Automatic parking control method and device, electronic equipment and storage medium

Abstract

The application discloses an automatic parking control method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a planned parking track of a vehicle, and predicting first state information representing a driving state of the vehicle; wherein the planned parking track comprises a plurality of planned track points, and second state information of the planned track points at least comprises a second position and a second heading angle of the planned track points; selecting a planned track point on the planned parking track as a reference track point based on the first state information and the second state information of each planned track point; measuring a tracking error between the first state information and the second state information of the reference track point; and obtaining a control parameter for automatic parking based on the tracking error. The above scheme can improve the accuracy of the vehicle tracking the parking track during automatic parking, thereby improving the parking effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to an automatic parking control method and device, an electronic device and a storage medium. BACKGROUND

[0002] Automatic parking refers to obtaining a vehicle position and environment information by a computer, planning a parking trajectory based on the environment information, and enabling the vehicle to enter a parking space along the parking trajectory.

[0003] In an automatic parking system, an automatic parking control algorithm usually has a lag, and the vehicle has inertia. When the vehicle is controlled to automatically park, it is difficult to ensure that the vehicle accurately travels along the parking trajectory, resulting in poor parking effect.

[0004] Therefore, how to improve the accuracy of the vehicle tracking the parking trajectory during automatic parking to improve the parking effect is a problem to be solved at present. SUMMARY

[0005] The present application provides at least an automatic parking control method and device, an electronic device and a storage medium, which can improve the accuracy of the vehicle tracking the parking trajectory during automatic parking to improve the parking effect.

[0006] The first aspect of the present application provides an automatic parking control method, comprising: obtaining a planned parking trajectory of a vehicle, and predicting first state information representing a self-vehicle driving state of the vehicle; wherein the planned parking trajectory comprises a plurality of planned trajectory points, and second state information of the planned trajectory points comprises at least a second position and a second heading angle of the planned trajectory points; selecting a planned trajectory point as a reference trajectory point on the planned parking trajectory based on the first state information and the second state information of each planned trajectory point; measuring a tracking error between the first state information and the second state information of the reference trajectory point; and analyzing a control parameter for automatic parking based on the tracking error; wherein the control parameter comprises at least one of a front wheel steering angle and a steering wheel steering angle.

[0007] Therefore, by predicting the first state information of the self-vehicle driving state of the vehicle and obtaining the reference point based on the first state information, the tracking error is obtained based on the reference point and the first state information, and the automatic parking control is performed based on the tracking error. The vehicle can be controlled in advance based on the predicted first state information of the vehicle, thereby compensating for the delay caused by the lag of the automatic parking control algorithm and the inertia of the vehicle. The accuracy of the vehicle tracking the parking trajectory during automatic parking can be improved to improve the parking effect.

[0008] The second aspect of the present application provides an automatic parking control device, comprising: an acquisition module configured to acquire a planned parking trajectory of a vehicle and predict first state information representing a self-driving state of the vehicle; wherein the planned parking trajectory comprises a plurality of planned trajectory points, and second state information of the planned trajectory points comprises at least a second position and a second heading angle of the planned trajectory points; a selection module configured to select a planned trajectory point on the planned parking trajectory as a reference trajectory point based on the first state information and the second state information of each planned trajectory point; an error calculation module configured to measure a tracking error between the first state information and the second state information of the reference trajectory point; and a control parameter calculation module configured to analyze and obtain a control parameter for automatic parking based on the tracking error; wherein the control parameter comprises at least one of a front wheel steering angle and a steering wheel steering angle.

[0009] The third aspect of the present application provides an electronic device comprising a memory and a processor coupled to each other, wherein the processor is configured to execute program instructions stored in the memory to implement the automatic parking control method of the first aspect.

[0010] The fourth aspect of the present application provides a computer-readable storage medium having program instructions stored thereon, wherein the program instructions are executed by a processor to implement the automatic parking control method of the first aspect.

[0011] The above scheme can predict the first state information of the self-driving state of the vehicle, obtain a reference point based on the first state information, obtain a tracking error based on the reference point and the first state information, and perform automatic parking control based on the tracking error. The vehicle can be controlled in advance based on the predicted first state information of the vehicle, thereby compensating for the hysteresis of the automatic parking control algorithm and the delay caused by the inertia of the vehicle, improving the accuracy of the vehicle tracking the parking trajectory during automatic parking, and improving the parking effect.

[0012] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, but not limiting the present application. BRIEF DESCRIPTION OF DRAWINGS

[0013] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the technical solutions of the present application.

[0014] Figure 1 is a flowchart of an embodiment of the automatic parking control method of the present application;

[0015] Figure 2 is a flowchart of another embodiment of the automatic parking control method of the present application;

[0016] Figure 3is a flowchart of another embodiment of the automatic parking control method of the present application;

[0017] Figure 4 is a schematic diagram of a reference point of another embodiment of the automatic parking control method of the present application;

[0018] Figure 5 is a flowchart of another embodiment of the automatic parking control method of the present application;

[0019] Figure 6 is a flowchart of another embodiment of the automatic parking control method of the present application;

[0020] Figure 7 is a schematic diagram of a framework of an embodiment of the automatic parking control device of the present application;

[0021] Figure 8 is a schematic diagram of a framework of an embodiment of the electronic device of the present application;

[0022] Figure 9 is a schematic diagram of a framework of an embodiment of the computer readable storage medium of the present application. DETAILED DESCRIPTION

[0023] The schemes of the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0024] In the following description, specific details are set forth in order to provide a thorough understanding of the present application. However, persons having ordinary skill in the art will appreciate that the present application can be practiced without the specific details.

[0025] The term "and / or" herein merely describes an association relationship of associated objects, and means that there can be three relationships, for example, A and / or B can mean that there are three cases of A alone, A and B together, and B alone. In addition, the character " / " herein generally means that the front and rear associated objects are in an "or" relationship. In addition, "multiple" herein means two or more than two. In addition, the term "at least one" herein means any one of multiple or any combination of at least two of multiple, for example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0026] Please refer to Figure 1 , Figure 1 is a flowchart of an embodiment of the automatic parking control method of the present application. Specifically, it can include the following steps:

[0027] Step S11: obtaining a planned parking trajectory of the vehicle, and predicting first state information representing a driving state of the vehicle; wherein the planned parking trajectory comprises a plurality of planned trajectory points, and second state information of the planned trajectory points comprises at least a second position and a second heading angle of the planned trajectory points.

[0028] In the embodiments of the present disclosure, the execution subject of the automatic parking control method can include at least one of a vehicle-mounted computer, a driving controller, etc., and can also include at least one of a mobile terminal device such as a mobile phone, a portable computer, etc. In a specific implementation scenario, the planned parking trajectory can be updated in real time as the parking environment of the vehicle changes, and then the automatic parking control method controls the vehicle in real time based on the real-time updated planned parking trajectory to ensure smooth automatic parking; for example, in an automatic parking scenario, when the vehicle is automatically parked, a parking space next to the vehicle has a vehicle entering or leaving, the planned parking trajectory can be updated in real time to avoid surrounding vehicles.

[0029] In a specific implementation scenario, the planned parking trajectory can include 201 discrete planned trajectory points, and the automatic parking control method of the present application can control the vehicle to travel to the planned trajectory points in sequence until the last planned trajectory point is reached; in other implementation scenarios, the number of planned trajectory points can also be other values, such as 400, 249, 159, etc., which are not limited in the present application. It should be noted that the second position and the second heading angle of the planned trajectory point represent the position and the heading angle of the vehicle when the vehicle travels to the planned trajectory point.

[0030] In the embodiments of the present disclosure, the automatic parking control of the vehicle is performed through a lateral control technology, that is, the speed of the vehicle is kept unchanged, and only the front wheel steering angle of the vehicle is controlled to control the travel trajectory of the vehicle, and the front wheel steering angle of the vehicle can be controlled by controlling the steering wheel steering angle of the vehicle.

[0031] In the embodiments of the present disclosure, the first state information includes a first position and a first heading angle of the vehicle; the first position represents a position of the vehicle after traveling for a time Δt while keeping the current speed and the current heading angle unchanged, and the time Δt is a prediction time which can be set according to actual conditions and is not limited in the present application; the first heading angle represents a heading angle of the current vehicle after traveling for a time Δt while keeping the current speed and the current front wheel steering angle unchanged; please refer to Figure 2 , Figure 2 is a flowchart of another embodiment of the automatic parking control method of the present application, and specifically, the first state information representing the driving state of the vehicle in step S11 can include:

[0032] Step S21: obtaining an axle distance of the vehicle and third state information representing a current driving state of the vehicle; wherein the third state information can include a current speed, a current position, a current front wheel steering angle, and a current heading angle.

[0033] Step S22: predicting a driving position of the vehicle after driving for the prediction time length at the current speed as the first position based on the current position and the current heading angle, and predicting a heading angle of the vehicle after driving for the prediction time length at the current speed and the current front wheel steering angle as the first heading angle based on the current heading angle and the wheelbase of the vehicle.

[0034] In one specific implementation scenario, the first position and the first heading angle can be calculated by the following formula:

[0035]

[0036] wherein v t is the current speed of the vehicle, which is considered constant during the entire automatic parking process since the vehicle is controlled in the lateral direction in the possible implementation examples; x t+1 , y t+1 are the horizontal coordinate and the vertical coordinate of the first position of the vehicle in the natural coordinate system, respectively; θ t represents the current heading angle, θ t+1 represents the first heading angle, δ t represents the current front wheel steering angle of the vehicle, and L represents the wheelbase of the vehicle.

[0037] Step S12: selecting a planning track point on the planning parking track as the reference track point based on the first state information and the second state information of each planning track point.

[0038] Please refer to Figure 3 , Figure 3 is a flowchart of another embodiment of the automatic parking control method of the present application. Specifically, the above step S12 can include:

[0039] Step S31: obtaining the Euclidean distance corresponding to the planning track point based on the first position and the second position of the planning track point.

[0040] In one specific implementation scenario, the Euclidean distances between all the planning track points and the first position of the vehicle can be obtained by traversing all the planning track points.

[0041] Step S32: selecting the planning track point with the minimum Euclidean distance as the matching track point.

[0042] In one specific implementation scenario, after obtaining the Euclidean distances between all the planning track points and the first position of the vehicle by traversing all the planning track points, the planning track point with the minimum Euclidean distance is selected as the matching track point.

[0043] Step S33: determining the reference track point on the planning parking track based on the first state information and the second state information of the matching track point.

[0044] In one specific implementation scenario, before determining the reference trajectory point by matching the trajectory points, it is necessary to determine the projection trajectory point of the matching trajectory point; the matching trajectory point, the projection trajectory point and the reference trajectory point are all one point in the planning trajectory points, and one of the obtained projection trajectory points is taken as the reference trajectory point. Specifically, please refer to Figure 4 , Figure 4 is a schematic diagram of the reference point of another embodiment of the automatic parking control method of the present application; specifically, the Frenet coordinate system can be established based on the reference line of the planning parking trajectory, the actual trajectory of the vehicle is the representation of the actual driving trajectory of the vehicle in the natural coordinate system during the automatic parking process, and the first position point corresponds to the point on the actual driving trajectory after the vehicle position is predicted for Δt time; then, after the matching trajectory point is obtained based on the minimum Euclidean distance, the projection trajectory point can be approximately calculated by the matching trajectory point: taking the first position point as the center, the Euclidean distance between the first position point and the matching trajectory point as the radius to make a circular arc, and the circular arc needs to pass through the matching trajectory point, and the intersection point formed by the circular arc and the planning parking trajectory in the Frenet coordinate system determines the projection trajectory point; further, the arc length Es between the matching trajectory point and the projection trajectory point can be approximately expressed as: wherein, is the unit tangent vector of the planning parking trajectory at the matching trajectory point, is the unit tangent vector of the planning parking trajectory at the reference trajectory point, is the coordinate of the first position point of the vehicle, is the coordinate of the matching trajectory point, and only one projection trajectory point can be obtained through the positive and negative signs of the arc length Es, that is, only one reference trajectory point is determined; is parallel to , that is, the second heading angle of the vehicle at the matching trajectory point and the reference trajectory point is equal;

[0045] Step S13: measure the tracking error between the first state information and the second state information of the reference trajectory point.

[0046] In the embodiments of the present disclosure, the tracking error includes a lateral error and a heading angle error; please refer to Figure 5 , Figure 5 is a flowchart of another embodiment of the automatic parking control method of the present application, specifically, measuring the tracking error between the first state information and the second state information of the reference trajectory point includes:

[0047] Step S51: measure the lateral error based on the first position, the second position of the reference trajectory point and the unit normal vector of the planning parking trajectory at the matching trajectory point;

[0048] In one specific implementation scenario, the lateral error can be calculated by the formula wherein e d is the lateral error value, is the second position coordinate of the reference trajectory point, is the unit normal vector of the planned parking trajectory at the matching trajectory point.

[0049] Step S52: measure the heading angle error based on the first heading angle and the second heading angle of the reference trajectory point.

[0050] In one specific implementation scenario, the heading angle error can be calculated by the formula e θ = θ - θ r wherein e θ represents the heading angle error, θ is the first heading angle, and θ r is the second heading angle at the reference trajectory point.

[0051] The above scheme can further reduce the tracking error by taking the projection trajectory point of the matching trajectory point as the reference trajectory point.

[0052] Step S14: analyze the control parameters for automatic parking based on the tracking error; wherein the control parameters include at least one of the front wheel steering angle and the steering wheel steering angle.

[0053] In one possible implementation, before "analyzing the control parameters for automatic parking based on the tracking error", it can further include: filtering the tracking error using a maximum derivative tracker.

[0054] In one specific implementation scenario, the maximum derivative tracker can be designed as:

[0055]

[0056] wherein v(t) is the input signal, x1 and x2 are respectively v, the filtered results, r and h0 are respectively the speed factor and the filtering factor, r and h0 are to be designed parameters, h is the step length, and the expression is:

[0057]

[0058] wherein fhan is the maximum control synthesis function, and fsg(x, d) = (sign(x+d) - sign(x-d)) / 2.

[0059] The state equation expression of the vehicle kinematics tracking error model is as follows:

[0060]

[0061] The above formula can be simplified as follows: Among them, e d e θ These represent the lateral error and heading angle error in the Frenet coordinate system, respectively, k r To plan the curvature of the parking trajectory at the reference trajectory point, v is the current vehicle speed, δ f Let u2 be the current front wheel steering angle, u2 be the feedforward control parameter, and L be the vehicle wheelbase. In this implementation scenario, after obtaining the tracking error through the vehicle's first state information and the second state information of the reference trajectory point, the tracking error curve is not smooth enough because the tracking error of the planned parking trajectory is different at different planned trajectory points. Ultimately, when steering wheel control is performed based on this tracking error, it will cause steering wheel vibration, resulting in low user ride comfort and reduced tracking accuracy. By filtering the obtained tracking error through the fastest differential tracker, the error curve can be smoothed, abrupt changes can be eliminated, thereby reducing steering wheel vibration and improving tracking accuracy.

[0062] In one possible implementation, the control parameters for automatic parking are obtained based on the tracking error, including: processing the tracking error using a linear quadratic regulator to obtain feedback control parameters; the feedback control parameters include at least one of the front wheel angle and the steering wheel angle. It should be noted that the front wheel angle or steering wheel angle in the feedback control parameters obtained here is different from the front wheel angle or steering wheel angle in the final control parameters used for automatic parking. The feedback control parameters here have not been adjusted by feedforward control, so there is a large error.

[0063] In one possible implementation, the feedback control parameter is the product of the target matrix and -1 multiplied by the tracking error matrix. The target matrix is ​​the K matrix corresponding to the minimum value of the cost function of the linear quadratic regulator. The tracking error includes lateral error and heading angle error, and the tracking error matrix is ​​a matrix composed of lateral error and heading angle error.

[0064] In a specific implementation scenario, the design of a linear quadratic regulator includes: If the influence of the Cu² term on the system is ignored, the discrete two-degree-of-freedom model can be designed as follows:

[0065] X(k+1)=A d X(k)+B d U(k);

[0066]

[0067] Where I is the identity matrix, dt is one sampling period, and X(k+1) is the tracking error matrix at time k+1, i.e., e at time k+1. d e θ The matrix formed X(k) is the tracking error matrix at k moment; U(k) is the control input matrix at k moment, which represents the optimal front wheel steering angle at k moment, let U(k) = -K*X(k), then X(k+1) = (A d -B d *K)*X(k); define the cost function Wherein, That is, the combination matrix of the tracking error matrix at each moment; That is, the combination matrix of the control input matrix at each moment; Q, R are weight matrices.

[0068] The design goal of the linear quadratic regulator is to find the K matrix in U(k) = -K*X(k) to make the cost function minimum, in this paper, the K matrix that makes the cost function minimum is called the target matrix; the minimum value point can be found by the zero point of the derivative of the cost function with respect to time:

[0069] Substitute U(k) = -K*X(k) into the cost function J, then Assume that there is a constant matrix P such that: Simplify to get the Riccati equation: A d T P+PA d +Q-PBR -1 B T P = 0, after the P matrix is obtained by iteration method, the K matrix can be represented as: K = -B d T PR -1 , substitute U(k) calculation formula to get U(k) = B d T PR -1 X(k), since U(k) represents the optimal front wheel steering angle at k moment, then the U(k) obtained here is the feedback control parameter.

[0070] In one possible implementation, before "processing the tracking error based on the linear quadratic regulator to obtain the feedback control parameter", it further includes: establishing a K matrix table; wherein the K matrix table includes vehicle speed intervals, cost functions and target matrices; querying the K matrix table to obtain the target matrix.

[0071] In one possible implementation, establishing a K matrix table includes: dividing the parking vehicle speed section into several vehicle speed intervals; calculating the target matrix corresponding to the minimum value of the cost function at the vehicle speed interval; recording the correspondence between the obtained target matrix and different vehicle speed intervals and different cost functions.

[0072] In a specific implementation scenario, the value of the K matrix is only related to the vehicle speed, and the vehicle speed in the parking condition is low, usually less than 2 km / h. Therefore, for example, the speed range of 0-2 km / h can be divided into 20 speed intervals at a speed interval of 0.1 km / h, and the K matrix corresponding to the cost function of the current set Q and R is solved respectively, and the obtained target matrix is recorded for query. Offline query avoids great waste of computing power, improves the real-time response of the control system, and improves the corresponding speed.

[0073] In a possible implementation, please refer to Figure 6 , Figure 6 is a flowchart of another embodiment of the automatic parking control method of the present application. Specifically, the control parameters for automatic parking obtained by analysis based on the tracking error further include:

[0074] Step S61: calculating a feedforward control parameter; the feedforward control parameter is used to compensate for the steady-state error caused by the curvature of the planned parking trajectory;

[0075] Step S62: adding the feedforward control parameter and the feedback control parameter to obtain the control parameters for automatic parking.

[0076] In a possible implementation, the second state information of the planned trajectory point further includes the curvature of the planned parking trajectory at the planned trajectory point, and calculating the feedforward control parameter includes: calculating the product of the wheelbase of the vehicle and the curvature of the trajectory at the reference point to obtain the feedforward control parameter.

[0077] In a specific implementation scenario, according to the kinematic model, the side slip of the vehicle is ignored, and the feedforward control parameter can be obtained according to the wheelbase L of the vehicle and the curvature kappa_m at the reference trajectory point, i.e. feed_forward=L*kappa_m, wherein feed_forward is the feedforward control parameter; the purpose of setting the feedforward is to eliminate the influence of Cu2 on the steady-state error, i.e. to compensate for the influence of the road curvature on the steady-state error. After obtaining the feedforward control parameter and the feedback control parameter, the control parameters for automatic parking can be calculated, i.e. steer_angle=feedforward-K*U(k), wherein steer_angle represents the front wheel steering angle, and the front wheel steering angle is multiplied by the steering ratio to obtain the steering wheel steering angle. For example, the steering ratio can be 15.

[0078] In the embodiment of the present disclosure, after the step S14, the method further comprises: in the case that the vehicle does not reach the last planning trajectory point in the plurality of planning trajectory points, performing the step of "obtaining the planning parking trajectory of the vehicle and predicting the first state information representing the driving state of the vehicle" and the subsequent steps to obtain the control parameters for subsequent automatic parking; in the case that the vehicle reaches the last planning trajectory point in the plurality of planning trajectory points, completing the automatic parking control. In the embodiment of the present disclosure, the automatic parking control of the vehicle controls the vehicle to automatically park until the vehicle reaches the last planning trajectory point in the planning trajectory. In a specific implementation scenario, there can be multiple planning parking trajectories in a complete automatic parking control process; the vehicle is controlled to track the last planning trajectory point in a planning parking trajectory, that is, to start tracking the planning parking trajectory, until the last planning trajectory point in the last planning parking trajectory is tracked, and the automatic parking control is completed.

[0079] The above scheme can control the vehicle in advance based on the predicted first state information of the vehicle, thereby compensating for the hysteresis of the automatic parking control algorithm and the delay caused by the inertia of the vehicle, improving the accuracy of the vehicle tracking the parking trajectory during automatic parking, and improving the parking effect.

[0080] Those skilled in the art can understand that the sequence of writing each step in the above method does not mean a strict execution sequence and does not constitute any limitation on the implementation process. The specific execution sequence of each step should be determined by its function and possible internal logic.

[0081] Please refer to Figure 7 , Figure 7 is a schematic diagram of an embodiment of the automatic parking control device 70 of the present application. Specifically, the automatic parking control device 70 comprises: an obtaining module 71 configured to obtain a planning parking trajectory of a vehicle and predict first state information representing a driving state of the vehicle; wherein the planning parking trajectory comprises a plurality of planning trajectory points, and the second state information of the planning trajectory point comprises at least a second position and a second heading angle of the planning trajectory point; a selection module 72 configured to select a planning trajectory point on the planning parking trajectory as a reference trajectory point based on the first state information and the second state information of each planning trajectory point; an error calculation module 73 configured to measure a tracking error between the first state information and the second state information of the reference trajectory point; and a control parameter calculation module 74 configured to analyze and obtain control parameters for automatic parking based on the tracking error; wherein the control parameters comprise at least one of a front wheel steering angle and a steering wheel steering angle.

[0082] The scheme can control the vehicle in advance based on the first state information of the vehicle, thereby compensating for the hysteresis of the automatic parking control algorithm and the delay caused by the inertia of the vehicle, improving the accuracy of the vehicle in tracking the parking trajectory during automatic parking, and improving the parking effect.

[0083] In some embodiments, the first state information includes a first position and a first heading angle of the vehicle; the obtaining module 71 includes: a state information obtaining sub-module, configured to obtain an axle distance of the vehicle and third state information representing a current driving state of the vehicle; the third state information includes a current speed, a current position, a current front wheel steering angle and a current heading angle; a state information predicting sub-module, configured to predict, based on the current position and the current heading angle, a driving position of the vehicle after driving for a prediction duration at the current speed as the first position, and predict, based on the current heading angle and the axle distance, a heading angle of the vehicle after driving for the prediction duration at the current speed and the current front wheel steering angle as the first heading angle.

[0084] In some embodiments, the selecting module 72 includes: a distance calculating sub-module, configured to obtain an Euclidean distance corresponding to the planning track point based on the first position and a second position of the planning track point; a matching sub-module, configured to select the planning track point with the minimum Euclidean distance as the matching track point; and a determining sub-module, configured to determine a reference track point on the planning parking track based on the first state information and second state information of the matching track point.

[0085] In some embodiments, the tracking error includes a lateral error and a heading angle error; the error calculating module 73 includes: a lateral error calculating sub-module, configured to measure the lateral error based on the first position, the second position of the reference track point and a unit normal vector of the planning parking track at the matching track point; and a heading angle error calculating sub-module, configured to measure the heading angle error based on the first heading angle and a second heading angle of the reference track point.

[0086] In some embodiments, the automatic parking control device 70 further includes a filtering module, configured to filter the tracking error using a maximum derivative tracker.

[0087] In some embodiments, the control parameter calculating module 74 includes a feedback sub-module, configured to process the tracking error based on a linear quadratic regulator to obtain a feedback control parameter; the feedback control parameter includes at least one of a front wheel steering angle and a steering wheel steering angle.

[0088] In some embodiments, the feedback control parameter is the product of the target matrix and -1 multiplied by the tracking error matrix, and the target matrix is ​​the K matrix corresponding to the minimum value of the cost function of the linear quadratic regulator; wherein, the tracking error includes lateral error and heading angle error, and the tracking error matrix is ​​a matrix composed of lateral error and heading angle error.

[0089] In some embodiments, the automatic parking control device 70 further includes a query module for establishing a K matrix table; wherein the K matrix table includes a vehicle speed range, a cost function, and a target matrix; and, querying the K matrix table to obtain the target matrix.

[0090] In some embodiments, the query module includes: a segmentation submodule for dividing the parking speed segment into several speed intervals; a target matrix calculation module for calculating the target matrix corresponding to the minimum value of the cost function under the speed interval; and a recording submodule for recording the correspondence between the obtained target matrix and different speed intervals and different cost functions.

[0091] In some embodiments, the control parameter calculation module 74 further includes: a feedforward submodule for calculating feedforward control parameters; the feedforward control parameters are used to compensate for the steady-state error caused by the curvature of the planned parking trajectory; and a calculation submodule for adding the feedforward control parameters to the feedback control parameters to obtain control parameters for automatic parking.

[0092] In some embodiments, the second state information of the planned trajectory point also includes the curvature of the planned parking trajectory at the planned trajectory point. The feedforward submodule is also used to calculate the product of the vehicle's wheelbase and the curvature of the trajectory at the reference point to obtain the feedforward control parameters.

[0093] Please see Figure 8 , Figure 8 This is a schematic diagram of the framework of one embodiment of the electronic device 80 of this application. The electronic device 80 includes a memory 81 and a processor 82 coupled to each other. The processor 82 is used to execute program instructions stored in the memory 81 to implement the steps in any of the above embodiments of the automatic parking control method. In a specific implementation scenario, the electronic device 80 may include, but is not limited to, a microcomputer, a server, etc. In addition, the electronic device 80 may also include mobile devices such as laptops and tablets, which are not limited here.

[0094] Specifically, the processor 82 is configured to control itself and the memory 81 to implement the steps of any of the above-described training method embodiments of the image detection model, or implement the steps in any of the above-described image detection method embodiments. The processor 82 can also be referred to as a CPU (Central Processing Unit). The processor 82 can be an integrated circuit chip having a processing capability of signals. The processor 82 can also be a general processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general processor can be a microprocessor or the processor can also be any conventional processor or the like. In addition, the processor 82 can be jointly implemented by integrated circuit chips.

[0095] The above scheme, by predicting the first state information of the vehicle and obtaining the reference point based on the first state information, obtaining the tracking error based on the reference point and the first state information, and performing automatic parking control based on the tracking error, can control the vehicle in advance based on the first state information of the vehicle, thereby compensating for the hysteresis of the automatic parking control algorithm and the delay caused by the inertia of the vehicle, and improving the accuracy of the vehicle tracking the parking trajectory during automatic parking, thereby improving the parking effect.

[0096] Please refer to Figure 9 , Figure 9 is a schematic diagram of an embodiment of the framework of the computer readable storage medium 90. The computer readable storage medium 90 stores program instructions 901 capable of being executed by the processor, and the program instructions 901 are used to implement the steps in any of the above-described automatic parking control method embodiments.

[0097] The above scheme, by predicting the first state information of the vehicle and obtaining the reference point based on the first state information, obtaining the tracking error based on the reference point and the first state information, and performing automatic parking control based on the tracking error, can control the vehicle in advance based on the first state information of the vehicle, thereby compensating for the hysteresis of the automatic parking control algorithm and the delay caused by the inertia of the vehicle, and improving the accuracy of the vehicle tracking the parking trajectory during automatic parking, thereby improving the parking effect.

[0098] In some embodiments, the apparatus provided by the embodiments of the present disclosure has functions or includes modules that can be used to perform the methods described in the above method embodiments, and the specific implementation can refer to the description of the above method embodiments. For brevity, it will not be repeated here.

[0099] The above description of the various embodiments is intended to be illustrative of the various embodiments and is not intended to limit the scope of the various embodiments. Many variations are possible which would be readily apparent to those skilled in the art. Some of these embodiments have been discussed above, but for brevity the specific disclosure thereof has not been provided. Any reference cited herein is incorporated by reference in its entirety.

[0100] In several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other manners. For example, the division of the above-described device embodiments is merely an example, and there can be another division manner. For example, a plurality of modules or a plurality of components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be implemented by using some interfaces, and a mere combination of the modules or components can not necessarily be a couping or direct couping or communication connection. For example, the couplings or communication connections between the modules or components can be implemented in electronic, mechanical, or other forms.

[0101] In addition, each function unit in the various embodiments of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit. The integrated unit can be implemented in the form of hardware or software function unit.

[0102] If the integrated unit is implemented in the form of software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such an understanding, the technical solutions of the present application essentially, or the part that contributes to the prior art, or all or a part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the methods in the various embodiments of the present application. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and various other media that can store program codes.

[0103] If the technical solution of the present application involves personal information, the product applying the technical solution of the present application has clearly informed the personal information processing rules before processing the personal information and obtained the personal independent consent. If the technical solution of the present application involves sensitive personal information, the product applying the technical solution of the present application has obtained the personal independent consent before processing the sensitive personal information and at the same time meets the requirement of "explicit consent". For example, at the personal information collection device such as camera, a clear and prominent sign is set to inform that it has entered the personal information collection range and will collect personal information. If the individual voluntarily enters the collection range, it is considered to agree to collect personal information. Or on the device for processing personal information, through the pop-up information or by asking the individual to upload his / her personal information, the individual's authorization is obtained under the condition of using obvious signs / information to inform the personal information processing rules. The personal information processing rules can include personal information processor, personal information processing purpose, processing method and type of processed personal information, etc.

Claims

1. An automatic parking control method characterized by, The method comprises: acquiring a planned parking trajectory of a vehicle and predicting first state information representing a self-vehicle driving state of the vehicle; wherein the planned parking trajectory comprises a plurality of planned trajectory points, and second state information of the planned trajectory points comprises at least a second position and a second heading angle of the planned trajectory points; the first state information comprises a first position and a first heading angle of the vehicle; the first position represents a position of the vehicle after driving for a prediction time while keeping a current speed and a current heading angle unchanged, and the first heading angle represents a heading angle of the vehicle after driving for the prediction time while keeping the current speed and a current front wheel steering angle unchanged; selecting, based on the first state information and the second state information of each of the planned trajectory points, a planned trajectory point on the planned parking trajectory as a reference trajectory point; measuring a tracking error between the first state information and the second state information of the reference trajectory point; analyzing, based on the tracking error, a control parameter for automatic parking; wherein the control parameter comprises at least one of a front wheel steering angle and a steering wheel steering angle; the selecting, based on the first state information and the second state information of each of the planned trajectory points, a planned trajectory point on the planned parking trajectory as a reference trajectory point comprises: obtaining, based on the first position and the second position of the planned trajectory point, an Euclidean distance corresponding to the planned trajectory point; selecting, as a matching trajectory point, a planned trajectory point with a minimum Euclidean distance; determining, based on the first state information and the second state information of the matching trajectory point, the reference trajectory point on the planned parking trajectory.

2. The method of claim 1, wherein, after the analyzing, based on the tracking error, the control parameter for automatic parking, the method further comprises: in a case where the vehicle does not reach a last planned trajectory point in the plurality of planned trajectory points, performing the acquiring a planned parking trajectory of a vehicle and predicting first state information representing a self-vehicle driving state of the vehicle and subsequent steps to obtain a subsequent control parameter for automatic parking; in a case where the vehicle reaches the last planned trajectory point in the plurality of planned trajectory points, completing automatic parking control.

3. The method of claim 1, wherein: the predicting first state information representing a self-vehicle driving state of the vehicle comprises: acquiring a wheelbase of the vehicle and third state information representing a current driving state of the vehicle; wherein the third state information comprises a current speed, a current position, a current front wheel steering angle, and a current heading angle; predicting, based on the current position and the current heading angle, a driving position of the vehicle after driving for a prediction time length while keeping the current speed unchanged, as the first position; and predicting, based on the current heading angle and the wheelbase, a heading angle of the vehicle after driving for the prediction time length while keeping the current speed and the current front wheel steering angle unchanged, as the first heading angle.

4. The method of claim 1, wherein, the tracking error comprises a lateral error and a heading angle error; and the measuring a tracking error between the first state information and the second state information of the reference trajectory point comprises: measure the lateral error based on the first position, a second position of the reference trajectory point, and a unit normal vector of the planned parking trajectory at the matching trajectory point; measure the heading angle error based on the first heading angle and a second heading angle of the reference trajectory point.

5. The method of claim 1, wherein, Before the "analyzing the control parameters for automatic parking based on the tracking error", further comprising: filtering the tracking error using a fast differential tracker.

6. The method according to claim 1 or 5, characterized in that, The analyzing the control parameters for automatic parking based on the tracking error comprises: processing the tracking error based on a linear quadratic regulator to obtain feedback control parameters; the feedback control parameters comprise at least one of a front wheel steering angle and a steering wheel steering angle.

7. The method of claim 6, wherein, The feedback control parameters are a product of a target matrix multiplied by -1 and a tracking error matrix; the target matrix is a K matrix corresponding to a minimum value of a cost function of the linear quadratic regulator; the tracking error comprises a lateral error and a heading angle error, and the tracking error matrix is a matrix composed of the lateral error and the heading angle error.

8. The method of claim 7, wherein, Before the "processing the tracking error based on a linear quadratic regulator to obtain feedback control parameters", further comprising: establishing a K matrix table; the K matrix table comprises a vehicle speed interval, a cost function, and a target matrix; querying the K matrix table to obtain the target matrix.

9. The method of claim 8, wherein, The establishing a K matrix table comprises: dividing a parking speed section into a plurality of vehicle speed intervals; calculating a target matrix corresponding to a minimum value of the cost function in the vehicle speed interval; recording a correspondence relationship between the target matrix obtained and different vehicle speed intervals and different cost functions.

10. The method of claim 6, wherein, The analyzing the control parameters for automatic parking based on the tracking error further comprises: calculating a feedforward control parameter; the feedforward control parameter is used to compensate for a steady-state error caused by a curvature of the planned parking trajectory; adding the feedforward control parameter and the feedback control parameter to obtain the control parameters for automatic parking.

11. The method of claim 10, wherein, The second state information of the planned trajectory point further comprises a curvature of the planned parking trajectory at the planned trajectory point, and the calculating the feedforward control parameter comprises: calculating a product of a wheelbase of the vehicle and the curvature of the planned parking trajectory at the reference trajectory point to obtain the feedforward control parameter.

12. An automatic parking control device, characterized by comprising: comprising: an acquisition module, configured to acquire a planned parking trajectory of a vehicle and predict first state information representing a self-driving state of the vehicle; the planned parking trajectory comprises a plurality of planned trajectory points, and second state information of the planned trajectory point comprises at least a second position and a second heading angle of the planned trajectory point; the first state information comprises a first position and a first heading angle of the vehicle; the first position represents a position of the vehicle after a prediction time of driving under a condition that a current speed and a current heading angle remain unchanged, and the first heading angle represents a heading angle of the vehicle after the prediction time of driving under a condition that the current speed and a current front wheel steering angle remain unchanged. The selection module is configured to select the planning track point on the planning parking track as a reference track point based on the first state information and second state information of each planning track point; The error calculation module is configured to measure a tracking error between the first state information and second state information of the reference track point; The control parameter calculation module is configured to analyze a control parameter for automatic parking based on the tracking error, wherein the control parameter comprises at least one of a front wheel steering angle and a steering wheel steering angle. The selection of the planning track point on the planning parking track as the reference track point based on the first state information and second state information of each planning track point comprises: Obtaining an Euclidean distance corresponding to the planning track point based on a first position and a second position of the planning track point; Selecting the planning track point with the minimum Euclidean distance as a matching track point; Determining the reference track point on the planning parking track based on the first state information and second state information of the matching track point.

13. An electronic device, comprising: The processor is configured to execute program instructions stored in the memory to implement the automatic parking control method according to any one of claims 1 to 11.

14. A computer-readable storage medium having stored thereon program instructions, wherein, The program instructions, when executed by the processor, implement the automatic parking control method according to any one of claims 1 to 11.

Images