CN112277931A

CN112277931A - Vertical parking trajectory generation method and device, vehicle and storage medium

Info

Publication number: CN112277931A
Application number: CN202011127803.5A
Authority: CN
Inventors: 李飞
Original assignee: Shanghai OFilm Smart Car Technology Co Ltd
Current assignee: Shanghai OFilm Smart Car Technology Co Ltd
Priority date: 2020-10-20
Filing date: 2020-10-20
Publication date: 2021-01-29
Anticipated expiration: 2040-10-20
Also published as: CN112277931B

Abstract

The method comprises the steps of dividing a parking path planning process into four stages, calculating a reference curve of a path corresponding to a current stage of a vehicle according to a vehicle model and a current scene in different stages, generating a target path with continuous curvature according to the reference curve, generating a vertical parking path according to the target path, and controlling the vehicle to park in a target storage according to the vertical parking path. The application also provides a vertical parking track generation device, a vehicle and a storage medium. According to the method and the device, automatic parking can be more in line with driving habits, and driving experience is improved.

Description

Vertical parking trajectory generation method and device, vehicle and storage medium

Technical Field

The application relates to the technical field of vehicle control, in particular to a vertical parking track generation method and device, a vehicle and a storage medium.

Background

In recent years, with the continuous development and application of automatic driving technology, the comfort and rationality of automatic driving become more and more important. Aiming at the automatic parking process, a path is mainly planned for a vehicle according to a parking space scene, and the vehicle follows the planned path to finish automatic parking.

However, in the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art: the parking track with continuous curvature can bring good parking experience, and the requirement of continuous curvature can be well met by introducing a convolution line into the parking track design. But also brings the problems of complex calculation, plate carving calculation of starting and ending points of the convolution line and the like.

Disclosure of Invention

In view of the above problems, the present application provides a method, an apparatus, a vehicle, and a storage medium for generating a vertical parking trajectory, which can make automatic parking more suitable for driving habits.

A first aspect of the present application provides a vertical parking trajectory generation method, including:

an initial stage, an adjustment stage, a warehousing stage and a warehouse kneading stage;

in the initial stage, a target position in a target library position and a position coordinate (ob) of an obstacle are acquired_x,ob_y) And initial pose information of the vehicle, the initial pose information including initial position coordinates (carp) of the vehicle_x,carp_y) And course angle information;

in the adjusting stage, determining a first reference curve based on the initial position coordinates of the vehicle and the position coordinates of the obstacle, and calculating a minimum parking circle of the warehousing stage, wherein the center coordinates of the minimum parking circle are (Ox, Oy); if the abscissa of the initial position coordinate is smaller than the abscissa of the circle center coordinate, generating a first target track based on the initial position and the first reference curve, wherein the first target track comprises a first target point;

in the warehousing stage, if the tail of the vehicle is not located in the target warehousing position, taking the minimum parking circle as a second reference curve of the warehousing stage, and generating a second target track based on the first target point and the second reference curve, wherein the second target track comprises a second target point; and

and in the warehouse kneading stage, determining a third reference curve according to the position of the target warehouse position, and generating a third target track based on the second target point and the third reference curve.

A second aspect of the present application provides a vertical parking trajectory generation device, including:

the division module is used for dividing the whole stage of parking the vehicle into a target storage position into an initial stage, an adjustment stage, a storage stage and a storage kneading stage;

an acquisition module for acquiring a target position in the target library location and a position coordinate (ob) of the obstacle at the initial stage_x,ob_y) And initial pose information of the vehicle, the initial pose information including initial position coordinates (carp) of the vehicle_x,carp_y) And course angle information;

a generating module, configured to determine, in the adjusting stage, a first reference curve based on the initial position coordinates of the vehicle and the position coordinates of the obstacle, and calculate a minimum parking circle of the warehousing stage, where coordinates of a center of the minimum parking circle are (Ox, Oy); if the abscissa of the initial position coordinate is smaller than the abscissa of the circle center coordinate, generating a first target track based on the initial position and the first reference curve, wherein the first target track comprises a first target point;

the generating module is further configured to, in the warehousing stage, if the vehicle tail of the vehicle is not located in the target warehousing location, use the minimum parking circle as a second reference curve of the warehousing stage, and generate a second target trajectory based on the first target point and the second reference curve, where the second target trajectory includes a second target point; and

and the generating module is further used for determining a third reference curve according to the position of the target warehouse position in the warehouse kneading stage and generating a third target track based on the second target point and the third reference curve.

A third aspect of the present application provides a vehicle comprising:

the device comprises a memory, a processor and a communication bus, wherein the memory is in communication connection with the processor through the communication bus; and a plurality of program modules are stored in the memory, and are loaded by the processor and execute the vertical parking trajectory generation method.

A fourth aspect of the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the vertical parking trajectory generation method as described above.

According to the vertical parking track generation method, the device, the vehicle and the medium, the whole stage of parking the vehicle into the target storage position is divided into an initial stage, an adjustment stage, a storage stage and a library kneading stage, different target tracks are generated aiming at different stages, and the vehicle is controlled to park into the target storage position according to the generated target tracks. The method and the device can generate the track points with continuous curvature, which can be executed by the vehicle, the calculated amount is simple, and the generated track meets the driving habit of the driver.

Drawings

Fig. 1 is a flowchart illustrating a method for generating a vertical parking trajectory according to an embodiment of the present application.

Fig. 2 is a schematic view of an application scenario including an obstacle according to an embodiment of the present application.

Fig. 3 is a schematic view of an application scenario without obstacles according to an embodiment of the present application

FIG. 4 is a schematic diagram of generating a second target track according to an embodiment of the present application.

Fig. 5 is a functional block diagram of a vertical parking trajectory generation apparatus according to an embodiment of the present application.

Fig. 6 is a schematic structural diagram of a vehicle according to an embodiment of the present application.

Detailed Description

In order that the objects, features and advantages of the present application can be more clearly understood, the present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict. In the following description, numerous specific details are set forth to provide a thorough understanding of the present application, and the described embodiments are merely a subset of the embodiments of the present application and are not intended to be a complete embodiment.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

Referring to fig. 1, fig. 1 is a schematic flow chart of a vertical parking trajectory generation method according to an embodiment of the present application. The order of the steps in the flow chart may be changed and some steps may be omitted according to different needs. For convenience of explanation, only portions related to the embodiments of the present application are shown.

The vertical parking track generation method is applied to the vehicle. For the vehicle needing to enter the vertical parking track generation, the vertical parking track generation function provided by the method of the application can be directly integrated on the vehicle, or a client used for realizing the vertical parking track generation method of the application is installed. For another example, the vertical parking trajectory generation method provided by the present application may also be operated on the vehicle in a Software Development Kit (SDK) form, an interface of the vertical parking trajectory generation function is provided in an SDK form, and a processor or other devices may implement the vertical parking trajectory generation function through the provided interface. The vertical parking trajectory generation method includes the following steps.

And step S1, dividing the whole stage of parking the vehicle into a target storage space into an initial stage, an adjustment stage, a warehousing stage and a library kneading stage.

In the embodiment, a parking path planning process is divided into four stages, a reference curve of a path corresponding to the current stage of the vehicle is calculated according to a vehicle model and a current scene in different stages, a forward-view window tracking algorithm is adopted to generate a target track with continuous curvature, a parking track is generated according to the target track, and the vehicle is controlled to park in a target storage space according to the parking track.

The four stages include a first stage, a second stage, a third stage, and a fourth stage. The first stage is an initial stage, namely a stage when the vehicle just enters a parking plan; the second phase is an adjustment phase (as shown from point P to point a in fig. 2), that is, the vehicle is outside the target parking space, but the vehicle cannot enter the target parking space through reversing at the current position; the third stage is a warehousing stage (as shown from point a to point B in fig. 2), that is, the vehicle is outside the target depot, but the vehicle can enter the depot by backing up the vehicle at the current position; the fourth stage is a garage kneading stage (as shown in fig. 2, point B to point C, and point C to point D), that is, the tail of the vehicle enters the target garage, and the vehicle can be parked in the target garage by planning a track for forward and reverse.

Step S2, in the initial stage, acquiring the position coordinates of the target storage position, the position coordinates of the obstacle and the initial pose information of the vehicle to be stored in the storage, wherein the initial pose information comprises the initial position coordinates and the course angle information of the vehicle.

In this embodiment, in a world coordinate system, when the vehicle is at the initial position, the vehicle receives a parking instruction for parking, a camera of the vehicle, an ultrasonic radar and other sensors sense the surrounding environment of the vehicle to obtain a parking space condition, and position coordinates of an obstacle and position coordinates of the target storage space D are determined according to the parking space condition.

In other embodiments, the position and attitude of the vehicle may be calculated by a two-degree-of-freedom model of the vehicle over continuous time, or based on a combination of GPS and inertial navigation. It should be noted that the two-degree-of-freedom model of the vehicle and the GPS-based and inertial navigation combination are prior art, and are not described herein again.

In one embodiment, the position coordinates of the obstacle may be acquired by a binocular vision-based obstacle detection method.

Step S3, in the adjusting stage, determining a first reference curve based on the initial position coordinates of the vehicle and the position coordinates of the obstacle, and calculating a minimum parking circle of the warehousing stage, where the coordinates of the center of the minimum parking circle are (Ox, Oy); if the abscissa of the initial position coordinate is smaller than the abscissa of the circle center coordinate, a first target track is generated based on the initial position and the first reference curve, and the first target track comprises a first target point.

In the embodiment, whether the vehicle is currently in the initial stage or in the adjustment stage, it is determined that the vehicle can be directly backed up and put in storage according to the abscissa of the initial position and the abscissa of the center of the minimum parking circle, and the vehicle enters the storage stage; or the vehicle body is required to be adjusted through the adjusting stage again and then enters the warehousing stage.

Specifically, if the abscissa of the initial position coordinate is greater than or equal to the abscissa of the circle center coordinate, it is determined that the vehicle body does not need to be adjusted again, and the vehicle can be controlled to enter a garage kneading stage; and if the abscissa of the initial position coordinate is smaller than the abscissa of the circle center coordinate, determining that the vehicle needs to enter an adjusting stage to be adjusted.

As shown in fig. 2, in the adjusting stage, the vehicle does not need to enter the target parking space, but the vehicle is driven from the point P to the point a, so that the vehicle can be backed up and enter the parking space. The first reference curve in the adjustment phase is thus determined from the initial position coordinates of the vehicle and the position coordinates of the obstacle. In particular, the first reference curve of the adjustment phase is determined by the following formula:

wherein the carp_xIs the abscissa, ob, of the initial position of the vehicle_xIs the abscissa of the position of the obstacle, i is the vehicle body width, and d1 is the distance between the vehicle body and the target garage position. In this embodiment, d1 equals 1 meter.

And calculating a minimum parking circle of the warehousing stage based on the first reference curve and the position coordinates of the obstacles, wherein the center coordinate of the minimum parking circle is (O)_x，O_y)。

In this embodiment, the center coordinates of the minimum parking circle may be determined according to whether an obstacle exists on the right side of the target parking space. If there is an obstacle on the right side of the target parking space, the radius of the minimum parking circle is the minimum turning radius R of the vehicle, and the minimum parking circle satisfies that the vehicle can avoid the obstacle if running along a circular arc (obx, oby) (as shown in fig. 2), where the safe distance d2 is 0.2m, and the center coordinates of the circle are calculated by the following formula:

(ob_x-O_x)²+(ob_y-O_y)²＝(R-d2-l/2)²

if no obstacle exists on the right side of the target library position, as shown in fig. 3, the center coordinates of the circle are calculated and calculated by the following formula:

O_y＝targetp_y-R

wherein, targetp_yAre the coordinates of the target location point. The oblique parking space scene requires that the distance from the circle center O to a reference line (targetP line) corresponding to the target position point is R, and the coordinate of the circle center O can be obtained in the same way.

If the vehicle is determined to enter the adjusting stage, generating a first target track through a forward-looking window tracking algorithm based on the initial position and the first reference curve, wherein the first target track comprises a first target point.

In the present embodiment, a first target trajectory (a trajectory generated as Step1 shown in fig. 2) is generated by a forward-looking window tracking algorithm based on the first reference curve, and an end point of the first target trajectory is the first target point, shown as a in fig. 2.

Specifically, the vehicle model is simplified into a bicycle model, the rear shaft of the vehicle is taken as a tangent point, the longitudinal vehicle body of the vehicle is taken as a tangent line, and the front wheel deflection angle is controlled to simulate the vehicle to move along a first circular arc rail at a speed vThe track driving is carried out, curvature continuous path points are obtained, the driving distance of the single-step simulated vehicle is dl, and the maximum adjustment deflection angle of a single-step front wheel is delta alpha_max. The method for generating the first target track by adopting the forward-looking window tracking algorithm comprises the following steps:

setting an initial pose of the vehicle to Q (Qx, Qy, Qyaw), wherein Q_XIs the coordinate of the vehicle corresponding to the X-axis direction in the world coordinate system at the initial position, Q_yThe coordinate of the vehicle corresponding to the Y-axis direction in the world coordinate system at the initial position is shown, and Qyaw is the heading angle of the vehicle at the initial position.

Mapping a rear axle center of the vehicle onto the first reference curve based on the vehicle initial position coordinates, resulting in a mapped point P1(P1x, P1 y);

moving to a first target point G1 on the first reference curve according to the vehicle traveling direction with the mapped point P1 as a starting point, and determining pose information G1 of the vehicle at the first target point (G1x, G1y, G1 yaw). For example, a distance (e.g., 1 meter) is moved on the first reference curve to the first target point G1. G1X is a coordinate of the vehicle in the X-axis direction in the world coordinate system corresponding to the first target point, G1Y is a coordinate of the vehicle in the Y-axis direction in the world coordinate system corresponding to the first target point, and G1yaw is a heading angle of the vehicle at the first target point.

And generating a first target circle tangent to the longitudinal direction of the vehicle according to the initial position Q and the first target point G1, wherein the center of the first target circle is a point O1 and the radius is R1. In the present embodiment, the first target circle passes through the initial position Q and the first target point G1, and is tangent to the longitudinal direction of the vehicle at the initial position Q. The first target circle is tangent to the longitudinal direction of the vehicle, namely the first target circle is tangent to a straight line which takes the center of the rear axle of the vehicle as a starting point and has a direction vertical to the rear axle. After the initial position Q and the first target point G1 are determined, the radius R1 of the first target circle may be obtained according to geometric principles.

Controlling the vehicle to move a preset distance dl on the first target circle by taking the initial position as a starting point to reach an ith preset target point Qi, wherein i is a positive integer;

calculating the front wheel deflection angle and pose information of the vehicle at the ith preset target point Qi;

judging whether the error between the pose information of the ith preset target point Qi and the pose information of the first target point G1 is less than or equal to a preset error;

determining that the vehicle arrives at a first target point G1 when an error between the pose of the i-th preset target point Qi and the pose of the first target point G1 is less than or equal to the preset error;

the first target trajectory, which is the trajectory of the vehicle traveling on the first target circle from the initial position to the i-th target point (i.e., first target point G1), is output.

When the error between the pose information of the ith preset target point Qi and the pose information of the first target point G1 is larger than the preset error, controlling the vehicle to continuously move by a preset distance dl according to the front wheel deflection angle of the ith preset target point Qi; and acquiring pose information after the vehicle continues to move for a preset distance dl, determining that the vehicle reaches a first target point when the error between the acquired pose information and the pose of the first target point is less than or equal to the preset error, and outputting the first target track.

In this embodiment, the calculating the front wheel deflection angle and the pose information of the vehicle at the i-th preset target point Qi includes:

calculating a target front wheel yaw angle α 1 of the vehicle from the radius R1 of the first target circle_expIn which α 1_exp＝tan^-1(L/R1), L being the wheelbase of the vehicle, i.e. the distance between the front wheels of the vehicle and the rear wheels of the vehicle.

Based on the target front wheel deflection angle alpha 1_expCalculating an angle increment delta alpha of a front wheel deflection angle of the vehicle at the i-th preset target point Qi_i，Δα_i＝α1_exp-α_iWherein α is_iPresetting a target point for the vehicle at the ithQi actual front wheel yaw angle. When i is 1, α₁The front wheel yaw angle of the vehicle at the initial position. When i is greater than 1, the radius Ri (i-th time) of a circle obtained by combining the current position of the vehicle (e.g., coordinates of the i-th preset target point Qi) and a point on the first reference curve may be determined, and the front wheel yaw angle α of the vehicle calculated by the ackerman steering principle may be calculated_i＝tan^-1(L/Ri)。

It should be noted that the front wheel yaw angle of the vehicle at the initial position is a known angle, and the Δ α is_i∈[-Δα_max，Δα_max]，Δα_maxThe single step front wheel maximum adjustment yaw angle.

Updating the front wheel deflection angle of the vehicle at the i-th preset target point Qi to be alpha based on the angle increment_i′＝α_i-₁+Δα_i。

Calculating a first central angle beta_iThe first central angle is a central angle corresponding to an arc length when the vehicle runs to the ith preset target point on the first target circle, wherein beta is_i＝i×dl/R′_i，R′_i＝L/tanα_i′；

According to the initial pose information of the vehicle to be warehoused and the first central angle beta_iCalculating the pose information of the vehicle at the ith preset target point by the following formula:

Qi_yaw＝Q(i-1)_yaw+β_i

Qi_x＝Q(i-1)_x+R′_i*(sin(Qi_yaw)-sin(Q(i-1)_yaw))

Qi_y＝Q(i-1)_y+R′_i*(cos(Q(i-1)_yaw)-cos(Qi_yaw))

wherein, Qi_xCorresponding the coordinates of the vehicle in the X-axis direction in the world coordinate system at the ith preset target point, Qi_yCorresponding the coordinates of the vehicle in the Y-axis direction in the world coordinate system at the ith preset target point, Qi_yawIs the course angle, R 'of the vehicle at the ith preset target point'_i＝L/tanα_i′。

For example, at the initial position, the pose information of the vehicle is Q (Qx, Qy, Qyaw), and at the 1 st preset target point, the pose of the vehicle is:

Q1_yaw＝Q_yaw+β₁

Q1_x＝Q_x+R′₁*(sin(Q1_yaw)-sin(Q_yaw))

Q1_y＝Q_y+R′₁*(cos(Q_yaw)-cos(Q1_yaw))

when the 2 nd preset target point is reached, the pose of the vehicle is as follows:

Q2_yaw＝Q1_yaw+β₂

Q2_x＝Q1_x+R′₂*(sin(Q2_yaw)-sin(Q1_yaw))

Q2_y＝Q1_y+R′₂*(cos(Q1_yaw)-cos(Q2_yaw))

and so on, obtaining the pose information of the vehicle at the ith preset target point:

Qi_yaw＝Q(i-1)_yaw+β_i

Qi_x＝Q(i-1)_x+R′_i*(sin(Qi_yaw)-sin(Q(i-1)_yaw))

Qi_y＝Q(i-1)_y+R′_i*(cos(Q(i-1)_yaw)-cos(Qi_yaw))

step S4, in the warehousing stage, if the vehicle tail of the vehicle is not located in the target warehousing location, taking the minimum parking circle as a second reference curve of the warehousing stage, and generating a second target trajectory based on the first target point and the second reference curve, where the second target trajectory includes a second target point.

And after the first target track is generated, controlling the vehicle to travel to the first target point according to the first target track, and then entering a warehousing stage. In the present embodiment, whether the vehicle enters the warehousing stage or directly enters the kneading stage is determined by whether the tail of the vehicle is in the target warehouse location. If the tail of the vehicle is not located in the target storage position, taking the minimum parking circle as a second reference curve of the storage stage; and when the tail of the vehicle is positioned in the target warehouse position, controlling the vehicle to enter a warehouse kneading stage, and determining a third reference curve of the warehouse kneading stage according to the position of the target warehouse position.

In this embodiment, in the warehousing stage, the minimum parking circle is used as a second reference curve, a second target track is generated through a forward-looking window tracking algorithm, and the vehicle is controlled to enter the warehousing stage after traveling according to the second target track. Generating a second target trajectory by a forward looking window tracking algorithm based on the first target point and the second reference curve, the second target trajectory including a second target point.

In the present embodiment, a second target trajectory (trajectory generated as Step2 shown in fig. 2) is generated by a forward-looking window tracking algorithm based on the second reference curve, and an end point of the second target trajectory is the second target point.

Specifically, it should be noted that, as the second target trajectory is generated, the vehicle needs to be simplified into a bicycle model, which is not described herein again. As shown in fig. 4, the method for generating the second target trajectory by using the forward-looking window tracking algorithm includes:

updating the initial position of the vehicle to be the first target point;

mapping a rear axle center of the vehicle to the second reference curve based on the first target point, resulting in a second mapped point P2(P2x, P2 y);

moving to a second target point G2 on the second reference curve according to the vehicle traveling direction with the second mapping point P2 as a starting point, and determining pose information G2 of the vehicle at the second target point (G2x, G2y, G2 yaw). For example, a distance (e.g., 1 meter) is moved on the second reference curve to the second target point G2. G2X is a coordinate of the vehicle in the direction of an X axis in the world coordinate system corresponding to the second target point, G2Y is a coordinate of the vehicle in the direction of a Y axis in the world coordinate system corresponding to the second target point, and G2yaw is a heading angle of the vehicle at the second target point.

Generating a second target circle tangent to the longitudinal direction of the vehicle according to the first target point G1 and a second target point G2, wherein the center of the second target circle is a point O2 and the radius of the second target circle is R2; after the first and second target points G1 and G2 are determined, the radius R2 of the second target circle may be obtained according to geometric principles.

Controlling the vehicle to move a preset distance dl on the second target circle by taking a first target point as a starting point to reach a jth preset target point Qj, wherein j is greater than or equal to i, and j is a positive integer;

calculating the front wheel deflection angle and the pose information of the vehicle at the jth preset target point Qj;

judging whether the error between the pose information of the jth preset target point Qj and the pose information of the second target point G2 is smaller than or equal to the preset error;

determining that the vehicle reaches a second target point G2 when an error between the pose information of the jth preset target point Qj and the pose information of the second target point G2 is less than or equal to the preset error;

outputting the second target trajectory, which is a trajectory of the vehicle traveling from the first target point to the jth target point (i.e., a second target point G2) on the second target circle;

when the error between the pose information of the jth preset target point Qj and the pose information of the second target point G2 is larger than the preset error, controlling the vehicle to continuously move for a preset distance dl according to the front wheel deflection angle of the jth preset target point Qj; and acquiring the pose information of the vehicle after the vehicle continuously moves for a preset distance dl, determining that the vehicle reaches a second target point G2 when the error between the acquired pose information and the pose information of the second target point G2 is less than or equal to the preset error, and outputting a second target track.

In this embodiment, the calculating the pose information of the vehicle at the j-th preset target point includes:

calculating a target front wheel yaw angle α 2 of the vehicle from the radius R2 of the second target circle_expWherein α 2_exp＝tan^-1(L/R2), L being the wheelbase of the vehicle, i.e. the distance between the front wheels of the vehicle and the rear wheels of the vehicle.

Based on the target front wheel deflection angle alpha 2_expCalculating the angle increment delta alpha of the front wheel deflection angle of the vehicle at the jth preset target point Qj_j，Δα_j＝α2_exp-α_j. Wherein alpha is_jAnd presetting the actual front wheel deflection angle of the target point Qj for the vehicle at the jth position. When j is equal to i, α_jThe front wheel yaw angle of the vehicle at the first target point. When j is larger than i, the radius Rj (j times) of the circle obtained by the current position of the vehicle (such as the coordinates of the j preset target point Qj) and the point on the second reference curve can be determined, and the front wheel deflection angle alpha of the vehicle calculated by the Ackerman steering principle_j＝tan^-1(L/Rj), L being the wheelbase of the vehicle.

Updating the front wheel deflection angle of the vehicle at the jth preset target point Qj to be alpha based on the angle increment_j′＝α_j-1+Δα_j。

Calculating a second central angle beta_jThe second central angle is a central angle corresponding to an arc length when the vehicle runs to the jth preset target point on the second target circle, wherein β is_j＝j×dl/R′_j，R′_j＝L/tanα_j′；

According to the pose information of the vehicle at the jth preset target point and the second central angle beta_jCalculating the pose information of the vehicle at the j-th preset target point through the following formula:

Qj_yaw＝Q(j-1)_yaw+β_j

Qj_x＝Q(j-1)_x+R′_j*(sin(Qj_yaw)-sin(Q(j-1)_yaw))

Qj_y＝Q(j-1)_y+R′_j*(cos(Q(j-1)_yaw)-cos(Qj_yaw))

wherein, Qj_xCorresponding to the coordinate of the vehicle in the X-axis direction in the world coordinate system at the jth preset target point, Qj_yCorresponding to the coordinate of the vehicle in the Y-axis direction in the world coordinate system at the jth preset target point, Qj_yawPresetting a course angle of a target point for the vehicle at the jth position, Q (j-1)_xThe coordinate of the vehicle in the X-axis direction in the world coordinate system corresponding to the j-1 th preset target point, Q (j-1)_yThe coordinate of the vehicle in the Y-axis direction in the world coordinate system corresponding to the j-1 th preset target point, Q (j-1)_yawAnd presetting a course angle of a target point for the vehicle at the j-1 th position. It should be noted that, when j is equal to i, the pose information (Qi) of the target point is preset at the i-th position by the vehicle (i)_x，Qi_y，Qi_yaw) As initial pose information for calculating the pose information of the vehicle at the jth preset target point.

And step S5, in the kneading stage, determining a third reference curve according to the position of the target library position, and generating a third target track based on the second target point and the third reference curve.

In this embodiment, as shown in fig. 3, in the world coordinate system, the target library position is a rectangle, four vertices of the rectangle are determined to be a first vertex a1, a second vertex a2, a third vertex A3 and a fourth vertex a4, and coordinates of the four vertices are obtained respectively. The third reference curve may be a line that passes through a midpoint of a side formed by the first vertex and the second vertex and is perpendicular to the side formed by the first vertex and the second vertex, or a line that passes through a midpoint of a side formed by the third vertex and the fourth vertex and is perpendicular to the side formed by the third vertex and the fourth vertex.

In the present embodiment, a third target trajectory (trajectory generated as Step3 shown in fig. 2) is generated by a forward looking window tracking algorithm based on the third reference curve, and an end point of the third target trajectory is the third target point.

It should be noted that, as the third target trajectory is generated, the vehicle needs to be simplified into a bicycle model, which is not described herein again. Specifically, the method for generating the third target track by adopting the forward-looking window tracking algorithm comprises the following steps:

updating the first target point to be the second target point;

mapping the rear axle center of the vehicle to be warehoused to the third reference curve based on the second target point to obtain a third mapping point P3(P3x, P3 y);

moving the vehicle to a target storage location D on the third reference curve according to the driving direction of the vehicle by taking the third mapping point P3 as a starting point, and determining the position and orientation information D (Dx, Dy, Dyaw) of the vehicle at the target storage location; and Dx is the coordinate of the vehicle in the X-axis direction in the world coordinate system corresponding to the target storage position, Dy is the coordinate of the vehicle in the Y-axis direction in the world coordinate system corresponding to the target storage position, and Dyaw is the heading angle of the vehicle in the target storage position.

Generating a third target circle which is tangent to the longitudinal direction of the vehicle according to the second target point G2 and the target depot D, wherein the center of the third target circle is a point O3 and the radius of the third target circle is R3; after the second target point G2 and the target library position D are determined, the radius R3 of the third target circle may be obtained according to geometric principles.

Controlling the vehicle to move a preset distance dl on the third target circle by taking a second target point as a starting point to reach a kth preset target point Qk, wherein k is greater than or equal to j, and k is a positive integer;

calculating the front wheel deflection angle and the pose information of the vehicle at the kth preset target point Qk;

judging whether the error between the pose information of the kth preset target point Qk and the pose information of the target library position is smaller than or equal to the preset error or not;

when the error between the pose information of the kth preset target point Qk and the pose information of the target position is smaller than or equal to the preset error, determining that the vehicle reaches the target position;

outputting the third target track, wherein the third target track is a track of the vehicle traveling from the second target point to the target depot on the third target circle;

when the error between the pose information of the kth preset target point Qk and the pose information of the target library position is larger than the preset error, controlling the vehicle to continuously move for a preset distance dl according to the front wheel deflection angle of the kth preset target point Qk; and acquiring the pose information after the vehicle continues to move for a preset distance d1, determining that the vehicle reaches a target library position when the error between the acquired pose information and the pose information of the target library position is less than or equal to the preset error, and outputting the third target track.

In this embodiment, the calculating the front wheel deflection angle and the pose information of the vehicle at the kth preset target point Qk includes:

calculating a target front wheel yaw angle α 3 of the vehicle from the radius R3 of the third target circle_expWherein α 3_exp＝tan^-1(L/R3), L being the wheelbase of the vehicle, i.e. the distance between the front wheels of the vehicle and the rear wheels of the vehicle.

Based on the target front wheel deflection angle alpha 3_expCalculating the angle increment delta alpha of the front wheel deflection angle of the vehicle at the k-th preset target point Qk_k，Δα_k＝α3_exp-α_k. Wherein alpha is_kAnd presetting the actual front wheel deflection angle of the target point Qk for the vehicle at the kth. When k is j, α_kThe front wheel yaw angle of the vehicle at the second target point. When k is larger than j, the radius Rk (k times) of the circle obtained by the current position of the vehicle (such as the coordinates of the k-th preset target point Qk) and the point on the tangent track can be determined, and the front wheel deflection angle alpha of the vehicle calculated by the Ackerman steering principle_k＝tan^-1(L/Rk), L being the wheelbase of the vehicle.

Updating the front wheel deflection angle of the vehicle at the kth preset target point Qk to be alpha based on the angle increment_k′＝α_k-₁+Δα_k。

Calculating a third central angle beta_kThe third central angle isA central angle corresponding to an arc length when the vehicle travels to the kth preset target point on the third target circle, wherein β_k＝k×dl/R_k′；

According to the pose information of the vehicle at the jth preset target point and the third central angle beta_kCalculating the pose information of the vehicle at the kth preset target point through the following formula:

Qk_yaw＝Q(k-1)_yaw+β_k

Qk_x＝Q(k-1)_x+R′k*(sin(Qk_yaw)-sin(Q(k-1)_yaw))

Qk_y＝Q(k-1)_y+R′_k*(cos(Q(k-1)_yaw)-cos(Qk_yaw))

wherein, Qk_XCorresponding to the coordinate of the vehicle in the X-axis direction in a world coordinate system at the k-th preset target point, Qk_yCorresponding to the coordinate of the vehicle in the Y-axis direction in a world coordinate system at the k-th preset target point, Qk_yawIs the course angle, R 'of the vehicle at the k-th preset target point'_k＝L/tanα_k′，Q(k-1)_xThe coordinates of the vehicle in the X-axis direction in the world coordinate system corresponding to the k-1 th preset target point, Q (k-1)_yThe coordinates of the vehicle in the Y-axis direction in the world coordinate system corresponding to the k-1 th preset target point, Q (k-1)_{Variable aw}And presetting a course angle of a target point for the vehicle at the k-1. It should be noted that, when k is j, the pose information (Qj) of the target point is preset at the j-th position by the vehicle (Qj)_x，Qj_y，Qj_yaw) As initial pose information for calculating pose information of the vehicle at a kth preset target point.

In one embodiment, the method for generating a vertical parking trajectory further includes:

generating a parking trajectory based on the first, second, and third target trajectories.

In this embodiment, the vehicle is controlled to travel from an initial position to the first target point according to the first target trajectory, the vehicle is controlled to keep the front wheel yaw angle of the first target point unchanged, the vehicle is controlled to travel from the first target point to the second target point according to the second target trajectory, the vehicle is continuously controlled to keep the front wheel yaw angle of the second target point unchanged, and the vehicle is controlled to travel from the second target point to a target garage position according to the third target trajectory. Therefore, the curvature continuity is met at the joint of the first target track and the second target track (namely, the first target point) and the joint of the second target track and the third target track (namely, the second target point) by fixing the front wheel deflection angle at the joint. The steering wheel angle of the vehicle can be continuously changed, and the steering wheel angle is more consistent with a real driving scene.

And if the abscissa of the initial position coordinate is greater than or equal to the abscissa of the circle center coordinate, determining that the vehicle body does not need to be adjusted again, controlling the vehicle to enter a kneading stage, taking the minimum parking circle as a fourth reference curve of the kneading stage after the vehicle enters the kneading stage, and generating a fourth target track through a forward-looking window tracking algorithm based on the initial position and the fourth reference curve.

In this embodiment, when the abscissa of the initial position coordinate of the vehicle is greater than or equal to the abscissa of the circle center coordinate, the vehicle may be directly controlled to enter a kneading stage, and a fourth target trajectory is generated by using the minimum parking circle as a fourth reference curve of the kneading stage, and the vehicle is controlled to directly reverse and put in storage according to the fourth target trajectory.

In this embodiment, the method of generating the fourth target trajectory is similar to the method of generating the second target trajectory. A second target trajectory is generated by a forward looking window tracking algorithm based on the first target point and the second reference curve, and a fourth target trajectory is generated by a forward looking window tracking algorithm based on the initial position and the fourth reference curve. And the second reference curve and the fourth reference curve are both the minimum parking circles. Therefore, the method of generating the fourth target trajectory will not be described herein.

In this embodiment, when it is determined that the vehicle can be directly backed up and put in storage, the fourth target track may be directly used as a parking track, and the vehicle may be controlled to park in the target storage according to the parking track.

Fig. 1 is a diagram illustrating in detail a vertical parking trajectory generation method according to the present application, by which a vertical parking trajectory generation speed can be increased. The functional modules and the hardware device architecture for implementing the vertical parking trajectory generation device are described below with reference to fig. 5 and 6. It is to be understood that the embodiments are illustrative only and that the scope of the claims is not limited to this configuration.

Fig. 5 is a functional block diagram of a vertical parking trajectory generation device according to an embodiment of the present application.

In some embodiments, the vertical parking trajectory generation apparatus 100 may include a plurality of functional modules composed of program code segments. The program codes of the respective program segments in the vertical parking trajectory generation device 100 may be stored in a memory of the vehicle 10 and executed by at least one processor in the vehicle 10 to implement the function of horizontal autonomous parking.

Referring to fig. 5, in the present embodiment, the vertical parking trajectory generation device 100 may be divided into a plurality of functional modules according to the functions performed by the device, and the functional modules are used for executing the steps in the corresponding embodiment of fig. 1 to realize the function of horizontal autonomous parking. In the present embodiment, the functional modules of the vertical parking trajectory generation device 100 include: the device comprises a dividing module 101, an obtaining module 102 and a generating module 103.

The dividing module 101 is used for dividing the whole stage of parking the vehicle into a target storage position into an initial stage, an adjustment stage, a warehousing stage and a warehouse kneading stage;

the obtaining module 102 is configured to obtain a target position in the target library location and a position coordinate (ob) of an obstacle in the initial stage_x，ob_y) And initial pose information of the vehicle, the initial pose information including initial position coordinates (carp) of the vehicle_x，carp_y) And course angle information;

the generating module 103 is configured to, in the adjusting stage, calculate a minimum parking circle of the warehousing stage based on a first reference curve determined by the initial position coordinates of the vehicle and the position coordinates of the obstacle, where the center coordinates of the minimum parking circle are (Ox, Oy); if the abscissa of the initial position coordinate is smaller than the abscissa of the circle center coordinate, generating a first target track based on the initial position and the first reference curve, wherein the first target track comprises a first target point;

the generating module 103 is further configured to, in the warehousing stage, if the vehicle tail of the vehicle is not located in the target warehousing location, use the minimum parking circle as a second reference curve of the warehousing stage, and generate a second target trajectory based on the first target point and the second reference curve, where the second target trajectory includes a second target point; and

the generating module 103 is further configured to, in the library kneading stage, determine a third reference curve according to the position of the target library position, and generate a third target trajectory based on the second target point and the third reference curve.

Fig. 6 is a schematic structural diagram of a vehicle according to an embodiment of the present application. The vehicle 10 includes a memory 11, a processor 12, and a communication bus 13, wherein the memory 11 is communicatively coupled to the processor 12 via the communication bus 13.

The vehicle 10 further comprises a computer program 14, such as a program for vertical parking trajectory generation, stored in the memory 11 and executable on the processor 12.

The steps of the method for generating a vertical parking trajectory in the exemplary embodiment of the method are implemented when the computer program 14 is executed by the processor 12. Alternatively, the processor 12 executes the computer program 14 to realize the functions of the modules/units in the system embodiment.

Illustratively, the computer program 14 may be partitioned into one or more modules/units, which are stored in the memory 11 and executed by the processor 12 to accomplish the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, the instruction segments describing the execution process of the computer program 14 in the electronic device 1. For example, the computer program 14 may be partitioned into modules 101 and 103 in FIG. 5.

Those skilled in the art will appreciate that the schematic diagram 6 is merely an example of the vehicle 10 and is not intended to limit the vehicle 10, and that the vehicle 10 may include more or fewer components than shown, or some components in combination, or different components, for example, the vehicle 10 may also include input devices, etc.

The Processor 12 may be a Central Processing Unit (CPU), and may include other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and the processor 12 is the control center of the vehicle 10 and connects the various parts of the overall vehicle 10 using various interfaces and lines.

The memory 11 may be used to store the computer program 14 and/or modules/units, and the processor 12 may implement various functions of the vehicle 10 by running or executing the computer program and/or modules/units stored in the memory 11 and invoking data stored in the memory 11. The storage 11 may include an external storage medium and may also include a memory. In addition, the memory 11 may include a high speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.

The integrated modules/units of the vehicle 10, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the methods of the embodiments may be implemented by a computer program, which may be stored in a computer-readable storage medium and used by a processor to implement the steps of the embodiments of the methods. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present application and not for limiting, and although the present application is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present application without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A vertical parking trajectory generation method, characterized by comprising:

in the initial stage, a target position in a target library position and a position coordinate (ob) of an obstacle are acquired_x，ob_y) And initial pose information of the vehicle, the initial pose information including initial position coordinates (carp) of the vehicle_x，carp_y) And course angle information;

2. The method for generating a vertical parking trajectory according to claim 1, further comprising:

if the abscissa of the initial position coordinate is larger than or equal to the abscissa of the circle center coordinate, determining that the vehicle enters a kneading warehouse stage;

taking the minimum mooring circle as a fourth reference curve of the kneading stage;

generating a fourth target trajectory based on the initial position and the fourth reference curve.

3. The vertical parking trajectory generation method according to claim 1 or 2, wherein the first reference curve is determined by the following equation:

wherein the carp_xIs the abscissa, ob, of the initial position of the vehicle_xAnd the abscissa of the position of the obstacle is represented by l, the width of the vehicle body and d1, which is a preset value.

4. The vertical parking trajectory generation method according to claim 3, wherein the center coordinates of the minimum parking circle are calculated by the following formula:

wherein ob_xIs the abscissa, ob, of the position of the obstacle_yIs the ordinate of the position of the obstacle, R is the minimum turning radius of the vehicle, and d2 is the safety distance.

5. The method for generating a vertical parking trajectory according to claim 3, wherein the generating a first target trajectory based on the initial position and the first reference curve includes:

mapping the rear axle center of the vehicle to the first reference curve based on the initial position coordinates of the vehicle to obtain a first mapping point;

moving the vehicle to a first target point on the first reference curve by taking the first mapping point as a starting point according to the driving direction of the vehicle, and determining the pose information of the vehicle at the first target point;

generating a first target circle which is tangent to the longitudinal direction of the vehicle according to the initial position coordinates of the vehicle and the first target point, wherein the center of the first target circle is a point O1, and the radius of the first target circle is R1;

controlling the vehicle to move a preset distance d1 on the first target circle to reach an ith preset target point by taking an initial position as a starting point, wherein i is a positive integer;

calculating the front wheel deflection angle and pose information of the vehicle at the ith preset target point;

judging whether the error between the pose information of the ith preset target point and the pose information of the first target point is smaller than or equal to a preset error or not;

when the error between the pose of the ith preset target point and the pose of the first target point is smaller than or equal to the preset error, determining that the vehicle reaches the first target point;

and outputting the first target track, wherein the first target track is a track of the vehicle on the first target circle from the initial position to the ith preset target point.

6. The method for generating a vertical parking trajectory according to claim 5, wherein the generating a first target trajectory based on the initial position and the first reference curve further comprises:

when the error between the pose of the ith preset target point and the pose of the first target point is larger than the preset error, controlling the vehicle to continuously move for a preset distance d1 according to the front wheel deflection angle of the ith preset target point;

acquiring the pose information of the vehicle after the vehicle continues to move for a preset distance d1, and determining that the vehicle reaches a first target point when the error between the acquired pose information and the pose of the first target point is less than or equal to the preset error;

and outputting the first target track, wherein the first target track is a track of the vehicle on the target circle from the initial position to the ith preset target point.

7. The vertical parking trajectory generation method according to claim 5, wherein the calculating of the front wheel deflection angle and the pose information of the vehicle at the i-th preset target point includes:

calculating a target front wheel yaw angle α 1 of the vehicle from the radius R1 of the first target circle_expIn which α 1_exp＝tanh^-1(L/R1), L being the wheelbase of the vehicle;

calculating an angle increment delta alpha of a front wheel deflection angle of the vehicle at the i-th preset target point Qi_i，Δα_i＝α1_exp-α_iWherein, α is_iPresetting an actual front wheel deflection angle of a target point Qi for the vehicle at the ith;

updating the front wheel deflection angle of the vehicle at the i-th preset target point Qi to be alpha_i′＝α_i-1+Δα_i；

Calculating a first central angle beta_iThe first central angle is a central angle corresponding to an arc length when the vehicle runs to the ith preset target point on the first target circle, wherein beta is_i＝i×d1/R′_i；

According to the initial pose information of the vehicle and the first central angle beta_iCalculating the pose information of the vehicle at the ith preset target point through the following formula,

Qi_yaw＝Q(i-1)_yaw+β_i

Qi_x＝Q(i-1)_x+R′_i*(sin(Qi_yaw)-sin(Q(i-1)_yaw))

Qi_y＝Q(i-1)_y+R′_i*(cos(Q(i-1)_yaw)-cos(Qi_yaw))

wherein R'_i＝L/tanα_i′，Qi_xFor the coordinates of the vehicle in the direction of the X-axis in the world coordinate system at the ith preset target point, Qi_yFor the coordinates of the vehicle in the direction of the Y axis in the world coordinate system when the i-th preset target point is located, Qi_yawFor the vehicle in the ith preset target point course angle, Q (i-1)_xFor the vehicle in the i-1 th preset target point corresponding to the X-axis coordinate in the world coordinate system, Q (i-1)_yFor the vehicle in the i-1 th preset target point corresponding to the Y-axis coordinate in the world coordinate system, Q (i-1)_yawAnd presetting a course angle of the vehicle at the i-1 th target point.

8. The vertical parking trajectory generation method according to any one of claims 4 to 7, wherein the generating a second target trajectory based on the first target point and the second reference curve includes:

updating the initial position of the vehicle to be the first target point;

based on the first target point, mapping the rear axle center of the vehicle to the second reference curve to obtain a second mapping point;

moving the vehicle to a second target point on the second reference curve according to the driving direction of the vehicle by taking the second mapping point as a starting point, and determining the pose information of the vehicle at the second target point;

generating a second target circle which is tangent to the longitudinal direction of the vehicle according to the first target point and the second target point, wherein the center of the second target circle is a point O2, and the radius is R2;

controlling the vehicle to move a preset distance d1 on the second target circle to reach a jth preset target point by taking a first target point as a starting point, wherein j is greater than or equal to i, and j is a positive integer;

calculating the front wheel deflection angle and pose information of the vehicle at the jth preset target point;

judging whether the error between the pose information of the jth preset target point and the pose information of the second target point is smaller than or equal to the preset error or not;

when the error between the pose information of the jth preset target point and the pose information of the second target point is smaller than or equal to the preset error, determining that the vehicle reaches the second target point;

and outputting the second target track, wherein the second target track is a track of the vehicle running from the first target point to the jth preset target point on the second target circle.

9. The method for generating a vertical parking trajectory according to claim 8, wherein the generating a second target trajectory based on the first target point and the second reference curve further comprises:

when the error between the pose information of the jth preset target point and the pose information of the second target point is larger than the preset error, controlling the vehicle to continuously move for a preset distance d1 according to the front wheel deflection angle of the jth preset target point;

and acquiring the pose information of the vehicle after the vehicle continuously moves for a preset distance d1, determining that the vehicle reaches a second target point when the error between the pose information of the jth preset target point and the pose information of the second target point is less than or equal to the preset error, and outputting a second target track.

10. The vertical parking trajectory generation method according to claim 9, wherein the calculating of the front wheel deflection angle and the pose information of the vehicle at the j-th preset target point includes:

calculating a target front wheel yaw angle α 2 of the vehicle from the radius R2 of the second target circle_expWherein α 2_exp＝tanh^-1(L/R2), L being the wheelbase of the vehicle;

calculating the angle increment delta alpha of the front wheel deflection angle of the vehicle at the jth preset target point_jWherein, Δ α_j＝α2_exp-α_j；

Updating the front wheel deflection angle of the vehicle at the jth preset target point Qj to alpha_j', wherein, α_j′＝α_j-1+Δα_j；

Calculating a second central angle beta_jThe second central angle is a central angle corresponding to an arc length when the vehicle runs to the jth preset target point on the second target circle, wherein β is_j＝j×d1/R′_j；

According to the pose information of the vehicle at the j preset target point and the second central angle beta_jCalculating the pose information of the vehicle at the jth preset target point through the following formula,

Qj_yaw＝Q(j-1)_yaw+β_j

Qj_x＝Q(j-1)_x+R′_j*(sin(Qj_yaw)-sin(Q(j-1)_yaw))

Qj_y＝Q(j-1)_y+R′_j*(cos(Q(j-1)_yaw)-cos(Qj_yaw))

wherein R'_j＝L/taα_j′，Qj_xCorresponding to the coordinate of the vehicle in the X-axis direction in the world coordinate system at the jth preset target point, Qj_yCorresponding to the coordinate of the vehicle in the Y-axis direction in the world coordinate system at the jth preset target point, Qj_yawPresetting a course angle of a target point for the vehicle at the jth position, Q (j-1)_xFor the vehicle at j-1Let the target point correspond to the coordinate in the X-axis direction in the world coordinate system, Q (j-1)_yThe coordinate of the vehicle in the Y-axis direction in the world coordinate system corresponding to the j-1 th preset target point, Q (j-1)_yawAnd presetting a course angle of a target point for the vehicle at the j-1 th position.

11. The vertical parking trajectory generation method according to claim 8, wherein the generating a third target trajectory based on the second target point and the third reference curve includes:

updating the first target point to be the second target point;

based on the second target point, mapping the rear axle center of the vehicle to be warehoused to the third reference curve to obtain a third mapping point;

moving the vehicle to a target storage location on the third reference curve by taking the third mapping point as a starting point according to the driving direction of the vehicle, and determining the pose information of the vehicle at the target storage location;

generating a third target circle which is tangent to the longitudinal direction of the vehicle according to the second target point and the target position, wherein the center of the third target circle is a point O3, and the radius is R3;

controlling the vehicle to move a preset distance d1 on the third target circle by taking a second target point as a starting point to reach a kth preset target point, wherein k is greater than or equal to j, and k is a positive integer;

calculating the front wheel deflection angle and pose information of the vehicle at the kth preset target point;

judging whether the error between the pose information of the kth preset target point and the pose information of the target library position is smaller than or equal to the preset error or not;

when the error between the pose information of the kth preset target point and the pose information of the target position is smaller than or equal to the preset error, determining that the vehicle reaches the target position;

and outputting the third target track, wherein the third target track is a track of the vehicle running from the second target point to the target storage position on the third target circle.

12. The method for generating a vertical parking trajectory according to claim 11, wherein the generating a third target trajectory based on the second target point and the third reference curve further comprises:

when the error between the pose information of the kth preset target point and the pose information of the target library position is larger than the preset error, controlling the vehicle to continuously move for a preset distance d1 according to the front wheel deflection angle of the kth preset target point;

and acquiring the pose information after the vehicle continues to move for a preset distance d1, determining that the vehicle reaches a target library position when the error between the acquired pose information and the pose information of the target library position is less than or equal to the preset error, and outputting the third target track.

13. The vertical parking trajectory generation method according to claim 11, wherein the calculating the front wheel deflection angle and the pose information of the vehicle at the k-th preset target point includes:

calculating a target front wheel yaw angle α 3 of the vehicle from the radius R3 of the third target circle_expWherein α 3_exp＝tanh^-1(L/R3), L being the wheelbase of the vehicle;

calculating the angle increment delta alpha of the front wheel deflection angle of the vehicle at the k-th preset target point_k，Δα_k＝α3_exp-α_k；

Updating the front wheel deflection angle of the vehicle at the k-th preset target point to be alpha_k', wherein, α_k′＝α_k-1+Δα_k；

Calculating a third central angle beta_kThe third central angle is a central angle corresponding to an arc length of the vehicle when the vehicle travels to the kth preset target point on the third target circle, wherein β_k＝k×d1/R′_k；

According to the pose information of the vehicle at the k-th preset target point and the third central angle beta_kBy the followingCalculating the pose information of the vehicle at the k-th preset target point by a formula,

Qk_yaw＝Q(k-1)_yaw+β_k

Qk_x＝Q(k-1)_x+R′_k*(sin(Qk_yaw)-sin(Q(k-1)_yaw))

Qk_y＝Q(k-1)_y+R′_k*(cos(Q(k-1)_yaw)-cos(Qk_yaw))

wherein R'_k＝L/tanα_k′，Qk_xCorresponding to the coordinate of the vehicle in the X-axis direction in a world coordinate system at the k-th preset target point, Qk_yCorresponding to the coordinate of the vehicle in the Y-axis direction in a world coordinate system at the k-th preset target point, Qk_yawPresetting a course angle of a target point for the vehicle at the kth, Q (k-1)_xThe coordinates of the vehicle in the X-axis direction in the world coordinate system corresponding to the k-1 th preset target point, Q (k-1)_yThe coordinates of the vehicle in the Y-axis direction in the world coordinate system corresponding to the k-1 th preset target point, Q (k-1)_yawAnd presetting a course angle of a target point for the vehicle at the k-1.

14. A vertical parking trajectory generation device, characterized by comprising:

an acquisition module for acquiring a target position in the target library location and a position coordinate (ob) of the obstacle at the initial stage_x，ob_y) And initial pose information of the vehicle, the initial pose information including initial position coordinates (carp) of the vehicle_x，carp_y) And course angle information;

15. A vehicle, characterized in that the vehicle comprises:

the device comprises a memory, a processor and a communication bus, wherein the memory is in communication connection with the processor through the communication bus; and

the memory stores a plurality of program modules that are loaded by the processor and execute the vertical parking trajectory generation method according to any one of claims 1 to 13.

16. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a vertical parking trajectory generation method according to any one of claims 1 to 13.