Vehicle lane centering control method and device

Abstract

The embodiment of the present invention discloses a lane centering control method and device for a vehicle. The method includes: obtaining lane line data; and dynamically adjusting control parameters based on the lane line data, wherein the control parameters include: filter parameters of a Kalman filter for lane line data processing, and / or control parameters of a PID controller for trajectory tracking control. By dynamically adjusting the control parameters, the dynamic response capability of the lane centering control function is improved, thereby meeting the control requirements of more scenarios.

Description

Technical Field

[0001] The present invention relates to autonomous driving technology, and in particular to a lane centering control method and device for a vehicle. Background Art

[0002] Lane Centering Control (LCC) is a comfort-assisted driving function that helps the driver keep the car in the middle of the lane during driving. When the LCC function is turned on, if the car deviates from the center of the lane, the system will automatically apply steering force to bring the car back to the center of the lane to ensure the driving safety of the car.

[0003] In lane centering control, a front camera is usually used as the main perception device to capture real-time images of the road. These images are processed by algorithms to identify lane line data. These lane line data often contain noise and interference information, which can be filtered through filters to obtain more accurate lane line data. Then, path planning is performed based on the filtered lane line data to generate an ideal trajectory that can guide the vehicle to drive in the center. In order to achieve accurate tracking of this trajectory, local trajectory tracking control can be performed on the vehicle to control the vehicle to maintain driving in the center.

[0004] However, the current lane centering control solution performs well in high-speed scenarios where the road conditions are good, the lane lines themselves and the camera perception are good, and the vehicle control only requires a small or slow steering wheel to be stably controlled. However, for other scenarios (for example, entering a small radius curve at high speed), it is easy for the vehicle to deviate from the lane or go out of the lane. Therefore, the current lane centering control solution needs to be improved. Summary of the invention

[0005] A vehicle lane centering control method and device according to an embodiment of the present invention can improve the dynamic response capability of the lane centering control function to meet the control requirements of more scenarios.

[0006] A lane centering control method for a vehicle according to an embodiment of the present invention comprises: acquiring lane line data; and dynamically adjusting control parameters based on the lane line data, wherein the control parameters comprise: filtering parameters of a Kalman filter for lane line data processing, and / or control parameters of a PID controller for trajectory tracking control.

[0007] The dynamically adjusting control parameters based on the lane line data includes: identifying the scene based on the lane line data; and dynamically adjusting the control parameters based on the identified scene; wherein different scenes represent different degrees of lane line changes.

[0008] Wherein, identifying the scene based on the lane line data includes: based on the lane line data, comparing the changes of the lane lines of the vehicle within a predetermined time and distance to identify the scene.

[0009] Wherein, identifying the scene based on the lane line data includes: identifying the scene based on a first parameter, wherein the first parameter includes: an angle between the vehicle and the lane line, and / or a curvature of the lane line.

[0010] Among them, based on the first parameter, identifying the scene in which the vehicle is located includes: judging whether the current angle between the vehicle and the lane line has the same sign as the angle in the previous cycle; if the current angle has a different sign from the angle in the previous cycle, resetting the maximum angle, the first walking distance and the first walking time; if the current angle has the same sign as the angle in the previous cycle, judging the size relationship between the current angle and the first angle threshold; if the current angle is less than the first angle threshold, keeping the values ​​of the maximum angle, the first walking distance and the first walking time unchanged; if the current angle is greater than the first angle threshold, updating the values ​​of the maximum angle, the first walking distance and the first walking time; judging whether the maximum angle is greater than the second angle threshold, and whether the first walking distance and the first walking time are respectively within their respective preset ranges, wherein the second angle threshold is greater than the first angle threshold; if the maximum angle is less than the second angle threshold, the first walking distance is not within the preset distance range, or the first walking time is within the preset distance range, If the time is not within the preset time range, the scene is determined to be the first dynamic scene; if the maximum angle is greater than the second angle threshold, and the first walking distance and the first walking time are both within their respective preset ranges, the relationship between the current angle and the third angle threshold that is greater than the first angle threshold and whether the scene in the previous cycle is the first dynamic scene are determined; if the current angle is less than the third angle threshold or the scene in the previous cycle is not the first dynamic scene, then it is determined whether the current angle and the distance to the center line of the lane have the same sign; if the current angle and the distance to the center line of the lane have different signs, the scene is determined to be the first dynamic scene; if the current angle and the distance to the center line of the lane have the same sign, the scene is determined to be the second dynamic scene; if the current angle is greater than the third angle threshold and the scene in the previous cycle was the first dynamic scene, then the scene is determined to be the third dynamic scene; wherein, the first to third dynamic scenes respectively indicate that the changes in the lane lines intensify in turn.

[0011] Wherein, the identifying of the scene based on the first parameter includes: determining whether the sign of the current lane line curvature is the same as that of the lane line curvature in the previous cycle; if the signs are not the same, resetting the maximum lane line curvature, the second walking distance and the second walking time; if the signs are the same, determining whether the current lane line curvature is greater than the first curvature threshold; if the current lane line curvature is less than the first curvature threshold, keeping the values ​​of the maximum lane line curvature, the second walking distance and the second walking time unchanged; if the current lane line curvature is greater than the first curvature threshold, updating the values ​​of the maximum lane line curvature, the second walking distance and the second walking time; determining whether the maximum lane line curvature and the current lane line curvature are greater than the second curvature threshold, and whether the second walking distance and the second walking time are respectively within their respective preset ranges, wherein the second curvature threshold is greater than the first curvature threshold; when the maximum lane line curvature is less than the second curvature threshold, the current lane line curvature is less than the second curvature threshold, and the second walking distance is not within the preset distance range When the second walking distance is within the preset time range, or the second walking time is not within the preset time range, the scene is determined to be the first dynamic scene; when the maximum lane line curvature and the current lane line curvature are both greater than the second curvature threshold, and the second walking distance and the second walking time are both within their respective preset ranges, it is determined whether the current angle is greater than the third angle threshold and whether the scene in the previous cycle is the first dynamic scene; if the current angle is less than the third angle threshold or the scene in the previous cycle is not the first dynamic scene, it is determined whether the current angle and the distance from the center line of the lane have the same sign; if the current angle and the distance from the center line of the lane have different signs, it is determined that the scene is the first dynamic scene; if the current angle and the distance from the center line of the lane have the same sign, it is determined that the scene is the second dynamic scene; if the current angle is greater than the third angle threshold and the scene in the previous cycle was the first dynamic scene, it is determined that the scene is the third dynamic scene; wherein, the first to third dynamic scenes respectively indicate that the changes in the lane lines intensify in turn.

[0012] Among them, the dynamically adjusting the control parameters based on the identified scene includes: when the scene is a non-low-dynamic scene, setting a time delay value, and using the control parameters corresponding to the non-low-dynamic scene; when the scene is a low-dynamic scene, determining whether the time delay value is greater than 0; if not greater than 0, using the control parameters corresponding to the low-dynamic scene; if greater than 0, attenuating the time delay value, and using the control parameters corresponding to the previous non-low-dynamic scene.

[0013] A lane centering control device for a vehicle according to an embodiment of the present invention comprises: a lane line processing module for processing lane line data; a trajectory planning module for planning a driving trajectory based on the lane line data output by the lane line processing module; and a trajectory tracking module for controlling the vehicle based on the driving trajectory planned by the trajectory planning module; wherein the lane line processing module comprises: a Kalman filter for performing Kalman filtering on the lane line data; a scene recognition unit for identifying the current scene based on the lane line data; wherein the trajectory tracker comprises: a PID controller for performing trajectory tracking control; wherein the lane line processing module further comprises: a first control unit for adjusting the filtering parameters of the Kalman filter based on the scene, and / or the trajectory tracker further comprises: a second control unit for adjusting the control parameters of the PID controller based on the scene.

[0014] A computer device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method according to the embodiment of the present invention.

[0015] A computer-readable storage medium according to an embodiment of the present invention stores a computer program / instruction thereon, and when the computer program / instruction is executed by a processor, the steps of the method according to the embodiment of the present invention are implemented.

[0016] A computer program product according to an embodiment of the present invention includes a computer program / instruction, and when the computer program / instruction is executed by a processor, the steps of the method according to the embodiment of the present invention are implemented.

[0017] Beneficial effects of the embodiments of the present invention:

[0018] The lane centering control solution of this embodiment dynamically adjusts the filtering parameters of the Kalman filter and / or dynamically adjusts the control parameters of the PID controller based on real-time lane line data. Therefore, the dynamic adaptability of the centering control function can be enhanced. For example, the solution of this embodiment is not only suitable for high-speed scenarios that only require a small or slow steering wheel to achieve stable control, but also has adaptability to complex scenarios such as high-speed entry into small-radius curves, poor lane line perception, variable lanes on urban roads, and rapidly changing connecting curves. Therefore, the centering control solution of this embodiment can improve the dynamic response capability of the lane centering control function to meet the control requirements of more scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Other details and advantages of the present invention will become apparent from the detailed description provided below. It should be understood that the following drawings are merely illustrative and thus cannot be considered as limiting the present invention, and the following will be described in detail with reference to the drawings, wherein:

[0020] Figure 1 is a schematic structural diagram of an embodiment of a lane centering control device for a vehicle of the present invention;

[0021] Figure 2 is a flow chart of an embodiment of a vehicle lane centering control method of the present invention;

[0022] Figure 3 is a structural schematic diagram of another embodiment of a lane centering control device for a vehicle of the present invention;

[0023] Figures 4 to 6 is a schematic flow chart of an embodiment of a method for identifying a dynamic scene of the present invention;

[0024] Figure 7 is a flow chart of an embodiment of a method for adjusting filtering parameters of a Kalman filter based on an identified dynamic scene of the present invention;

[0025] Figure 8 is a flow chart of an embodiment of a method for adjusting control parameters of a PID controller based on an identified dynamic scene of the present invention;

[0026] Fig. 9 is a schematic diagram of the angle between a vehicle and a lane line according to an embodiment of the present invention;

[0027] Fig.10 Schematic diagram of the structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention clearer and more understandable, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the present invention.

[0029] In the description of the present invention, it is to be understood that the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. Moreover, the terms "first", "second", etc. are applicable to distinguishing similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0030] like Figure 1, which is a schematic diagram of the structure of an embodiment of a lane centering control device for a vehicle of the present invention. The lane centering control device may be, for example, an automatic driving system of a vehicle, such as a domain controller in a vehicle or a similar device or apparatus with a control function.

[0031] The lane centering control device includes: ABPR (Any Boundary Process, lane line processing module) 10, trajectory planning module 20 and trajectory tracking module 30. ABPR10 receives lane line data from the camera and processes the lane line data, such as motion compensation based on motion compensation unit 101 and Kalman filtering based on Kalman filter 102. The trajectory planning module 20 plans the driving trajectory of the vehicle based on the lane line data processed by ABPR10. The trajectory tracking module 30 controls the steering angle of the front wheels of the vehicle (such as the steering wheel angle) based on the driving trajectory planned by the trajectory planning module 20 to control the vehicle to drive in the center according to the planned trajectory. In the trajectory tracking module 30, feedforward control of the vehicle can be performed based on the feedforward unit 301, and feedback control can be performed based on the PID (Proportional-Integral-Derivative) controller 302, so that the vehicle can drive in the center based on the planned trajectory.

[0032] exist Figure 1 In the process, a Kalman filter 102 with fixed parameters is generally used to process lane line data, and a PID controller 302 with fixed parameters is used to track and control the local trajectory. This solution is very suitable for high-speed scenarios with good road conditions, good lane line perception and camera perception, and stable control with only a small / slow steering wheel. However, for complex scenarios such as high-speed small radius curves, poor lane line perception, variable lanes on urban roads, and rapidly changing connecting curves, the accuracy of lane line curvature perception will be reduced due to the rapid change of lane lines. Therefore, the use of a Kalman filter 102 and a PID controller 302 with fixed parameters may not be able to make sufficient control instructions, which may easily cause the vehicle to deviate from or be controlled out of the lane.

[0033] Based on this, an embodiment of the present invention provides a vehicle lane centering control method, such as Figure 2 As shown, the method includes:

[0034] Step S30: Acquire lane line data.

[0035] The lane line data can be, for example, Figure 1 The lane line data may be provided by the camera, or the lane line data may be filtered by the Kalman filter 102 .

[0036] Step S32: Based on the lane line data, dynamically adjust the filter parameters of the Kalman filter and / or dynamically adjust the control parameters of the PID controller, that is, use a Kalman filter and / or PID controller with variable control parameters instead of fixed parameters.

[0037] In step S32, scene recognition can be performed based on the lane line data, for example, the scene can be divided into low dynamic, medium dynamic and high dynamic scenes, where different scenes represent different degrees of lane line changes. And for scenes with different dynamics, different and variable Kalman filter parameters and / or PID control parameters are used, so as to improve the adaptability of the vehicle centering function in different scenes.

[0038] The principle of scene recognition can be, for example, based on parameters such as lane curvature and / or the angle between the vehicle and the lane, comparing the changes in the lane within a specified time and distance to achieve scene recognition. It should be noted that the above scene division is only an example and not a limitation, and the scene can be divided more flexibly based on needs.

[0039] like Figure 3 FIG. 2 is a schematic diagram of the structure of another embodiment of the vehicle lane centering control device of the present invention. Figure 3 As shown, a scene recognition unit 103 is added to the ABPR10 for identifying the scene. The scene recognition unit 103 can use the lane line data from the camera, or the lane line data output by the Kalman filter 102. A control unit 104 is also added to the ABPR10 for adjusting the filtering parameters of the Kalman filter 102 based on the output of the scene recognition unit 103. In addition, a control unit 303 is added to the trajectory tracking module 30 for adjusting the control parameters of the PID controller 302 based on the output of the scene recognition unit 103.

[0040] Specifically, the embodiment of scene recognition can refer to Figures 4 to 6 As shown, the embodiment of adjusting the filtering parameters of the Kalman filter 102 can refer to Figure 7 As shown, the embodiment of adjusting the control parameters of the PID controller 302 can refer to Figure 8 shown.

[0041] like Figure 4 and 6 The figure shows a schematic diagram of scene recognition based on the angle between the vehicle and the lane line.

[0042] The angle between the vehicle and the lane line can be the yaw angle or heading angle of the vehicle, wherein the yaw angle refers to the angle between the center line of the vehicle and the lane line, and the heading angle refers to the angle between the speed direction of the vehicle and the lane line. In general, the yaw angle and the heading angle are approximately equal.

[0043] like Fig. 9 As shown in Figure 1, it is a schematic diagram of the yaw angle ψ. Fig. 9 In the ego vehicle coordinate system, the center of the rear axle of the ego vehicle is used as the origin. The x-axis represents the direction of the centerline (central axis) of the vehicle, and the y-axis is perpendicular to the x-axis. The angle ψ between the x-axis and the lane line is the yaw angle. In the ego vehicle coordinate system, the yaw angle or other parameters have positive and negative signs, for example, following the standard of positive on the left and negative on the right. Fig. 9 As shown, since the lane line is on the left side of the x-axis, the yaw angle ψ is positive.

[0044] like Figure 4 and 6 As shown, the method for identifying a scene based on the angle between a vehicle and a lane line includes the following steps:

[0045] Step S40: Obtain the angle between the vehicle and the lane line.

[0046] The obtained angles include: the angle h_current between the vehicle and the lane line in the current cycle (this time), and the angle h_last between the vehicle and the lane line in the previous cycle (last time). h_current is used as h_last in the next cycle.

[0047] Step S41: Determine whether h_current and h_last have the same sign. If the determination result of step S41 is yes (same sign), execute step S43, otherwise (different signs), execute step S42.

[0048] For the description of symbols, please refer to the above Fig. 9 In step S41, when it is determined that h_current and h_last have the same sign, it indicates that the vehicle continuously deviates to the same side (left side or right side) of the lane line.

[0049] Step S42: Set the maximum angle h_max=0, the walking distance h_dist=0 and the walking time h_time=0, that is, reset the three parameters.

[0050] Step S43: Determine whether h_current is greater than a threshold h_thr1 (angle threshold). If so, execute step S44; if so, execute step S45.

[0051] Among them, h_thr1 is the initial threshold value, and the relevant parameters are updated only when h_current reaches h_thr1.

[0052] Step S44: Keep the values ​​of the maximum angle h_max, the walking distance h_dist and the walking time h_time unchanged.

[0053] Step S45: Update the maximum angle h_max, the walking distance h_dist and the walking time h_time.

[0054] For example, if the current value h_current is greater than h_max, then h_max = h_current is set. If the current value is less than h_max, then h_max is maintained unchanged. Travel distance h_dist = (current cycle speed * cycle time) + previously accumulated travel distance. Travel time = cycle time + previously accumulated travel time.

[0055] Step S46: Execute the following three conditions:

[0056] a. Whether the maximum angle h_max is greater than the threshold h_thr2, where h_thr2 is greater than h_thr1.

[0057] b. Whether the walking distance h_dist is between h_dist_thr1 and h_dist_thr2.

[0058] c. Whether the walking time h_time is between h_time_thr1 and h_time_thr2.

[0059] Among them, the above three conditions are mainly used to judge whether the vehicle has a large angle change in a short time and short distance, so as to judge the change of the lane line, that is, to judge the dynamic situation of the scene where the vehicle is located.

[0060] Step S60: Determine whether the above three conditions a, b and c are met at the same time. If any one of them is not met, execute step S61. If all three are met, execute step S62.

[0061] Step S61: Determine that the current scene is a first dynamic scene, such as a low dynamic scene.

[0062] Step S62: Determine whether h_current is greater than h_thr3 and whether the previous cycle is the first dynamic scene. If either condition is not met, execute step S63. If both conditions are met, execute step S65.

[0063] Among them, h_thr3 needs to be greater than h_thr1, but h_thr3 can be less than h_thr2. The reason for this design is that when entering this place based on the conditions of step S46, the yaw angle may be a little smaller when entering this place because the requirements of maximum yaw angle, walking distance and time need to be met. When entering this place based on step S60, although the curvature changes greatly, the yaw angle does not have a large deviation, indicating that the tracking control of the trajectory can still keep up, and some adjustments are also needed.

[0064] Step S63: Determine whether h_current and the distance to the center line of the lane have the same sign. If so, execute step S64; if not, execute step S61.

[0065] The lane centerline distance may be, for example, the distance between the center axis of the vehicle and the lane centerline, which also follows the principle of positive on the left and negative on the right.

[0066] Step S64: Determine that the current scene is a second dynamic scene, such as a medium dynamic scene.

[0067] Step S65: Determine that the current scene is a third dynamic scene, such as a high dynamic scene.

[0068] Step S66: When the current scene is the second dynamic scene or the third dynamic scene, the scene needs to be maintained for a certain period of time, and then step S67 is executed to enter the next cycle.

[0069] exist Figure 6 In the present invention, only three dynamic scenes, low, medium and high, are divided. For those skilled in the art, parameters such as thresholds may be divided more finely or roughly to divide more or fewer dynamic scenes.

[0070] like Figure 5 and 6 As shown, it is a flow chart of a method for recognizing scenes based on lane line curvature, wherein Figure 6 Some of them have been explained above and will not be repeated here. Figure 5 As shown, this part includes:

[0071] Step S50: Obtain lane line curvature.

[0072] The acquired lane curvature includes: the lane curvature cur_current of the current cycle (this time), and the lane curvature cur_last of the previous cycle (last time). Among them, cur_current is used as cur_last of the next cycle.

[0073] Step S51: Determine whether cur_current and cur_last have the same sign. If the determination result of step S51 is yes (same sign), execute step S53, otherwise (different signs), execute step S52.

[0074] Step S52: Set the maximum curvature cur_max=0, the walking distance c_dist=0 and the walking time c_time=0, that is, reset the three parameters.

[0075] Step S53: Determine whether cur_current is greater than a threshold value c_thr1 (curvature threshold value). If so, execute step S54; if so, execute step S55.

[0076] Among them, c_thr1 is the initial threshold value, and the relevant parameters are updated only when cur_current reaches c_thr1.

[0077] Step S54: Keep the values ​​of maximum curvature cur_max, walking distance c_dist and walking time c_time unchanged.

[0078] Step S55: Update the maximum curvature cur_max, walking distance c_dist and walking time c_time.

[0079] For example, if the current value cur_current is greater than cur_max, cur_max=cur_current is set; if the current value is less than cur_max, cur_max is maintained unchanged. Travel distance c_dist=(current cycle speed*cycle time)+previous accumulated travel distance. Travel time c_time=cycle time+previous accumulated travel time.

[0080] Step S56: Execute the following four conditions:

[0081] a. Whether the maximum curvature cur_max is greater than the threshold value c_thr2, where c_thr2 is greater than c_thr1.

[0082] b. Whether the walking distance c_dist is between c_dist_thr1 and c_dist_thr2.

[0083] b. Whether the walking time c_time is between c_time_thr1 and c_time_thr2.

[0084] d. Whether the current curvature cur_current is greater than the threshold c_thr2.

[0085] The remaining steps refer to Figure 6 As shown, no further description is given here.

[0086] In this embodiment, by Figures 4 to 6 The steps shown can determine whether the vehicle is currently in a low-dynamic, medium-dynamic or high-dynamic scenario. Based on this judgment result, you can perform Figure 7 And / or the adjustment operation shown in 8 to adapt to different dynamic scenes.

[0087] like Figure 7FIG. 1 is a schematic diagram of a method for adjusting the filtering parameters of a Kalman filter, which includes the following steps:

[0088] Step S70: Obtain the current dynamic scene DynSt and the last different dynamic scene DynSt_last.

[0089] For example, if the previous dynamic scene was low dynamic, the previous dynamic scene was medium dynamic, and the current dynamic scene is medium dynamic, then the current dynamic scene and the previous dynamic scene are obtained.

[0090] Step S71: Determine the type of the current DynSt. If it is non-low dynamic, execute step S72; if it is low dynamic, execute step S74.

[0091] Step S72: Set the time delay value DynSt_Lane_Delay.

[0092] Step S73: Obtain filtering parameters of the Carr filter corresponding to the dynamic scene.

[0093] The filtering parameters may be, for example, Q and R matrix parameters of the Carr filter. For example, the corresponding parameters for low dynamic scenes (Q1, R1), the corresponding parameters for medium dynamic scenes (Q2, R2), and the corresponding parameters for high dynamic scenes (Q3, R3) may be preset.

[0094] If the process is transferred from step S72 to step S73, the dynamic scene in step S73 is DynSt. If the process is transferred from step S76 to step S73, the dynamic scene in step S73 is DynSt_last.

[0095] Step S74: Determine whether DynSt_Lane_Delay is greater than 0, if so, execute step S76. Otherwise, execute step S75.

[0096] Step S75, obtaining the filter parameters of the Carr filter corresponding to the low dynamic scene. Then, executing step S77.

[0097] Step S76: Attenuate DynSt_Lane_Delay and use DynSt_last as the dynamic scene in step S73, and then execute step S73.

[0098] The attenuation of DynSt_Lane_Delay may be, for example, the result of subtracting the cycle time or a preset value from DynSt_Lane_Delay.

[0099] Step S77, setting the Kalman filter based on the filtering parameters obtained in step S73 or step S75.

[0100] In step S77, the filtering parameters may be firstly low-pass filtered to prevent data jitter caused by sudden changes in the parameters.

[0101] In this embodiment, the filtering parameters of the Kalman filter are dynamically adjusted based on dynamic scenarios (reflecting changes in lane lines) to enhance the adaptability to different scenarios.

[0102] like Figure 8 FIG. 1 is a schematic diagram of a method for adjusting the control parameters of a PID controller, which includes the following steps:

[0103] Step S80: Obtain the current dynamic scene DynSt and the last different dynamic scene DynSt_last.

[0104] Step S81: Determine the type of the current DynSt. If it is non-low dynamic, execute step S72; if it is low dynamic, execute step S84.

[0105] Step S82: Set the time delay value DynSt_Lane_Delay.

[0106] Step S83: non-low dynamic control.

[0107] If the process jumps from step S82 to step S83, the dynamic scene in step S83 is DynSt. If the process jumps from step S86 to step S83, the dynamic scene in step S83 is DynSt_last.

[0108] Step S84: Determine whether DynSt_Lane_Delay is greater than 0, if so, execute step S86. Otherwise, execute step S85.

[0109] Step S85, low dynamic control.

[0110] Step S86: Attenuate DynSt_Lane_Delay and use DynSt_last as the dynamic scene in step S83, and then go to step S83.

[0111] Here, the attenuation of DynSt_Lane_Delay may be, for example, the result of subtracting the cycle time from DynSt_Lane_Delay.

[0112] Step S87, determine whether the PID controller uses a fixed gain or a piecewise interpolation gain. If a fixed gain is used, execute step S88; if an interpolation method is used, execute step S89.

[0113] Step S88: Apply a fixed gain to each term (P term, I term and D term) of the PID controller to set the PID controller.

[0114] Among them, different scenarios correspond to different gains. In step S88, based on the dynamic scenarios determined in step S83 and step S85, the gains corresponding to the P item, the I item and the D item are obtained respectively, and then applied to the PID controller to adjust the gain of each item in the PID controller. In addition, in order to prevent sudden changes in the control signal, each output after the gain is applied can be low-pass filtered.

[0115] Step S89: Based on the linear interpolation method, the dynamic gain corresponding to the dynamic scene is obtained, and the PID controller is set.

[0116] For example, the dynamic gains corresponding to the P item, the I item, and the D item are obtained respectively in the current scene (the output of step S83 or S85) by linear interpolation, and then the dynamic gains are applied to the P item, the I item, and the D item respectively, and a low-pass filter is applied to the output result of the D item to prevent sudden changes in the control signal.

[0117] In this embodiment, the control parameters of the PID controller are dynamically adjusted based on dynamic scenarios (reflecting changes in lane lines) to enhance the adaptability to different scenarios.

[0118] like Fig.10 , is a schematic diagram of the structure of an embodiment of a computer device of the present invention, which includes a memory, a processor and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the method described in the embodiment of the present invention.

[0119] The computer device of this embodiment may be, for example, a controller in a vehicle, such as a domain controller, an HPC (High Performance Computer), an ECU (Electronic Control Unit), a chip, and the like.

[0120] In addition, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program / instruction is stored. When the computer program / instruction is executed by a processor, the steps of the method described in the embodiment of the present invention are implemented.

[0121] In addition, an embodiment of the present invention further provides a computer program product, including a computer program / instruction, which implements the steps of the method described in the embodiment of the present invention when executed by a processor.

[0122] The description of the above device, storage medium and program product embodiments is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device, storage medium and program product embodiments of this application, please refer to the description of the method embodiment of this application for understanding.

[0123] The processor may be at least one of an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, a microprocessor, etc. It is understandable that the electronic device that implements the function of the processor may also be other, and the embodiments of the present application are not specifically limited.

[0124] The above-mentioned computer storage medium / memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory (Flash Memory), a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM) and the like; it can also be various terminals including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0125] It should be noted that the above description is only for example and not for limitation of the present invention. In other embodiments of the present invention, the method may have more, fewer or different steps, and the order, inclusion and function of each step may be different from that described and illustrated. For example, generally multiple steps can be combined into a single step, and a single step can also be divided into multiple steps. For those of ordinary skill in the art, without paying creative work, the sequential changes of each step are also within the scope of protection of the present invention.

[0126] The technical solution of the present invention, 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. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor or a microcontroller to perform all or part of the steps of the method described in each embodiment of the present invention.

[0127] Those skilled in the art will appreciate that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed.

[0128] Although the present invention has been disclosed as above with preferred embodiments, the present invention is not limited thereto. Any changes and modifications made by any person skilled in the art without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention, and therefore the protection scope of the present invention should be subject to the scope defined by the claims.

Claims

1. A lane centering control method for a vehicle, characterized in that: include: Get lane line data; Based on the lane line data, identifying the scene in which the vehicle is located, where different scenes represent different degrees of lane line changes; as well as Based on the identified scene, dynamically adjusting control parameters, the control parameters including: filtering parameters of a Kalman filter used for lane line data processing; The identifying the scene based on the lane line data includes: Based on a first parameter, identifying a scene, wherein the first parameter includes: an angle between the vehicle and a lane line; The identifying the scene based on the first parameter includes: Determine whether the current angle between the vehicle and the lane line has the same sign as the angle in the previous cycle; If the sign of the current angle is different from that of the previous cycle, the maximum angle, the first walking distance and the first walking time are reset; If the current angle has the same sign as the angle in the previous cycle, then determine the magnitude relationship between the current angle and the first angle threshold; If the current angle is less than the first angle threshold, the values ​​of the maximum angle, the first walking distance and the first walking time are kept unchanged; If the current angle is greater than the first angle threshold, the values ​​of the maximum angle, the first walking distance and the first walking time are updated; Determine whether the maximum angle is greater than a second angle threshold, and whether the first walking distance and the first walking time are respectively within respective preset ranges, wherein the second angle threshold is greater than the first angle threshold; If the maximum angle is less than the second angle threshold, the first walking distance is not within the preset distance range, or the first walking time is not within the preset time range, then the scene is determined to be the first dynamic scene; If the maximum angle is greater than the second angle threshold, and the first walking distance and the first walking time are both within their respective preset ranges, determine the magnitude relationship between the current angle and a third angle threshold greater than the first angle threshold, and whether the scene in the previous cycle is the first dynamic scene; If the current angle is less than the third angle threshold or the scene in the previous cycle is not the first dynamic scene, determine whether the current angle and the lane centerline distance have the same sign; If the current angle and the distance from the lane centerline have different signs, the scene is determined to be the first dynamic scene; If the current angle and the distance from the center line of the lane have the same sign, it is determined that the scene is the second dynamic scene; If the current angle is greater than the third angle threshold and the scene in the previous cycle is the first dynamic scene, it is determined that the scene is the third dynamic scene.

2. The lane centering control method according to claim 1, characterized in that: The dynamically adjusting the control parameter based on the identified scene includes: When the scene is not the first dynamic scene, setting the time delay value and using the control parameters corresponding to the non-first dynamic scene; When the scene is a first dynamic scene, determining whether the time delay value is greater than 0; If it is not greater than 0, the control parameters corresponding to the first dynamic scene are used; If it is greater than 0, the time delay value is attenuated, and the control parameters corresponding to the previous non-first dynamic scene are used.

3. A vehicle lane centering control method, characterized in that: include: Get lane line data; Based on the lane line data, identifying the scene; as well as Based on the identified scenario, dynamically adjusting control parameters, the control parameters including: control parameters of a PID controller for trajectory tracking control; The identifying the scene based on the lane line data includes: Based on a first parameter, identifying the scene in which the vehicle is located, wherein the first parameter includes: an angle between the vehicle and the lane line and a curvature of the lane line; The identifying the scene based on the first parameter includes: Determine whether the sign of the current lane curvature is the same as that of the lane curvature in the previous cycle; If the signs are different, the maximum lane curvature, the second travel distance, and the second travel time are reset; If the signs are the same, determine whether the curvature of the current lane line is greater than the first curvature threshold; If the current lane line curvature is less than the first curvature threshold, the values ​​of the maximum lane line curvature, the second walking distance, and the second walking time are kept unchanged; If the current lane line curvature is greater than the first curvature threshold, the values ​​of the maximum lane line curvature, the second walking distance, and the second walking time are updated; Determining whether the maximum lane line curvature and the current lane line curve are greater than a second curvature threshold, and whether the second walking distance and the second walking time are respectively within respective preset ranges, wherein the second curvature threshold is greater than the first curvature threshold; When the maximum lane line curvature is less than the second curvature threshold, the current lane line curvature is less than the second curvature threshold, the second walking distance is not within the preset distance range, or the second walking time is not within the preset time range, determining that the scene is the first dynamic scene; When the maximum lane line curvature and the current lane line curvature are both greater than the second curvature threshold, and the second walking distance and the second walking time are both within their respective preset ranges, it is determined whether the current angle between the vehicle and the lane line is greater than the third angle threshold and whether the scene in the previous cycle is the first dynamic scene; If the current angle is less than the third angle threshold or the scene in the previous cycle is not the first dynamic scene, determine whether the current angle and the lane centerline distance have the same sign; If the current angle and the distance from the lane centerline have different signs, the scene is determined to be the first dynamic scene; If the current angle and the distance from the center line of the lane have the same sign, it is determined that the scene is the second dynamic scene; If the current angle is greater than the third angle threshold and the scene in the previous cycle is the first dynamic scene, it is determined that the scene is the third dynamic scene.

4. The lane centering control method according to claim 3, characterized in that: The dynamically adjusting the control parameter based on the identified scene includes: When the scene is not the first dynamic scene, setting the time delay value and using the control parameters corresponding to the non-first dynamic scene; When the scene is a first dynamic scene, determining whether the time delay value is greater than 0; If it is not greater than 0, the control parameters corresponding to the first dynamic scene are used; If it is greater than 0, the time delay value is attenuated, and the control parameters corresponding to the previous non-first dynamic scene are used.

5. A lane centering control device for a vehicle, characterized in that: include: Lane line processing module, used to process lane line data; A trajectory planning module, used to plan a driving trajectory based on the lane line data output by the lane line processing module; as well as A trajectory tracking module, used to control the vehicle based on the driving trajectory planned by the trajectory planning module; Wherein, the lane line processing module includes: A Kalman filter, configured to perform Kalman filtering on the lane line data; A scene recognition unit, used to identify the current scene based on lane line data; Wherein, the trajectory tracking module includes: PID controller, used to perform trajectory tracking control; Wherein, the lane line processing module further includes: a first control unit, used to adjust the filtering parameters of the Kalman filter based on the scene in which it is located, and / or, the trajectory tracking module further includes: a second control unit, used to adjust the control parameters of the PID controller based on the scene in which it is located; Wherein, the scene recognition unit is specifically used for: Based on a first parameter, identifying a scene, wherein the first parameter includes: an angle between the vehicle and the lane line, and / or a curvature of the lane line; The identifying the scene based on the first parameter includes: Determine whether the current angle between the vehicle and the lane line has the same sign as the angle in the previous cycle; If the sign of the current angle is different from that of the previous cycle, the maximum angle, the first walking distance and the first walking time are reset; If the current angle has the same sign as the angle in the previous cycle, then determine the magnitude relationship between the current angle and the first angle threshold; If the current angle is less than the first angle threshold, the values ​​of the maximum angle, the first walking distance and the first walking time are kept unchanged; If the current angle is greater than the first angle threshold, the values ​​of the maximum angle, the first walking distance and the first walking time are updated; Determine whether the maximum angle is greater than a second angle threshold, and whether the first walking distance and the first walking time are respectively within respective preset ranges, wherein the second angle threshold is greater than the first angle threshold; If the maximum angle is less than the second angle threshold, the first walking distance is not within the preset distance range, or the first walking time is not within the preset time range, then the scene is determined to be the first dynamic scene; If the maximum angle is greater than the second angle threshold, and the first walking distance and the first walking time are both within their respective preset ranges, determine the magnitude relationship between the current angle and a third angle threshold greater than the first angle threshold, and whether the scene in the previous cycle is the first dynamic scene; If the current angle is less than the third angle threshold or the scene in the previous cycle is not the first dynamic scene, determine whether the current angle and the lane centerline distance have the same sign; If the current angle and the distance from the lane centerline have different signs, the scene is determined to be the first dynamic scene; If the current angle and the distance from the center line of the lane have the same sign, it is determined that the scene is the second dynamic scene; If the current angle is greater than the third angle threshold and the scene in the previous cycle is the first dynamic scene, then determining that the scene is the third dynamic scene; And / or, identifying the scene based on the first parameter includes: Determine whether the sign of the current lane curvature is the same as that of the lane curvature in the previous cycle; If the signs are different, the maximum lane curvature, the second travel distance, and the second travel time are reset; If the signs are the same, determine whether the curvature of the current lane line is greater than the first curvature threshold; If the current lane line curvature is less than the first curvature threshold, the values ​​of the maximum lane line curvature, the second walking distance, and the second walking time are kept unchanged; If the current lane line curvature is greater than the first curvature threshold, the values ​​of the maximum lane line curvature, the second walking distance, and the second walking time are updated; Determining whether the maximum lane line curvature and the current lane line curve are greater than a second curvature threshold, and whether the second walking distance and the second walking time are respectively within respective preset ranges, wherein the second curvature threshold is greater than the first curvature threshold; When the maximum lane line curvature is less than the second curvature threshold, the current lane line curvature is less than the second curvature threshold, the second walking distance is not within the preset distance range, or the second walking time is not within the preset time range, determining that the scene is the first dynamic scene; When the maximum lane line curvature and the current lane line curvature are both greater than the second curvature threshold, and the second walking distance and the second walking time are both within their respective preset ranges, it is determined whether the current angle between the vehicle and the lane line is greater than the third angle threshold and whether the scene in the previous cycle is the first dynamic scene; If the current angle is less than the third angle threshold or the scene in the previous cycle is not the first dynamic scene, determine whether the current angle and the lane centerline distance have the same sign; If the current angle and the distance from the lane centerline have different signs, the scene is determined to be the first dynamic scene; If the current angle and the distance from the center line of the lane have the same sign, it is determined that the scene is the second dynamic scene; If the current angle is greater than the third angle threshold and the scene in the previous cycle is the first dynamic scene, it is determined that the scene is the third dynamic scene.

6. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

8. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images