Lane keeping method and device applied to autonomous vehicle, equipment and medium

Abstract

The invention discloses a path matching method, device and equipment for an automatic driving vehicle and a medium, and the method comprises the steps: collecting road condition image information corresponding to a target vehicle, and determining road parameters according to the road condition image information; determining lane coordinates corresponding to a vehicle coordinate system according to the road parameters, and obtaining vehicle driving parameters corresponding to the target vehicle; and determining a target direction rotation angle corresponding to the target vehicle according to the vehicle driving parameters and the lane coordinates, and controlling the target vehicle to keep the lane based on the target direction rotation angle. Based on the technical scheme, the target direction turning angle corresponding to the target vehicle is determined according to the vehicle driving parameters and the lane coordinates, so that effective control over vehicle steering is achieved, the precision and robustness of vehicle transverse control are improved, and the flexibility of a lane keeping auxiliary system of the intelligent vehicle and the driving safety of a driver are improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle autonomous driving technology, and in particular to a lane keeping method, device, equipment and medium applied to an autonomous driving vehicle. Background Art

[0002] With the development of autonomous driving technology, advanced driver assistance systems have emerged. Lane keeping assist technology, as one of the key functions of advanced driver assistance systems, can greatly reduce the incidence of traffic accidents and alleviate the driver's operating burden. Its research is of great significance to the development of intelligent networking of automobiles.

[0003] However, the existing technical solutions mainly include two parts: the perception layer and the control layer. The perception layer is the sensor's analysis of lane line information to obtain the vehicle's lateral position; the control layer mainly uses the lateral control algorithm to adjust the vehicle's lateral position or make the vehicle follow the track. It can be seen that the existing technical solutions consider the parameters of the vehicle and the road more and cannot be adaptively adjusted according to the driver's status. Summary of the Invention

[0004] The present invention provides a lane keeping method, device, equipment and medium for autonomous vehicles, which determine the target direction angle corresponding to the target vehicle based on the vehicle's driving parameters and lane coordinates, thereby achieving effective control of the vehicle's steering, improving the accuracy and robustness of the vehicle's lateral control, and thereby improving the flexibility of the intelligent vehicle's lane keeping assistance system and the driver's driving safety.

[0005] According to one aspect of the present invention, a lane keeping method for an autonomous driving vehicle is provided, comprising:

[0006] Collecting road condition image information corresponding to the target vehicle and determining road parameters based on the road condition image information;

[0007] Determining lane coordinates corresponding to a vehicle coordinate system based on the road parameters, and obtaining vehicle driving parameters corresponding to the target vehicle;

[0008] A target direction angle corresponding to the target vehicle is determined according to the vehicle driving parameters and the lane coordinates, and the target vehicle is controlled to perform lane keeping based on the target direction angle.

[0009] According to another aspect of the present invention, a lane keeping device for an autonomous driving vehicle is provided, comprising:

[0010] A data acquisition module is used to collect road condition image information corresponding to the target vehicle and determine road parameters based on the road condition image information;

[0011] a data processing module, configured to determine lane coordinates corresponding to a vehicle coordinate system based on the road parameters, and to obtain vehicle driving parameters corresponding to the target vehicle;

[0012] A vehicle control module is used to determine a target direction angle corresponding to the target vehicle according to the vehicle driving parameters and the lane coordinates, and control the target vehicle to keep the lane based on the target direction angle.

[0013] According to another aspect of the present invention, an electronic device is provided, comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the lane keeping method applied to an autonomous driving vehicle as described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the lane keeping method applied to an autonomous driving vehicle as described in any embodiment of the present invention when executed.

[0018] The technical solution of an embodiment of the present invention collects road image information corresponding to a target vehicle and determines road parameters based on the road image information; determines lane coordinates corresponding to a vehicle coordinate system based on the road parameters and obtains vehicle driving parameters corresponding to the target vehicle; determines a target direction angle corresponding to the target vehicle based on the vehicle driving parameters and the lane coordinates, and controls the target vehicle to maintain its lane based on the target direction angle. Based on the above technical solution, by determining the target direction angle corresponding to the target vehicle based on the vehicle driving parameters and lane coordinates, effective control of vehicle steering is achieved, improving the accuracy and robustness of the vehicle's lateral control, thereby enhancing the flexibility of the intelligent vehicle's lane keeping assist system and the driver's driving safety.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 1 is a flow chart of a lane keeping method for an autonomous driving vehicle provided by an embodiment of the present invention;

[0022] Figure 2 is a flow chart of a lane keeping method applied to an autonomous driving vehicle provided by an embodiment of the present invention;

[0023] Figure 3 1 is a schematic structural diagram of a lane keeping system controller provided by an embodiment of the present invention;

[0024] Figure 4 This is a structural block diagram of a lane keeping device for an autonomous driving vehicle provided by an embodiment of the present invention;

[0025] Figure 5 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged 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. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Example 1

[0029] Figure 1 This is a flow chart of a lane keeping method for an autonomous vehicle provided by an embodiment of the present invention. This embodiment is applicable to the case where the lane keeping function is activated, control information is determined based on the collected road data and vehicle data, and the vehicle is controlled to keep the lane based on the control information. This method can be executed by a lane keeping device for an autonomous vehicle. The lane keeping device for an autonomous vehicle can be implemented in the form of hardware and / or software. The lane keeping device for an autonomous vehicle can be configured in an electronic device, which can be a terminal device or a server. Figure 1 As shown, the method includes:

[0030] S110 , collecting road condition image information corresponding to the target vehicle, and determining road parameters according to the road condition image information.

[0031] The target vehicle may be a vehicle using a lane keeping function. The road condition image information may be image information corresponding to the road acquired by a sensor system installed in the target vehicle. This image information may include image data acquired by the image sensor and radar point cloud data corresponding to the road acquired by a lidar. Road parameters may be lane data associated with the road, including road width, road curvature, etc.

[0032] Specifically, multiple onboard sensors collect road image information, perform sensory fusion analysis on the extracted lane markings, and output lane parameters, primarily including the lateral distance C0 of the lane marking from the sensor's optical axis centerline, the vehicle's heading angle C1 relative to the lane marking, the lane marking's curvature C2, and the lane marking's curvature change rate C3. For example, an onboard camera or other image acquisition device acquires real-time image information of the road environment surrounding the target vehicle. The captured images are then preprocessed, such as by denoising and contrast enhancement. Image recognition algorithms are then used to extract road features, such as lane markings, traffic signs, obstacles, and road surface conditions, from the preprocessed images. Based on these extracted road features, geometric calculations and pattern recognition are then used to determine road parameters, such as lane marking position, curvature, and width, traffic sign type and location, obstacle distance and speed, and road surface type and condition.

[0033] S120. Determine lane coordinates corresponding to a vehicle coordinate system according to the road parameters, and obtain vehicle driving parameters corresponding to the target vehicle.

[0034] The vehicle coordinate system can be a vehicle coordinate system established with the target vehicle as the origin. Lane coordinates can be coordinate values corresponding to the current road. Vehicle driving parameters can be understood as parameters generated by the target vehicle during driving, and may include heading angle, speed, acceleration, etc.

[0035] Specifically, based on road parameters such as lane curvature, width, and heading angle, the global road coordinate system is mapped to the vehicle's local coordinate system through geometric transformation. For example, using the vehicle's real-time position and attitude angle, the lane centerline, sideline and other features are projected into a coordinate system with the vehicle's center of mass as the origin through a homogeneous transformation matrix to generate lane coordinates. Then, vehicle-mounted sensors such as wheel speed sensors, IMUs, and steering wheel angle sensors are used to collect vehicle driving parameters in real time, including vehicle speed, acceleration, yaw rate, steering angle, wheel speed difference, etc. Parameters that are difficult to measure directly, such as the center of mass sideslip angle and tire lateral force, can be estimated in combination with the vehicle dynamics model corresponding to the target vehicle. For example, the lane line equation is used to calculate the coordinates (x, y) of the lane line in front of the vehicle's lane in the vehicle coordinate system. The lane line equation calculation formula is as follows: y = C0 + C0*x + C1*x 2 +C2*x 3 +C3*x 3 ; x = v x *T p ; Among them, v x is the longitudinal speed of the vehicle, T p To simulate the driver's forward preview time. Read the signal information on the vehicle CAN bus to obtain the vehicle's real-time motion information; mainly including: the vehicle's longitudinal speed v x , the vehicle's steering wheel angle δ sw , and all the information required for lane keeping control. Technicians can set the corresponding data extraction method according to their needs, which will not be described here.

[0036] S130. Determine a target direction angle corresponding to the target vehicle according to the vehicle driving parameters and the lane coordinates, and control the target vehicle to perform lane keeping based on the target direction angle.

[0037] The target direction angle may be understood as a steering wheel angle for controlling the target vehicle to maintain lane.

[0038] Specifically, the lateral offset Δy and heading angle deviation Δψ between the vehicle's current position and the lane centerline can be calculated based on the lane coordinate system. For example, by comparing the coordinates of the vehicle's center of mass with the projected point of the lane centerline, and combining the vehicle's heading angle with the angle between the lane tangent and the vehicle's direction, the vehicle's relative posture within the lane is quantified. A control algorithm, such as a PID controller or model predictive control (MPC), is then used to calculate the target steering angle δ based on the vehicle's driving parameters (vehicle speed v, yaw rate γ, and errors Δy and Δψ). This target steering angle δ is then converted into a steering wheel control command, which is sent via the CAN bus to the electric power steering system, driving the motor to adjust the steering angle.

[0039] On the basis of the above technical solution, the determining of the target direction angle corresponding to the target vehicle according to the vehicle driving parameters and the lane coordinates includes: determining a first preview coordinate according to a first preview time and the lane coordinates; determining a coordinate deviation value and an expected lateral acceleration according to the first preview coordinates and the lane coordinates, and determining the target steering wheel angle according to the coordinate deviation value and the lateral acceleration.

[0040] The first preview time is a preset ideal preview time. The first preview coordinate may be a road coordinate corresponding to the preset ideal preview time. The coordinate deviation value may be understood as the deviation value between the first preview coordinate and the lane coordinate. The expected lateral acceleration may be the lateral acceleration of the vehicle calculated under ideal conditions.

[0041] Specifically, the preview distance (D_prev=v×T_prev) can be calculated based on the preset first preview time (T_prev) and the real-time speed of the vehicle (v), and then in the lane coordinate system, the point D_prev in front of the current vehicle position along the lane centerline is selected as the first preview coordinate (X_prev, Y_prev). For example, when the vehicle speed is 30m / s and T_prev=1.5s, the preview distance is 45 meters. By comparing the current position of the vehicle (X_curr, Y_curr) with the preview coordinates, the lateral deviation (ΔY=Y_prev-Y_curr) and the heading angle deviation (ΔΨ) are calculated. Combined with the preview time and deviation, the required acceleration is calculated by the formula, and then the target steering wheel angle can be determined based on the coordinate deviation value and the lateral acceleration.

[0042] For example, based on the feedforward control part of the lateral deviation, under ideal conditions, the vehicle travels for a time T p After that, at t+T p The position coordinates at the moment should be equal to the position coordinates of the preview point. From this, the expected optimal lateral acceleration expression can be obtained as follows: in is the desired lateral acceleration, T p is the preview time, e y To simulate the lateral deviation between the preview point on the center line of the forward lane and the vehicle, y L To simulate the lateral deviation between the preview point and the vehicle on the left lane line of the driver's forward driving, y R It simulates the lateral deviation between the preview point on the right lane line facing forward and the vehicle.

[0043] The technical solution of the embodiment of the present invention designs a lane keeping system feedforward controller for low-speed and high-speed vehicle driving based on lateral deviation, calculates the desired steering wheel angle, and further corrects and compensates the desired steering wheel angle based on the feedback control method of the lateral acceleration deviation, outputting the corrected desired steering wheel angle, thereby improving the accuracy of calculating the target steering wheel angle and ensuring the accuracy of lane following.

[0044] Based on the above technical solution, the target steering wheel angle is determined according to the coordinate deviation value and the lateral acceleration, including: obtaining a proportional coefficient corresponding to the target vehicle, and minimizing an objective function value according to the proportional coefficient, the coordinate deviation value and the expected lateral acceleration; determining a preview time corresponding to the minimum objective function value, and determining the target steering wheel angle according to the preview time and the road parameters.

[0045] The proportionality factor can be a parameter in a pre-set objective function. This parameter can be pre-calibrated for the target vehicle, or the driver can select a desired vehicle mode, and then determine the corresponding proportionality factor from a pre-established mapping table based on that mode. Vehicle designers can set the proportionality factor as needed; the specific method is not detailed here. The objective function value can be determined using a pre-set objective function. The preview time can be understood as the preview time corresponding to the minimum objective function value found in the mapping table.

[0046] Specifically, it is possible to extract the proportional coefficient K associated with the current driving mode, such as the comfort / sport mode, the vehicle speed and the road adhesion coefficient from the vehicle control parameter library. For example, on a low-adhesion road surface (μ<0.3), the K value is automatically reduced by 30% to suppress oversteering. For example, in actual driving, the driver's forward-looking behavior will be affected by factors such as the vehicle's driving state and the driving environment ahead. A shorter preview distance can ensure high tracking accuracy, but the driver's foresight of the road ahead will deteriorate, leading to mental tension and frequent adjustments to the vehicle's posture, resulting in uncomfortable oscillations in the driving trajectory, and increasing the preview distance to minimize the objective function according to the preset proportional coefficient: J = α1·E+α2·a ymax , where α1 and α2 are proportional coefficients. Different parameter combinations will alleviate the discomfort caused by vehicle trajectory oscillation, but will reduce the accuracy of tracking control and thus increase tracking error. A preview time adaptive method based on the curvature of the target trajectory is introduced, and an evaluation function corresponding to different driving styles is established. If a larger α1 value is taken, it means that more attention is paid to the accuracy of tracking control; if a larger α2 value is taken, it means that more attention is paid to ride comfort. E is the cumulative value of tracking error under preview time, a ymaxis the maximum value of lateral acceleration. When J reaches the minimum value J min When the corresponding preview time T p0 The optimal preview time under the vehicle speed may be a pre-set mapping relationship table of the objective function value and the preview time, and then the preview time corresponding to the objective function value is searched through the mapping relationship table.

[0047] The technical solution of the embodiment of the present invention introduces a preview time adaptive scheme based on the curvature of the target trajectory, thereby ensuring that the calculated preview time is consistent with the driver's behavior, thereby improving the calculation accuracy of the preview time and further improving the accuracy of lane keeping.

[0048] On the basis of the above technical solution, the target steering wheel angle is determined according to the preview time and the road parameters, including: determining a time compensation value according to the road parameters, and determining a target preview time based on the preview time and the time compensation value; and determining the target steering wheel angle according to the target preview time and the coordinate deviation value.

[0049] The time compensation value may be a compensation value of the preview time calculated according to the road parameters.

[0050] Specifically, a time compensation value is determined according to the road parameters, and a target preview time is determined based on the preview time and the time compensation value, and then a target steering wheel angle is determined according to the target preview time and the coordinate deviation value. For example, the above-mentioned optimal preview time is less applicable to lanes with variable curvatures, and the optimal preview time T needs to be adjusted. p0 Compensation correction is performed, and then the correction preview time ΔT is introduced p The relationship expression with lane curvature ρ is as follows: ΔT p =ΔT pmax ·e -λρ , where ρ is the lane curvature, ΔT pmax is the maximum value of the corrected preview time, and λ is the correction coefficient. Finally, the adaptive preview time expression is as follows: T p =T p0 +T p .

[0051] The technical solution of the embodiment of the present invention takes into account the accuracy of lane line tracking and the driving comfort requirements, introduces a preview time adaptive method based on the curvature of the target trajectory, and improves the accuracy of lane centering control and driving comfort of vehicles on roads with variable curvature.

[0052] On the basis of the above technical solution, the target steering wheel angle is determined according to the target preview time and the coordinate deviation value, including: determining the operating condition of the target vehicle based on vehicle driving parameters, and determining a vehicle angle calculation formula according to the operating condition; determining the feedforward steering wheel angle of the target vehicle under the operating condition based on the vehicle angle calculation formula, the coordinate deviation value and the target preview time, and determining the target steering wheel angle according to the feedforward steering wheel angle.

[0053] The operating condition may be the current operating state of the target vehicle, such as a high-speed condition and a low-speed condition. The vehicle steering angle calculation formula may be a predetermined steering angle calculation formula corresponding to different vehicle operating conditions. The feedforward steering wheel angle may be a steering wheel angle calculated based on feedforward control of the lateral deviation.

[0054] Specifically, the vehicle's current operating conditions are comprehensively judged through on-board sensor data and road parameters, for example: high-speed straight driving conditions: vehicle speed > 80km / h and road curvature < 0.001rad / m; low-speed curve conditions: vehicle speed < 40km / h and road curvature > 0.003rad / m; and then differentiated turning angle calculation strategies are selected according to the identified conditions: high-speed straight driving conditions: adopt the "feedforward compensation + feedback correction" architecture, the feedforward item generates the basic turning angle based on the lateral deviation of the preview point, and the feedback item is calculated through PI The D controller suppresses residual errors. For low-speed cornering conditions: Enable the "path curvature coupling" mode. The steering angle calculation formula is directly related to the road curvature and vehicle speed. For example, the steering angle amplitude is positively correlated with the curvature and negatively correlated with the vehicle speed. Within the selected formula framework, the preview point coordinates are generated based on the target preview time (T_target), and the lateral deviation ΔY between the current vehicle position and the preview point is calculated. The feedforward angle δ_ff and the feedback correction amount δ_fb, such as the PID output, are superimposed to generate the target steering wheel angle δ_target.

[0055] Based on the above technical solution, the determining the target steering wheel angle based on the feedforward steering wheel angle includes: obtaining a lateral acceleration feedback coefficient and an actual lateral acceleration corresponding to the target vehicle; determining a feedback compensation steering wheel angle based on the actual lateral acceleration, the lateral acceleration feedback coefficient, and the expected lateral acceleration; and determining the target steering wheel angle based on the feedforward steering wheel angle and the feedback compensation steering wheel angle.

[0056] The lateral acceleration feedback coefficient can be a preset parameter used to calculate the lateral acceleration feedback deviation, a pre-calibrated constant corresponding to the target vehicle. The actual lateral acceleration can be the lateral acceleration value corresponding to the target vehicle, collected by a sensor. The feedback compensation steering wheel angle can be a compensation value calculated based on the feedback of the lateral acceleration deviation.

[0057] Specifically, the lateral acceleration feedback coefficient (K_af) associated with the current driving mode (e.g., comfort / sport), vehicle speed, and road adhesion coefficient can be extracted from the vehicle control parameter library. For example, in comfort mode, K_af takes a small value (e.g., 0.6) to suppress overcorrection; in sport mode, K_af takes a large value (e.g., 1.2) to enhance response sensitivity. The actual lateral acceleration (a_lat_act) is acquired in real time by the onboard inertial measurement unit (IMU) with a sampling frequency ≥ 100Hz. The deviation (Δa = a_lat_des - a_lat_act) between the desired lateral acceleration (a_lat_des) and the actual value is then calculated. Based on the deviation Δa and the feedback coefficient K_af, the feedback compensation steering wheel angle (δ_fb) is determined using a table lookup method. The feedforward angle (δ_ff, generated by the lateral deviation of the preview point) is superimposed with the feedback compensation angle (δ_fb) to generate the target steering wheel angle (δ_target). δ_target is smoothed using the steering system dynamic model (taking into account the transmission ratio and response delay), for example, by using a second-order filter to suppress high-frequency jitter, and is ultimately output to the electric power steering system (EPS).

[0058] Based on the above technical solution, the control of the target vehicle to keep lane based on the target direction angle includes: sending the target direction angle to the electric power steering controller of the target vehicle; and the electric power steering controller controlling the target vehicle to keep lane according to the target direction angle.

[0059] The electric power steering controller may be a power steering system provided in a vehicle that relies on an electric motor to provide auxiliary torque.

[0060] Specifically, the calculated target direction angle is transmitted to the Electric Power Steering System (EPS) controller in real time via the vehicle network. After receiving the target direction angle, the EPS controller combines the current actual steering wheel angle and the physical limitations of the steering system, and calculates the motor drive torque through built-in control algorithms such as the PID controller. The EPS motor converts the torque into steering wheel rotation, adjusts the wheel angle through the steering column and gear rack mechanism, and then controls the target vehicle to keep in the lane.

[0061] The technical solution of the embodiment of the present invention is to collect road image information corresponding to the target vehicle and determine road parameters based on the road image information; determine lane coordinates corresponding to the vehicle coordinate system based on the road parameters, and obtain vehicle driving parameters corresponding to the target vehicle; determine the target direction angle corresponding to the target vehicle based on the vehicle driving parameters and the lane coordinates, and control the target vehicle to maintain lane based on the target direction angle. Based on the above technical solution, the lane keeping system controller is designed by adopting the method of lateral deviation feedforward and lateral acceleration deviation feedback, simulating the thinking process of human driver pre-aiming, realizing effective control of vehicle steering, improving the accuracy and robustness of vehicle lateral control, and thereby improving the flexibility of the lane keeping assist system of intelligent vehicles and the driving safety of drivers.

[0062] Example 2

[0063] Figure 2 This is a flow chart of a lane keeping method for an autonomous vehicle provided by an embodiment of the present invention. This embodiment further optimizes the technical solution of the lane keeping method for an autonomous vehicle based on the above technical solution. Figure 2 As shown, the method includes:

[0064] The lane line parameters are output through multi-sensor perception fusion: Specifically, the road condition image information is collected through the on-board multi-sensor, and the extracted lane lines are perceived, fused and analyzed to output the lane line parameters; mainly including: the lateral distance C0 of the lane line from the center line of the sensor optical axis, the heading angle C1 of the vehicle relative to the lane line, the curvature C2 of the lane line, the curvature change rate C3 of the lane line, etc.

[0065] Use the lane line equation to calculate the coordinates of the lane line ahead: Specifically, use the lane line equation to calculate the coordinates (x, y) of the lane line ahead of the vehicle in the vehicle's travel lane. The lane line equation calculation formula is as follows: y = C0 + C0*x + C1*x 2 +C2*x 3 +C3*x 3 ; x = v x *T p ; Among them, v x is the longitudinal speed of the vehicle, T p It is used to simulate the driver's forward preview time.

[0066] Get the target vehicle's driving parameters: Specifically, read the signal information on the vehicle's CAN bus to obtain the vehicle's real-time motion information; mainly including: the vehicle's longitudinal speed v x , the vehicle's steering wheel angle δ sw , ...etc. and all the information needed for lane keeping control.

[0067] Calculate the expected steering wheel angle: Input the lane line parameter information and vehicle motion state information into the lane keeping controller designed based on the pure tracking control method. The structure of the lane keeping controller provided in this embodiment is as follows: Figure 3 As shown, the desired steering wheel target angle is calculated Specifically include:

[0068] Feedforward control based on lateral deviation: Under ideal conditions, the vehicle travels for a period of time T p After that, at t+T p The position coordinates at the moment should be equal to the position coordinates of the preview point. From this, the expected optimal lateral acceleration expression can be obtained as follows: in, is the desired lateral acceleration, T p is the preview time, e y To simulate the lateral deviation between the preview point on the center line of the forward lane and the vehicle, y L To simulate the lateral deviation between the preview point and the vehicle on the left lane line of the driver's forward driving, y R It simulates the lateral deviation between the preview point on the right lane line facing forward and the vehicle.

[0069] When the vehicle is traveling at low speed, the curvature of its driving trajectory 1 / R is related to the steering wheel angle δ sw Follow the following relationship:

[0070] Among them, i sw is the steering system transmission ratio. The desired steering wheel angle can be obtained for: Where: D p It is the product of vehicle speed and preview time, that is, D p =v x *T p .

[0071] However, in the actual driving process, there is a lag in reaction and action from the driver's perception of the environment to the execution of the operation. This patent introduces and 1 / 1+T h The two hysteresis links s simulate the real driver's driving and correct the expected steering wheel angle to make it conform to human driving characteristics. The corrected expected steering wheel angle δ sw1 The expression is as follows: Among them, t d is the delay time of nervous system reaction, T hIt is the lag time of the driver's steering wheel operation. According to relevant research, this patent takes t d =0.2s,T h =0.1s.

[0072] The above equation assumes a low-speed vehicle, treating it as an ideal system. However, for high-speed vehicles, the dynamic response cannot be ignored. Taking the vehicle's dynamic response into account, the transfer function from lateral acceleration to steering wheel angle is defined as the correction factor C(s), expressed as follows:

[0073]

[0074] Among them, C0 and T c is the correction factor, G ay is the lateral acceleration steady-state gain, T y1 , T1 is the time constant, and K is the stability factor. λ∈

[01] , usually taking λ=0.5 can achieve good lane centering effect. Then, the feedforward steering wheel angle expression based on the lateral deviation Δe under high-speed conditions is as follows:

[0075]

[0076] Feedback control based on lateral acceleration deviation: Specifically, the driver's reaction lag during driving, the nonlinear characteristics of the car under high-speed driving conditions, and the adverse effects of complex driving conditions. When the vehicle is controlled to track the lane centerline only by the steering wheel angle obtained by the lateral deviation, its actual lateral acceleration a y and the desired optimal lateral acceleration There will be a certain deviation between them, which will lead to a large error in tracking the lane centerline. In order to compensate for the trajectory tracking error caused by the lateral acceleration deviation, this patent adopts a feedback control method based on the lateral acceleration deviation to correct and compensate the desired steering wheel angle. The expression of this correction is as follows: Where: η is the lateral acceleration feedback coefficient, which needs to be continuously adjusted dynamically. It has strong robustness and can ensure good tracking effect of the controller within a large range of values.

[0077] Finally, the steering wheel angle expression obtained by the lane keeping system controller based on lateral deviation feedforward and lateral acceleration deviation feedback is as follows: sw =δ sw2 +Δδ sw .

[0078] In summary, the feedback correction of the lateral acceleration deviation can compensate for the tracking error caused by the aforementioned adverse effects, thereby improving the control performance of the lane keeping system controller.

[0079] It should be noted that in actual driving, the driver's forward-looking behavior will be affected by factors such as the vehicle's driving state and the driving environment ahead. A shorter preview distance can ensure high tracking accuracy, but the driver's foresight of the road ahead will be reduced, leading to mental tension, frequent adjustments to the vehicle's posture, and uncomfortable oscillations in the driving trajectory. Increasing the preview distance: J = α1·E + α2·a ymax

[0080] Among them, α1 and α2 are proportional coefficients. Different parameter combinations will alleviate the discomfort caused by vehicle trajectory oscillation, but will reduce the accuracy of tracking control and thus increase tracking error. Considering the accuracy of lane line tracking and the requirements of driving comfort, a preview time adaptive method based on the curvature of the target trajectory is introduced to correspond to different driving styles. If a larger α1 value is taken, it means that the accuracy of tracking control is more concerned; if a larger α2 value is taken, it means that the ride comfort is more concerned. E is the cumulative value of tracking error under preview time, a ymax is the maximum value of lateral acceleration. When J reaches the minimum value J min When the corresponding preview time T p0 is the optimal preview time at this speed. The above optimal preview time is less applicable to lanes with variable curvatures, so the optimal preview time T p0 Compensation correction is carried out. The correction preview time ΔT is introduced p The relationship expression with lane curvature ρ is as follows: ΔT p =ΔT pmax ·e -λρ , where: ρ is the lane curvature, ΔT pmax is the maximum value of the corrected preview time, and λ is the correction coefficient. Finally, the adaptive preview time expression is: T p =T p0 +ΔT p .

[0081] Control the vehicle to perform lane control: Specifically, the calculated desired steering wheel target angle is sent to the electric power steering controller to control the vehicle to achieve lane centering and ensure vehicle driving safety.

[0082] The technical solution of the embodiment of the present invention uses a forward-looking camera to identify and output left and right lane line parameters, calculates the current lane centerline using the lane line equation, and searches for a preview point on the lane centerline in front of the vehicle based on the current position of the vehicle's rear wheel center. Assuming the vehicle travels to the target point according to a certain turning radius, the vehicle's front wheel angle is then calculated based on the distance from the vehicle's current position to the preview point, the turning radius, and the geometric relationship between the preview point and the vehicle's front heading. This controls the vehicle's lateral tracking error with respect to the lane centerline, enabling lane keeping assistance and centering, effectively improving driving safety. Furthermore, to address the nonlinear, time-varying, hysteresis, and motion uncertainty characteristics of vehicles, two hysteresis links are introduced to simulate real-world driver driving, correcting the desired steering wheel angle to align it with human driving characteristics. A feedback control method based on lateral acceleration deviation is used to correct and compensate for the desired steering wheel angle calculated based on the lateral deviation, compensating for the error in trajectory tracking based on the lateral deviation, achieving effective vehicle control, and improving the accuracy and robustness of vehicle lateral control.

[0083] Example 3

[0084] Figure 4 This is a schematic diagram of the structure of a lane keeping device for an autonomous driving vehicle provided by an embodiment of the present invention. Figure 4 As shown, the device includes: a data acquisition module 410, a data processing module 420 and a vehicle control module 430; wherein,

[0085] The data acquisition module 410 is used to acquire road condition image information corresponding to the target vehicle and determine road parameters based on the road condition image information;

[0086] a data processing module 420 for determining lane coordinates corresponding to a vehicle coordinate system based on the road parameters, and obtaining vehicle driving parameters corresponding to the target vehicle;

[0087] The vehicle control module 430 is configured to determine a target direction angle corresponding to the target vehicle according to the vehicle driving parameters and the lane coordinates, and control the target vehicle to perform lane keeping based on the target direction angle.

[0088] Based on the above technical solution, the vehicle control module is used to determine the first preview coordinate based on the first preview time and the lane coordinate, wherein the first preview time is a preset ideal preview time; determine the coordinate deviation value and the expected lateral acceleration based on the first preview coordinate and the lane coordinate, and determine the target steering wheel angle based on the coordinate deviation value and the lateral acceleration.

[0089] Based on the above technical solution, the vehicle control module is used to obtain a proportional coefficient corresponding to the target vehicle, and minimize the objective function value based on the proportional coefficient, the coordinate deviation value and the expected lateral acceleration; determine the preview time corresponding to the minimum objective function value, and determine the target steering wheel angle based on the preview time and the road parameters.

[0090] Based on the above technical solution, the vehicle control module is used to determine the time compensation value according to the road parameters, and determine the target preview time based on the preview time and the time compensation value; and determine the target steering wheel angle according to the target preview time and the coordinate deviation value.

[0091] Based on the above technical solution, the vehicle control module is used to determine the operating condition of the target vehicle based on the vehicle driving parameters, and determine the vehicle angle calculation formula according to the operating condition; determine the feedforward steering wheel angle of the target vehicle under the operating condition based on the vehicle angle calculation formula, the coordinate deviation value and the target preview time, and determine the target steering wheel angle according to the feedforward steering wheel angle.

[0092] Based on the above technical solution, the vehicle control module is used to obtain the lateral acceleration feedback coefficient and actual lateral acceleration corresponding to the target vehicle; determine the feedback compensation steering wheel angle based on the actual lateral acceleration, the lateral acceleration feedback coefficient and the expected lateral acceleration; and determine the target steering wheel angle based on the feedforward steering wheel angle and the feedback compensation steering wheel angle.

[0093] Based on the above technical solution, the vehicle control module is used to send the target direction angle to the electric power steering controller of the target vehicle; the electric power steering controller controls the target vehicle to keep the lane according to the target direction angle.

[0094] The technical solution of the embodiment of the present invention is to collect road image information corresponding to the target vehicle and determine road parameters based on the road image information; determine lane coordinates corresponding to the vehicle coordinate system based on the road parameters, and obtain vehicle driving parameters corresponding to the target vehicle; determine the target direction angle corresponding to the target vehicle based on the vehicle driving parameters and the lane coordinates, and control the target vehicle to maintain lane based on the target direction angle. Based on the above technical solution, the lane keeping system controller is designed by adopting the method of lateral deviation feedforward and lateral acceleration deviation feedback, simulating the thinking process of human driver pre-aiming, realizing effective control of vehicle steering, improving the accuracy and robustness of vehicle lateral control, and thereby improving the flexibility of the lane keeping assist system of intelligent vehicles and the driving safety of drivers.

[0095] The lane keeping device for an autonomous driving vehicle provided in an embodiment of the present invention can execute the lane keeping method for an autonomous driving vehicle provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0096] Example 4

[0097] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0098] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12 and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0099] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0100] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the lane keeping method applied to an autonomous vehicle.

[0101] In some embodiments, the lane keeping method applied to an autonomous vehicle may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the lane keeping method applied to an autonomous vehicle described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the lane keeping method applied to an autonomous vehicle by any other appropriate means (e.g., by means of firmware).

[0102] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0103] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0104] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0105] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0106] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0107] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0108] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0109] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A lane keeping method for an autonomous driving vehicle, characterized in that: include: Collecting road condition image information corresponding to the target vehicle and determining road parameters based on the road condition image information; Determining lane coordinates corresponding to a vehicle coordinate system based on the road parameters, and obtaining vehicle driving parameters corresponding to the target vehicle; A target direction angle corresponding to the target vehicle is determined according to the vehicle driving parameters and the lane coordinates, and the target vehicle is controlled to perform lane keeping based on the target direction angle.

2. The method according to claim 1, characterized in that The determining of a target direction angle corresponding to the target vehicle according to the vehicle driving parameters and the lane coordinates includes: Determining a first preview coordinate according to the first preview time and the lane coordinate, wherein the first preview time is a preset ideal preview time; A coordinate deviation value and an expected lateral acceleration are determined according to the first preview coordinate and the lane coordinate, and the target steering wheel angle is determined according to the coordinate deviation value and the lateral acceleration.

3. The method according to claim 2, characterized in that The determining the target steering wheel angle according to the coordinate deviation value and the lateral acceleration includes: Obtaining a proportional coefficient corresponding to the target vehicle, and minimizing an objective function value according to the proportional coefficient, the coordinate deviation value, and the expected lateral acceleration; A preview time corresponding to a minimum objective function value is determined, and the target steering wheel angle is determined according to the preview time and the road parameters.

4. The method according to claim 3, characterized in that The determining the target steering wheel angle according to the preview time and the road parameters includes: determining a time compensation value according to a road parameter, and determining a target preview time based on the preview time and the time compensation value; The target steering wheel angle is determined according to the target preview time and the coordinate deviation value.

5. The method according to claim 4, characterized in that Determining the target steering wheel angle according to the target preview time and the coordinate deviation value includes: Determining an operating condition of the target vehicle based on vehicle driving parameters, and determining a vehicle turning angle calculation formula according to the operating condition; The feedforward steering wheel angle of the target vehicle under the operating condition is determined based on the vehicle angle calculation formula, the coordinate deviation value, and the target preview time, and the target steering wheel angle is determined according to the feedforward steering wheel angle.

6. The method according to claim 5, characterized in that The determining the target steering wheel angle according to the feedforward steering wheel angle comprises: Obtaining a lateral acceleration feedback coefficient and an actual lateral acceleration corresponding to the target vehicle; determining a feedback-compensated steering wheel angle based on the actual lateral acceleration, the lateral acceleration feedback coefficient, and a desired lateral acceleration; The target steering wheel angle is determined according to the feedforward steering wheel angle and the feedback compensation steering wheel angle.

7. The method according to claim 1, characterized in that The controlling the target vehicle to perform lane keeping based on the target direction angle includes: sending the target direction angle to an electric power steering controller of the target vehicle; The electric power steering controller controls the target vehicle to keep in the lane according to the target direction angle.

8. A lane keeping device for an autonomous driving vehicle, characterized in that: include: A data acquisition module is used to collect road condition image information corresponding to the target vehicle and determine road parameters based on the road condition image information; a data processing module, configured to determine lane coordinates corresponding to a vehicle coordinate system based on the road parameters, and to obtain vehicle driving parameters corresponding to the target vehicle; A vehicle control module is used to determine a target direction angle corresponding to the target vehicle according to the vehicle driving parameters and the lane coordinates, and control the target vehicle to keep the lane based on the target direction angle.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the lane keeping method applied to an autonomous driving vehicle as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which are used to enable a processor to implement the lane keeping method for an autonomous driving vehicle according to any one of claims 1 to 7 when executed.

Images