Automatic parking method and device and vehicle

Abstract

The embodiment of the invention discloses an automatic parking method and device and a vehicle. The method comprises the steps of obtaining state information of a target path point, obtaining a vehicle feed-forward steering wheel angle and an angle change rate of the feed-forward steering wheel angle based on a target curvature, obtaining a feedback steering wheel angle corresponding to a vehicle, obtaining a target steering wheel angle based on the feed-forward steering wheel angle and the feedback steering wheel angle, and outputting the target steering wheel angle. The vehicle course angle of the vehicle is adjusted based on the target steering wheel angle, and then parking is conducted based on the vehicle course angle and the planned parking path. In this way, the feedforward steering wheel angle of the feedforward control system can be obtained through the target curvature, and then the control parameters of the feedback control system are dynamically adjusted through the angle change rate corresponding to the feedforward steering wheel angle. Therefore, the feedback control system is more matched with a controlled object (an entity in which the vehicle transversely moves or a steering system for driving the vehicle to transversely swing), so that the vehicle can be more fit with a planned parking path in an actual parking process.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and more specifically, to an automatic parking method, device, and vehicle. Background Art

[0002] With the continuous development of vehicle technology, automatic parking technology is also gradually improving. In related methods, when a vehicle is automatically parking, it can park based on a generated parking path. However, in related methods, there is still a problem that the vehicle is prone to deviate from the parking path during the parking process. Summary of the Invention

[0003] In view of the above problems, the present application proposes an automatic parking method, device, vehicle and computer program product to improve the above problems.

[0004] In a first aspect, the present application provides an automatic parking method, the method comprising: obtaining status information corresponding to a target path point, the target path point being the path point closest to the vehicle among multiple path points in a planned parking path, the status information comprising a target curvature; obtaining a feedforward steering wheel angle of the vehicle and an angle change rate corresponding to the feedforward steering wheel angle based on the target curvature, the feedforward steering wheel angle being a steering wheel angle calculated by a feedforward control system of the vehicle based on the target curvature; obtaining a feedback steering wheel angle corresponding to the vehicle based on the angle change rate and a feedback control system; obtaining a target steering wheel angle based on the feedforward steering wheel angle and the feedback steering wheel angle, so that the vehicle adjusts its heading angle based on the target steering wheel angle, and then parks based on the vehicle heading angle and the planned parking path.

[0005] In a second aspect, the present application provides an automatic parking device, the device comprising: an information acquisition unit for acquiring status information corresponding to a target path point, the target path point being the path point closest to the vehicle among multiple path points in a planned parking path, the status information comprising a target curvature; a steering wheel angle acquisition unit for obtaining, based on the target curvature, a feedforward steering wheel angle of the vehicle and an angle change rate corresponding to the feedforward steering wheel angle, the feedforward steering wheel angle being a steering wheel angle calculated by a feedforward control system of the vehicle based on the target curvature; obtaining a feedback steering wheel angle corresponding to the vehicle based on the angle change rate and a feedback control system; a parking control unit for obtaining a target steering wheel angle based on the feedforward steering wheel angle and the feedback steering wheel angle, so that the vehicle adjusts its heading angle based on the target steering wheel angle, and then parks based on the vehicle heading angle and the planned parking path.

[0006] In a third aspect, the present application provides a vehicle comprising one or more processors and a memory; one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the above-mentioned method.

[0007] In a fourth aspect, the present application provides a computer program product, comprising a computer program / instruction, which implements the steps of the above method when executed by a processor.

[0008] In a fifth aspect, the present application provides a computer-readable storage medium, in which program code is stored, wherein the above method is executed when the program code is run.

[0009] The present application provides an automatic parking method, apparatus, vehicle, computer program product, and storage medium. After obtaining state information corresponding to a target path point, the method can obtain, based on a target curvature, a feedforward steering wheel angle representing the steering wheel angle calculated by a feedforward control system based on the target curvature and the corresponding angle change rate of the feedforward steering wheel angle. The method also obtains a feedback steering wheel angle corresponding to the vehicle based on the angle change rate and a feedback control system. The method then obtains a target steering wheel angle based on the feedforward steering wheel angle and the feedback steering wheel angle, allowing the vehicle to adjust its heading angle based on the target steering wheel angle and thereby park based on the vehicle heading angle and a planned parking path. The above-described method allows the feedforward steering wheel angle of the feedforward control system to be obtained based on the target curvature, and the control parameters of the feedback control system to be dynamically adjusted based on the angle change rate of the feedforward steering wheel angle, thereby enabling the feedback control system to better coordinate with the controlled object (the entity that moves laterally or the steering system that drives the vehicle's yaw motion), thereby enabling the vehicle to more closely adhere to the planned parking path during actual parking. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A flowchart of an automatic parking method proposed in an embodiment of the present application;

[0012] Figure 2 Shows this application Figure 1 A flowchart of an implementation method proposed in S150;

[0013] Figure 3 Shows this application Figure 2A flowchart of an implementation method proposed in S153;

[0014] Figure 4 A schematic diagram showing a method for obtaining a reference feedback steering wheel angle proposed in this application is shown;

[0015] Figure 5 A schematic diagram showing the correspondence between the lateral distance error and the heading angle error of the front vehicle according to the present application is shown;

[0016] Figure 6 A schematic diagram showing the correspondence between the lateral distance error and the heading angle error of a vehicle after adjustment proposed in this application is shown;

[0017] Figure 7 A schematic diagram of obtaining a feedback steering wheel angle proposed in this application is shown;

[0018] Figure 8 A schematic diagram showing a vehicle starting steering wheel angle before adjustment proposed in the present application is shown;

[0019] Figure 9 A schematic diagram showing an adjusted vehicle starting steering wheel angle proposed in the present application is shown;

[0020] Figure 10 A schematic diagram showing a method for obtaining a target steering wheel angle proposed in this application is shown;

[0021] Figure 11 A flowchart of an automatic parking method proposed in another embodiment of the present application is shown;

[0022] Figure 12 A schematic diagram of a PID control system proposed in this application is shown;

[0023] Figure 13 A flowchart of obtaining a preferred target steering wheel angle proposed in this application is shown;

[0024] Figure 14 A structural block diagram of an automatic parking device proposed in an embodiment of the present application is shown;

[0025] Figure 15 Shown is a structural block diagram of a vehicle proposed in this application. DETAILED DESCRIPTION

[0026] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0027] In an embodiment of the present application, the inventors propose an automatic parking method, apparatus, vehicle, computer program product, and storage medium. After obtaining state information corresponding to a target path point, the method can obtain, based on a target curvature, a feedforward steering wheel angle representing the steering wheel angle calculated by a feedforward control system based on the target curvature and the corresponding angle change rate of the feedforward steering wheel angle. Based on the angle change rate and a feedback control system, the corresponding feedback steering wheel angle of the vehicle is obtained. Based on the feedforward steering wheel angle and the feedback steering wheel angle, a target steering wheel angle is obtained, so that the vehicle adjusts its heading angle based on the target steering wheel angle, and then parks based on the vehicle heading angle and a planned parking path. Through the above-described method, the feedforward steering wheel angle of the feedforward control system can be obtained based on the target curvature, and the control parameters of the feedback control system can be dynamically adjusted based on the angle change rate of the feedforward steering wheel angle, so that the feedback control system and the controlled object (the entity that moves laterally of the vehicle or the steering system that drives the vehicle's yaw motion) are more coordinated, thereby allowing the vehicle to more closely adhere to the planned parking path during actual parking.

[0028] See also Figure 1 , an embodiment of the present application provides an automatic parking method, the method comprising:

[0029] S110: Obtain status information corresponding to the target path point.

[0030] Among them, the target path point can be the path point closest to the vehicle among the multiple path points of the planned parking path. The planned parking path of the vehicle can be the parking path calculated by the path planning module in the vehicle based on the current road conditions of the vehicle. The path point can be a point on the planned parking path, the path point can be a point sampled from the planned parking path, and the path point can be the starting point or end point or inflection point or other point of the planned parking path. The state information corresponding to the target path point may include target position information, target heading angle and target curvature. The target position information can be the coordinate point corresponding to the target path point in a specified coordinate system (such as a vehicle coordinate system, a geodetic coordinate system, a world coordinate system, etc.). The target heading angle can be the heading angle of the vehicle corresponding to the target path point. The target curvature can characterize the degree of curvature of the planned parking path at the target path point.

[0031] As one approach, the vehicle's driving information and multiple path points in the vehicle's planned parking path may be acquired, and a target path point may be obtained based on the multiple path points and position information of the planned parking path.

[0032] Among them, the vehicle's driving information may include the vehicle's position information, vehicle heading angle, vehicle driving direction and vehicle speed. The position information may be the coordinate point corresponding to the vehicle's current position in the same coordinate system as the target position information corresponding to the target path point. The vehicle heading angle may be the angle between the vehicle's center of mass velocity and the horizontal axis in the ground coordinate system. In the embodiment of the present application, the vehicle heading angle may represent the direction of the vehicle's head. The vehicle's driving direction may be forward or backward. In the embodiment of the present application, if the vehicle's driving direction is forward, 1 may be used to represent the vehicle's driving direction. If the vehicle's driving direction is backward, -1 may be used to represent the vehicle's driving direction.

[0033] Optionally, the vehicle's location information, vehicle direction, vehicle heading angle, and vehicle speed can be collected based on a data collection device on the vehicle. In an embodiment of the present application, the data collection device may include a wheel speed sensor, an acceleration sensor, an angular velocity sensor, and the like.

[0034] Optionally, the planned parking path of the vehicle may be processed based on a preset sampling algorithm (eg, equidistant sampling or equal time difference sampling, etc.) to obtain a plurality of path points in the planned parking path of the vehicle.

[0035] As a method, the direction of the corresponding planned parking path can be obtained based on the vehicle's driving direction, and the distances between multiple vehicles and the path points can be obtained based on the vehicle's current position information and the positions of multiple path points along the vehicle's driving direction in the planned parking path, and the path point corresponding to the shortest distance can be used as the target path point.

[0036] As a method, multiple path points can be obtained based on the planned parking path, and the status information corresponding to each path point can be obtained. After the target path point is determined, the status information corresponding to the path point is used as the status information corresponding to the target path point.

[0037] S120: Based on the target curvature, obtain a feedforward steering wheel angle of the vehicle and an angle change rate corresponding to the feedforward steering wheel angle, wherein the feedforward steering wheel angle is a steering wheel angle calculated by a feedforward control system of the vehicle based on the target curvature.

[0038] The feedforward steering wheel angle can be used by the vehicle's feedforward control system to calculate the steering wheel angle required to move from a target path point to the next path point in the planned parking path. The vehicle's feedforward control system can be used to adjust the vehicle's acceleration, braking, or steering operations. For example, the feedforward control system can be a steering system or a torque system. The rate of change of the angle corresponding to the feedforward steering wheel angle can represent the speed of change of the feedforward steering wheel angle.

[0039] As a method, a feedforward steering wheel angle of the vehicle can be obtained based on the target curvature; and the feedforward steering wheel angle of the vehicle is differentiated to obtain the angle change rate.

[0040] Optionally, the vehicle's turning radius can be derived based on the inverse of the target curvature, and the vehicle's feedforward steering wheel angle can be derived based on the vehicle's turning radius and wheelbase. The vehicle's turning radius can be the distance from the steering center to the ground contact point of the front outer steering wheel during vehicle travel. The vehicle's wheelbase can be the distance between the midpoints of two adjacent wheels on the same side of the vehicle and the vehicle's longitudinal symmetry plane. The vehicle's feedforward steering wheel angle can then be calculated using the following formula:

[0041]

[0042]

[0043] Among them, curv can represent the target curvature, R can represent the turning radius of the vehicle, L can represent the wheelbase of the vehicle, δ ff It can represent the feedforward steering wheel angle of the vehicle.

[0044] Optionally, the feedforward steering wheel angle of the vehicle can be differentiated to obtain the angle change rate. Then, the angle change rate can be calculated as follows:

[0045]

[0046] in, may represent the angular change rate of the feedforward steering wheel angle of the vehicle, curv may represent the target curvature, R may represent the turning radius of the vehicle, and L may represent the wheelbase of the vehicle.

[0047] S130: Based on the angle change rate and the feedback control system, obtain a feedback steering wheel angle corresponding to the vehicle.

[0048] The feedback steering wheel angle may be a steering wheel angle calculated by the feedback control system based on an angle change rate. In an embodiment of the present application, the feedback control system may be a PID control system (Proportional-Integral-Derivative Controller).

[0049] As a method, a feedback steering wheel angle corresponding to the vehicle can be obtained based on position information, vehicle heading angle, vehicle speed, target position information, target heading angle, angle change rate and feedback control system.

[0050] Optional, such as Figure 2As shown, the feedback steering wheel angle corresponding to the vehicle can be obtained based on the position information, vehicle heading angle, vehicle speed, target position information, target heading angle, angle change rate and feedback control system, including:

[0051] S131: Obtain a lateral distance error based on the position information and the target position information.

[0052] Among them, the lateral distance error can represent the difference between the lateral distance of the vehicle's current position and the target path point.

[0053] As a method, the lateral distance between the vehicle and the target path point can be calculated based on the coordinate point of the vehicle in the coordinate system (i.e., the position information of the vehicle) and the coordinate point of the target path point in the coordinate system (i.e., the target position information of the target path point), and the lateral distance can be used as the lateral distance error.

[0054] S132: Obtaining a heading angle error based on the vehicle heading angle and the target heading angle.

[0055] The heading angle error may represent the difference between the vehicle heading angle at the current position of the vehicle and the target heading angle at the target path point.

[0056] As one approach, a deviation of a heading angle between the vehicle and the target path point may be calculated based on the vehicle heading angle and the target path point's target heading angle, and the deviation of the heading angle may be used as a heading angle error.

[0057] S133: Obtaining a feedback steering wheel angle corresponding to the vehicle based on the lateral distance error, the heading angle error, the vehicle speed, the angle change rate, and the feedback control system.

[0058] As a way, Figure 3 As shown, based on the lateral distance error, heading angle error, vehicle speed, angle change rate and feedback control system, the corresponding feedback steering wheel angle of the vehicle is obtained, including:

[0059] S1331: Based on the vehicle speed and the angle change rate, obtain the control parameters of the feedback control system.

[0060] The control parameters of the feedback control system may include a proportional parameter, an integral parameter, and a differential parameter. In the embodiment of the present application, kp may be used to represent the proportional parameter, ki may be used to represent the integral parameter, and kd may be used to represent the differential parameter.

[0061] As a method, based on the vehicle speed, the angle change rate and the first preset relationship, the reference control parameter of the feedback control system can be obtained. The first preset relationship indicates that at the same vehicle speed, the greater the angle change rate, the greater the reference control parameter, and also indicates that at the same angle change rate, the greater the vehicle speed, the greater the reference control parameter; based on the vehicle speed and the second preset relationship, the gain parameter corresponding to the reference control parameter can be obtained. The second preset relationship indicates that the smaller the vehicle speed, the smaller the gain parameter; based on the reference control parameter and the gain parameter, the control parameter of the feedback control system can be obtained.

[0062] The reference control parameters may include a proportional reference parameter, an integral reference parameter, and a differential reference parameter. In an embodiment of the present application, kp_1 may be used to represent the proportional reference parameter, ki_1 may be used to represent the integral reference parameter, and kd_1 may be used to represent the differential reference parameter. Gain parameters may include a proportional gain parameter, an integral gain parameter, and a differential gain parameter. In an embodiment of the present application, kp_gain may be used to represent the proportional gain parameter, ki_gain may be used to represent the integral gain parameter, and kd_gain may be used to represent the differential gain parameter.

[0063] Optional, such as Figure 4 As shown, when obtaining the reference control parameter, the absolute value of the angular velocity change rate and the vehicle speed can be used as inputs respectively, and the reference control parameter can be obtained based on a preset first preset relationship to obtain the reference control parameter; when obtaining the gain parameter, the vehicle speed can be used as input, and the gain parameter can be obtained based on a preset second preset relationship to obtain the gain parameter; after obtaining the reference control parameter and the gain parameter, the product of the proportional reference parameter in the reference control parameter and the proportional gain parameter in the gain parameter (i.e., kp_1*kp_gain) can be obtained, and the product of the proportional reference parameter and the proportional gain parameter can be smoothed and filtered to obtain the proportional parameter in the control parameter. The product of the integral reference parameter in the reference control parameter and the integral gain parameter in the gain parameter (i.e., ki_1*ki_gain) can be obtained, and the product of the integral reference parameter and the integral gain parameter can be smoothed and filtered to obtain the integral parameter in the control parameter. The product of the differential reference parameter in the reference control parameter and the differential gain parameter in the gain parameter (i.e., kd_1*kd_gain) can be obtained, and the product of the differential reference parameter and the differential gain parameter can be smoothed and filtered to obtain the differential parameter in the control parameter, and then the control parameter can be obtained based on the proportional parameter, the integral parameter, and the differential parameter. In the embodiment of the present application, a low-pass filter, a sliding average filter, or the like can be used to smooth the product of the proportional reference parameter and the proportional gain parameter.

[0064] S1332: Based on the lateral distance error, the heading angle error and the control parameter, obtain a feedback steering wheel angle corresponding to the vehicle.

[0065] As a method, based on the lateral distance error, heading angle error and control parameters, a reference feedback steering wheel angle corresponding to the vehicle can be obtained; based on the reference feedback steering wheel angle corresponding to the vehicle and the vehicle's driving direction, a feedback steering wheel angle corresponding to the vehicle can be obtained, and the direction of the feedback steering wheel angle is the same as the vehicle's driving direction.

[0066] The reference feedback steering wheel angle may include a first reference feedback steering wheel angle and a second reference feedback steering wheel angle.

[0067] Optional, such as Figure 4 As shown, a first feedback steering wheel angle can be obtained based on the product of the lateral control error and the control parameter; a second feedback steering wheel angle can be obtained based on the product of the heading angle error and the control parameter. After obtaining the first feedback steering wheel angle and the second feedback steering wheel angle, the first feedback steering wheel angle and the second feedback steering wheel angle are superimposed to obtain a reference feedback steering wheel angle.

[0068] In an embodiment of the present application, the first feedback steering wheel angle can be adjusted based on the lateral control error based on the PID control system, and the second feedback steering wheel angle can be adjusted based on the heading angle error based on the PID control system, so that the reference feedback steering wheel angle can be adjusted to obtain the feedback steering wheel angle, and then the target steering wheel angle can be obtained, so that the vehicle can be adjusted based on the target steering wheel angle; and the target steering wheel angle and vehicle speed can be input into the vehicle's lateral tracking error dynamics model, wherein the vehicle's lateral tracking error dynamics model can be used to obtain the lateral distance error and the heading angle error, so that the lateral distance error and the heading angle error can be reduced based on the adjusted target steering wheel angle.

[0069] For example, Figure 5 and Figure 6 As shown, Figure 5 It can be shown as a schematic diagram of the corresponding lateral distance error and heading angle error of the vehicle before adjustment. Figure 6 It can be seen that the lateral distance error and heading angle error of the vehicle after adjustment correspond to the following diagram. Figure 5 and Figure 6 Figure (a) in the figure can represent the number of path segments of the planned parking path (i.e., TopPathID), Figure 5 and Figure 6 Figure (b) in the figure can represent the lateral distance error of the vehicle during parking (i.e., CtrlErrDist). Figure 5 and Figure 6Figure (c) in the figure can represent the heading angle error of the vehicle during parking (i.e., CtrlErrPsi). Figure 5 and Figure 6 Figure (d) in the figure can represent the feedforward steering wheel angle of the vehicle during the parking process (i.e., CtrlSteerAngFF). Figure 5 and Figure 6 Figure (d) in the figure can represent the speed of the vehicle during the parking process (i.e., EstVehSpd). Figure 5 As shown in Figure (b), the maximum value of the vehicle's lateral distance error is 0.051m, which can be obtained by Figure 5 As shown in Figure (c), the maximum heading angle error of the vehicle is 0.043rad (about 2.46°); Figure 6 As shown in Figure (b), the maximum value of the vehicle's lateral distance error is 0.01m, which can be obtained by Figure 6 As shown in Figure (c), the maximum heading angle error of the vehicle is 0.025rad (about 1.43°).

[0070] As a way, Figure 7 As shown, the feedback steering wheel angle corresponding to the vehicle can be obtained based on the product of the reference feedback steering wheel angle and the vehicle's driving direction (forward is 1, backward is -1).

[0071] In an embodiment of the present application, if the vehicle's driving direction is forward at the end of a path, the corresponding feedback steering wheel angle of the vehicle is positive. If the vehicle is immediately changed to reverse at this time, then before the vehicle shifts gears, the vehicle's speed gradually decreases, and the gain parameter can be reduced based on the reduced speed, thereby reducing the feedback steering wheel angle, and the target steering wheel angle can be reduced based on the feedforward steering wheel angle and the reduced feedback steering wheel angle. Therefore, when the vehicle shifts gears, the vehicle heading angle error adjustment amount is close to 0, thereby avoiding the vehicle's steering wheel from turning back. In actual driving conditions, if the vehicle's heading angle error is large at the end of the gear shift, the gain parameter can be proportionally reduced based on the reduced speed, thereby reducing the target steering wheel angle, and then reducing the steering wheel's counter-steering angle, so that the vehicle is more stable when shifting gears, reducing the need for driver intervention.

[0072] For example, Figure 8 and Figure 9 As shown, Figure 8 This is a schematic diagram of the vehicle starting steering wheel before adjustment. Figure 9 It can be a schematic diagram of the vehicle starting steering wheel after adjustment. Figure 8 and Figure 9 Figure (a) in the figure can represent the number of path segments of the planned parking path (i.e., TopPathID), Figure 8 and Figure 9 Figure (b) in the figure can represent the vehicle steering wheel angle (i.e., CtrlOutSteerAngReq), Figure 8 and Figure 9 Figure (c) in the figure can represent the feedback steering wheel angle (i.e. CtrlSteerAngFB), Figure 8 and Figure 9 Figure (d) in the figure can represent the heading angle error of the vehicle during parking (i.e., CtrlErrPsi). Figure 8 and Figure 9 Figure (e) in the figure can represent the speed of the vehicle during the parking process (i.e., EstVehSpd). Figure 8 As shown in Figure (b), before adjusting the vehicle steering wheel angle, when the vehicle starts, the vehicle steering wheel angle needs to be reversed from -54° to 43.9°, and then the vehicle steering wheel angle is reversed from 43.9° to -54°. During this process, the reverse amount of the vehicle steering wheel angle is 97.9°, which can be calculated by Figure 8 As shown in Figure (c), the heading angle error is 0.02rad at this time; and through Figure 9 As shown in Figure (b), after adjusting the vehicle's steering wheel angle, the vehicle does not need to be reversed when starting. Figure 8 As shown in Figure (c), the heading angle error is also 0.02rad.

[0073] S140: Obtaining a target steering wheel angle based on the feedforward steering wheel angle and the feedback steering wheel angle, so that the vehicle adjusts a vehicle heading angle based on the target steering wheel angle, and then parks based on the vehicle heading angle and the planned parking path.

[0074] The target steering wheel angle may be the angle at which the vehicle steering wheel actually needs to be rotated.

[0075] As a method, during the actual parking process, the vehicle can superimpose the feedforward steering wheel angle and the feedback steering wheel angle to obtain the vehicle's current target steering wheel angle, so that the vehicle can adjust the vehicle heading angle based on the current target steering wheel angle, and thus make the vehicle more in line with the planned parking path; after the vehicle moves based on the current target direction angle, it continues to obtain the next target path point based on the vehicle's driving information, and obtains the next target steering wheel angle based on the vehicle's driving information and the status information of the next target path point, and then the vehicle can be moved based on the next target steering wheel angle until the vehicle completes parking according to the planned parking path.

[0076] In the embodiments of this application, Figure 10As shown, the feedforward steering wheel angle can be obtained based on the target curvature of the target path point, and the angle change rate can be obtained based on the feedforward steering wheel angle, so as to obtain the control parameters of the PID control system based on the angle change rate, the vehicle speed, the first preset relationship and the second preset relationship; and the lateral distance error and the heading angle error can be obtained based on the state information of the target path point and the driving information of the vehicle. Thereafter, the feedback steering wheel angle can be obtained based on the control parameters, the lateral distance error and the heading angle error. Finally, the feedforward steering wheel angle and the feedback steering wheel angle are superimposed to obtain the target steering wheel angle.

[0077] This embodiment provides an automatic parking method. After obtaining state information corresponding to a target path point, the method can obtain, based on a target curvature, a feedforward steering wheel angle representing the steering wheel angle calculated by a feedforward control system based on the target curvature, and the corresponding angle change rate of the feedforward steering wheel angle. The method also obtains the corresponding feedback steering wheel angle of the vehicle based on the angle change rate and a feedback control system. The method then obtains a target steering wheel angle based on the feedforward steering wheel angle and the feedback steering wheel angle, allowing the vehicle to adjust its heading angle based on the target steering wheel angle, and then to park based on the vehicle heading angle and a planned parking path. This method allows the feedforward steering wheel angle of the feedforward control system to be obtained based on the target curvature, and then dynamically adjusts the control parameters of the feedback control system based on the angle change rate of the feedforward steering wheel angle, thereby improving the coordination between the feedback control system and the controlled object (the lateral motion of the vehicle or the steering system that drives the yaw motion of the vehicle), thereby ensuring that the vehicle adheres more closely to the planned parking path during actual parking.

[0078] See also Figure 11 , an embodiment of the present application provides an automatic parking method, the method comprising:

[0079] S210: Acquire status information corresponding to a target path point, where the target path point is the path point closest to the vehicle among multiple path points in the planned parking path, and the status information includes a target curvature.

[0080] S220: Based on the target curvature, obtain the feedforward steering wheel angle of the vehicle and the angle change rate corresponding to the feedforward steering wheel angle, where the feedforward steering wheel angle is the steering wheel angle calculated by the feedforward control system of the vehicle based on the target curvature.

[0081] S230: Based on the position information, the vehicle heading angle, the vehicle speed, the target position information, the target heading angle, the angle change rate and the feedback control system, obtain a feedback steering wheel angle corresponding to the vehicle.

[0082] As a method, a feedback steering wheel angle corresponding to the vehicle can be obtained based on position information, vehicle heading angle, vehicle speed, target position information, target heading angle, angle change rate and feedback control system.

[0083] In an embodiment of the present application, a feedforward control system and a PID control system can be used to jointly control the steering wheel angle of the vehicle so that the vehicle more closely follows the planned parking path. The feedforward control system can calculate the feedforward steering wheel angle based on the vehicle's driving information and the state information of the target path points in the planned parking path. Furthermore, the PID control system can continuously adjust the control parameters within the PID control system based on the current vehicle's driving information and the feedforward steering wheel angle, so that the feedback steering wheel angle output by the PID control system adjusts the feedforward steering wheel angle to output the final vehicle steering wheel angle. The vehicle can then be controlled based on the final steering wheel angle to achieve a more precise control effect, thereby improving the vehicle's tracking accuracy for the planned parking path and increasing the success rate of parking.

[0084] It should be noted that because the performance of a PID control system is affected by many factors, the control parameters of the PID control system need to be adjusted according to the system characteristics. This may lead to the following question: how to adjust the control parameters of the PID control system to achieve better control results? The inventors' long-term experiments have shown that the control parameters of the PID control system can be adjusted based on the vehicle's feedforward steering wheel angle change rate.

[0085] The reason is that, see Figure 12 The PID control system in the feedforward control system and the PID control system is a closed-loop control system. The closed-loop control system can be composed of a PID control system, an output value, and a lateral tracking error (including a lateral distance error and a heading angle error). The lateral tracking error can be the controlled object of the closed-loop control system, and the output value of the lateral tracking error is the output value of the closed-loop control system. The actual output value of the lateral tracking error affects the input of the PID control system. After the reference value output by the feedforward control system is given to the closed-loop control system, the reference value of the feedforward control system and the actual output value are compared to obtain the error between the two. The error is then input into the PID control system. After computational processing, the PID control system outputs a control variable, thereby obtaining the output of the lateral tracking error. It can be seen from this that because the performance and stability of the PID control system directly affect the output value of the lateral tracking error, if the dynamic characteristics between the lateral tracking error and the PID control system are unstable, the output error will increase, thereby affecting the control effect. Therefore, the lateral tracking error needs to remain relatively stable with the PID control system.

[0086] Furthermore, in practical applications, to better understand and track lateral tracking error, a dynamic model of the vehicle's lateral tracking error can be established. This dynamic model can be used to systematically analyze the dynamic characteristics of the lateral tracking error. In the dynamic model of the lateral tracking error, the input variables can be vehicle speed and front wheel angle (in the Ackerman steering model, the front wheel angle is equal to the vehicle's steering wheel angle). Based on the vehicle speed and front wheel angle, the lateral tracking error (including lateral distance error and heading angle error) can be calculated. By analyzing the dynamic model of the lateral tracking error, the transfer function of the lateral tracking error can be derived. Based on the transfer function of the lateral tracking error, the influencing factor of the lateral tracking error can be determined, and the control parameters of the PID control system can be adjusted based on the influencing factor of the lateral tracking error. Since, in practical applications, the dynamic model of the lateral tracking error is related to the angle change rate of the feedforward steering wheel, the influencing factor of the lateral tracking error can be the angle change rate, and the lateral tracking error needs to remain relatively stable with the PID control system. Therefore, the control parameters of the PID control system can be adjusted based on the angle change rate.

[0087] Among them, the dynamic model of the vehicle's lateral tracking error can be:

[0088]

[0089] Among them, y can represent the lateral distance error, It can express the rate of change of lateral distance error, It can express the rate of change of the lateral distance error rate of change, Can represent the heading angle, It can represent the heading angle error, It can express the rate of change of heading angle error. C f It can represent the front wheel cornering stiffness, l f It can represent the wheelbase of the front wheel corresponding to the center of mass, C r It can represent the rear wheel cornering stiffness, l r It can represent the wheelbase of the center of mass of the rear wheels, m can represent the weight of the vehicle, v x It can represent the longitudinal velocity of the vehicle, I z It can represent the vehicle's moment of inertia, δ f It can represent the front wheel angle.

[0090] As a method, the vehicle's lateral tracking error dynamic model can be rewritten as a state-space equation of the lateral tracking error. After obtaining the state-space equation of the lateral tracking error, the state-space equation of the lateral tracking error can be Laplace transformed to obtain the transfer function of the lateral tracking error.

[0091] Among them, the state space equation of the vehicle's lateral tracking error can be:

[0092]

[0093] Among them, A can be expressed as x can represent B can represent u can represent δ f (Front wheel angle).

[0094] Among them, the transfer function of the lateral tracking error can be:

[0095]

[0096] Wherein, G(S) can represent the lateral tracking error, X(S) can represent the state quantity of the lateral tracking error (i.e., the lateral distance error and the heading angle error), U(S) can represent the control command output (i.e., the output value corresponding to the lateral distance error and the heading angle error), S can represent the variable of the Laplace transform, and I can represent the unit matrix.

[0097] Optionally, after converting the state space direction of the lateral tracking error into a transfer function of the lateral tracking error, it can be known from the transfer function that the lateral tracking error is related to the matrix A and the matrix B, and it can be known from the expression of the matrix A that the matrix A is related to the vehicle longitudinal velocity v x Related.

[0098] Optionally, the longitudinal velocity of the vehicle may be obtained based on the vehicle heading angle, wherein the longitudinal velocity calculation formula of the vehicle may be:

[0099]

[0100] Among them, v x It can represent the longitudinal velocity of the vehicle, v can represent the tangential velocity of the vehicle, Can represent the heading angle.

[0101] Optionally, the vehicle heading angle may be obtained based on the target curvature, wherein the calculation formula of the vehicle heading angle may be:

[0102]

[0103] in, It can represent the heading angle, v can represent the tangential speed of the vehicle, curv can represent the target curvature, and t can represent time.

[0104] Optionally, a calculation formula for the target curvature may be obtained based on a calculation formula for the angle change rate, wherein the calculation formula for the target curvature may be:

[0105]

[0106] Among them, curv can represent the target curvature, L can represent the wheelbase of the vehicle, It can represent the rate of change of the vehicle's feedforward steering wheel angle.

[0107] In the embodiment of the present application, in the Laplace domain, the lateral tracking error can be determined based on the matrix A and the matrix B, and it can be known based on the expression of the matrix A that the matrix A is related to the longitudinal velocity v of the vehicle. x Related, and based on the vehicle's longitudinal velocity v x The calculation formula shows that the vehicle longitudinal speed v x Angle with vehicle heading Related. And based on the vehicle heading angle The calculation formula shows that the vehicle heading angle It is related to the target curvature. Based on the calculation formula of the target curvature, it can be known that the target curvature and the angle change rate are related. Therefore, the influencing factor of the lateral tracking error can be the angle change rate So the angle change rate can be When the angle changes, the lateral tracking error will change with the rate of change of the angle changes.

[0108] In summary, since the lateral tracking error can change based on the change of the angle change rate, and in the derivation process of the feedforward control system and the PID control system, the lateral tracking error needs to be stable with the PID control system because the angle change rate If the angular rate of change changes, the lateral tracking error will also change accordingly. Therefore, the control parameters of the PID control system must also be adjusted accordingly to maintain the stability of the entire control system. Therefore, the PID control system's control parameters can be adjusted by monitoring the angle change rate to better adapt to the dynamic changes of the feedforward and PID control systems. Based on the angle change rate and the feedback control system, the corresponding feedback steering wheel angle of the vehicle can be obtained. When the angle change rate is large, the feedforward and PID control systems are more sensitive to external interference and parameter changes, necessitating an increase in the proportional coefficient of the PID control system to improve system response speed and reduce error. When the angle change rate is small, the proportional coefficient of the PID control system can be appropriately reduced to avoid overshoot and oscillation. Furthermore, the integral and differential coefficients can also be adjusted based on the angle change rate to optimize the static and dynamic performance of the system.

[0109] S240: Obtaining a target steering wheel angle based on the feedforward steering wheel angle and the feedback steering wheel angle, so that the vehicle adjusts the vehicle heading angle based on the target steering wheel angle, and then parks based on the vehicle heading angle and the planned parking path.

[0110] This embodiment provides an automatic parking method that, through the aforementioned method, allows the feedforward steering wheel angle of the feedforward control system to be derived from the target curvature. The control parameters of the feedback control system are then dynamically adjusted based on the angular change rate corresponding to the feedforward steering wheel angle. This allows the feedback control system to better coordinate with the controlled object (the entity causing the vehicle's lateral motion or the steering system causing the vehicle's yaw motion), thereby ensuring that the vehicle adheres more closely to the planned parking path during actual parking. Furthermore, this embodiment rationally deduces that the control parameters of the PID control system can be adjusted based on the angular change rate corresponding to the feedforward steering wheel angle, thereby better adapting to the dynamic changes of the feedforward and PID control systems and thereby improving the control effectiveness of both the feedforward and PID control systems.

[0111] In order to better understand the solutions in the embodiments of the present application, the process of a preferred implementation scheme is introduced below.

[0112] See also Figure 13 Based on step S1, the target path point and the status information corresponding to the target path point can be obtained, the feedforward steering wheel angle corresponding to the target path point can be calculated based on step S2, and the angle change rate corresponding to the feedforward steering wheel angle can be obtained based on step S4; then, step S5 can obtain the reference control parameter based on the vehicle speed, the angle change rate and the first preset relationship, and step S6 can obtain the gain parameter based on the vehicle speed and the second preset relationship. After obtaining the reference control parameter and the gain parameter, the control parameter can be obtained based on step S7; before obtaining the feedback steering wheel angle, the lateral distance error and the heading angle error can be obtained based on step S3, and after obtaining the lateral distance error and the heading angle error, the feedback steering wheel angle can be obtained through step S8 based on the obtained control parameters, and finally, the target steering wheel angle can be obtained through step S9 based on the feedback reverse wheel angle and the feedforward steering wheel angle.

[0113] See also Figure 14 The present application provides an automatic parking device 800, the device 800 comprising:

[0114] The information acquisition unit 810 is configured to acquire status information corresponding to a target path point, where the target path point is the path point closest to the vehicle among multiple path points in the planned parking path, and the status information includes a target curvature.

[0115] The steering wheel angle acquisition unit 820 is used to obtain the feedforward steering wheel angle of the vehicle and the angle change rate corresponding to the feedforward steering wheel angle based on the target curvature. The feedforward steering wheel angle is the steering wheel angle calculated by the feedforward control system of the vehicle based on the target curvature; based on the angle change rate and the feedback control system, the corresponding feedback steering wheel angle of the vehicle is obtained.

[0116] The parking control unit 830 is configured to obtain a target steering wheel angle based on the feedforward steering wheel angle and the feedback steering wheel angle, so that the vehicle adjusts its heading angle based on the target steering wheel angle, and then parks based on the vehicle heading angle and the planned parking path.

[0117] As a method, the steering wheel angle acquisition unit 820 is specifically used to obtain the feedback steering wheel angle corresponding to the vehicle based on the position information, the vehicle heading angle, the vehicle speed, the target position information, the target heading angle, the angle change rate and the feedback control system.

[0118] Optionally, the steering wheel angle acquisition unit 820 is specifically used to obtain a lateral distance error based on the position information and the target position information; obtain a heading angle error based on the vehicle heading angle and the target heading angle; and obtain a feedback steering wheel angle corresponding to the vehicle based on the lateral distance error, the heading angle error, the vehicle speed, the angle change rate and the feedback control system.

[0119] Optionally, the steering wheel angle acquisition unit 820 is specifically used to obtain the control parameters of the feedback control system based on the vehicle speed and the angle change rate; and obtain the feedback steering wheel angle corresponding to the vehicle based on the lateral distance error, the heading angle error and the control parameters.

[0120] Optionally, the steering wheel angle acquisition unit 820 is specifically used to obtain a reference control parameter of the feedback control system based on the vehicle speed, the angle change rate and a first preset relationship, the first preset relationship being characterized in that at the same vehicle speed, the greater the angle change rate, the greater the reference control parameter, and being characterized in that at the same angle change rate, the greater the vehicle speed, the greater the reference control parameter; based on the vehicle speed and a second preset relationship, a gain parameter corresponding to the reference control parameter is obtained, the second preset relationship being characterized in that the smaller the vehicle speed, the smaller the gain parameter; based on the reference control parameter and the gain parameter, the control parameter of the feedback control system is obtained.

[0121] As a method, the steering wheel angle acquisition unit 820 is specifically used to obtain a reference feedback steering wheel angle corresponding to the vehicle based on the lateral distance error, the heading angle error and the control parameter; and obtain a feedback steering wheel angle corresponding to the vehicle based on the reference feedback steering wheel angle corresponding to the vehicle and the vehicle's driving direction, wherein the direction of the feedback steering wheel angle is the same as the vehicle's driving direction.

[0122] As one approach, the steering wheel angle acquisition unit 820 is specifically configured to obtain the feedforward steering wheel angle of the vehicle based on the target curvature; and to derive the feedforward steering wheel angle of the vehicle to obtain the angle change rate.

[0123] The following will be combined Figure 15 A vehicle provided in this application is described.

[0124] See also Figure 15 Based on the aforementioned automatic parking method and apparatus, embodiments of the present application further provide another vehicle 100 capable of executing the aforementioned automatic parking method. Vehicle 100 includes a processor 102, a memory 104, and a data acquisition device 106. The memory 104 stores a program capable of executing the aforementioned embodiments, and the processor 102 can execute the program stored in the memory 104.

[0125] The processor 102 may include one or more processing cores. The processor 102 utilizes various interfaces and circuits to connect various components within the vehicle 100. It executes instructions, programs, code sets, or instruction sets stored in the memory 104 and accesses data stored in the memory 104 to perform various functions and process data for the vehicle 100. Optionally, the processor 102 may be implemented in the form of at least one of a network processor (NPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 102 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; the NPU is responsible for processing multimedia data such as video and images; and the modem is responsible for wireless communication. It is understandable that the above-mentioned modem may not be integrated into the processor 102, but may be implemented separately through a communication chip.

[0126] The memory 104 may include random access memory (RAM), read-only memory (ROM), and double data rate synchronous dynamic random access memory (DDR). The memory 104 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 104 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the various method embodiments described below, etc. The data storage area may also store data created by the vehicle 100 during use (such as a phone book, audio and video data, chat history data, etc.).

[0127] The data acquisition device 106 is used to collect driving information of the vehicle 100. Optionally, the data acquisition device 106 may include a wheel speed sensor, an acceleration sensor, an angular velocity sensor, and the like.

[0128] An embodiment of the present application provides a computer program product, which may include a computer program / instruction, and which, when executed by a processor, implements the method described in the above method embodiment.

[0129] An embodiment of the present application provides a computer-readable storage medium having program code stored therein, wherein the program code can be invoked by a processor to execute the method described in the above method embodiment.

[0130] The computer-readable storage medium can be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read-Only Memory), an EPROM, a hard disk, or a ROM. Alternatively, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program codes for executing any of the method steps described above. These program codes can be read from or written to one or more computer program products. The program codes can be compressed, for example, in an appropriate form.

[0131] In summary, the present application provides an automatic parking method, apparatus, vehicle, computer program product, and storage medium. After obtaining state information corresponding to a target path point, the method can obtain, based on a target curvature, a feedforward steering wheel angle representing the steering wheel angle calculated by a feedforward control system based on the target curvature and the corresponding angle change rate of the feedforward steering wheel angle. Based on the angle change rate and a feedback control system, the method can obtain a corresponding feedback steering wheel angle for the vehicle. Based on the feedforward steering wheel angle and the feedback steering wheel angle, the method can obtain a target steering wheel angle, so that the vehicle adjusts its heading angle based on the target steering wheel angle, and then parks based on the vehicle heading angle and a planned parking path. Through the above-described method, the feedforward steering wheel angle of the feedforward control system can be obtained based on the target curvature, and the control parameters of the feedback control system can be dynamically adjusted based on the angle change rate of the feedforward steering wheel angle, so that the feedback control system and the controlled object (the entity that moves laterally or the steering system that drives the vehicle's yaw motion) are more coordinated, thereby allowing the vehicle to more closely adhere to the planned parking path during actual parking.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An automatic parking method, characterized in that: The method comprises: Obtaining state information corresponding to a target path point, the target path point being the path point closest to the vehicle among multiple path points in the planned parking path, the state information including a target curvature; Based on the target curvature, obtaining a feedforward steering wheel angle of the vehicle and an angle change rate corresponding to the feedforward steering wheel angle, wherein the feedforward steering wheel angle is a steering wheel angle calculated by a feedforward control system of the vehicle based on the target curvature; Based on the angle change rate and the feedback control system, obtaining a feedback steering wheel angle corresponding to the vehicle; A target steering wheel angle is obtained based on the feedforward steering wheel angle and the feedback steering wheel angle, so that the vehicle adjusts a vehicle heading angle based on the target steering wheel angle, and then parks based on the vehicle heading angle and the planned parking path.

2. The method according to claim 1, characterized in that The vehicle has corresponding driving information, the driving information including position information, vehicle speed, and the vehicle heading angle, the state information also including target position information and target heading angle, and obtaining a feedback steering wheel angle corresponding to the vehicle based on the angle change rate and the feedback control system, including: A feedback steering wheel angle corresponding to the vehicle is obtained based on the position information, the vehicle heading angle, the vehicle speed, the target position information, the target heading angle, the angle change rate and a feedback control system.

3. The method according to claim 2, characterized in that The obtaining of a feedback steering wheel angle corresponding to the vehicle based on the position information, the vehicle heading angle, the vehicle speed, the target position information, the target heading angle, the angle change rate, and a feedback control system includes: Obtaining a lateral distance error based on the position information and the target position information; Obtaining a heading angle error based on the vehicle heading angle and the target heading angle; A feedback steering wheel angle corresponding to the vehicle is obtained based on the lateral distance error, the heading angle error, the vehicle speed, the angle change rate and the feedback control system.

4. The method according to claim 3, characterized in that The obtaining of a feedback steering wheel angle corresponding to the vehicle based on the lateral distance error, the heading angle error, the vehicle speed, the angle change rate, and the feedback control system includes: obtaining a control parameter of the feedback control system based on the vehicle speed and the angle change rate; A feedback steering wheel angle corresponding to the vehicle is obtained based on the lateral distance error, the heading angle error, and the control parameter.

5. The method according to claim 4, characterized in that The obtaining of control parameters of the feedback control system based on the vehicle speed, the angle change rate, and the feedback control system includes: obtaining a reference control parameter of the feedback control system based on the vehicle speed, the angle change rate, and a first preset relationship, wherein the first preset relationship indicates that, at the same vehicle speed, the greater the angle change rate, the greater the reference control parameter, and also indicates that, at the same angle change rate, the greater the vehicle speed, the greater the reference control parameter; obtaining a gain parameter corresponding to the reference control parameter based on the vehicle speed and a second preset relationship, wherein the second preset relationship indicates that the smaller the vehicle speed, the smaller the gain parameter; Based on the reference control parameter and the gain parameter, a control parameter of the feedback control system is obtained.

6. The method according to claim 4, characterized in that The driving information further includes a vehicle driving direction, and obtaining a feedback steering wheel angle corresponding to the vehicle based on the lateral distance error, the heading angle error, and the control parameter includes: Obtaining a reference feedback steering wheel angle corresponding to the vehicle based on the lateral distance error, the heading angle error, and the control parameter; A feedback steering wheel angle corresponding to the vehicle is obtained based on a reference feedback steering wheel angle corresponding to the vehicle and the vehicle's driving direction, wherein the direction of the feedback steering wheel angle is the same as the vehicle's driving direction.

7. The method according to claim 1, characterized in that The obtaining, based on the target curvature, a feedforward steering wheel angle of the vehicle and an angle change rate corresponding to the feedforward steering wheel angle includes: obtaining a feedforward steering wheel angle of the vehicle based on the target curvature; The angle change rate is obtained by differentiating the feedforward steering wheel angle of the vehicle.

8. An automatic parking device, characterized in that: The device comprises: an information acquisition unit, configured to acquire state information corresponding to a target path point, the target path point being the path point closest to the vehicle among multiple path points in the planned parking path, the state information including a target curvature; a steering wheel angle acquisition unit, configured to obtain a feedforward steering wheel angle of the vehicle and an angle change rate corresponding to the feedforward steering wheel angle based on the target curvature, wherein the feedforward steering wheel angle is a steering wheel angle calculated by a feedforward control system of the vehicle based on the target curvature; and obtain a feedback steering wheel angle corresponding to the vehicle based on the angle change rate and a feedback control system; A parking control unit is configured to obtain a target steering wheel angle based on the feedforward steering wheel angle and the feedback steering wheel angle, so that the vehicle adjusts a vehicle heading angle based on the target steering wheel angle, and then parks based on the vehicle heading angle and the planned parking path.

9. A vehicle, characterized in that: including one or more processors and memory; One or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores program code, wherein when the program code is run, the method according to any one of claims 1 to 7 is executed.

Images