresponding to the target steering wheel angle based on the mapping relationship between steering wheel angle and torque, and calculate the target steering force corresponding to the target torque based on the correspondence between torque and steering force. Based on the target steering force, it controls the steering wheel rotation of the vehicle to keep the vehicle in the lane.

[0060] In this embodiment, the real-time position of the vehicle and its corresponding reference position can be obtained. Based on the positional deviation between the real-time position and the reference position, the vehicle steering curvature corresponding to the real-time position is calculated. Then, the target steering wheel angle corresponding to the curvature is calculated, and the vehicle is controlled to maintain lane position based on the target steering wheel angle. Since the positional deviation between the real-time position and the reference position can include both lateral and longitudinal positional deviations, the vehicle steering curvature can be accurately calculated based on the distance between the real-time position and the reference position in the perpendicular direction of the vehicle's travel direction and the distance in the vehicle's travel direction. The target steering wheel angle can then be accurately calculated based on the vehicle steering curvature, improving the accuracy of the target steering wheel angle calculation. This allows the lane-keeping system to precisely control the vehicle to remain in a designated lane based on the target steering wheel angle, improving the comfort and reliability of lane-keeping and thus meeting the requirements for comfortable and reliable lane-keeping.

[0061] In another embodiment of this disclosure, the lane keeping device can accurately determine real-time driving data based on map information obtained by the navigation system, positioning information collected by the positioning system, and environmental images collected by vehicle sensors.

[0062] Specifically, during vehicle operation, the navigation system can acquire map information in real time, the positioning system can collect positioning information in real time, vehicle sensors can collect environmental images in real time, and the lane keeping device can acquire and process the map information, environmental images, and positioning information to obtain real-time driving data.

[0063] Optionally, in this embodiment of the disclosure, S110 may specifically include:

[0064] S1102. Obtain the real-time location of the vehicle.

[0065] S1104. Find the reference position corresponding to the real-time position among the preset navigation trajectory points. The navigation trajectory points are determined based on the environmental images collected by the vehicle, the vehicle's starting position, the vehicle's ending position, and map information.

[0066] Among them, the environmental image can be image information of the surrounding environment of the vehicle's location, which can be acquired by an image acquisition device.

[0067] Optionally, the environmental image may include lane line information, traffic light positions, obstacle positions, obstacle movement speeds, and speed limit information.

[0068] Optionally, the image acquisition device may include a camera, an image sensor, and a depth camera, etc.

[0069] In some embodiments, the vehicle's starting position may be the initial navigation position at the moment the user initiates route planning.

[0070] For example, when determining the preset navigation trajectory points, the vehicle keeping device can obtain the initial navigation position set by the user at the moment of starting path planning, and use it as the starting position of the vehicle.

[0071] In other embodiments, the vehicle's starting position may be the vehicle's actual position at the previous moment when the real-time position was collected.

[0072] For example, when determining the preset navigation trajectory points, the vehicle keeping device can obtain the real-time navigation position of the vehicle after starting path planning, and use the navigation position of the previous moment as the initial navigation position.

[0073] The vehicle's destination can be a pre-determined navigation destination.

[0074] Among them, map information can be the map information obtained for planning navigation trajectory points.

[0075] In this embodiment of the disclosure, in order to accurately obtain navigation trajectory points, before S1102, the lane keeping method may further include:

[0076] S1. Determine the local map information of the vehicle based on the vehicle's starting position, ending position, and global map information.

[0077] The global map information can be global high-definition map information. Specifically, global high-definition map information can be a type of global map information that includes a global high-resolution map.

[0078] Optionally, the global high-precision map can be pre-stored in the storage module, or it can be cached in real time, or it can be obtained in real time through the navigation system; there are no restrictions here.

[0079] Specifically, after the lane keeping device obtains the vehicle's starting position and ending position, it can determine the area where the vehicle is located in real time based on the positioning information. It can then filter out the global high-precision map information of the area where the vehicle is located in real time and the high-precision map information of the ending position from the pre-stored global map information as local map information.

[0080] Optionally, the map information of the area where the real-time location is located can be either the map information of the real-time location itself or a high-precision map information of a preset distance range centered on the real-time location.

[0081] The preset distance can be the maximum distance used to obtain local map information.

[0082] S2. Determine navigation trajectory points based on environmental images and local map information.

[0083] In this embodiment of the present disclosure, the lane keeping device can plan a driving path within the area where the real-time location is located based on information such as lane line information, traffic light positions, obstacle positions, obstacle movement speed, speed limit information, and local map information in the environmental image. Then, it can extract preset trajectory points from the driving path according to a predetermined driving distance as navigation trajectory points.

[0084] Optionally, obstacles may include vehicles, pedestrians, traffic lights, etc. around the vehicle, without limitation.

[0085] Therefore, in this embodiment of the present disclosure, a preset navigation trajectory point can be determined based on the environmental images collected by the vehicle, the vehicle's starting position, the vehicle's ending position, and global map information. Based on the preset navigation trajectory point and the real-time position, a reference position can be accurately determined. Thus, real-time driving data can be accurately determined based on the collected images.

[0086] In other embodiments of this disclosure, the lane keeping device can accurately calculate the vehicle steering curvature based on lateral and longitudinal position deviations.

[0087] In this embodiment of the disclosure, after acquiring the real-time position and the reference position, the lane keeping device can subtract the lateral position of the real-time position from the lateral position of the reference position to obtain the lateral position deviation, and at the same time, subtract the longitudinal position of the real-time position from the longitudinal position of the reference position to obtain the longitudinal position deviation.

[0088] Optionally, in this embodiment of the disclosure, S120 may specifically include:

[0089] S1202. Calculate the ratio of the square of the lateral position deviation to the square of the longitudinal position deviation.

[0090] Specifically, after the lane keeping device calculates the lateral and longitudinal position deviations, it can calculate the square of the longitudinal position deviation and divide the lateral position deviation by the square of the longitudinal position deviation to obtain the ratio of the lateral position deviation to the square of the longitudinal position deviation.

[0091] S1204. Multiply the ratio by the preset value to obtain the vehicle steering curvature.

[0092] The preset value can be a pre-set value used to calculate the vehicle's steering curvature. Furthermore, the preset value is 2 when the angle between the straight line formed by connecting the real-time position and the reference position and the vehicle's driving direction is less than the preset angle.

[0093] In this embodiment of the disclosure, after the lane keeping device obtains the real-time position and the reference position, it calculates the lateral and longitudinal coordinate deviations between the real-time position and the reference position by combining the Ackerman steering model. Based on the lateral coordinate deviation, it calculates the lateral distance between the real-time position and the reference position, and based on the longitudinal coordinate deviation, it calculates the longitudinal distance between the real-time position and the reference position. Then, it calculates the ratio of the square of the lateral distance to the square of the longitudinal distance, and multiplies the ratio by a preset value to obtain the vehicle steering curvature.

[0094] Optionally, the formula for calculating the vehicle's steering curvature can be:

[0095] curvature = 2 * offset / distance 2

[0096] Where curvature is the curvature, offset is the vertical distance, distance is the horizontal distance, and 2 is the preset value.

[0097] In this embodiment of the disclosure, in order to accurately calculate the ratio of the square of the lateral deviation to the square of the longitudinal deviation, the lane keeping may further include the following steps before S1202:

[0098] S1200 determines the first included angle based on the real-time position, the reference position, and the vehicle's steering center.

[0099] S1201. Calculate the second angle based on the first included angle, turning radius, lateral distance, and longitudinal distance.

[0100] Accordingly, S1202 can specifically include:

[0101] When the second included angle is less than the preset angle, calculate the ratio of the square of the lateral position deviation to the square of the longitudinal position deviation.

[0102] S1200 may include: connecting the steering center to the real-time position to obtain a first steering radius, connecting the steering center to the reference position to obtain a second steering radius, and using the angle between the first steering radius and the second steering radius as the first angle.

[0103] S1201 may include: connecting the real-time position to the reference position; calculating a third angle between the connecting line and the first turning radius based on a first included angle; calculating a fourth angle between the connecting line and the second turning radius; and calculating a second included angle based on the fourth included angle, wherein the third included angle and the fourth included angle are equal. The second included angle is the same as the angle between the straight line formed by connecting the real-time position and the reference position and the vehicle's direction of travel.

[0104] The preset angle can be the maximum angle used to calculate curvature. Alternatively, the preset angle can be a very small angle such as 1°, 2°, 3°, or 4°.

[0105] Figure 2 A schematic diagram illustrating the principle of calculating vehicle steering curvature provided in an embodiment of this disclosure is shown.

[0106] like Figure 2 As shown, the vehicle's real-time position is C1, and the reference position is C2. Both the real-time position C1 and the reference position C2 can be the vehicle's midpoint. The lane-keeping device can use the Ackerman steering model to group the steering centers of the inner and outer wheels of the vehicle at the real-time position C1 and the reference position C2 into a single center, i.e., determine the vehicle's steering center O. Based on the real-time position C1, the reference position C2, and the steering center O, the real-time position C1 is connected to the steering center O to obtain the first steering radius R1. The reference position C2 is connected to the steering center O to obtain the second steering radius R2. The angle between the first steering radius R1 and the second steering radius R2 is taken as the first included angle 2θ. The third included angle between the line connecting the real-time position C1 and the reference position C2 and the first steering radius is calculated based on the first included angle. The fourth included angle between the line connecting the real-time position C1 and the reference position C2 and the second steering radius is calculated. The second included angle θ is calculated based on the fourth included angle. When the second included angle θ is approximately 0, the ratio of the square of the lateral distance to the square of the longitudinal distance is calculated.

[0107] Therefore, based on Figure 2 We know that sin(2θ) = distance / R, tanθ = offset / distance. Since the second included angle θ≈0, sinθ≈θ. Therefore, the formula for calculating the vehicle steering curvature can be:

[0108] curvature=1 / R=sin2θ / distance≈2*offset / distance 2 .

[0109] Therefore, in the disclosed embodiment, the lateral and longitudinal distances between the real-time position and the reference position can be calculated based on the position deviation, and the ratio of the square of the lateral distance to the longitudinal distance can be calculated. Then, the ratio is multiplied by a preset value to accurately calculate the vehicle steering curvature.

[0110] In some embodiments of this disclosure, in order to accurately control the vehicle for lane keeping, after the lane keeping device calculates the target steering wheel angle, it can calculate the target torque corresponding to the target steering wheel angle and control the vehicle for lane keeping based on the target torque.

[0111] Optionally, real-time driving data may also include real-time steering wheel angle.

[0112] The real-time steering wheel angle can be the steering wheel angle detected in real time by a steering wheel detection device.

[0113] In this embodiment of the disclosure, in order to accurately calculate the target torque of the vehicle, the lane keeping device can calculate the target torque based on the target steering wheel angle and the real-time steering wheel angle, and control the vehicle to maintain the lane based on the target torque.

[0114] Specifically, S140 may include:

[0115] S1401. Calculate the steering wheel angle error between the target steering wheel angle and the real-time steering wheel angle.

[0116] S1402. Perform proportional-integral-derivative (PID) calculations on the steering angle error to obtain the target torque of the vehicle.

[0117] S1403, Lane keeping is controlled by vehicle based on target torque.

[0118] Among them, the proportional-integral-differential (PID) calculation can perform proportional, integral, and differential calculations on the steering angle error to obtain the target torque of the vehicle.

[0119] Specifically, the lane keeping device can calculate the angle error between the target steering wheel angle and the real-time steering wheel angle, input the angle error to the PID controller, use the PID controller to perform PID calculation on the angle error to obtain the target torque of the vehicle, generate steering control information based on the target torque, and send the steering control information to the Electric Power Steering (EPS) system through the controller area network, so as to use the EPS to control the vehicle steering and perform lane keeping control of the vehicle.

[0120] Optionally, the formula for PID calculation can be:

[0121] Torque=KP*(Error(k)-Error(k-1))+KI*Error(k)+KD*(E(k)-2Error(k-1)+Error(k-2))

[0122] Where Torque is the target torque, KP is the proportional coefficient of the PID controller, KI is the integral coefficient of the PID controller, KD is the derivative coefficient of the PID controller, k is the period, Error(k) is the angular error in period k, Error(k-1) is the angular error in period k-1, and Error(k-2) is the angular error in period k-2. KP, KI, and KD can be preset coefficients as needed.

[0123] Therefore, in this embodiment of the disclosure, the target torque can be accurately calculated based on the real-time steering wheel angle in the real-time driving data, so as to control the vehicle for lane keeping.

[0124] In another embodiment of this disclosure, in order to improve the accuracy of lane keeping, the target steering wheel angle can be corrected based on the real-time heading angle before calculating the target steering wheel angle corresponding to the vehicle steering curvature, so as to control the vehicle to keep in the lane based on the corrected target steering wheel angle.

[0125] Figure 3 A schematic flowchart of another lane keeping method provided in an embodiment of this disclosure is shown.

[0126] like Figure 3 As shown, the lane keeping method may include the following steps.

[0127] S310: Obtain real-time driving data of the vehicle.

[0128] S320. Based on the positional deviation between the real-time position and the reference position, calculate the vehicle steering curvature corresponding to the real-time position.

[0129] S330, Calculate the target steering wheel angle corresponding to the vehicle's steering curvature.

[0130] S310~S330 are similar to S110~S130, and will not be described in detail here.

[0131] S340: Correct the target steering wheel angle using the real-time heading angle.

[0132] In this embodiment of the disclosure, after the lane keeping device calculates the target steering wheel angle and obtains the real-time heading angle, it can use the real-time heading angle to correct the target steering wheel angle to obtain the corrected target steering wheel angle.

[0133] In this embodiment of the disclosure, the real-time heading angle can be obtained by a heading angle acquisition device.

[0134] In this embodiment of the disclosure, in order to improve the accuracy of lane keeping, S340 may specifically include:

[0135] The target steering wheel angle is corrected using the real-time heading angle.

[0136] Correspondingly, correcting the target steering angle using the real-time heading angle can include:

[0137] The first steering wheel angle correction value is calculated using the real-time heading angle and real-time position.

[0138] The target steering wheel angle is corrected based on the first steering wheel angle correction value to obtain the corrected target steering wheel angle.

[0139] The calculation of steering wheel angle correction using real-time heading angle and real-time position can specifically include the following steps:

[0140] The position deviation between the real-time position and the reference position is calculated using PID to obtain the reference heading angle corresponding to the reference position;

[0141] The PID calculation is performed on the heading angle error between the reference heading angle and the real-time heading angle to obtain the first steering wheel angle correction value;

[0142] The target steering wheel angle is corrected using the first steering wheel angle correction value.

[0143] The positional deviation between the real-time position and the reference position can include both the lateral and longitudinal positional deviations.

[0144] The reference heading angle can be a heading angle reference value used to calculate the first steering wheel angle correction value.

[0145] The first steering wheel angle correction value can be the output angle that corrects the target steering wheel angle.

[0146] Specifically, after acquiring the real-time heading angle and real-time position, the lane-keeping device calculates the position deviation between the real-time position and the reference position. The position deviation is input to the PID controller, which performs PID calculation on the position deviation to obtain the reference heading angle corresponding to the reference position. Then, the heading angle error between the reference heading angle and the real-time heading angle is calculated, and the heading angle deviation is input to the PID controller. The PID controller performs PID calculation on the heading angle error to obtain the first steering wheel angle correction value. The first steering wheel angle correction value is added to the target steering wheel angle to correct the target steering wheel angle using the first steering wheel angle correction value.

[0147] Optionally, the PID controller can be a serial controller.

[0148] Figure 4 A schematic diagram illustrating the principle of a lane keeping method provided in an embodiment of this disclosure is shown.

[0149] like Figure 4 As shown, the PID controller can be a serial controller, which may include an outer-loop PID controller and an inner-loop PID controller. First, the lane-keeping device acquires the real-time position sent by the vehicle's positioning device and obtains a reference position. It calculates the position error between the real-time position and the reference position and inputs the position error to the outer-loop PID controller to obtain the reference heading angle corresponding to the reference position. Then, it acquires the real-time heading angle and calculates the heading angle error between the real-time heading angle and the reference heading angle. This heading angle error is input to the inner-loop PID controller to obtain a first steering wheel angle correction value. Next, the first steering wheel angle correction value is added to the target steering wheel angle to correct the target steering wheel angle using the first steering wheel angle correction value.

[0150] S350 controls the vehicle to maintain lane position based on the corrected target steering wheel angle.

[0151] In this embodiment of the disclosure, after the lane keeping device determines the corrected target steering wheel angle, it can calculate the target torque based on the corrected target steering wheel angle, and control the vehicle to maintain the lane based on the target torque.

[0152] In this embodiment of the disclosure, in order to improve the accuracy of lane keeping, the lane keeping device can use the corrected target steering wheel angle and the real-time steering wheel angle to calculate the target torque, and control the vehicle to keep in the lane based on the target torque.

[0153] Specifically, the S350 is similar to the S140, so we will not go into details here.

[0154] Therefore, in this embodiment of the present disclosure, before calculating the target steering wheel angle corresponding to the vehicle steering curvature, a PID calculation can be performed on the position deviation between the real-time position and the reference position to obtain the reference heading angle corresponding to the reference position. Then, a PID calculation is performed on the heading angle error between the reference heading angle and the real-time heading angle to obtain the first steering wheel angle correction value. This method can calculate the first steering wheel angle correction value based on the position deviation and the heading angle error, thereby improving the calculation accuracy of the first steering wheel angle correction value. Based on the first steering wheel angle correction value, the target steering wheel angle can be accurately corrected, and the vehicle can be controlled to maintain lanes based on the corrected target steering wheel angle. Therefore, the accuracy of lane keeping is improved.

[0155] In another embodiment of this disclosure, in order to further improve the accuracy of lane keeping, before calculating the target steering wheel angle corresponding to the vehicle steering curvature, the target steering wheel angle can be corrected based on the position of the lane center point to obtain the corrected target steering wheel angle, so as to control the vehicle to keep in the lane based on the corrected target steering wheel angle.

[0156] In some embodiments of this disclosure, the lane keeping device can correct the target steering wheel angle calculated using the vehicle steering curvature based on the position of the lane center point.

[0157] Figure 5 A schematic flowchart of another lane keeping method provided in an embodiment of this disclosure is shown.

[0158] like Figure 5 As shown, the lane keeping method may include the following steps.

[0159] S510: Obtain real-time driving data of the vehicle.

[0160] In this embodiment of the disclosure, the real-time driving data includes the real-time location, the reference location corresponding to the real-time location, the real-time heading angle corresponding to the real-time location, and the location of the lane center point.

[0161] The center point of the lane can be the center point of the lane line on which the vehicle is traveling.

[0162] Optionally, the position of the lane center point can be obtained by an image acquisition device.

[0163] S520. Based on the positional deviation between the real-time position and the reference position, calculate the vehicle steering curvature corresponding to the real-time position.

[0164] S530, Calculate the target steering wheel angle corresponding to the vehicle's steering curvature.

[0165] S510~S530 are similar to S110~S130, and will not be described in detail here.

[0166] S540: Correct the target steering wheel angle using the position of the lane center point.

[0167] The target steering wheel angle can be the steering wheel angle calculated using the vehicle's steering curvature.

[0168] In this embodiment of the disclosure, in order to improve the accuracy of lane keeping, the lane keeping device can calculate the lateral position compensation value corresponding to the delay time, calculate the compensated lateral position of the lane center point based on the lateral position compensation value and the lane center point position, and calculate the second steering wheel angle correction value based on the compensated lateral position of the lane center point position.

[0169] Optionally, in this embodiment, S540 may specifically include:

[0170] S5402. Calculate the lateral position compensation value based on the real-time heading angle, the vehicle's lateral speed, and the delay duration.

[0171] S5404. Add the lateral position compensation value to the lateral position of the lane center point to obtain the compensated lateral position of the lane center point.

[0172] S5406. Integrate the compensated lateral position to obtain the second steering wheel angle correction value.

[0173] S5408. Add the second steering wheel angle correction value and the corrected target steering wheel angle.

[0174] The lateral velocity of a vehicle can be the component of its speed in the direction perpendicular to the lane lines.

[0175] The delay duration can be the delay duration of the vehicle control system.

[0176] The lateral position of the lane center point can be the x-coordinate of the lane center point.

[0177] The lateral position compensation value can be the lateral position deviation caused by the delay time.

[0178] The lateral position of the lane center point can be the component of the lane center point position in the direction perpendicular to the lane line.

[0179] Optionally, the formula for calculating the second steering wheel angle correction value can be:

[0180] compensate_angle=∫(local refy + / -speed*local_theta*time_com)dt

[0181] Where, compensate_angle is the second steering wheel angle correction value, local refy _x is the lateral position of the lane center point, _speed is the lateral speed of the vehicle, _time_com is the delay time, and _local_theta is the real-time heading angle.

[0182] S550 controls the vehicle to maintain lane position based on the corrected target steering wheel angle.

[0183] S550 is similar to S140, so it will not be described in detail here.

[0184] Therefore, in this embodiment of the present disclosure, before calculating the target steering wheel angle corresponding to the vehicle steering curvature, the corrected target steering wheel angle can be corrected based on the position of the lane center point to obtain the corrected target steering wheel angle, so as to control the vehicle to maintain the lane based on the corrected target steering wheel angle, thereby further improving the accuracy of lane keeping.

[0185] In other embodiments of this disclosure, the lane keeping device may further correct the target steering wheel angle, which has been corrected using the real-time heading angle, based on the position of the lane center point.

[0186] Figure 6 A schematic flowchart of another lane keeping method provided in an embodiment of this disclosure is shown.

[0187] like Figure 6 As shown, the lane keeping method may include the following steps.

[0188] S610: Obtain real-time driving data of the vehicle.

[0189] In this embodiment of the disclosure, the real-time driving data includes the real-time location, the reference location corresponding to the real-time location, and the location of the lane center point.

[0190] S620. Based on the positional deviation between the real-time position and the reference position, calculate the vehicle steering curvature corresponding to the real-time position.

[0191] S630, Calculate the target steering wheel angle corresponding to the vehicle's steering curvature.

[0192] S610~S630 are similar to S110~S130, and will not be described in detail here.

[0193] S640: Corrects the target steering wheel angle using the real-time heading angle.

[0194] The target steering wheel angle can be the steering wheel angle calculated using the vehicle's steering curvature.

[0195] S640 is similar to S340, so it will not be described in detail here.

[0196] S650: The target steering wheel angle is corrected again using the position of the lane center point.

[0197] The S650 is similar to the S540, so it will not be described in detail here.

[0198] S660 controls the vehicle to maintain lane position based on the corrected target steering wheel angle.

[0199] S660 is similar to S140, so it will not be described in detail here.

[0200] Therefore, in this embodiment of the present disclosure, before calculating the target steering wheel angle corresponding to the vehicle steering curvature, the target steering wheel angle, which has been corrected using the real-time heading angle, can be corrected again based on the position of the lane center point. The vehicle can then be controlled to maintain the lane based on the corrected target steering wheel angle, thereby improving the accuracy of lane keeping.

[0201] Figure 7 A schematic diagram of the structure of a lane keeping device provided in an embodiment of this disclosure is shown.

[0202] In some embodiments of this disclosure, Figure 7 The lane keeping device shown can be executed by a lane keeping unit within a lane keeping system. The lane keeping unit can be a processor or a controller.

[0203] like Figure 7 As shown, the lane keeping device 700 may include: a data acquisition module 710, a calculation module, and a lane keeping module 740. The calculation module may include a vehicle steering curvature calculation module 720 and a target steering wheel angle calculation module 730. It can be understood that the calculation modules may be performed by the same module or by different modules.

[0204] The data acquisition module 710 can be configured to acquire real-time driving data of the vehicle, including the real-time location and the reference location corresponding to the real-time location;

[0205] The vehicle steering curvature calculation module 720 can be configured to calculate the vehicle steering curvature corresponding to the real-time position based on the positional deviation between the real-time position and the reference position.

[0206] The target steering wheel angle calculation module 730 can be configured to calculate the target steering wheel angle corresponding to the vehicle's steering curvature.

[0207] The lane keeping module 740 can be configured to control the vehicle to keep in the lane based on the target steering wheel angle.

[0208] In this embodiment, the real-time position of the vehicle and its corresponding reference position can be obtained. Based on the positional deviation between the real-time position and the reference position, the vehicle steering curvature corresponding to the real-time position is calculated. Then, the target steering wheel angle corresponding to the curvature is calculated, and the vehicle is controlled to maintain lane position based on the target steering wheel angle. Since the positional deviation between the real-time position and the reference position can include both lateral and longitudinal positional deviations, the vehicle steering curvature can be accurately calculated based on the distance between the real-time position and the reference position in the perpendicular direction of the vehicle's travel direction and the distance in the vehicle's travel direction. The target steering wheel angle can then be accurately calculated based on the vehicle steering curvature, improving the accuracy of the target steering wheel angle calculation. This allows the lane-keeping system to precisely control the vehicle to remain in a designated lane based on the target steering wheel angle, improving the comfort and reliability of lane-keeping and thus meeting the requirements for comfortable and reliable lane-keeping.

[0209] In some embodiments of this disclosure, the positional deviation includes lateral positional deviation and longitudinal positional deviation; wherein, the vehicle steering curvature calculation module 720 may include: a distance calculation unit, a ratio calculation unit, and a vehicle steering curvature calculation unit;

[0210] This ratio calculation unit can be configured to calculate the ratio of the square of the lateral deviation to the square of the longitudinal deviation;

[0211] The vehicle steering curvature calculation unit can be configured to multiply the ratio by a preset value to obtain the vehicle steering curvature.

[0212] In some embodiments of this disclosure, real-time driving data also includes real-time steering wheel angle;

[0213] The lane keeping module 740 may include: a steering angle error calculation unit, a target torque calculation unit, and a lane keeping unit.

[0214] This steering angle error calculation unit can be configured to calculate the steering angle error between the target steering wheel angle and the real-time steering wheel angle;

[0215] The target torque calculation unit can be configured to perform proportional-integral-derivative (PID) calculations on the steering angle error to obtain the vehicle's target torque.

[0216] The target torque calculation unit can be configured to control the vehicle for lane keeping based on the target torque.

[0217] In some embodiments of this disclosure, the real-time driving data also includes the real-time heading angle corresponding to the real-time position;

[0218] The device may further include: a first correction module;

[0219] The lane keeping module 740 can be configured to control the vehicle to keep in the lane based on the corrected target steering wheel angle.

[0220] In some embodiments of this disclosure, the first correction module may include: a reference heading angle calculation unit, a first correction value calculation unit, and a first correction unit.

[0221] The reference heading angle calculation unit can be configured to perform PID calculation on the position deviation between the real-time position and the reference position to obtain the reference heading angle corresponding to the reference position.

[0222] The first correction value calculation unit can be configured to perform PID calculation on the heading angle error between the reference heading angle and the real-time heading angle to obtain the first steering wheel angle correction value;

[0223] The first correction unit can be configured to correct the target steering wheel angle using a first steering wheel angle correction value.

[0224] In some embodiments of this disclosure, the real-time driving data also includes the position of the lane center point;

[0225] The device may further include: a second correction module;

[0226] The second correction module can be configured to correct the target steering wheel angle using the position of the lane center point.

[0227] The lane keeping module 740 can be configured to control the vehicle to keep in the lane based on the corrected target steering wheel angle.

[0228] In some embodiments of this disclosure, the second correction module may include: a compensation value calculation unit, a lateral position summation unit, a second correction value calculation unit, and a second correction unit.

[0229] The compensation calculation unit can be configured to calculate the lateral position compensation value based on the real-time heading angle, the vehicle's lateral speed, and the delay duration.

[0230] The lateral position summing unit can be configured to add the lateral position compensation value to the lateral position of the lane center point to obtain the compensated lateral position of the lane center point.

[0231] The second correction value calculation unit can be configured to perform integral calculation on the compensated lateral position to obtain the second steering wheel angle correction value;

[0232] The second correction unit can be configured to correct the target steering wheel angle using the second steering wheel angle correction value.

[0233] In some embodiments of this disclosure, the data acquisition module 710 may include: a real-time location acquisition unit and a reference location determination unit;

[0234] The real-time location acquisition unit can be configured to acquire the real-time location of the vehicle.

[0235] The reference position determination unit can be configured to find the reference position corresponding to the real-time position among preset navigation trajectory points. The navigation trajectory points are determined based on the environmental images collected by the vehicle, the vehicle's starting position, the vehicle's ending position, and global map information.

[0236] In some embodiments of this disclosure, the data acquisition module 710 may further include: a local map information determination unit and a navigation trajectory point determination unit.

[0237] The local map information determination unit can be configured to determine the local map information of a vehicle based on the vehicle's starting position, the vehicle's ending position, and global map information.

[0238] The navigation trajectory point determination unit can be configured to determine navigation trajectory points based on environmental images and local map information.

[0239] It should be noted that, Figure 7 The lane keeping device 700 shown can perform Figure 1 and Figure 6 The various steps in the method embodiment shown are implemented. Figure 1 and Figure 6 The processes and effects in the method embodiments shown are not described in detail here.

[0240] Figure 8 A schematic diagram of the hardware circuit structure of a lane keeping device provided in an embodiment of this disclosure is shown.

[0241] like Figure 8 As shown, the lane keeping device 800 may include a controller 801 and a memory 802 storing computer program instructions.

[0242] Specifically, the controller 801 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0243] Memory 802 may include a mass storage device for information or instructions. For example, and not limitingly, memory 802 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 802 may include removable or non-removable (or fixed) media. Where appropriate, memory 802 may be internal or external to the integrated gateway device. In a particular embodiment, memory 802 is a non-volatile solid-state memory. In a particular embodiment, memory 802 includes read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (Electrically Programmable ROM, EPROM), an electrically erasable programmable PROM (EEPROM), an electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0244] The controller 801 performs the steps of the lane keeping method provided in the embodiments of this disclosure by reading and executing computer program instructions stored in the memory 802.

[0245] In one example, the lane-keeping device 800 may also include a transceiver 803 and a bus 804. Wherein, as... Figure 8 As shown, the controller 801, memory 802 and transceiver 803 are connected via bus 804 and communicate with each other.

[0246] Bus 804 includes hardware, software, or both. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 804 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0247] The following are embodiments of a computer-readable storage medium provided in this disclosure. This computer-readable storage medium belongs to the same inventive concept as the lane keeping methods in the above embodiments. For details not described in detail in the embodiments of the computer-readable storage medium, please refer to the embodiments of the lane keeping methods described above.

[0248] This embodiment provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform a lane-keeping method, the method comprising:

[0249] Acquire real-time driving data of the vehicle, including real-time location and the corresponding reference location;

[0250] Calculate the vehicle steering curvature corresponding to the real-time position based on the positional deviation between the real-time position and the reference position.

[0251] Calculate the target steering wheel angle corresponding to the vehicle's steering curvature;

[0252] Control the vehicle to maintain lane position based on the target steering wheel angle.

[0253] Of course, the computer-executable instructions provided in the embodiments of this disclosure are not limited to the above-described method operations, but can also perform related operations in the lane keeping method provided in any embodiment of this disclosure.

[0254] Based on the above description of the implementation methods, those skilled in the art can clearly understand that this disclosure can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer cloud platform (which may be a personal computer, a server, or a network cloud platform, etc.) to execute the lane-keeping methods provided in the various embodiments of this disclosure.

[0255] Note that the above description is merely a preferred embodiment and the technical principles employed in this disclosure. Those skilled in the art will understand that this disclosure is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this disclosure. Therefore, although this disclosure has been described in detail through the above embodiments, it is not limited to the above embodiments. Many other equivalent embodiments may be included without departing from the concept of this disclosure, and the scope of this disclosure is determined by the scope of the appended claims.

Claims

1. A lane keeping method characterized by, The method comprises: acquiring real-time driving data of a vehicle, the real-time driving data comprising a real-time position and a reference position corresponding to the real-time position, and further comprising a lane center point position; calculating a vehicle steering curvature corresponding to the real-time position based on a position deviation between the real-time position and the reference position; calculating a target steering wheel angle corresponding to the vehicle steering curvature; calculating a lateral position compensation value based on a real-time heading angle corresponding to the real-time position, a lateral speed of the vehicle, and a delay time length; adding the lateral position compensation value to a lateral position of the lane center point position to obtain a compensated lateral position of the lane center point position; integrally calculating the compensated lateral position to obtain a second steering wheel angle correction value; correcting the target steering wheel angle by using the second steering wheel angle correction value; controlling the vehicle to keep the lane based on the corrected target steering wheel angle.

2. The method of claim 1, wherein, The position deviation comprises a lateral position deviation and a longitudinal position deviation; wherein the calculation of the vehicle steering curvature corresponding to the real-time position based on the position deviation between the real-time position and the reference position comprises: calculating a ratio of the square of the lateral position deviation to the square of the longitudinal position deviation; multiplying the ratio by a preset value to obtain the vehicle steering curvature.

3. The method of claim 1, wherein, The real-time driving data further comprises a real-time steering wheel angle, and the method further comprises: calculating an angle error between the target steering wheel angle and the real-time steering wheel angle; performing proportional-integral-derivative (PID) calculation on the angle error to obtain a target torque of the vehicle; controlling the vehicle to keep the lane based on the target torque.

4. The method of claim 1, wherein, The real-time driving data further comprises a real-time heading angle corresponding to the real-time position; wherein, after the calculation of the target steering wheel angle corresponding to the vehicle steering curvature, the method further comprises: correcting the target steering wheel angle by using the real-time heading angle.

5. The method of claim 4, wherein, The correction of the target steering wheel angle by using the real-time heading angle to obtain a corrected target steering wheel angle comprises: performing PID calculation on the position deviation between the real-time position and the reference position to obtain a reference heading angle corresponding to the reference position; performing PID calculation on a heading angle error between the reference heading angle and the real-time heading angle to obtain a first steering wheel angle correction value; correcting the target steering wheel angle by using the first steering wheel angle correction value.

6. The method of claim 1, wherein, The acquisition of the real-time driving data of the vehicle comprises: acquiring a real-time position of the vehicle; finding a reference position corresponding to the real-time position among preset navigation track points, the navigation track points being determined based on an environment image collected by the vehicle, a vehicle starting position, a vehicle ending position, and global map information.

7. The method of claim 6, wherein, Before the acquisition of the real-time position of the vehicle, the method further comprises: determining local map information of the vehicle based on the vehicle starting position, the vehicle ending position, and the global map information; determining the navigation track points based on the environment image and the local map information.

8. A lane keeping device characterized by comprising: The method comprises: The data acquisition module is configured to acquire real-time driving data of the vehicle, the real-time driving data comprising a real-time position and a reference position corresponding to the real-time position, and the real-time driving data further comprising a lane center point position; The calculation module is configured to calculate a vehicle steering curvature corresponding to the real-time position based on a position deviation between the real-time position and the reference position, and to calculate a target steering wheel angle corresponding to the vehicle steering curvature; The second correction module comprises a compensation value calculation unit, a lateral position summation unit, a second correction value calculation unit, and a second correction unit; The compensation value calculation unit is configured to calculate a lateral position compensation value based on a real-time heading angle corresponding to the real-time position, a lateral velocity of the vehicle, and a delay time length; The lateral position summation unit is configured to add the lateral position compensation value to a lateral position of the lane center point position to obtain a compensated lateral position of the lane center point position; The second correction value calculation unit is configured to perform integral calculation on the compensated lateral position to obtain a second steering wheel angle correction value; The second correction unit is configured to correct the target steering wheel angle by using the second steering wheel angle correction value; The lane keeping module is configured to control the vehicle to perform lane keeping based on the corrected target steering wheel angle.

9. A lane keeping apparatus characterized by comprising: The lane keeping method comprises the following steps: acquiring real-time driving data of the vehicle, the real-time driving data comprising a real-time position and a reference position corresponding to the real-time position, and the real-time driving data further comprising a lane center point position; calculating a vehicle steering curvature corresponding to the real-time position based on a position deviation between the real-time position and the reference position, and calculating a target steering wheel angle corresponding to the vehicle steering curvature; performing integral calculation on the compensated lateral position to obtain a second steering wheel angle correction value; 10. A computer-readable storage medium having stored thereon a computer program, characterized in that, correcting the target steering wheel angle by using the second steering wheel angle correction value; controlling the vehicle to perform lane keeping based on the corrected target steering wheel angle. The lane keeping method comprises the following steps: acquiring real-time driving data of the vehicle, the real-time driving data comprising a real-time position and a reference position corresponding to the real-time position, and the real-time driving data further comprising a lane center point position; calculating a vehicle steering curvature corresponding to the real-time position based on a position deviation between the real-time position and the reference position, and calculating a target steering wheel angle corresponding to the vehicle steering curvature; performing integral calculation on the compensated lateral position to obtain a second steering wheel angle correction value; correcting the target steering wheel angle by using the second steering wheel angle correction value; controlling the vehicle to perform lane keeping based on the corrected target steering wheel angle. The lane keeping method comprises the following steps: acquiring real-time driving data of the vehicle, the real-time driving data comprising a real-time position and a reference position corresponding to the real-time position, and the real-time driving data further comprising a lane center point position; calculating a vehicle steering curvature corresponding to the real-time position based on a position deviation between the real-time position and the reference position, and calculating a target steering wheel angle corresponding to the vehicle steering curvature; performing integral calculation on the compensated lateral position to obtain a second steering wheel angle correction value; correcting the target steering wheel angle by using the second steering wheel angle correction value; controlling the vehicle to perform lane keeping based on the corrected target steering wheel angle.

Images