CN111196271A

CN111196271A - Automatic parking method, device, equipment and storage medium

Info

Publication number: CN111196271A
Application number: CN202010071959.XA
Authority: CN
Inventors: 黄满洪; 罗铭; 裴超颖; 陈聪; 江键鑫; 李贵龙
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Apollo Intelligent Technology Beijing Co Ltd
Priority date: 2020-01-21
Filing date: 2020-01-21
Publication date: 2020-05-26

Abstract

The application discloses an automatic parking method, device, equipment and storage medium, and relates to the technical field of autonomous parking. The specific implementation scheme is as follows: the method comprises the steps of obtaining position information of a vehicle to be parked and azimuth information of a parking space, and determining a driving track of the vehicle to be parked according to the position information and the azimuth information, wherein the driving track comprises: the method comprises the steps of displacing a track and a driving speed, and further controlling a vehicle to be parked to move on the basis of the driving track so as to enable the vehicle to be parked on a parking space, namely, the determined driving track is not influenced by a parking starting position on the basis of the position of the vehicle to be parked and the direction information of the parking space, the driving speed is planned at the same time, and the parking success rate is improved.

Description

Automatic parking method, device, equipment and storage medium

Technical Field

The present application relates to the field of automatic driving technologies, and in particular, to an automatic parking method, an automatic parking device, an automatic parking apparatus, and a storage medium in an autonomous parking technology.

Background

The automatic parking system can automatically find the parking space, and a driver does not need to operate a steering wheel and observe the surrounding environment condition in the parking process, so that collision-free successful parking is realized. The planning control method is a key link in the automatic parking process, whether a comfortable, safe and collision-free parking path can be planned according to the environmental information acquired by the sensor, and the parking is automatically completed according to the planned parking path, so that the success rate of automatic parking is determined.

In the prior art, a geometric planning control method is generally adopted to plan a parking path. Specifically, according to the environment information of the vehicle to be parked acquired by the sensor, when the vehicle to be parked and the parking space meet certain conditions, a parking system is triggered to start, and then the vehicle to be parked is successfully parked through the processes of backward backing, forward library rubbing, backward library rubbing, linear backing and the like.

However, in the method, the starting of the parking system is greatly influenced by the parking starting position, the parking function can be started only when the vehicle to be parked and the parking space meet certain conditions, and the condition of brake scram is not considered in the parking process, so that the problem of low parking success rate exists.

Disclosure of Invention

The embodiment of the application provides an automatic parking method, device, equipment and storage medium, which are used for solving the problem of low parking success rate of the existing parking system.

In a first aspect, the present application provides an automatic parking method, comprising:

determining a driving track of the vehicle to be parked according to the position information of the vehicle to be parked and the azimuth information of the parking space, wherein the driving track comprises: displacement trajectory and travel speed;

and controlling the vehicle to be parked to move based on the running track so as to park the vehicle to be parked on the parking space.

In the embodiment, the determined running track is not influenced by the parking starting position based on the position of the vehicle to be parked and the direction information of the parking space, the running speed is planned, and the parking success rate is improved.

In a possible design of the first aspect, the determining a driving track of the vehicle to be parked according to the position information of the vehicle to be parked and the azimuth information of the parking space includes:

determining a displacement track of the vehicle to be parked according to the position information of the vehicle to be parked, the environment information of the area where the vehicle to be parked is located and the azimuth information of the parking space;

and determining the running speed of the vehicle to be parked according to the length of the displacement track.

In this embodiment, after the displacement trajectory is determined, the driving speed of the vehicle to be parked can be set according to the length of the displacement trajectory, so that when the vehicle to be parked is close to the parking space, the user experience is improved, the unsafe feeling of drivers and passengers is reduced, and sufficient reaction time is reserved for the drivers and passengers after the vehicle-mounted detection equipment fails.

Optionally, the determining the displacement trajectory of the vehicle to be parked according to the position information of the vehicle to be parked, the environmental information of the area where the vehicle to be parked is located, and the azimuth information of the parking space includes:

establishing a garage coordinate system according to the azimuth information of the parking space to be parked;

converting the position information of the vehicle to be parked into vehicle position information expressed based on the garage coordinate system, and converting the environment information of the area where the parking space is located into the boundary constraint condition of the parking space;

and determining the displacement track of the vehicle to be parked by taking the minimum number of parking vehicles as a target according to the vehicle position information represented by the garage coordinate system and the boundary constraint condition of the parking space to be parked.

In the embodiment, the optimal parking number (the minimum parking number) is used as a target, and under the guidance of the prior global path driving experience, the target position (parking space) and the boundary constraint condition are combined, and the planned displacement trajectory can be obtained through calculation by a geometric method.

In another possible design of the first aspect, before the controlling the vehicle to be parked to move based on the travel track, the method further includes:

determining a driving area of the vehicle to be parked according to the driving track;

acquiring information of the detected at least one obstacle of the vehicle to be parked based on the driving area;

determining a target obstacle in the at least one obstacle, wherein the target obstacle is the obstacle having the largest influence on the driving track in the at least one obstacle;

determining a processing plan for the driving track according to the position information of the target obstacle and the range of the driving area;

updating the travel trajectory based on the processing plan.

In the technical scheme, the determined driving track is updated by combining the detected obstacle information, so that the usability of the driving track can be ensured, and the comfort of drivers and passengers can be improved.

Optionally, the determining a processing plan for the driving trajectory according to the position information of the target obstacle and the range of the driving area includes:

if the target obstacle is not in the range of the driving area, keeping the driving track unchanged;

if the target obstacle is in the range of the driving area, determining the distance between the target obstacle and the vehicle to be parked in the driving direction of the vehicle;

when the distance is greater than or equal to the effective detection distance of the vehicle to be parked but smaller than the maximum detection distance of the vehicle to be parked, controlling the running speed in the running track to be changed into a preset speed, wherein the value of the preset speed is smaller than that of the running speed;

when the distance is smaller than the effective detection distance of the vehicle to be parked but larger than the safe braking distance of the vehicle to be parked, controlling the running speed in the running track to be changed into a linear decreasing speed;

and when the distance is smaller than or equal to the safe stopping distance of the vehicle to be parked, controlling the running speed in the running track to be changed into the maximum deceleration so as to stop the vehicle to be parked in the shortest time length.

In the embodiment, after the driving track is determined, the obstacle processing strategy is adopted, so that the comfort is improved under the condition of ensuring the safety, the automatic parking system can better meet the requirements of users, the user experience of the system is greatly improved, and the competitive power of products on the market is enhanced.

In still another possible design of the first aspect, the controlling the vehicle to be parked to move based on the driving track so that the vehicle to be parked is parked at the parking space includes:

calculating deviation according to the position information of the vehicle to be parked and the running track to obtain speed deviation, transverse distance deviation and course angle deviation;

determining the running acceleration of the vehicle to be parked according to the speed deviation and a speed controller of the vehicle to be parked, wherein the speed controller is designed and formed by adopting a PID method;

determining the running direction of the vehicle to be parked according to the transverse distance deviation, the course angle deviation and a direction controller of the vehicle to be parked, wherein the direction controller is designed and formed by adopting a PID method;

and controlling the vehicle to be parked to run based on the running track according to the running acceleration and the running direction so as to enable the vehicle to be parked on the parking space.

According to the technical scheme, in the parking process, the parking direction and speed are adjusted based on the speed deviation, the transverse distance deviation and the course angle deviation, and the parking success rate is further improved.

In yet another possible design of the first aspect, the vehicle to be parked adopts at least one of the following adjustment manners during parking the parking space: forward adjustment, downward kneading and adjustment in the storehouse, upward kneading and adjustment in the storehouse.

According to the technical scheme, based on parking spaces and lane line information in the environment, the longitudinal and transverse distances of the vehicle are adjusted in a forward adjusting mode, the problem that the starting area of the automatic parking system is too small is solved, and the starting area and the parking success rate of parking can be effectively improved.

In yet another possible design of the first aspect, the method further includes:

acquiring contour parameters of the vehicle to be parked; and processing the head of the vehicle to be parked into an arc-shaped profile according to the profile parameters of the vehicle to be parked.

In the embodiment, the loss of the driving space caused by insufficient consideration of the outer contour in a narrow space is solved by accurately fitting the outer contour of the vehicle with a curve, and the success rate of parking is improved.

In a second aspect, the present application provides an automatic parking apparatus comprising: the device comprises a processing module and a control module;

the processing module is used for determining a driving track of the vehicle to be parked according to the position information of the vehicle to be parked and the azimuth information of the parking space, and the driving track comprises: displacement trajectory and travel speed;

the control module is used for controlling the vehicle to be parked to move based on the running track so as to enable the vehicle to be parked on the parking space.

In a possible design of the second aspect, the processing module is specifically configured to determine a displacement trajectory of the vehicle to be parked according to the position information of the vehicle to be parked, the environment information of the area where the vehicle to be parked is located, and the azimuth information of the parking space, and determine the driving speed of the vehicle to be parked according to the length of the displacement trajectory.

Optionally, the processing module is configured to determine a displacement trajectory of the vehicle to be parked according to the position information of the vehicle to be parked, the environmental information of the area where the vehicle to be parked is located, and the azimuth information of the parking space, and specifically includes:

the processing module is specifically configured to establish a garage coordinate system according to the azimuth information of the parking space, convert the position information of the vehicle to be parked into vehicle position information expressed based on the garage coordinate system, convert the environment information of the area where the parking space is located into the boundary constraint condition of the parking space, and determine the displacement trajectory of the vehicle to be parked according to the vehicle position information expressed by the garage coordinate system and the boundary constraint condition of the parking space, with the minimum number of parking bars as a target.

In another possible design of the second aspect, the processing module is further configured to, before the control module controls the vehicle to be parked to move based on the travel track, determine a travel area of the vehicle to be parked according to the travel track, acquire information of at least one detected obstacle of the vehicle to be parked based on the travel area, determine a target obstacle among the at least one obstacle, where the target obstacle is an obstacle having the greatest influence on the travel track, determine a processing plan for the travel track according to the position information of the target obstacle and the range of the travel area, and update the travel track based on the processing plan.

Optionally, the processing module is configured to determine a processing plan for the travel track according to the position information of the target obstacle and the range of the travel area, and specifically includes:

the processing module is specifically configured to keep the travel track unchanged when the target obstacle is not within the range of the travel area, determine a distance between the target obstacle and the vehicle to be parked in the vehicle travel direction when the target obstacle is within the range of the travel area, control the travel speed in the travel track to change to a preset speed when the distance is greater than or equal to an effective detection distance of the vehicle to be parked but less than a maximum detection distance of the vehicle to be parked, control the travel speed in the travel track to change to a linearly decreasing speed when the distance is less than the effective detection distance of the vehicle to be parked but greater than a brake safe distance of the vehicle to be parked, and control the travel speed in the travel track to change to a linearly decreasing speed when the distance is less than or equal to the brake safe distance of the vehicle to be parked, and controlling the running speed in the running track to be changed into the maximum deceleration so as to stop the vehicle to be parked in the shortest time length.

In yet another possible design of the second aspect, the control module is specifically configured to perform deviation calculation according to the position information of the vehicle to be parked and the driving track to obtain a speed deviation, a lateral distance deviation, and a heading angle deviation, determine the driving acceleration of the vehicle to be parked according to the speed deviation and a speed controller of the vehicle to be parked, where the speed controller is designed by using a PID method, determine the driving direction of the vehicle to be parked according to the lateral distance deviation, the heading angle deviation, and a direction controller of the vehicle to be parked, and the direction controller is designed by using a PID method, and control the vehicle to be parked to drive on the driving track according to the driving acceleration and the driving direction, so that the vehicle to be parked is parked at the parking space.

In yet another possible design of the second aspect, the vehicle to be parked adopts at least one of the following adjustment manners during parking the parking space: forward adjustment, downward kneading and adjustment in the storehouse, upward kneading and adjustment in the storehouse.

In another possible design of the second aspect, the processing module is further configured to obtain a contour parameter of the vehicle to be parked, and process the nose of the vehicle to be parked into an arc-shaped contour according to the contour parameter of the vehicle to be parked.

The apparatus provided in the second aspect of the present application may be configured to perform the method provided in the first aspect, and the implementation principle and the technical effect are similar, which are not described herein again.

In a third aspect, the present application provides an electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the first aspect and its various possible designs.

In a fourth aspect, the present application provides a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of the first aspect as well as possible designs of the first aspect.

In a fifth aspect, the present application provides an automatic parking method, comprising:

planning a parking track and a parking speed of a vehicle to be parked according to the relationship between the position information of the vehicle to be parked and the azimuth information of the parking space to be parked;

and controlling the vehicle to be parked to park at the parking speed by taking the parking track as a reference.

One embodiment in the above application has the following advantages or benefits: the method comprises the steps of obtaining position information of a vehicle to be parked and azimuth information of a parking space, and determining a driving track of the vehicle to be parked according to the position information and the azimuth information, wherein the driving track comprises: the method comprises the steps of displacing a track and a driving speed, and further controlling a vehicle to be parked to move on the basis of the driving track so as to enable the vehicle to be parked on a parking space, namely, the determined driving track is not influenced by a parking starting position on the basis of the position of the vehicle to be parked and the direction information of the parking space, the driving speed is planned at the same time, and the parking success rate is improved.

Other effects of the above-described alternative will be described below with reference to specific embodiments.

Drawings

The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:

fig. 1 is a schematic view of an application scenario of an automatic parking method according to an embodiment of the present application;

fig. 2 is a schematic flow chart of an automatic parking method according to a first embodiment of the present application;

FIG. 3 is a schematic diagram of a coordinate system of the garage according to the present embodiment;

FIG. 4 is a schematic view of a mirror relationship between a left garage and a right garage in a garage coordinate system;

FIG. 5 is a schematic diagram of checking whether the maximum downward kneading pool radius can be obtained in the kneading pool process;

FIG. 6 is a schematic view of dangerous points and operation features that may be concerned when a vehicle to be parked enters a garage;

FIG. 7 is a schematic illustration of Ackerman steering of a vehicle;

fig. 8 is a schematic flow chart of an automatic parking method according to a second embodiment of the present application;

FIG. 9 is a schematic diagram of a speed plan corresponding to a driving trajectory;

fig. 10 is a flowchart illustrating an automatic parking method according to a third embodiment of the present application;

FIG. 11 is a schematic view of the geometric relationship between the position of the vehicle to be parked and the desired position;

FIG. 12 is a schematic diagram of a bilinear interpolation method;

FIG. 13 is a schematic view of determining a direction of travel of a vehicle to be parked;

FIG. 14 is a schematic view of a parking process of a vehicle to be parked;

FIG. 15 is a schematic shape view of the outer contour of the vehicle;

FIG. 16 is a schematic view of a selection of arc-shaped contour points of a vehicle nose;

fig. 17 is a schematic view of a control process of automatic parking;

FIG. 18 is a schematic diagram comparing an automatic start area supportable by the automatic parking system of the present application with an existing automatic parking system;

fig. 19 is a schematic structural diagram of an automatic parking device according to an embodiment of the present application;

fig. 20 is a block diagram of an electronic device for implementing the automatic parking method according to the embodiment of the present application.

Detailed Description

The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

An Automatic Parking System (APS) is also called as an automatic parking position, namely, the automatic parking system can automatically find a parking space, a driver does not need to operate a steering wheel and observe the surrounding environment condition in the parking process, and a system for automatically and correctly completing the action of parking into the parking space can be realized through a vehicle-mounted detection device (parking radar) and a vehicle-mounted processor, so that a great amount of time and energy are saved for the driver, particularly a novice driver, and the collision accident caused by the lack of the parking experience of the driver is greatly compensated. The planning control method is a key link of automatic parking, is a brain for automatic parking operation of vehicles, and the intelligentization degree of the planning control method is the embodiment of the intelligentization level of the whole automatic parking system. Therefore, whether a comfortable and safe non-collision parking path can be planned according to the environmental information acquired by the vehicle-mounted sensor, and whether the vehicle steering system, the braking system and the power system are automatically controlled to complete parking along the planned parking path will determine the success rate of automatic parking.

At present, a geometric planning control method is generally adopted in an automatic parking algorithm, specifically, a sensor is adopted to obtain environment information of an area where a vehicle to be parked is located, an environment global coordinate system is established, the position between the vehicle to be parked and a parking space is determined according to the global coordinate system, then the vehicle is backed up after the vehicle to be parked meets a critical intersection state, and then the vehicle is backed up backwards after the vehicle is backed up backwards, wherein the vehicle adopts a minimum turning radius R_minForward kneading the garage until the vehicle runs forward to a set boundary constraint condition or runs to a stop of an obstacle and still can meet the warehousing condition, switching the vehicle back to a backward kneading state, and finally, if the vehicle can find that the radius of the backward kneading garage is tangent to the central axis, directly switching the vehicle to a straight backward reversing state, otherwise, repeating the steps until the vehicle to be parked can run forward to a set boundary constraint condition, or stopping the vehicle until the vehicle to be parked can still meet the warehousing conditionThe condition that the radius of the kneading warehouse is tangent to the central axis in the backward process is met, and finally the automatic warehousing of the vehicle to be parked is realized.

However, the above-described conventional parking system has the following problems:

1) the parking success rate is greatly influenced by the parking starting position, a side vehicle needs to keep a certain lateral and longitudinal distance to park the vehicle, otherwise, a parking system cannot be triggered to start;

2) the parking planning algorithm has 2 extremes, one mode is a planning method adopting numerical optimization, the optimal solution is carried out through a modeling mode, the environment information can be considered globally, but the calculation amount is large, the real-time performance is poor, and the other mode is a geometric planning method which has good real-time performance but lacks the consideration of the global environment, so that the collision caused by insufficient consideration of obstacles is easily caused;

3) the parking speed planning adopts a constant speed as a planning speed, the planning speed has a sudden change condition, so that the user experience feeling can be reduced, meanwhile, as the target distance is closer and closer, the planning speed is not reduced and is close, the unsafe feeling of drivers and passengers is easily brought, the drivers and passengers are worried about hitting the target, and after the sensor fails, the reaction time reserved for the drivers and passengers in a non-deceleration mode is shorter;

4) the parking realizes the vehicle motion in a small range, the requirements on the control precision of the position and the gesture are high, the existing path following method has poor universality and insufficient local precision, and particularly the gesture angle precision of the termination position does not reach the standard.

In summary, the existing automatic parking method has the problem of low success rate of parking.

In view of the above method, an embodiment of the present application provides an automatic parking method, which obtains position information of a vehicle to be parked and azimuth information of a parking space, and determines a driving track of the vehicle to be parked according to the position information and the azimuth information, where the driving track includes: the method comprises the steps of displacing a track and a driving speed, and further controlling a vehicle to be parked to move on the basis of the driving track so as to enable the vehicle to be parked on a parking space, namely, the determined driving track is not influenced by a parking starting position on the basis of the position of the vehicle to be parked and the direction information of the parking space, the driving speed is planned at the same time, and the parking success rate is improved.

The automatic parking method of the embodiment of the application is mainly a planning control method of a driving track, and the following requirements are met: firstly, a vehicle to be parked can be automatically parked into a parking space from a certain position without collision in an automatic driving state, the higher the experience efficiency is, the better the experience efficiency is, and the more comfortable the body feeling is, the better the experience efficiency is; secondly, in order to meet the requirement of low computation power and mass production, the planning control method cannot use complex algorithm operation, otherwise the computation power of the vehicle to be parked is easily exceeded.

Specifically, the automatic parking method mainly comprises two main links: (1) planning a link: the method comprises the following steps of dividing into a transverse planning mode and a longitudinal planning mode, wherein the transverse planning mode judges a forward or reverse mode of a vehicle to be parked according to the relative position relation between the vehicle to be parked and a parking space to be parked, the azimuth information of the parking space to be parked and the environment information of an area where the parking space to be parked is located, a displacement track in a corresponding direction is generated by adopting a straight line and arc curve planning mode, and the longitudinal planning mode generates a corresponding speed planning mode by combining a uniform acceleration/deceleration motion principle according to the length of the displacement track; (2) and (3) a control link: calculating deviation amount according to the position information of the vehicle to be parked and the planned driving track, converting the solved displacement deviation and the solved course angle deviation into a transverse control expected steering wheel angle through a PID method, converting the solved speed deviation into a longitudinal control expected acceleration through the PID method, and realizing the tracking of the vehicle on the planned track through the expected steering wheel angle and the expected acceleration.

In the embodiment of the application, on a low-computation-power mass-producible platform (an on-board processor), a planning control method mainly adopts a geometric planning algorithm with small computation amount and high efficiency, such as a linear planning method and a polynomial planning method, and the control adopts a PID algorithm which is simplest and can embody a feedback idea most, so that the real-time performance of the planning control method is ensured.

Further, the preset algorithm in the embodiment is mainly implemented by a general algorithm, but an advanced design concept is fused in the logic implementation process of the algorithm, which is mainly shown in that: the method comprises the steps of considering prior global path driving experience, guiding path planning, considering path and speed unification, realizing a comfortable obstacle processing strategy, considering the complete geometric shape of a vehicle body, not making approximation, ensuring the success rate and the reasonability of solution in a crowded environment, considering vehicle position and angle tracking deviation, and adopting a linear combination PID method to guarantee the requirements of vehicle end point position and angle precision.

It can be understood that, in practical applications, the products to which the present technical solution can be applied may include: an automatic parking system or an autonomous parking system for vehicles, etc.

It is to be understood that before describing particular embodiments of the present application, a description will first be given of an application scenario of the present application.

Fig. 1 is a schematic application scenario diagram of an automatic parking method according to an embodiment of the present application. Referring to fig. 1, the application scenario may include: the parking device comprises a vehicle to be parked on a road and a plurality of parking spaces on two sides of the road. The vehicle-mounted detection device can detect obstacle information around the vehicle to be parked, the vehicle-mounted processor can determine a parking space of the vehicle to be parked according to the detected obstacle information and environment information of an area where the vehicle to be parked is located, and then the driving track, which is required to move when the vehicle to be parked is parked in the parking space, is determined based on the position information of the vehicle to be parked, the azimuth information of the parking space and the obstacle information around the vehicle to be parked.

In this embodiment, the vehicle-mounted detection device may also detect characteristics of surrounding objects during the driving process of the autonomous vehicle, for example, characteristics such as a driving direction and a driving path of a traffic participant, and information such as a distance change with a road obstacle or a roadside stationary object.

The onboard processor may be called a vehicle computer or an onboard unit (OBU) in the vehicle to be parked, and may not only realize automatic control of the vehicle to be parked, but also complete some other operations. The embodiment of the application does not limit the specific operation executed by the onboard processor, and can be determined according to actual conditions.

For example, the vehicle to be parked in the embodiment of the present application may be an autonomous vehicle or a manned vehicle, and the present application is not limited thereto.

It is understood that the execution subject of the embodiment of the present application may be an onboard device, for example, an onboard processor such as a vehicle computer or an onboard unit. The concrete expression form of the vehicle-mounted equipment can be determined according to actual conditions.

The technical solution of the present application will be described in detail below with reference to specific examples. It should be noted that the following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

Fig. 2 is a schematic flow chart of an automatic parking method according to a first embodiment of the present application. As shown in fig. 2, the automatic parking method may include the steps of:

s21, determining the driving track of the vehicle to be parked according to the position information of the vehicle to be parked and the azimuth information of the parking space, wherein the driving track comprises: displacement trajectory and travel speed.

In this embodiment, when there is a demand for stopping a vehicle to be parked at a parking space on both sides of a road, the vehicle-mounted device may first determine position information of the vehicle to be parked and azimuth information (including the position information and the direction information) of the parking space, further determine a displacement trajectory of the vehicle to be parked through a preset path planning method based on the position information of the vehicle to be parked and the azimuth information of the parking space, and finally determine a planned speed of the vehicle to be parked when the vehicle is parked at the parking space based on the displacement trajectory.

As an example, the step S21 can be specifically implemented by the following steps:

and A1, determining the displacement track of the vehicle to be parked according to the position information of the vehicle to be parked, the environment information of the area where the vehicle to be parked is located and the azimuth information of the parking space.

In this embodiment, before determining the displacement trajectory of the vehicle to be parked, the vehicle-mounted device first performs data preprocessing on the acquired information, which is mainly to perform unified processing on the environmental information of the area where the vehicle to be parked is located and the azimuth information of the parking space, and establish a garage coordinate system, so that path planning of vehicle entering the garage is realized under the garage coordinate system.

Furthermore, in order to facilitate calculation of the planning algorithm, environment information of the area where the vehicle to be parked is located can be converted into a target position and boundary constraints and displayed in the form of a point set. The system can be related to the selection of a garage coordinate system, the coordinate conversion and other related processing.

Optionally, in this embodiment, a specific manner of determining the displacement trajectory of the vehicle to be parked is as follows:

a11, establishing a garage coordinate system according to the azimuth information of the parking space.

For example, fig. 3 is a schematic diagram of a coordinate system of the garage in this embodiment. As shown in fig. 3, the vehicle-mounted device may establish a garage coordinate system according to the acquired azimuth information of the parking space. The garage coordinate system comprehensively considers algorithm code multiplexing and can be compatible with a vertical library, a parallel library and an inclined library. Specifically, referring to FIG. 3, points A ', B', C ', and D' constitute a vertical library A 'B' C 'D', and point A, B, C, D constitutes an oblique library ABCD.

Optionally, the garage coordinate system further conforms to the idea of realizing left and right garage entering through mirroring. For example, fig. 4 is a schematic diagram illustrating a mirror relationship between a left library and a right library in a garage coordinate system. As shown in fig. 4, in the planning process of the parking method, based on only right-entering processing (shown by a solid line), but when left-entering processing (shown by a dashed line) occurs, referring to fig. 4, the center-to-perpendicular line of AB is taken as a symmetry axis, four corner points of the garage and the vehicle pose are respectively mirrored, the pose information of the vehicle is processed according to right-entering processing, and after a driving track is calculated, the mirroring processing is performed and output.

And A12, converting the position information of the vehicle to be parked into vehicle position information expressed based on a garage coordinate system, and converting the environment information of the area where the parking space is located into the boundary constraint condition of the parking space.

In this embodiment, after the garage coordinate system is established, the vehicle-mounted device may perform conversion processing on the position information of the vehicle to be parked and the environment information of the area where the vehicle to be parked, for example, convert the road information of the vehicle to be parked, the obstacle information of the area where the vehicle is located, and the position information of the vehicle to be parked into the coordinates of the garage coordinate system, in combination with the mirror image condition of the garage coordinate system. Specifically, the processing may be performed by using a translation-first rotation method, as shown in formula (1) and formula (2).

Wherein trans _ color _ x and trans _ color _ y denote coordinates from the origin (x)₀,y₀) The distance translated to the garage coordinate system (x ', y'), trans-theta, is expressed from the original coordinate (x ', y'), (x₀,y₀) Translated to the rotation angle of the garage coordinate system (x ', y').

And A13, determining the displacement track of the vehicle to be parked by taking the minimum parking number as a target according to the vehicle position information represented by the garage coordinate system and the boundary constraint condition of the parking space.

In this embodiment, the vehicle-mounted device takes the optimal number of parking spots (the minimum number of parking spots) as a target, and performs calculation by a geometric method under the guidance of the prior global path driving experience and in combination with a target position (parking space) and a boundary constraint condition to obtain a planned displacement trajectory.

For example, fig. 5 is a schematic diagram illustrating checking whether the maximum downward rolling stock radius can be obtained in the rolling stock process. As shown in fig. 5, the number is optimized to obtain the maximum radius R that enables the vehicle to be parked to roll down the garage.

Fig. 6 is a schematic view of dangerous points and operation features that may be concerned when a vehicle to be parked enters a garage. As shown in fig. 6, a plurality of vehicles are parked on one side of the road, the vertical distance between the vehicles and the garage is D, the vertical distance between the lane line and the garage is h, and the intersection point of the parking space 002 and the parking space 001 of the vehicle to be parked is P₁And P₄The intersection point of the parking space 002 to be parked and the parking space 003 is P₂、P₃. Vehicle to be parkedIs c₁、c₂、c₃、c₄. The prior global path driving experience refers to a dangerous point and the operation characteristics of a skilled driver which can be concerned in the operation parking process, when a vehicle to be parked falls backwards in a first R gear, a tangent point P2 is a dynamic point, dynamic pressure points are carried out according to the situation of an obstacle near a point P2 in a 003 library, and meanwhile, the distance between the c1 position of the vehicle to be parked and the space above the garage can be concerned to prevent rotary collision.

Specifically, a manner of calculating the displacement trajectory by a geometric method will be described by taking the schematic diagram shown in fig. 5 as an example. In the schematic diagram shown in fig. 5, the C point coordinate (x) is known_C,y_C) The included angle between the vehicle body of the vehicle to be parked and the parking space is α, and the width of the parking space is w_pThen, the reference radius of rotation R can be obtained by the following formula (3)_refThe reference radius of rotation R_refThe pose of the vehicle to be parked can be used as an index for judging whether the pose of the vehicle to be parked is favorable for warehousing.

R_ref＝(x_C-w_p)/(sin(α)*tan(α/2)) (3)

After the vehicle to be parked finishes the first downward rolling of the garage, no matter the vehicle to be parked rotates upwards with any radius, the vehicle rotates to the maximum degree as long as the center of the circle of the rotation is on the left side of the vehicle body, and the reference rotation radius R_refCan reach the maximum, at this time, theoretically, R can be obtained_refThe largest reference radius of rotation, but directly solving the optimum requires solving the transcendental equation, so for simplicity, the method of traversing the radius of rotation is used here.

Illustratively, in the present embodiment, the reference radius of rotation is in the range of [ R ]_min,+∞]Wherein R is_minThe minimum turning radius of the vehicle to be parked can be determined by using the ackermann steering principle, and the formula (4) is as follows:

wherein l is the wheel base of the vehicle to be parked, W is the wheel base of the vehicle to be parked, α_maxTo be mooredThe maximum turning angle of the steering wheel of the vehicle.

In the embodiment, the vehicle-mounted device can select the traverse steering wheel corner within the range of the reference rotation radius, and fig. 7 is a schematic diagram of the ackermann steering of the vehicle. Referring to fig. 7, the relationship between the steering wheel angle and the turning radius according to ackermann steering is shown in equation (5):

R＝W/tan(γ/K)+w/2 (5)

wherein, γ is the steering wheel angle of the vehicle to be parked, W is the wheel track of the vehicle to be parked, W is the vehicle width of the vehicle to be parked, K is the transmission ratio of the vehicle to be parked, and β is γ/K.

And A2, determining the running speed of the vehicle to be parked according to the length of the displacement track.

In this embodiment, after the vehicle-mounted device determines the displacement trajectory, in order to improve user experience and reduce insecurity of the driver and the crew when the vehicle to be parked approaches the parking space, and when the vehicle-mounted detection device fails, enough reaction time is reserved for the driver and the crew, and the vehicle-mounted device can also set the running speed of the vehicle to be parked according to the length of the displacement trajectory.

And S22, controlling the vehicle to be parked to move based on the driving track so as to enable the vehicle to be parked on the parking space.

In this embodiment, after the driving track of the vehicle to be parked is determined, the vehicle-mounted device may control the vehicle to be parked to move according to the displacement track at the determined driving speed, so that the vehicle to be parked is accurately and safely parked at the parking space.

Optionally, in the path planning process of this embodiment, a driving experience of the global path is introduced, and a relationship between different planning states can be connected in a narrow space, so that failure of parking caused by front-back connection is prevented, and the success rate of parking is improved.

According to the automatic parking method provided by the embodiment of the application, the position information of the vehicle to be parked and the azimuth information of the parking space are obtained, and the driving track of the vehicle to be parked is determined according to the position information and the azimuth information, and the driving track comprises the following steps: the method comprises the steps of displacing a track and a driving speed, and further controlling a vehicle to be parked to move on the basis of the driving track so as to enable the vehicle to be parked on a parking space, namely, the determined driving track is not influenced by a parking starting position on the basis of the position of the vehicle to be parked and the direction information of the parking space, the driving speed is planned at the same time, and the parking success rate is improved.

Fig. 8 is a flowchart illustrating an automatic parking method according to a second embodiment of the present application. As shown in fig. 8, before the execution of the above-mentioned S22, the automatic parking method may further include the steps of:

and S81, determining the driving area of the vehicle to be parked according to the driving track.

In this embodiment, the vehicle-mounted device first infers an area that the vehicle to be parked needs to occupy when moving according to the travel track, based on the determined travel track, the length information, the width information, and the like of the vehicle to be parked, where the area is the travel area of the vehicle to be parked.

And S82, acquiring information of the detected at least one obstacle of the vehicle to be parked based on the driving area.

In the present embodiment, the vehicle to be parked has mounted thereon an on-vehicle detection device, detects whether there is an obstacle in the travel area with the on-vehicle detection device, and upon determining the presence, acquires information of the detected at least one obstacle. The number of obstacles may be determined according to actual conditions, and is not described herein.

And S83, determining a target obstacle in the at least one obstacle, wherein the target obstacle is the obstacle having the largest influence on the running track in the at least one obstacle.

The vehicle-mounted equipment can screen the detected at least one obstacle based on the driving area, and selects a target obstacle having a large influence on the track, so that the processing complexity is reduced, and the processing efficiency is improved.

And S84, determining a processing plan for the driving track according to the position information of the target obstacle and the range of the driving area.

In the present embodiment, the travel area of the vehicle to be parked is estimated from the travel locus, and whether the target obstacle is within the travel area is determined.

For example, fig. 9 is a schematic diagram of a speed plan corresponding to a driving track. Referring to fig. 9, the abscissa S represents the distance between the target obstacle and the vehicle to be parked in the vehicle traveling direction, and the ordinate represents the traveling speed of the vehicle to be parked. S_maxRepresenting the maximum distance that the on-board detection device of the vehicle to be parked is most capable of detecting, i.e. the maximum detection distance, S_mRepresenting the effective distance most detected by the on-board detection device of the vehicle to be parked, i.e. the effective detection distance, S_minIndicating a safe stopping distance of the vehicle to be parked. The vehicle-mounted equipment of the embodiment can make a decision on the determined target obstacle based on the running track, and the decision type is divided into 4 forms of braking, track shortening, track keeping, track re-planning and the like.

For example, in this embodiment, the step S84 may be implemented by the following steps, that is, the process plan may include several cases:

and S841, judging whether the target obstacle is in the range of the driving area, if not, executing S842, and if so, executing S843.

S842, keeping the running track unchanged;

in this embodiment, if the target obstacle is not within the range of the driving area, which indicates that the presence of the target obstacle does not have any influence on the movement of the vehicle to be parked, the determined driving trajectory may be unchanged, including: the displacement track and the running speed are unchanged.

S843, determining the distance between the target obstacle and the vehicle to be parked in the vehicle running direction.

Further, based on the size relationship of the space, the next processing is executed, and the processing procedure includes: track shortening, track re-planning and stopping are specifically as follows:

s844, the effective detection distance S of the vehicle to be parked is larger than or equal to the distance_mBut less than the maximum detection distance S of the vehicle to be parked_maxWhen the speed of the vehicle is changed to the preset speed V, the control device controls the running speed in the running track to be changed to the preset speed V_{Preset of}。

Wherein the value of the preset speed is smaller than the value of the running speed.

Illustratively, the on-board detection device detects the distance S effectively_mAnd the maximum detection distance S_maxThere may be some error in the detected obstacle, but it may be used as a reference to continue the detection in that direction to verify the detection result. Thus, as shown in FIG. 9, the distance is greater than or equal to the effective detection distance S of the vehicle to be parked_mBut less than the maximum detection distance S of the vehicle to be parked_maxIn time, the obstacle is decided to be the track shortening, and the vehicle speed limiting V is adopted_{Preset of}The vehicle to be parked can travel, that is, move based on the displacement trajectory, but the original traveling speed (set maximum speed) needs to be changed to a preset speed that is less than the traveling speed in order to allow a sufficient reaction time when an obstacle actually appears.

S845, when the distance is smaller than the effective detection distance S of the vehicle to be parked_mBut is greater than the safe braking distance S of the vehicle to be parked_minAnd meanwhile, the running speed in the running track is controlled to be changed into a linear decreasing speed.

As shown in fig. 9, the effective detection distance S is smaller at the interval than the vehicle to be parked_mBut is greater than the safe braking distance S of the vehicle to be parked_minThat is, when the obstacle really appears, the vehicle to be parked can continue to move based on the displacement track, but the vehicle needs to travel at the limited speed with the linear decreasing speed, so as to ensure that the vehicle does not collide with the obstacle before the vehicle is braked and stopped, and ensure the comfort of the user.

The comfort is improved by adopting the barrier processing strategy under the condition of ensuring the safety, so that the automatic parking system can better meet the requirements of users, the user experience of the system is greatly improved, and the competitive capacity of products on the market is enhanced.

S846, when the distance is less than or equal to the safe braking distance S of the vehicle to be parked_minThen, the running speed is controlled to be changed to the maximum deceleration V in the running track_minSo that the parked vehicle is stopped within the shortest period of time.

As shown in fig. 9, the pitch is less than or equal to the safe brake distance S of the vehicle to be parked_minRunning rail of vehicle to be parkedObstacles suddenly appear in the track, but in order to avoid the collision to the maximum extent, the brake is stopped by adopting the maximum acceleration.

And S85, updating the driving track based on the processing plan.

In this embodiment, after determining the processing plan for the driving trajectory, the vehicle-mounted device may process the driving trajectory, that is, perform corresponding processing on the determined driving trajectory according to the decision-making condition of the obstacle, and check the updated driving trajectory, so as to prevent an invalid trajectory from being planned, and perform a round of collision detection.

According to the automatic parking method provided by the embodiment of the application, the driving area of the vehicle to be parked is determined according to the driving track, information of at least one detected obstacle of the vehicle to be parked is further obtained on the basis of the driving area, the target obstacle having the largest influence on the driving track is determined in the at least one obstacle, and finally, the processing plan aiming at the driving track is determined according to the position information of the target obstacle and the range of the driving area, and the driving track is updated. In the technical scheme, the determined driving track is updated by combining the detected obstacle information, so that the usability of the driving track can be ensured, and the comfort of drivers and passengers can be improved.

Fig. 10 is a schematic flow chart of an automatic parking method according to a third embodiment of the present application, which is based on the foregoing embodiments. As shown in fig. 10, in this embodiment, the step S22 may include the following steps:

s101, calculating deviation according to the position information and the running track of the vehicle to be parked to obtain speed deviation, transverse distance deviation and course angle deviation.

In this embodiment, the vehicle-mounted device may find a track point closest to the vehicle to be parked as an expected position in the planned driving track according to the position information (x, y) of the vehicle to be parked, and solve the speed deviation, the lateral distance deviation, and the heading angle deviation according to the relationship between the position of the vehicle to be parked and the expected position.

Optionally, the trace point closest to the vehicle may be determined by traversing the euclidean distance between each point on the driving trajectory and the position (x, y) of the vehicle to be parked, and the point with the smallest distance is the closest trace point and is determined according to the formula (6).

Wherein (x)_n,y_n) Is the nth point on the driving track.

For example, fig. 11 is a schematic view of a geometric relationship between the position of the vehicle to be parked and the desired position. The point A is the actual position of the vehicle to be parked, the point B is the expected position of the vehicle to be parked on the displacement track, and the point C is the next following point of the expected position on the displacement track. As shown in fig. 11, the lateral distance deviation, vehicle _ error, and the heading angle deviation, heading _ error are solved mainly through a geometric relationship (similar triangle principle) between an actual position point a of the vehicle to be parked and an expected position point B on the displacement trajectory, specifically, the solving formulas are formula (7) and formula (8), and the speed deviation, speed _ error, is obtained through the solving formula (9).

lateral_error＝dy·cos(heading)-dx·sin(heading) (7)

heading_error＝θ-heading (8)

speed_error＝v_ref-v (9)

Wherein, the heading is a heading angle at the expected position point B, which is abbreviated as h in the figure, namely an included angle between the expected position point B and an X axis, dx is a transverse distance between the actual position point A and the expected position point B, dy is a longitudinal distance between the actual position point A and the expected position point B, and theta is an included angle between the actual position point A and the X axis of the vehicle to be parked; v. of_refV is the current speed of the vehicle to be parked for the determined travel speed in the travel trajectory.

And S102, determining the running acceleration of the vehicle to be parked according to the speed deviation and a speed controller of the vehicle to be parked, wherein the speed controller is designed and formed by adopting a PID method.

In practical application, a control deviation is formed according to a given value and an actual output value, the deviation is combined in proportion, integration and differentiation linearly to form a control quantity, a controlled object is controlled, and the controller obtained through design is called a PID controller.

In the present embodiment, the speed controller of the vehicle to be parked is a kind of PID controller, and thus the speed deviation is input to the speed controller and output as the running acceleration of the vehicle to be parked.

Further, if necessary, bilinear interpolation may be used to obtain the throttle/brake amount percentage required for throttle-by-wire/braking. Illustratively, fig. 12 is a schematic diagram of the principle of the bilinear interpolation method. Referring to fig. 12, assuming the throttle/brake percentage as the value of the function f at point P ═ x, y, assume that f is known to be at Q₁₁＝(x₁,y₁)、Q₁₂＝(x₁,y₂)、Q₂₁＝(x₂,y₁) And Q₂₂＝(x₂,y₂) For the four points, the calculation steps for determining the percentage of accelerator/brake amount are as follows:

firstly, linear interpolation is carried out in the x direction to respectively obtain f points R₁The sum f of (f) at point R₂The values of (b) are shown in equation (10) and equation (11):

wherein R is₁＝(x,y₁) (10)

Wherein R is₂＝(x,y₂) (11)

Then, linear interpolation is performed in the y direction to obtain a value of f at the point P, as shown in formula (12):

combining equation (10), equation (11) and equation (12), f (p) can be obtained, referring to equation (13):

s103, determining the driving direction of the vehicle to be parked according to the transverse distance deviation, the course angle deviation and a direction controller of the vehicle to be parked, wherein the direction controller is designed and formed by adopting a PID method.

In this embodiment, the direction controller of the vehicle to be parked is also a PID controller, fig. 13 is a schematic diagram for determining the driving direction of the vehicle to be parked, and referring to fig. 13, in this embodiment, the direction controller may include: a PID controller 1 for lateral distance deviation and a PID controller 2 for heading angle deviation. Thus, the first output ρ relating to the steering wheel is solved using the lateral distance deviation as an input to the PID controller 1₁Solving a second output quantity rho related to the steering wheel by taking the heading angle deviation as the input of the PID controller 2₂According to the first output rho₁And a second output quantity ρ₂The effects of (b) form a linear combination and finally output the ideal curvature ρ in the direction of travel.

Alternatively, referring to fig. 13, the first output amount ρ₁K, the second output quantity p₂The weight coefficient of (1-k).

In the embodiment, the linear combination of the PID controllers is adopted for direction control, and the lateral distance deviation and the course angle deviation are considered in the direction control process, so that the position and angle accuracy of the parking terminal state can be better guaranteed.

And S104, controlling the vehicle to be parked to run based on the running track according to the running acceleration and the running direction so as to enable the vehicle to be parked on the parking space.

In the embodiment of the application, the vehicle-mounted equipment can update the running acceleration and the running direction in real time in the moving process of the vehicle to be parked, and then controls the vehicle to be parked to run based on the running track based on the real-time running acceleration and the running direction, so that the position and angle accuracy of the parking end point state is better guaranteed, and the success rate of the vehicle to be parked on the parking space is improved.

According to the automatic parking method provided by the embodiment of the application, deviation amount calculation is carried out according to the position information and the running track of the vehicle to be parked, so that speed deviation, transverse distance deviation and course angle deviation are obtained, the running acceleration of the vehicle to be parked is determined according to the speed deviation and the speed controller of the vehicle to be parked, the running direction of the vehicle to be parked is determined according to the transverse distance deviation, the course angle deviation and the direction controller of the vehicle to be parked, and finally the vehicle to be parked is controlled to run based on the running track according to the running acceleration and the running direction. According to the technical scheme, in the parking process, the parking direction and speed are adjusted based on the speed deviation, the transverse distance deviation and the course angle deviation, and the parking success rate is further improved.

Further, in the foregoing embodiments of the present application, during the process of parking the vehicle in the parking space, at least one of the following adjustment manners is adopted: forward adjustment, downward kneading and adjustment in the storehouse, upward kneading and adjustment in the storehouse.

For example, fig. 14 is a schematic diagram of a parking process of a vehicle to be parked. As shown in fig. 14, the parking process of the vehicle to be parked (simply referred to as a vehicle) is as follows: determining the relative relation between the pose of the vehicle and the parking space, judging whether the transverse and longitudinal distances between the vehicle and the parking space meet parking conditions, if not, firstly adjusting in the forward direction, then kneading the garage downwards, if so, directly kneading the garage downwards, then, judging whether the garage entering depth meets, if not, sequentially executing track walking or barrier braking, kneading the garage upwards and kneading the garage downwards, if so, judging whether the vehicle body is stopped rightly, if not, adjusting in the garage, and if so, ending the parking.

Therefore, the warehousing state of the vehicle to be parked is mainly divided into 4 modes of forward adjustment, downward library kneading, upward library kneading and in-warehouse adjustment, and the functions of each mode are respectively as follows:

forward adjustment: the parking area of the vehicle to be parked is wider, the vehicle can independently and autonomously drive a distance forward only after the visual or ultrasonic detection of the available parking space, and the rules of firstly adjusting the lateral distance and then adjusting the longitudinal distance are adopted in the driving process. The lateral distance is adjusted to ensure that the vehicle does not exceed the safety sideline opposite to the parking space in the downward garage kneading and rotating process, the lateral distance is increased as much as possible to be beneficial to the optimal number of the parking spaces, and the longitudinal distance is adjusted to enable the vehicle to reach the optimal state by a smaller turning radius.

Kneading the warehouse downwards: in the process of kneading the garage downwards for the first time, the aim that the driving track of the right rear wheel can always go around the upper right corner point of the garage is mainly taken as the target, and then the process of kneading the garage downwards takes the aim that the center of a rear axle of a vehicle drives on the center line of the garage as the target.

Kneading the storehouse upwards: the goal of the upward library is to adjust the posture of the vehicle body to a state that the vehicle body can be put in a warehouse, the optimal turning radius is calculated according to the posture of the vehicle body, the maximum radius of the next downward library is taken as a goal beneficial to putting in the warehouse, but because the optimal solution of a geometric relation equation needs to be solved by a transcendental equation, in order to reduce the solving difficulty, a method of traversing the rotating radius is adopted for solving.

Adjusting in a warehouse: in the process of kneading the garage downwards, if the parking space has the transverse displacement correction, at the moment, the space behind or in front is enough, the vehicle can adjust the transverse distance in the garage until meeting the warehousing index, and then the vehicle can continue to back up.

According to the technical scheme, based on the parking spaces and lane line information in the environment, the vehicle is adjusted in the longitudinal and transverse distances in a forward adjusting mode, the problem that the starting area of the automatic parking system is too small is solved, and the starting area and the parking success rate of the parking can be effectively improved.

Further, in the embodiment of the present application, the automatic parking method may further include the steps of:

acquiring contour parameters of a vehicle to be parked;

and processing the head of the vehicle to be parked into an arc-shaped profile according to the profile parameters of the vehicle to be parked.

For example, fig. 15 is a schematic shape diagram of the outer contour of the vehicle. Fig. 16 is a schematic diagram of the selection of arc-shaped contour points of the vehicle head. As shown in fig. 15, although the outline of the vehicle to be parked is approximated by a rectangular ABCD, the calculation mode can be simplified, but the actual vehicle head is in an arc shape, and in the actual application process, the estimation of the distance between the front obstacle is conservative, which may cause the problem that the narrow space is likely to cause insufficient utilization of the available space.

Specifically, as shown in fig. 16, point a is a vehicle body left side arc start position, point b is a position where a left nose protrudes most, and point c is a nose front end arc end position, and coordinates of points a, b, and c with respect to the vehicle rear axle center are recorded by a ruler tool, and it is assumed that coordinates of a are a (3.24,0.93) and coordinates of c are c (3.84, 0.53). The head shape is fitted in an arc mode as follows:

assuming that the equation for the circle is as shown in equation (14):

x²+y²+mx+ny+p＝0 (14)

substituting the coordinates of the points a, b and c into a formula (14) respectively to form a linear ternary equation, and calculating the values of m, n and p respectively, so that the sizes of the circle center and the radius can be known, wherein the specific calculation formula is as follows:

x_c＝-0.5×m (15)

y_c＝-0.5×n (16)

specifically, in the schematic diagram shown in fig. 15, if there is an obstacle at point D (3.84,0.93), the position is a critical collision point according to the rectangular shape of the vehicle head, and the vehicle body contour is still at a certain distance from point D by using the circular arc calculation, so that the system can utilize space to a greater extent in a narrow space, and the competitiveness of the product is improved.

By combining the technical solutions of the above embodiments, fig. 17 is a schematic diagram of a control process of automatic parking. Referring to fig. 17, an execution body of the automatic parking includes a planning module and a control module, and in this case, the automatic parking method mainly includes: the method comprises the steps that the vehicle-mounted equipment obtains positioning information (including position information of a vehicle to be parked and azimuth information of a parking space), environment information of an area where the vehicle to be parked is located and system information (including basic attribute information of the vehicle, such as the minimum rotation radius and the like) of the vehicle to be parked, the environment information and the system information of the vehicle to be parked are input into a planning module of the vehicle-mounted equipment to plan a running track of the vehicle to be parked, the planning module inputs a processed track (running track) into a control module, and the control module determines a speed control quantity and a steering wheel control quantity of the vehicle to be parked according to the track and the obtained positioning information (optional, the environment information and the system information) and transmits the speed control quantity and the steering wheel control quantity to the vehicle to be parked.

Optionally, as shown in fig. 17, the planning module mainly executes flows of data preprocessing, driving track generation, obstacle processing, obstacle decision, track processing, track checking, and the like according to the acquired positioning information, environment information, and system information, and the feedback information of the vehicle, and the control module mainly executes steps of deviation amount acquisition, speed control, direction control, and the like according to the track output by the planning module, and then combines the acquired positioning information, environment information, and system information, and the feedback information of the vehicle, so as to output a speed control amount and a steering wheel control amount, and the like.

For example, fig. 18 is a schematic diagram comparing an automatic start area supported by the automatic parking system of the present application and an existing automatic parking system. Referring to fig. 18, a parking space of a vehicle to be parked is a parking space 002, and practice proves that the technical scheme of the present application can automatically start an automatic parking process within a range shown by a vertical line a and a vertical line B, whereas an existing automatic parking system can only automatically start an automatic parking process within a range shown by a vertical line B and a vertical line C. Wherein the distance between the perpendicular line A and the center line of the parking space 002 is s₁The distance between the center line of the parking space 002 and the perpendicular line B is s_r. Therefore, the automatic parking device has the advantages that the starting range is large, the limitation of trigger conditions is avoided, and the application range is wider.

While the embodiments of the automatic parking method mentioned in the present application have been described above, the following embodiments of the apparatus of the present application may be used to implement the embodiments of the method of the present application. For details which are not disclosed in the embodiments of the apparatus of the present application, reference is made to the embodiments of the method of the present application.

Fig. 19 is a schematic structural diagram of an automatic parking device according to an embodiment of the present application. The device can be integrated in or realized by an on-board device. As shown in fig. 19, in the present embodiment, the automatic parking apparatus 19 may include: a processing module 191 and a control module 192.

The processing module 191 is configured to determine a driving trajectory of the vehicle to be parked according to the position information of the vehicle to be parked and the azimuth information of the parking space, where the driving trajectory includes: displacement trajectory and travel speed;

the control module 192 is configured to control the vehicle to be parked to move based on the driving track, so that the vehicle to be parked is parked at the parking space.

In a possible design of the embodiment of the application, the processing module 191 is specifically configured to determine a displacement trajectory of the vehicle to be parked according to the position information of the vehicle to be parked, the environmental information of the area where the vehicle to be parked is located, and the azimuth information of the parking space, and determine the driving speed of the vehicle to be parked according to the length of the displacement trajectory.

Optionally, the processing module 191 is configured to determine a displacement trajectory of the vehicle to be parked according to the position information of the vehicle to be parked, the environment information of the area where the vehicle to be parked is located, and the azimuth information of the parking space, and specifically includes:

the processing module 191 is specifically configured to establish a garage coordinate system according to the azimuth information of the parking space, convert the position information of the vehicle to be parked into vehicle position information represented by the garage coordinate system, convert the environment information of the area where the parking space is located into the boundary constraint condition of the parking space, and determine the displacement trajectory of the vehicle to be parked according to the vehicle position information represented by the garage coordinate system and the boundary constraint condition of the parking space, with the minimum number of parking bars as a target.

In another possible design of the embodiment of the application, the processing module 191 is further configured to, before the control module 192 controls the vehicle to be parked to move based on the driving track, determine a driving area of the vehicle to be parked according to the driving track, obtain information of at least one detected obstacle of the vehicle to be parked based on the driving area, determine a target obstacle among the at least one obstacle, where the target obstacle is an obstacle having the largest influence on the driving track among the at least one obstacle, determine a processing plan for the driving track according to the position information of the target obstacle and the range of the driving area, and update the driving track based on the processing plan.

Optionally, the processing module 191 is configured to determine a processing plan for the driving trajectory according to the position information of the target obstacle and the range of the driving area, and specifically includes:

the processing module 191 is specifically configured to keep the travel track unchanged when the target obstacle is not within the range of the travel area, determine a distance between the target obstacle and the vehicle to be parked in the vehicle travel direction when the target obstacle is within the range of the travel area, control the travel speed in the travel track to change to a preset speed when the distance is greater than or equal to an effective detection distance of the vehicle to be parked but less than a maximum detection distance of the vehicle to be parked, control the travel speed in the travel track to change to a linearly decreasing speed when the distance is less than the effective detection distance of the vehicle to be parked but greater than a brake safe distance of the vehicle to be parked, and control the travel speed in the travel track to change to a linearly decreasing speed when the distance is less than or equal to the brake safe distance of the vehicle to be parked, and controlling the running speed in the running track to be changed into the maximum deceleration so as to stop the vehicle to be parked in the shortest time length.

In another possible design of the embodiment of the present application, the control module 192 is specifically configured to perform deviation calculation according to the position information of the vehicle to be parked and the driving track to obtain a speed deviation, a lateral distance deviation, and a heading angle deviation, and determine the driving acceleration of the vehicle to be parked according to the speed deviation and a speed controller of the vehicle to be parked, where the speed controller is designed by using a PID method, and the driving direction of the vehicle to be parked is determined according to the lateral distance deviation, the heading angle deviation, and a direction controller of the vehicle to be parked, and the direction controller is designed by using a PID method, and the vehicle to be parked is controlled to drive on the driving track according to the driving acceleration and the driving direction, so that the vehicle to be parked is parked at the parking space.

In another possible design of the embodiment of the present application, during the process of parking the vehicle in the parking space, at least one of the following adjustment manners is adopted: forward adjustment, downward kneading and adjustment in the storehouse, upward kneading and adjustment in the storehouse.

In another possible design of the embodiment of the present application, the processing module 191 is further configured to obtain a contour parameter of the vehicle to be parked, and process a nose of the vehicle to be parked into an arc-shaped contour according to the contour parameter of the vehicle to be parked.

The apparatus provided in the embodiment of the present application may be used to execute the method in the embodiments shown in fig. 2 to fig. 18, and the implementation principle and the technical effect are similar, which are not described herein again.

It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the processing module may be a processing element separately set up, or may be implemented by being integrated in a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and a function of the processing module may be called and executed by a processing element of the apparatus. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.

Further, according to an embodiment of the present application, an electronic device and a computer-readable storage medium are also provided.

Fig. 20 is a block diagram of an electronic device for implementing the automatic parking method according to the embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.

As shown in fig. 20, the electronic apparatus includes: one or more processors 201, memory 202, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). Fig. 20 illustrates an example of one processor 201.

Memory 202 is a non-transitory computer readable storage medium as provided herein. The memory stores instructions executable by at least one processor to cause the at least one processor to execute the automatic parking method provided by the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to execute the automatic parking method provided by the present application.

The memory 202, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules (e.g., the processing module 191, the control module 192 shown in fig. 19) corresponding to the automatic parking method in the embodiment of the present application. The processor 201 executes various functional applications of the server and data processing by running non-transitory software programs, instructions and modules stored in the memory 202, that is, implements the automatic parking method in the above-described method embodiments.

The memory 202 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the electronic apparatus for automatic parking, and the like. Further, the memory 202 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 202 may optionally include memory located remotely from the processor 201, and these remote memories may be connected to the automated parking electronics via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device of the automatic parking method may further include: an input device 203 and an output device 204. The processor 201, the memory 202, the input device 203, and the output device 204 may be connected by a bus or other means, and the bus connection is exemplified in fig. 20.

The input device 203 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the auto-park electronic apparatus, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, or other input device. The output devices 204 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.

Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

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

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

Further, the present application provides an automatic parking method, including:

The parking trajectory is actually the displacement trajectory, and the parking speed is actually the traveling trajectory.

For the implementation principle and the beneficial effects of the automatic parking method described herein, reference may be made to the descriptions in the above embodiments, and further description is omitted here.

According to the technical scheme of the embodiment of the application, the position information of the vehicle to be parked and the azimuth information of the parking space are obtained, and the running track of the vehicle to be parked is determined according to the position information and the azimuth information, and the running track comprises the following components: the method comprises the steps of displacing a track and a driving speed, and further controlling a vehicle to be parked to move on the basis of the driving track so as to enable the vehicle to be parked on a parking space, namely, the determined driving track is not influenced by a parking starting position on the basis of the position of the vehicle to be parked and the direction information of the parking space, the driving speed is planned at the same time, and the parking success rate is improved.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.

The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An automatic parking method, comprising:

2. The method according to claim 1, wherein the determining the driving track of the vehicle to be parked according to the position information of the vehicle to be parked and the azimuth information of the parking space comprises:

3. The method according to claim 2, wherein the determining the displacement trajectory of the vehicle to be parked according to the position information of the vehicle to be parked, the environment information of the area where the vehicle to be parked is located, and the azimuth information of the parking space comprises:

4. The method according to claim 1, wherein before the controlling the vehicle to be parked to move based on the travel trajectory, the method further comprises:

updating the travel trajectory based on the processing plan.

5. The method of claim 4, wherein determining a treatment plan for the travel trajectory based on the position information of the target obstacle and the range of the travel area comprises:

6. The method according to any one of claims 1 to 5, wherein the controlling the vehicle to be parked to move based on the travel track so that the vehicle to be parked is parked at the parking space comprises:

7. The method according to any one of claims 1 to 5, characterized in that the vehicle to be parked adopts at least one of the following adjustments during parking into the parking space: forward adjustment, downward kneading and adjustment in the storehouse, upward kneading and adjustment in the storehouse.

8. The method according to any one of claims 1-5, further comprising:

acquiring contour parameters of the vehicle to be parked;

9. An automatic parking device, comprising: the device comprises a processing module and a control module;

10. The device according to claim 9, wherein the processing module is specifically configured to determine a displacement trajectory of the vehicle to be parked according to the position information of the vehicle to be parked, the environment information of the area where the vehicle to be parked is located, and the azimuth information of the parking space, and determine the driving speed of the vehicle to be parked according to the length of the displacement trajectory.

11. The device according to claim 10, wherein the processing module is configured to determine a displacement trajectory of the vehicle to be parked according to the position information of the vehicle to be parked, the environment information of the area where the vehicle to be parked is located, and the azimuth information of the parking space, and specifically includes:

12. The apparatus according to claim 9, wherein the processing module is further configured to, before the control module controls the vehicle to be parked to move based on the travel track, determine a travel area of the vehicle to be parked according to the travel track, acquire information of at least one detected obstacle of the vehicle to be parked based on the travel area, determine a target obstacle among the at least one obstacle, the target obstacle being an obstacle having a largest influence on the travel track among the at least one obstacle, determine a processing plan for the travel track according to the position information of the target obstacle and a range of the travel area, and update the travel track based on the processing plan.

13. The apparatus according to claim 12, wherein the processing module is configured to determine a processing plan for the travel trajectory according to the position information of the target obstacle and the range of the travel area, specifically:

14. The device according to any one of claims 9 to 13, wherein the control module is specifically configured to perform deviation calculation according to the position information of the vehicle to be parked and the driving track to obtain a speed deviation, a lateral distance deviation and a heading angle deviation, determining the running acceleration of the vehicle to be parked according to the speed deviation and a speed controller of the vehicle to be parked, wherein the speed controller is designed and formed by adopting a PID method, determining the running direction of the vehicle to be parked according to the transverse distance deviation, the course angle deviation and a direction controller of the vehicle to be parked, wherein the direction controller is designed and formed by adopting a PID method, and controlling the vehicle to be parked to run based on the running track according to the running acceleration and the running direction so as to enable the vehicle to be parked on the parking space.

15. The device according to any one of claims 9-13, wherein the vehicle to be parked adopts at least one of the following adjustments during parking into the parking space: forward adjustment, downward kneading and adjustment in the storehouse, upward kneading and adjustment in the storehouse.

16. The device according to any one of claims 9 to 13, wherein the processing module is further configured to obtain a contour parameter of the vehicle to be parked, and process a nose of the vehicle to be parked into an arc-shaped contour according to the contour parameter of the vehicle to be parked.

17. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1-8.

19. An automatic parking method, comprising: