CN111367252B

CN111367252B - Parking control method, device and system

Info

Publication number: CN111367252B
Application number: CN201811602310.5A
Authority: CN
Inventors: 李一鸣; 金宇和; 蔡金鹏; 吴楠
Original assignee: Beijing Tusimple Technology Co Ltd
Current assignee: Beijing Tusimple Technology Co Ltd
Priority date: 2018-12-26
Filing date: 2018-12-26
Publication date: 2024-02-06
Anticipated expiration: 2038-12-26
Also published as: CN116620265A; CN111367252A; CN116588083A

Abstract

The embodiment of the application provides a parking control method, equipment and a system. The parking control method includes: receiving a message of a vehicle to be parked requesting parking sent by a vehicle controller; determining a parking space and sending the identification of the parking space to a vehicle controller; acquiring point cloud data of a preset monitoring area corresponding to a parking space obtained by laser radar scanning; clustering the point cloud data to obtain a point cloud set of the vehicle to be parked; calculating a point cloud set of the vehicle to be parked and a vehicle point cloud model by using an iterative closest point ICP algorithm, obtaining and sending a rotation matrix and a translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model, so that a vehicle controller controls the running direction and the running speed of the vehicle to be parked in real time according to the rotation matrix and the translation matrix and finally stops in a parking space. The parking control method provided by the application has the advantages of high automation degree, high precision and the like, and meets the requirement of realizing automatic and accurate parking in multiple types of parking spaces with narrow spaces.

Description

Parking control method, device and system

Technical Field

The embodiment of the application relates to the technical field of intelligent transportation, in particular to a parking control method, equipment and a system.

Background

This section is intended to provide a background or context for embodiments of the present application that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.

With the development of cities and the popularization of passenger automobiles, the parking problem has become an important difficulty restricting the development of many cities. To solve this problem, automatic locking type parking spaces, crossed type parking spaces, multi-layered parking spaces, etc. have been developed, and in order to improve land utilization and parking management efficiency, the floor area of each parking space is generally set to accommodate exactly one vehicle. However, both the above-mentioned various types of parking spaces and the narrow parking space area place high demands on the degree of accuracy of parking.

Disclosure of Invention

In order to solve the problem of parking a vehicle, some existing solutions include, for example:

(1) Some technical schemes are that vehicle position is collected by vehicle-mounted GPS equipment to control the vehicle to park, however, the positioning precision (generally reaching meter level) of the GPS equipment cannot meet the requirement of accurate parking in parking spaces (the precision needs to reach centimeter level), in addition, the parking spaces in cities are mostly located in underground parking lots and are affected by on-ground buildings, indoor equipment and the like, and GPS signals are easily shielded to cause positioning failure.

(2) Still other solutions are to control the parking of the vehicle by using a vehicle-mounted camera to visually locate the parking mark line, however, the solution cannot realize accurate parking in centimeter level at present due to the limitation of algorithm and calculation force.

Therefore, the conventional vehicle parking mode is to position the vehicle and the parking space through a vehicle-mounted positioning device or a vehicle-mounted camera and the like, and the parking mode has the defects of large error, low speed and the like.

In view of the foregoing, the present application proposes a parking control method, apparatus and system that overcomes or at least partially solves the foregoing problems.

In a first aspect of embodiments of the present application, there is provided a parking control method applied to a master, including:

receiving a message of a vehicle to be parked requesting parking sent by a vehicle controller;

determining a parking space and sending the identification of the parking space to the vehicle controller so that the vehicle controller controls the vehicle to be parked to drive to the parking space;

acquiring point cloud data of a preset monitoring area corresponding to the parking space, which is obtained by laser radar scanning; the preset monitoring area comprises the parking space and a preset area which can enter the parking space;

Clustering the point cloud data to obtain a point cloud set of the vehicle to be parked;

calculating the point cloud set of the vehicle to be parked and a vehicle point cloud model by using an iterative closest point ICP algorithm to obtain a rotation matrix and a translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model; the vehicle point cloud model is a point cloud set obtained by scanning a vehicle stopped in the parking space by using a laser radar in advance;

and sending the rotation matrix and the translation matrix to enable the vehicle controller to control the running direction and the speed of the vehicle to be parked in real time according to the rotation matrix and the translation matrix and finally stop in the parking space.

In a second aspect of the embodiments of the present application, there is provided a parking control method applied to a vehicle controller, including:

sending a message that a vehicle to be parked requests parking;

receiving an identification of a parking space returned by a main controller, and controlling the vehicle to be parked to travel to the parking space;

receiving a rotation matrix and a translation matrix between a point cloud set of a vehicle to be parked and a vehicle point cloud model returned by a master controller; the vehicle point cloud model is a point cloud set obtained by scanning a vehicle stopped in the parking space by using a laser radar in advance;

And controlling the running direction and speed of the vehicle to be parked in real time according to the rotation matrix and the translation matrix so as to enable the vehicle to be parked to be finally parked in the parking space.

In a third aspect of the embodiments of the present application, there is provided a master controller, including a first processor, a first memory, and a computer program stored on the first memory and executable on the first processor, the first processor executing the steps in the foregoing parking control method applied to the master controller when the computer program is executed.

In a fourth aspect of the embodiments of the present application, there is provided a vehicle controller comprising a second processor, a second memory and a computer program stored on the second memory and executable on the second processor, when executing the computer program, performing the steps of the parking control method as described above applied to the vehicle controller.

In a fifth aspect of embodiments of the present application, there is provided a parking control system including: a master as described above, a vehicle controller as described above, and a lidar.

In a sixth aspect of embodiments of the present application, there is provided an automobile having a vehicle controller as described above mounted thereon.

In a seventh aspect of embodiments of the present application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a parking control method as previously described for a master.

In an eighth aspect of the embodiments of the present application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the parking control method as previously described for a vehicle controller.

By means of the technical scheme, the ICP algorithm is utilized to calculate the rotation amount and the translation amount of the vehicle to be parked to the parking space in the running process, the running direction and the speed of the vehicle to be parked are controlled according to the rotation amount and the translation amount, the vehicle to be parked is finally controlled to be accurately stopped at the parking space, the whole parking process is automatically completed, the centimeter-level precision can be achieved, and the high-precision accurate parking requirement can be met.

Drawings

The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present application are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings, in which:

Fig. 1 schematically illustrates an application scenario provided in an embodiment of the present application;

fig. 2 schematically illustrates a flow of a parking control method provided in an embodiment of the present application;

FIG. 3 schematically illustrates a preset area according to an embodiment of the present application;

fig. 4 schematically illustrates a preset area according to a further embodiment of the present application;

FIG. 5 schematically illustrates configuration modes of a master, a lidar and a predetermined monitoring area provided by an embodiment of the present application;

FIG. 6 schematically illustrates a determination of an initial translation matrix according to an embodiment of the present application;

fig. 7 schematically illustrates a flow of a parking control method applied to a master according to an embodiment of the present application;

fig. 8 schematically illustrates a flow of a parking control method applied to a vehicle controller provided in an embodiment of the present application;

FIG. 9 schematically illustrates an automobile provided by an embodiment of the present application;

fig. 10 schematically illustrates a parking control system provided in an embodiment of the present application.

In the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

Detailed Description

The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are presented merely to enable one skilled in the art to better understand and practice the present application and are not intended to limit the scope of the present application in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

Those skilled in the art will appreciate that embodiments of the present application may be implemented as a system, apparatus, device, method, or computer program product. Accordingly, the present disclosure may be embodied in the following forms, namely: complete hardware, complete software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.

Any number of elements in the drawings in this application are for illustration and not limitation, and any naming is used for distinction only and not for any limiting sense.

The principles and spirit of the present application are explained in detail below with reference to several representative embodiments thereof.

Summary of The Invention

In order to meet the requirements of automatic and accurate parking in various parking spaces with small space, the embodiment of the application provides a parking control method, firstly, a laser radar is utilized to scan a vehicle parked in the parking space to obtain a vehicle point cloud model, then the laser radar is utilized to scan the vehicle driving to the parking space in real time to obtain a point cloud set when the vehicle to be parked requests parking, and then a rotation matrix and a translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model are calculated through an ICP algorithm.

The parking control method provided by the application has the advantages of high automation degree, high precision and the like, can reach the precision of centimeter level, and meets the requirement of realizing automatic and accurate parking in multiple types of parking spaces with narrow spaces.

Application scene overview

The embodiment of the application provides an application scene illustration, as shown in fig. 1, a laser radar is arranged above a parking space, the laser radar is connected with a main controller, and the main controller acquires point cloud data obtained by laser radar scanning.

After the information is acquired by the vehicle controller, a parking space is allocated for the vehicle to be parked, then in the process that the vehicle to be parked drives to the parking space, the point cloud data acquired by the laser radar are clustered by the main controller to obtain a point cloud set of the vehicle to be parked in the driving process, a rotation matrix and a translation matrix between the point cloud set of the vehicle to be parked and a vehicle point cloud model corresponding to the parking space are calculated by an ICP algorithm, and the vehicle controller controls the driving direction and the driving speed of the vehicle to be parked in real time according to the rotation matrix and the translation matrix so as to enable the vehicle to be parked to be accurately stopped in the parking space.

It should be noted that the application scenario shown in fig. 1 is only shown for the convenience of understanding the spirit and principles of the present application, and embodiments of the present application are not limited in this respect. Rather, embodiments of the present application may be applied to any scenario where applicable.

Exemplary method

The parking control method provided in the embodiment of the present application is described below with reference to fig. 2 in conjunction with the application scenario of fig. 1.

As shown in fig. 2, an embodiment of the present application provides a parking control method, including:

in step S100, the vehicle controller transmits a message that the vehicle to be parked requests parking.

In the implementation, the vehicle controller and the master controller can send and receive messages through wireless communication modes such as WIFI, V2X, a base station and the like, and the application is not strictly limited. In consideration of stability of signals, messages can be sent and received between the master controller and the vehicle controller through V2X technology. In some embodiments, the vehicle controller may broadcast a message that the vehicle to be parked requests parking in the parking space via a V2X device installed on the vehicle to be parked.

In some embodiments, the vehicle controller may issue a message only when it is determined that the predetermined condition is satisfied, for example, it may be:

(1) The vehicle controller sends out a message after judging that the vehicle to be parked enters the parking lot; or alternatively, the first and second heat exchangers may be,

(2) The vehicle controller receives a preset trigger signal (such as a trigger signal sent by a road card device arranged at the entrance of the parking lot) and then sends out a message.

In some embodiments, the message sent by the vehicle controller may include one or more of the following:

(1) Vehicle identification of the vehicle to be parked;

(2) A vehicle model of a vehicle to be parked;

(3) Positioning data acquired by vehicle-mounted positioning equipment of a vehicle to be parked;

(4) And (5) communication connection identification.

Wherein the communication connection identifier includes, but is not limited to, one or both of a MAC address of the vehicle controller, a MAC address of the V2X communication device to which the vehicle controller is connected.

In step S200, the master controller receives a message that the vehicle to be parked requests parking, which is sent by the vehicle controller.

In some embodiments, the master may receive messages sent by the vehicle controller via the V2X device.

In step S300, the master controller determines a parking space and transmits an identification of the parking space to the vehicle controller.

To ensure that a stable communication connection is established between the master and the vehicle controller, in some embodiments, prior to step S300, the master parses the communication connection identification from the message sent by the vehicle controller; and establishes communication connection with the vehicle controller through the communication connection identifier. In some embodiments, the communication connection identification may be, but is not limited to, a MAC address of the vehicle controller and/or a MAC address of the V2X communication device to which the vehicle controller is connected.

In some embodiments, the master may be configured to manage the vehicle parking traffic for one or more parking spaces (e.g., all of the parking spaces in the entire parking area), the master may locally store the identification of all of the parking spaces managed by the master and the status of whether the parking spaces are occupied (i.e., whether the vehicle has stopped on the parking space), and when the master receives a request sent by the vehicle controller that the vehicle to be parked expects to park, the master may determine an empty parking space from all of the parking spaces managed by the master and send its identification to the vehicle controller.

In step S400, the vehicle controller determines a parking space according to the identification of the parking space sent by the master controller, and controls the vehicle to be parked to drive to the parking space.

In some embodiments, the identification of the parking space may be a number and/or location information of the parking space. For example, the number of the parking space may be a number such as 1,2, or 3, or may be m—n (indicating that the parking space is located in M rows and N columns of the parking lot), and the position information of the parking space may be latitude and longitude coordinates, or may be M rows and N columns (indicating that the parking space is located in M rows and N columns of the parking lot), or the like.

Step S500, a master controller acquires point cloud data of a preset monitoring area corresponding to the parking space, which is obtained by laser radar scanning; the preset monitoring area comprises the parking space and a preset area which can enter the parking space.

In some embodiments, the laser radar is always in a scanning state, and after the main controller sends the identification of the parking space to the vehicle controller, the main controller immediately starts to acquire the point cloud data obtained by scanning the laser radar according to a preset frequency.

For the purpose of calculating the rotational and translational amounts of a vehicle to be parked in a driving situation to a parking space, the predetermined monitoring area should comprise a parking space and a predetermined area accessible to the parking space.

In some embodiments, the preset area may be an area covered by extending a certain distance outward from each boundary of the parking space, as shown in fig. 3, and the preset area (shown by a dotted line) is an area covered by extending 5 meters outward from each boundary of the parking space.

In some embodiments, the preset area may be a rectangular area (i.e., an area through which the vehicle travels in the lane before driving into the parking space) connected to the parking space in the lane, where the length of the rectangular area may be set by itself, and the width is the same as the width of the lane. As shown in fig. 4, a preset area (shown by a dotted line) is a rectangular area connected with a parking space in a lane connected with the parking space, and the rectangular area is 15 m long and 7 m wide.

In some embodiments, the master controller may preprocess the point cloud data obtained by the laser radar in real time, for example, if the scanning range of the laser radar is greater than the predetermined monitoring area, the point cloud data of the area outside the predetermined monitoring area may be deleted according to the position of the predetermined monitoring area, and only the point cloud data of the predetermined monitoring area is reserved.

The main controller and the laser radar are used as two independent devices, a plurality of connection modes exist between the main controller and the laser radar, and a one-to-one correspondence exists between a preset monitoring area and a parking space. In view of the above, in practice, the master, the lidar and the predetermined monitoring area (parking space) may have a plurality of configuration modes as shown in fig. 5:

(a) One main controller is only connected with one laser radar, and one laser radar is only responsible for scanning operation of a preset monitoring area corresponding to one parking space;

(b) One main controller is only connected with one laser radar, and one laser radar is responsible for scanning work of a preset monitoring area corresponding to at least two parking spaces;

(c) One main controller is connected with at least two laser radars, and one laser radar is only responsible for scanning operation of a preset monitoring area corresponding to one parking space;

(d) One main controller is connected with at least two laser radars, and one laser radar is responsible for scanning work of a preset monitoring area corresponding to at least two parking spaces.

In the implementation, which configuration mode is adopted may be comprehensively determined according to the information such as the line number and the scanning range of the laser radar, which is not particularly limited in the embodiment of the present application.

In view of the fact that there are multiple configuration modes among the master controller, the laser radar and the parking spaces, in order to facilitate the master controller to determine the laser radar responsible for scanning the preset monitoring area corresponding to the parking spaces, in some embodiments, after determining the free parking spaces for the vehicles to be parked, the master controller determines the laser radar used for scanning the preset monitoring area corresponding to the parking spaces according to the configuration relation among the laser radar and the parking spaces, so that point cloud data obtained by scanning of the laser radar are obtained.

And step S600, the master controller clusters the point cloud data to obtain a point cloud set of the vehicle to be parked.

Specifically, when a vehicle to be parked runs and enters the scanning range of the laser radar, the laser beam can be shot onto the vehicle to be parked and returned to be received by the laser radar, point clouds corresponding to the vehicle to be parked can exist in the point cloud data obtained through scanning, and the point cloud data are clustered to extract a point cloud set of the vehicle to be parked.

This step may employ algorithms currently commonly used for clustering arbitrary shapes, such as: waveCluster, ROCK, CURE, K-Prototypes, DENCLUE, DBSCAN, etc.

Since the predetermined monitoring area may cover a public area (such as a lane shared by parking spaces) or other parking spaces in the parking lot, the acquired point cloud data may have point clouds corresponding to a plurality of vehicles (such as vehicles to be parked in other parking spaces or vehicles to be parked in other parking spaces) at the same time, in this case, clustering the point cloud data may obtain a point cloud set of a plurality of vehicles (including vehicles to be parked and other vehicles), and in view of this, in order to facilitate the master to cluster the point cloud set of the vehicles to be parked from the point cloud data, the embodiments of the present application provide the following several processing manners:

(1) In some embodiments, the master controller clusters the point cloud data to obtain point cloud sets of one or more vehicles, and determines the point cloud set of the vehicles corresponding to the driving state in the point cloud sets as the point cloud set of the vehicle to be parked.

In such embodiments, other parking spaces adjacent to the parking space requested by the vehicle to be parked may already be occupied, and therefore only one of the clustered point cloud sets is a vehicle corresponding to a driving state, and the other is a vehicle corresponding to a stationary state, and then the stationary state vehicles may be vehicles already stopped in the other parking spaces, in which case there is no need to pay attention to the point cloud set, but only to the point cloud set of the vehicle corresponding to the driving state.

(2) In some embodiments, the vehicle controller includes positioning data collected by the vehicle-mounted positioning device of the vehicle to be parked in the sent message, the master controller clusters the point cloud data to obtain one or more point cloud sets of the vehicle, and the point cloud sets including the positioning data in the point cloud sets are determined to be the point cloud sets of the vehicle to be parked.

In such embodiments, the positioning data collected by the vehicle positioning devices of different vehicles are the position information of different vehicles, and different vehicles can be distinguished through the positioning data, so that the point cloud set containing the positioning data collected by the vehicle positioning devices of the vehicles to be parked is the point cloud set of the vehicles to be parked.

In specific implementation, the vehicle-mounted positioning device may be a global positioning system GPS positioning device, a carrier phase differential RTK positioning device, a beidou satellite positioning system positioning device, a GLONASS positioning system positioning device, a Galileo positioning system positioning device, a global navigation satellite system GNSS positioning device, or the like.

(3) In some embodiments, the vehicle controller includes positioning data acquired by the vehicle-mounted positioning device of the vehicle to be parked in the sent message, and the master controller intercepts the point cloud data corresponding to the position corresponding to the positioning data and the point cloud data corresponding to the area within the preset length around the position in the point cloud data, and clusters the intercepted point cloud data to obtain the point cloud set of the vehicle to be parked.

In such embodiments, the positioning data collected by the vehicle positioning device of the vehicle to be parked corresponds to the position information of the vehicle to be parked, and the master controller may determine the position of the vehicle to be parked according to the positioning data, but since the position corresponding to the positioning data is a point position and cannot represent the position of the whole vehicle body in all positions, a preset length may be determined according to the length of the vehicle body of most vehicles, and further, the position corresponding to the positioning data and the area around the position within the preset length may be determined, and the area may cover the whole vehicle body. The master controller intercepts point cloud data corresponding to the area from the point cloud data, wherein the point cloud data necessarily comprises point clouds corresponding to the vehicles to be parked, and the point cloud data are clustered to obtain a point cloud set of the vehicles to be parked.

(4) In some embodiments, the vehicle controller includes the number of the lane where the vehicle to be parked is located in the sent message, and the master controller intercepts the point cloud data of the lane where the vehicle to be parked is located in the point cloud data according to the number of the lane where the vehicle to be parked is located and the known relative positions of each lane and the laser radar; clustering the point cloud data to obtain a point cloud set of one or more vehicles; and determining a point cloud set with intersection with the point cloud data of the lane where the vehicle to be parked is located in the point cloud sets of the one or more vehicles as the point cloud set of the vehicle to be parked.

In such embodiments, when the position of the lidar is determined, the relative positions of each lane and the lidar may be determined and stored as known information locally at the master; the main controller can determine which lane the vehicle to be parked runs on according to the number of the lane in which the vehicle to be parked is located; the main controller can intercept the point cloud data of the lane where the vehicle to be parked is located in the point cloud data by combining the relative position relation between each lane and the laser radar; after clustering the point cloud data to obtain one or more point cloud sets of the vehicles, the master controller finds the point cloud set with intersection with the point cloud data of the lane where the vehicle to be parked is located, and the point cloud set is the point cloud set of the vehicle to be parked.

(5) In some embodiments, the vehicle controller includes the number of the lane where the vehicle to be parked is located in the sent message, and the master controller intercepts the point cloud data of the lane where the vehicle to be parked is located in the point cloud data according to the number of the lane where the vehicle to be parked is located and the known relative positions of each lane and the laser radar, and clusters the intercepted point cloud data to obtain the point cloud set of the vehicle to be parked.

In such embodiments, when the position of the lidar is determined, the relative positions of each lane and the lidar may be determined and stored as known information locally at the master; the main controller can determine which lane the vehicle to be parked runs on according to the number of the lane in which the vehicle to be parked is located; and the master controller can intercept the point cloud data of the lane where the vehicle to be parked is positioned in the point cloud data by combining the relative position relation between each lane and the laser radar.

(6) In some embodiments, the vehicle controller includes in the sent message positioning data collected by the vehicle-mounted positioning device of the vehicle to be parked and the number of the lane in which it is located; the master controller intercepts point cloud data of a lane where the vehicle to be parked is located from the point cloud data according to the number of the lane where the vehicle to be parked is located and the known relative positions of each lane and the laser radar; the master controller clusters the point cloud data to obtain one or more point cloud sets of the vehicles, and the point cloud set which contains the positioning data and has intersection with the intercepted point cloud data of the lane where the vehicle to be parked is located in the point cloud sets is determined to be the point cloud set of the vehicle to be parked.

In such embodiments, the positioning data collected by the vehicle positioning devices of different vehicles are the position information of the different vehicles, and in general, the different vehicles can be distinguished by the positioning data, however, in consideration that the positioning data obtained by the vehicle positioning devices have a certain error, and adjacent lanes may be relatively close to each other, in order to distinguish vehicles whose positioning data are close to but are on different lanes, a point cloud set including the positioning data and having an intersection with the intercepted point cloud data of the lane where the vehicle to be parked is located may be determined as the point cloud set of the vehicle to be parked.

Step S700, calculating a point cloud set of a vehicle to be parked and a vehicle point cloud model by using an ICP algorithm by a master controller to obtain and send a rotation matrix and a translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model; the vehicle point cloud model is a point cloud set obtained by scanning a vehicle parked in a parking space in advance.

The ICP algorithm can be used for calculating a translation matrix and a rotation matrix among different point sets, the point cloud set of the vehicle to be parked is the point set corresponding to the vehicle to be parked in the driving process, and the vehicle point cloud model is the point set of the vehicle accurately stopped in the parking space, so that the translation matrix and the rotation matrix between the vehicle to be parked in the driving process and the vehicle accurately stopped in the parking space can be obtained by calculating the two point sets through the ICP algorithm. And, since the vehicle point cloud model is a point set of the vehicle accurately stopped in the parking space, a rotation matrix and a translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model correspond to a rotation amount and a translation amount of the vehicle to be parked to the parking space, respectively.

In consideration of different vehicle models, the point cloud set obtained by scanning the vehicles of different models by the lidar is also different, so in some embodiments, a plurality of vehicle point cloud models obtained by scanning the vehicles of a plurality of different vehicle models parked in the parking space by the lidar may be used in advance, and stored in a model library, and step S700 is performed as follows: the method comprises the steps that a master controller determines the vehicle model of a vehicle to be parked, a vehicle point cloud model matched with the vehicle model of the vehicle to be parked is selected in a model library, and an ICP algorithm is utilized to calculate a point cloud set of the vehicle to be parked and the vehicle point cloud model matched with the vehicle model of the vehicle to be parked.

For example, the model library includes a plurality of vehicle point cloud models a, b, c, d, e, F, g, the vehicle models corresponding to the vehicle point cloud models are A, B, C, D, E, F, G, when the vehicle model of the vehicle to be parked is F, the master controller can determine that the vehicle point cloud model matching the vehicle model of the vehicle to be parked is F through matching, and then can calculate the point cloud set of the vehicle to be parked and F by using the ICP algorithm.

Considering that for some vehicle models, a vehicle point cloud model matched with the model library may not be stored in the model library, in some embodiments, the parking control method provided by the embodiment of the application further includes: judging whether a vehicle point cloud model matched with the vehicle model of the vehicle to be parked is contained in the model library; if the vehicle model is not contained, an existing vehicle point cloud model is selected from the model library, the existing vehicle point cloud model is determined to be a vehicle point cloud model matched with the vehicle model of the vehicle to be parked, after the vehicle to be parked is stopped in a parking space, the vehicle to be parked is scanned by using a laser radar, and the point cloud set obtained by scanning is stored in the model library. Through the processing, when the vehicles with the same vehicle model number are expected to park in the parking space, the vehicle point cloud model matched with the vehicle model can be found in the model library.

In some embodiments, the vehicle controller includes the vehicle model of the vehicle to be parked in the transmitted message, and the master controller can parse the vehicle model of the vehicle to be parked from the message by parsing the received message.

In some embodiments, the master controller may first obtain a vehicle identification of the vehicle to be parked, and determine a vehicle model of the vehicle to be parked according to a known correspondence between the vehicle identification and the vehicle model. Wherein the vehicle identification may be a license plate number.

In some embodiments, the master may obtain the vehicle identification of the vehicle to be parked by capturing and identifying the license plate of the vehicle to be parked. For example, the master controller photographs a license plate of a vehicle to be parked using a camera.

In some embodiments, the vehicle controller includes in the transmitted message a vehicle identification of the vehicle to be parked, from which the master can parse after receiving the message.

The ICP algorithm calculates a rotation matrix and a translation matrix between a point cloud set of a vehicle to be parked and a vehicle point cloud model in an iterative mode, and in the iterative process of the ICP algorithm, the initial rotation matrix and the initial translation matrix adopted have very important influence on the accuracy of a final calculated result.

In some embodiments, step S700 is performed as follows:

step S702, determining a first average center and a second average center, wherein the coordinates of the first average center are the average value of the coordinates of a preset number of points, which are positioned at the forefront in the running direction of the vehicle to be stopped, in the point cloud set of the vehicle to be stopped; the coordinates of the second average center are the average value of the coordinates of a preset number of points, which are positioned at the forefront in the running direction of the vehicle to be stopped, in the vehicle point cloud model;

step S704, determining an initial rotation matrix and an initial translation matrix; the initial rotation matrix is a matrix used for rotating the first average center to the second average center; the initial translation matrix is a matrix used for translating the first average center to the second average center;

step S706, performing iterative computation on the point cloud set of the vehicle to be parked and the vehicle point cloud model by using the initial rotation matrix and the initial translation matrix to obtain a rotation matrix and a translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model.

As shown in fig. 6, the point cloud set of the vehicle to be parked is located in the coordinate system 1, and the vehicle point cloud model is located in the coordinate system 2; the n points (identified by the dotted line boxes) located at the forefront in the traveling direction of the vehicle to be stopped in the point cloud set of the vehicle to be stopped are P _i (x _i ,y _i ,z _i ) I=1, 2, 3..n, the first average center isThe n forefront points (identified by the dotted line boxes) in the vehicle point cloud model in the running direction of the vehicle to be stopped are Q _i (X _i ,Y _i ,Z _i ) I=1, 2, 3..n, the second average center is +.>First mean center +.>Rotate to the second average center +.>The matrix used is determined as the initial rotation matrix; first mean center +.>Translation to the second mean center->The matrix used is determined as the initial translation matrix.

In some embodiments, step S700 is performed as follows steps S708-S712:

step S708, the main controller analyzes positioning data acquired by the vehicle-mounted positioning equipment of the vehicle to be stopped from the message sent by the vehicle controller;

step S710, respectively determining an initial rotation matrix and an initial translation matrix; the initial rotation matrix is a matrix used for rotating points corresponding to positioning data to reference positioning points; the initial translation matrix is a matrix used for translating the point corresponding to the positioning data to the reference positioning point; the reference positioning point is a point corresponding to positioning data acquired by vehicle-mounted positioning equipment when a vehicle stops in a parking space in the process of determining the vehicle point cloud model;

step S712, performing iterative computation on the point cloud set of the vehicle to be parked and the vehicle point cloud model by using the initial rotation matrix and the initial translation matrix to obtain a rotation matrix and a translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model.

In the process of determining the vehicle point cloud model, the vehicle is loaded with vehicle-mounted positioning equipment, and when the vehicle stops in a parking space, the point determined by positioning data acquired by the vehicle-mounted positioning equipment on the vehicle is the reference positioning point.

In such embodiments, the on-board positioning device may be a GPS positioning device, an RTK positioning device, a Beidou satellite positioning system positioning device, a GLONASS positioning system positioning device, a Galileo positioning system positioning device, a global navigation satellite system GNSS positioning device, or the like.

The vehicle point cloud model is a point set of vehicles accurately parked in a parking space, and the point cloud set of the vehicles to be parked obtained through clustering is the point set of the vehicles to be parked in the running process, so that the point cloud set of the vehicles to be parked and the vehicle point cloud model obtained through clustering are calculated through an ICP algorithm, and the rotation amount and the translation amount of the vehicles to be parked in the running process to the parking space can be obtained. In the process, the accuracy of the vehicle point cloud model has a direct influence on the accuracy of the final calculation result. However, the number of lines of the laser radars is limited (such as 32 lines and 64 lines), when the laser radars at fixed positions are used for scanning vehicles parked in parking spaces, the number and the emission direction of laser beams are limited, the laser beams can only be emitted to a small area of a vehicle body, the obtained point cloud data can only reflect the small area of the vehicle body, the point cloud set obtained by clustering the point cloud data (namely, a vehicle point cloud model) cannot well reflect the position of the whole vehicle body, and even the vehicle point cloud model cannot be obtained through a clustering algorithm.

To overcome the above problems, in some embodiments, the vehicle point cloud model may be obtained according to steps S714 to S718:

in step S714, the vehicle that has traveled to the parking space and finally parked in the parking space is scanned beforehand by the lidar.

Step S716, converting the point cloud data when the vehicle does not reach the parking space into a coordinate system in which the point cloud data when the vehicle reaches the parking space is located.

In specific implementation, the process can utilize ICP algorithm to realize the conversion of point cloud data among different coordinate systems.

Step S718, the point cloud set obtained after conversion is determined as a vehicle point cloud model.

In the steps S714-S718, the laser radar is used to scan the moving vehicle, so that the laser beam can be emitted to more areas of the vehicle body, correspondingly, the obtained point cloud data can represent more areas of the vehicle body, the obtained vehicle point cloud model can also represent more areas of the vehicle body, the position of the whole vehicle body can be better represented, the requirement of the ICP algorithm is met, and the accuracy of the calculation result is improved.

Step S800, the vehicle controller controls the running direction and speed of the vehicle to be parked in real time according to the rotation matrix and the translation matrix between the point cloud set of the vehicle to be parked and the point cloud model of the vehicle, and finally the vehicle to be parked is stopped in the parking space.

In some embodiments, the vehicle controller achieves the purpose of controlling the traveling direction and speed of the vehicle to be parked in real time by controlling the steering system, the throttle control system, and the braking system of the vehicle to be parked.

Because the rotation matrix and the translation matrix between the point cloud set of the vehicle to be parked and the point cloud model of the vehicle are the rotation amount and the translation amount of the vehicle to be parked to the parking space respectively in the running process, the running direction and the running speed of the vehicle to be parked can be controlled in real time according to the rotation matrix and the translation matrix obtained through real-time calculation, so that the vehicle to be parked can be driven into the parking space.

In some embodiments, in step S600, the vehicle controller considers, in addition to the rotation matrix and the translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model, obstacles around the parking space (such as vehicles stationary on adjacent parking spaces) in controlling the traveling direction and speed of the vehicle to be parked, so as to ensure that the parking process of the vehicle to be parked is safe and smooth.

In the parking control method provided by the embodiment of the application, the vehicle point cloud model is a point cloud set obtained by scanning the vehicle accurately stopped in the parking space, so that the driving direction and speed of the vehicle to be parked are controlled according to the rotation matrix and the translation matrix, the vehicle point cloud model is taken as a target, and the vehicle point cloud model is overlapped with the vehicle point cloud model by rotating and translating the point cloud set of the vehicle to be parked, so that the aim of accurately stopping the vehicle to be parked in the parking space is fulfilled. The parking control method provided by the embodiment of the application has the advantages of high automation degree, high precision and the like, is suitable for being applied to various types of parking spaces such as automatic locking type parking spaces, crossed parking spaces, multi-layer parking spaces and the like, and is beneficial to solving the problems that the vehicle is inclined (parts such as tires and doors are easy to damage), is too close to an adjacent parking space (the doors are not opened), is difficult to leave the parking space (the time is long, and the adjacent parking space is required to be moved).

Based on the same inventive concept, the embodiment of the present application provides a parking control method applied to a master controller, as shown in fig. 7, including:

step A100, receiving a message of a vehicle to be parked requesting parking, which is sent by a vehicle controller;

step A200, determining a parking space and sending the identification of the parking space to the vehicle controller so that the vehicle controller controls the vehicle to be parked to drive to the parking space;

step A300, acquiring point cloud data of a preset monitoring area corresponding to the parking space, which is obtained by laser radar scanning; the preset monitoring area comprises the parking space and a preset area which can enter the parking space;

step A400, clustering the point cloud data to obtain a point cloud set of the vehicle to be parked;

step A500, calculating a point cloud set of the vehicle to be parked and a vehicle point cloud model by using an iterative closest point ICP algorithm to obtain a rotation matrix and a translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model; the vehicle point cloud model is a point cloud set obtained by scanning a vehicle stopped in the parking space by using a laser radar in advance;

and step A600, transmitting the rotation matrix and the translation matrix so that the vehicle controller can control the running direction and the running speed of the vehicle to be parked in real time according to the rotation matrix and the translation matrix and finally stop in the parking space.

In some embodiments, receiving a message sent by a vehicle controller that a vehicle to be parked requests parking includes: and receiving a message of the vehicle to be parked requesting parking, which is broadcast by the vehicle controller, through the vehicle-to-vehicle V2X device.

In some embodiments, before determining a parking space, further comprising: resolving a communication connection identifier from the message; and establishing communication connection with the vehicle controller through the communication connection identifier.

In some embodiments, the communication connection identification includes one or both of a MAC address of the vehicle controller, a MAC address of a vehicle-to-vehicle V2X communication device to which the vehicle controller is connected.

In some embodiments, determining a parking space includes: an empty parking space is determined from a plurality of preset parking spaces.

In some embodiments, the identification of the parking space includes: and the number and/or the position information of the parking spaces.

In some embodiments, each laser radar is only used for scanning a predetermined monitoring area corresponding to one parking space, and each master controller is only used for acquiring point cloud data obtained by scanning one laser radar.

In some embodiments, each laser radar is used for scanning a predetermined monitoring area corresponding to at least two parking spaces, and each master controller is only used for acquiring point cloud data obtained by scanning one laser radar.

In some embodiments, each laser radar is only used for scanning a predetermined monitoring area corresponding to one parking space, and each master controller is used for acquiring point cloud data obtained by scanning at least two laser radars.

In some embodiments, each laser radar is configured to scan a predetermined monitoring area corresponding to at least two parking spaces, and each master controller is configured to obtain point cloud data obtained by scanning at least two laser radars.

In some embodiments, obtaining point cloud data of a predetermined monitoring area corresponding to the parking space obtained by laser radar scanning includes:

determining a laser radar for scanning a preset monitoring area corresponding to the parking space;

and acquiring point cloud data obtained by laser radar scanning.

In some embodiments, obtaining point cloud data of a predetermined monitoring area corresponding to the parking space obtained by laser radar scanning, further includes:

and when judging that the scanning range of the laser radar is larger than the preset monitoring area corresponding to the parking space, preprocessing the point cloud data obtained by scanning the laser radar to obtain the point cloud data of the preset monitoring area corresponding to the parking space.

In some embodiments, clustering the point cloud data to obtain the point cloud set of the vehicle to be parked includes:

And clustering the point cloud data to obtain point cloud sets of one or more vehicles, and determining the point cloud set of the vehicle corresponding to the driving state in the point cloud sets of the one or more vehicles as the point cloud set of the vehicle to be stopped.

analyzing positioning data acquired by the vehicle-mounted positioning equipment of the vehicle to be stopped from the message;

and clustering the point cloud data to obtain point cloud sets of one or more vehicles, and determining the point cloud sets containing the positioning data in the point cloud sets of the one or more vehicles as the point cloud sets of the vehicles to be parked.

and intercepting the point cloud data corresponding to the position corresponding to the positioning data and the point cloud data corresponding to the area in the preset length around the position corresponding to the positioning data in the point cloud data, and clustering the intercepted point cloud data to obtain the point cloud set of the vehicle to be parked.

Analyzing the number of the lane where the vehicle to be parked is located from the message;

according to the number of the lane where the vehicle to be parked is located and the known relative positions of each lane and the laser radar, intercepting the point cloud data of the lane where the vehicle to be parked is located from the point cloud data;

clustering the point cloud data to obtain a point cloud set of one or more vehicles;

and determining a point cloud set with intersection with the point cloud data of the lane where the vehicle to be parked is located in the point cloud set of the one or more vehicles as the point cloud set of the vehicle to be parked.

according to the number of the lane where the vehicle to be parked is located and the known relative positions of each lane and the laser radar, intercepting the point cloud data of the lane where the vehicle to be parked is located in the point cloud data, and clustering the intercepted point cloud data to obtain a point cloud set of the vehicle to be parked.

Analyzing positioning data acquired by the vehicle-mounted positioning equipment of the vehicle to be parked and the number of the lane where the vehicle to be parked is located from the message;

and clustering the point cloud data to obtain point cloud sets of one or more vehicles, and determining the point cloud set which contains the positioning data and has intersection with the point cloud data of the lane where the vehicle to be parked is located in the point cloud set of the one or more vehicles as the point cloud set of the vehicle to be parked.

In some embodiments, calculating the set of point clouds of the vehicle to be parked and the vehicle point cloud model using an ICP algorithm includes:

determining a vehicle model of the vehicle to be parked;

selecting a vehicle point cloud model matched with the vehicle model of the vehicle to be parked from a model library;

calculating the point cloud set of the vehicle to be parked and a vehicle point cloud model matched with the vehicle model of the vehicle to be parked by utilizing an ICP algorithm; the model library comprises a plurality of vehicle point cloud models obtained by scanning vehicles of a plurality of different vehicle models parked in the parking space by utilizing a laser radar in advance.

In some embodiments, determining the vehicle model of the vehicle to be parked comprises: and analyzing the vehicle model of the vehicle to be stopped from the message.

In some embodiments, determining the vehicle model of the vehicle to be parked comprises: and analyzing the vehicle identification of the vehicle to be parked from the message, and determining the vehicle model of the vehicle to be parked according to the corresponding relation between the known vehicle identification and the vehicle model.

In some embodiments, the parking control method applied to the master controller provided in the embodiments of the present application further includes:

judging whether the model library contains a vehicle point cloud model matched with the vehicle model of the vehicle to be parked;

and if the vehicle model does not contain the parking space, selecting an existing vehicle point cloud model from the model library, determining the existing vehicle point cloud model as a vehicle point cloud model matched with the vehicle model of the vehicle to be parked, and after the vehicle to be parked is stopped in the parking space, scanning the vehicle to be parked by using the laser radar and storing the point cloud set obtained by scanning into the model library.

In some embodiments, calculating the point cloud set of the vehicle to be parked and the vehicle point cloud model by using an ICP algorithm to obtain a rotation matrix and a translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model, including:

Determining a first average center and a second average center, wherein the coordinates of the first average center are the average value of the coordinates of a preset number of points which are positioned at the forefront in the running direction of the vehicle to be stopped in the point cloud set of the vehicle to be stopped; the coordinates of the second average center are the average value of the coordinates of the preset number of points, which are positioned at the forefront in the running direction of the vehicle to be stopped, in the vehicle point cloud model;

determining an initial rotation matrix, wherein the initial rotation matrix is used for rotating the first average center to the second average center;

determining an initial translation matrix, wherein the initial translation matrix is used for translating the first average center to the second average center;

and carrying out iterative computation on the point cloud set of the vehicle to be parked and the vehicle point cloud model by using the initial rotation matrix and the initial translation matrix to obtain a rotation matrix and a translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model.

determining an initial rotation matrix, wherein the initial rotation matrix is a matrix used for rotating points corresponding to the positioning data to reference positioning points, and the reference positioning points are points corresponding to the positioning data acquired by vehicle-mounted positioning equipment when a vehicle stops in the parking space in the process of determining a vehicle point cloud model;

determining an initial translation matrix, wherein the initial translation matrix is a matrix used for translating the point corresponding to the positioning data to the reference positioning point;

In some embodiments, the vehicle point cloud model is determined as follows:

scanning a vehicle which drives to the parking space and finally parks in the parking space by utilizing a laser radar in advance;

converting the point cloud data when the vehicle does not reach the parking space into a coordinate system where the point cloud data when the vehicle reaches the parking space is located;

And determining the point cloud set obtained after conversion as the vehicle point cloud model.

The parking control method shown in fig. 7 and the parking control method shown in fig. 2 are implemented based on the same inventive concept, and have the same non-limiting embodiment, and the foregoing description of the parking control method shown in fig. 2 may be referred to specifically, and will not be repeated here.

Based on the same inventive concept, the present application also provides a parking control method applied to a vehicle controller, as shown in fig. 8, including:

step B100, sending a message that the vehicle to be parked requests parking;

step B200, receiving an identification of a parking space returned by the main controller, and controlling the to-be-parked vehicle to drive to the parking space;

step B300, receiving a rotation matrix and a translation matrix between a point cloud set of the vehicle to be parked and a vehicle point cloud model returned by the master controller; the vehicle point cloud model is a point cloud set obtained by scanning a vehicle stopped in the parking space by using a laser radar in advance;

and step B400, controlling the running direction and speed of the vehicle to be parked in real time according to the rotation matrix and the translation matrix so as to enable the vehicle to be parked to be finally parked in the parking space.

In some embodiments, sending a message that a vehicle to be parked requests parking in a parking space includes: and broadcasting a message that the vehicle to be parked requests to park in the parking space through the vehicle-to-vehicle everything V2X device.

In some embodiments, the message includes any one or more of the following information:

a vehicle identification of the vehicle to be parked;

the vehicle model of the vehicle to be stopped;

positioning data acquired by the vehicle-mounted positioning equipment of the vehicle to be stopped;

and (5) communication connection identification.

In some embodiments, sending a message that a vehicle to be parked requests parking includes:

the message is sent out after the vehicle to be parked enters a parking lot; or alternatively, the first and second heat exchangers may be,

and sending out the message after receiving a preset trigger signal.

In some embodiments, controlling the driving direction and speed of the vehicle to be stopped in real time according to the rotation matrix and the translation matrix includes: and controlling the running direction and speed of the vehicle to be parked in real time by controlling a steering system, an accelerator control system and a braking system of the vehicle to be parked according to the rotation matrix and the translation matrix.

The parking control method shown in fig. 8 and applied to the vehicle controller is implemented based on the same inventive concept as the parking control method shown in fig. 2, and has the same non-limiting embodiment, and the foregoing description of the parking control method shown in fig. 2 may be referred to, and will not be repeated here.

Based on the same inventive concept, the embodiments of the present application also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, provides the steps of the parking control method applied to a master according to the embodiments of the present application. The computer readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. In some embodiments, the computer-readable storage medium may be: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Based on the same inventive concept, the present embodiments also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, provides the respective steps in the parking control method applied to a vehicle controller. The computer readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. In some embodiments, the computer-readable storage medium may be: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Exemplary apparatus

Based on the same inventive concept, the embodiment of the present application further provides a master controller, where the master controller includes a first processor, a first memory, and a computer program stored on the first memory and executable on the first processor, and when the first processor runs the computer program, the first processor executes the parking control method applied to the master controller of fig. 7.

The method executed when the computer program in the first memory is executed is implemented based on the same inventive concept as the parking control method shown in fig. 2, and has the same non-limiting embodiment, and the description of the parking control method shown in fig. 2 in the foregoing exemplary method may be referred to specifically, and will not be repeated here.

Alternatively, in the present application, the first processor may be implemented by a circuit, a chip, or other electronic components. For example, the first processor may also include one or more microcontrollers, one or more Field Programmable Gate Arrays (FPGAs), one or more application specific circuits (ASICs), one or more Digital Signal Processors (DSPs), one or more integrated circuits, etc.

Alternatively, in the present application, the first memory may be implemented by a circuit, a chip, or other electronic components. For example, the first memory may include one or more read-only memory (ROM), random-access memory (RAM), flash memory, electrically programmable memory (EPROM), electrically programmable and erasable memory (EEPROM), embedded multimedia cards (eMMC), a hard disk drive, or any volatile or non-volatile medium or the like.

In this embodiment of the present application, the master controller may be a computer device in the form of an industrial personal computer, a server, a PC, a portable computer, a tablet computer, a PDA, an iMac, or the like.

Based on the same inventive concept, the embodiments of the present application also provide a vehicle controller including a second processor, a second memory, and a computer program stored on the second memory and executable on the second processor, the second processor executing the parking control method of fig. 8 applied to the vehicle controller when the computer program is executed.

The method executed by the computer program in the second memory when executed is implemented based on the same inventive concept as the parking control method shown in fig. 2, and has the same non-limiting embodiment, and reference may be made specifically to the description of the parking control method shown in fig. 2 in the foregoing exemplary method, which is not repeated here.

Alternatively, in the present application, the second processor may be implemented by a circuit, a chip, or other electronic components. For example, the second processor may also include one or more microcontrollers, one or more Field Programmable Gate Arrays (FPGAs), one or more application specific circuits (ASICs), one or more Digital Signal Processors (DSPs), one or more integrated circuits, etc.

Alternatively, in the present application, the second memory may be implemented by a circuit, a chip, or other electronic components. For example, the second memory may include one or more read-only memory (ROM), random Access Memory (RAM), flash memory, electrically programmable memory (EPROM), electrically programmable and erasable memory (EEPROM), embedded multimedia cards (eMMC), a hard disk drive, or any volatile or non-volatile medium or the like.

In this embodiment of the present application, the vehicle controller may be a DSP (Digital Signal Processing, digital signal processor), an FPGA (Field-Programmable Gate Array, field programmable gate array) controller, an industrial computer, a driving computer, an ECU (Electronic Control Unit ), an ARM or VCU (Vehicle Control Unit, vehicle controller), or the like, which is not specifically limited in this application.

Based on the same inventive concept, the embodiment of the present application also provides an automobile, as shown in fig. 9, on which a vehicle controller is mounted. The vehicle controller is used for sending a message that a vehicle to be parked requests parking, receiving an identification of a parking space returned by the main controller, and controlling the vehicle to be parked to drive to the parking space; receiving a rotation matrix and a translation matrix between a point cloud set of a vehicle to be parked and a vehicle point cloud model returned by a master controller; and controlling the running direction and speed of the vehicle to be parked in real time according to the rotation matrix and the translation matrix so as to enable the vehicle to be parked to be finally stopped in the parking space.

In some embodiments, the vehicle controller connects a steering system, a throttle control system, and a braking system of the vehicle. That is, the vehicle controller indirectly achieves the purpose of controlling the running direction and speed of the vehicle to be parked in real time by controlling the steering system, the throttle control system and the braking system of the automobile.

In some embodiments, the vehicle is further equipped with a vehicle-mounted V2X device connected to the vehicle controller.

The automobile can be a traditional automobile driven by human beings (such as a household car, an engineering vehicle, a fire truck, an ambulance, a vehicle and the like), can be an automatic driving vehicle, can be a vehicle consuming traditional energy sources such as gasoline, diesel oil and the like, and can be a vehicle consuming new energy sources such as electric energy, solar energy and the like. The automatic driving vehicle is a vehicle which is realized by utilizing an automatic driving technology and has the functions of carrying persons (such as a family car, a bus and the like), carrying goods (such as a common truck, a van, a closed truck, a tank truck, a flat truck, a container truck, a self-discharging truck, a special structure truck and the like) or special rescue (such as a fire truck, an ambulance and the like).

Exemplary System

Based on the same inventive concept, the embodiment of the present application further provides a parking control system, as shown in fig. 10, including: a master controller, a vehicle controller, and a lidar.

The working principle of the parking control system can refer to a parking control method as shown in fig. 2, and will not be described herein.

In the parking control system, the laser radar can be 16 lines, 32 lines or 64 lines, the more the laser beams are, the easier the scanned point cloud data can cover the whole body of the scanned vehicle, and the higher the cost is correspondingly; the hardware constituent structures of the master controller and the vehicle controller have been described in the exemplary apparatus, and are not described here again;

The parking control system and the parking control method shown in fig. 2 are implemented based on the same inventive concept, and have the same non-limiting implementation, and specific reference may be made to the description of the parking control method shown in fig. 2 in the foregoing exemplary method, which is not repeated herein.

In order to achieve the purpose that the laser radar scans a preset monitoring area (comprising a parking space and a preset area capable of entering the parking space), the laser radar can be mounted on a ceiling, a wall, mechanical equipment or a professional support frame of a parking lot in practical implementation.

In some embodiments, the master may be mounted within a central room of the parking lot or on a ceiling, wall, machinery or professional support frame of the parking lot and connected to the lidar.

In some embodiments, the vehicle controller is mounted on the vehicle to be parked.

In some embodiments, the vehicle controller is a device mounted outside the vehicle to be parked, for example, a device fixedly mounted on a place or mounted on any mobile device, and in these embodiments, the vehicle controller controls the steering system, the throttle control system and the braking system of the vehicle to be parked through wireless communication modes such as a base station, a WIFI and the like, so as to indirectly control the vehicle to be parked.

In some embodiments, as shown in fig. 5 (a), the master, the lidar and the predetermined monitoring area (parking space) are set in the following modes: each laser radar is only used for scanning a preset monitoring area, and each master controller is only used for acquiring real-time point cloud data obtained by scanning one laser radar.

In some embodiments, as shown in (b) of fig. 5, the master, lidar and predetermined monitoring area are set to the following modes: each laser radar is used for scanning at least two preset monitoring areas, and each master controller is only used for acquiring real-time point cloud data obtained by scanning one laser radar.

In some embodiments, as shown in (c) of fig. 5, the master, lidar and predetermined monitoring area are set to the following modes: each laser radar is only used for scanning a preset monitoring area, and each master controller is used for acquiring real-time point cloud data obtained by scanning at least two laser radars.

In some embodiments, as shown in (d) of fig. 5, the master, lidar and predetermined monitoring area are set to the following modes: each laser radar is used for scanning at least two preset monitoring areas, and each master controller is used for acquiring real-time point cloud data obtained by scanning at least two laser radars.

In some embodiments, as shown in fig. 10, the parking control system further includes: V2X devices connected to the master controller, and V2X devices connected to the vehicle controller.

In some embodiments, as shown in fig. 10, the parking control system further includes: and the power supply equipment is used for supplying power to the master controller and/or the laser radar.

In some embodiments, the parking control system further comprises: and the uninterruptible power supply UPS is used for supplying power to the master controller and/or the laser radar when the power supply equipment is powered off.

The foregoing has outlined rather broadly the more detailed description of the invention in order that the detailed description of the invention may be better understood, and the detailed description of the embodiments that follow is intended to be read in light of the accompanying claims.

It should be noted that although the operations of the methods of the present application are depicted in the drawings in a particular order, this does not require or imply that the operations must be performed in that particular order or that all illustrated operations be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.

Those of skill would further appreciate that the various illustrative logical blocks (illustrative logical block), units, and steps described in the exemplary embodiments may be implemented by electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components (illustrative components), elements, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design requirements of the overall system. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation is not to be understood as beyond the scope of the embodiments of the present application.

The various illustrative logical blocks, or units, or devices described in the embodiments of the application may be implemented or performed with a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination of these designed to perform the functions described. A general purpose processor may be a microprocessor, but in the alternative, the general purpose processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.

The steps of a method or algorithm described in the embodiments of the present application may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. In an example, a storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC, which may reside in a user terminal. In the alternative, the processor and the storage medium may reside as distinct components in a user terminal.

In one or more exemplary designs, the above-described functions described in the embodiments of the present application may be implemented in hardware, software, firmware, or any combination of the three. If implemented in software, the functions may be stored on a computer-readable medium or transmitted as one or more instructions or code on the computer-readable medium. Computer readable media includes both computer storage media and communication media that facilitate transfer of computer programs from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer. For example, such computer-readable media may include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to carry or store program code in the form of instructions or data structures and other data structures that may be read by a general or special purpose computer, or a general or special purpose processor. Further, any connection is properly termed a computer-readable medium, e.g., if the software is transmitted from a website, server, or other remote source via a coaxial cable, fiber optic cable, twisted pair, digital Subscriber Line (DSL), or wireless such as infrared, radio, and microwave, and is also included in the definition of computer-readable medium. The disks (disks) and disks (disks) include compact disks, laser disks, optical disks, DVDs, floppy disks, and blu-ray discs where disks usually reproduce data magnetically, while disks usually reproduce data optically with lasers. Combinations of the above may also be included within the computer-readable media.

Claims

1. A parking control method, characterized by comprising:

performing iterative computation on the point cloud set of the vehicle to be parked and the vehicle point cloud model by using the initial rotation matrix and the initial translation matrix to obtain a rotation matrix and a translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model; the vehicle point cloud model is a point cloud set obtained by scanning a vehicle stopped in the parking space by using a laser radar in advance; and

2. The parking control method according to claim 1, wherein receiving a message sent by a vehicle controller that a vehicle to be parked requests parking, includes: and receiving a message of the vehicle to be parked requesting parking, which is broadcast by the vehicle controller, through the vehicle-to-vehicle V2X device.

3. The parking control method according to claim 1, wherein before determining a parking space, further comprising: resolving a communication connection identifier from the message; and establishing communication connection with the vehicle controller through the communication connection identifier.

4. A parking control method according to claim 3, wherein the communication connection identifier includes one or both of a MAC address of the vehicle controller, a MAC address of a vehicle-to-vehicle V2X communication device to which the vehicle controller is connected.

5. The parking control method according to claim 1, wherein determining a parking space includes: an empty parking space is determined from a plurality of preset parking spaces.

6. The parking control method according to claim 1, wherein the identification of the parking space includes: and the number and/or the position information of the parking spaces.

7. The parking control method according to claim 1, wherein each laser radar is used for scanning only a predetermined monitoring area corresponding to one parking space, and each master controller is used for acquiring point cloud data obtained by scanning only one laser radar.

8. The parking control method according to claim 1, wherein each laser radar is used for scanning a predetermined monitoring area corresponding to at least two parking spaces, and each master controller is only used for acquiring point cloud data obtained by scanning one laser radar.

9. The parking control method according to claim 1, wherein each laser radar is only used for scanning a predetermined monitoring area corresponding to one parking space, and each master controller is used for acquiring point cloud data obtained by scanning at least two laser radars.

10. The parking control method according to claim 1, wherein each laser radar is used for scanning a predetermined monitoring area corresponding to at least two parking spaces, and each master controller is used for acquiring point cloud data obtained by scanning at least two laser radars.

11. The parking control method according to claim 1, wherein obtaining point cloud data of a predetermined monitoring area corresponding to the parking space obtained by laser radar scanning includes:

and acquiring point cloud data obtained by laser radar scanning.

12. The parking control method according to claim 11, wherein obtaining point cloud data of a predetermined monitoring area corresponding to the parking space obtained by laser radar scanning, further comprises:

13. The parking control method according to claim 1, wherein clustering the point cloud data to obtain the point cloud set of the vehicle to be parked includes:

14. The parking control method according to claim 1, wherein clustering the point cloud data to obtain the point cloud set of the vehicle to be parked includes:

15. The parking control method according to claim 1, wherein clustering the point cloud data to obtain the point cloud set of the vehicle to be parked includes:

16. The parking control method according to claim 1, wherein clustering the point cloud data to obtain the point cloud set of the vehicle to be parked includes:

17. The parking control method according to claim 1, wherein clustering the point cloud data to obtain the point cloud set of the vehicle to be parked includes:

18. The parking control method according to claim 1, wherein clustering the point cloud data to obtain the point cloud set of the vehicle to be parked includes:

19. The parking control method according to claim 1, wherein calculating the point cloud set of the vehicle to be parked and the vehicle point cloud model using an ICP algorithm includes:

determining a vehicle model of the vehicle to be parked;

20. The parking control method according to claim 19, wherein determining a vehicle model of the vehicle to be parked includes: and analyzing the vehicle model of the vehicle to be stopped from the message.

21. The parking control method according to claim 19, wherein determining a vehicle model of the vehicle to be parked includes: and analyzing the vehicle identification of the vehicle to be parked from the message, and determining the vehicle model of the vehicle to be parked according to the corresponding relation between the known vehicle identification and the vehicle model.

22. The parking control method according to claim 19, characterized by further comprising:

23. The parking control method according to claim 1, wherein the vehicle point cloud model is determined as follows:

24. A parking control method, characterized by comprising:

sending a message that a vehicle to be parked requests parking;

controlling the running direction and speed of the vehicle to be parked in real time according to the rotation matrix and the translation matrix so as to enable the vehicle to be parked to be finally parked in the parking space;

the method comprises the steps that the master controller determines a rotation matrix and a translation matrix between vehicle point cloud models, and the method comprises the following steps:

25. The parking control method according to claim 24, wherein transmitting a message that a vehicle to be parked requests parking in the parking space includes: and broadcasting a message that the vehicle to be parked requests to park in the parking space through the vehicle-to-vehicle everything V2X device.

26. The parking control method according to claim 24, wherein the message contains any one or more of the following information:

a vehicle identification of the vehicle to be parked;

the vehicle model of the vehicle to be stopped;

and (5) communication connection identification.

27. The parking control method according to claim 26, wherein the communication connection identification includes one or both of a MAC address of the vehicle controller, a MAC address of a vehicle-to-vehicle V2X communication device to which the vehicle controller is connected.

28. The parking control method according to claim 24, wherein transmitting a message that a vehicle to be parked requests parking includes:

and sending out the message after receiving a preset trigger signal.

29. The parking control method according to claim 24, wherein controlling the traveling direction and speed of the vehicle to be parked in real time according to the rotation matrix and the translation matrix includes: and controlling the running direction and speed of the vehicle to be parked in real time by controlling a steering system, an accelerator control system and a braking system of the vehicle to be parked according to the rotation matrix and the translation matrix.

30. A master controller comprising a first processor, a first memory and a computer program stored on the first memory and executable on the first processor, wherein the first processor, when executing the computer program, performs the steps of the parking control method of any one of claims 1 to 23.

31. A vehicle controller comprising a second processor, a second memory and a computer program stored on the second memory and executable on the second processor, wherein the second processor, when executing the computer program, performs the steps of the parking control method of any one of claims 24 to 29.

32. A parking control system, comprising: the master of claim 30, the vehicle controller of claim 31, and the lidar.

33. The parking control system of claim 32, wherein each of the lidars is configured to scan only a predetermined monitored area corresponding to one parking space, and each of the masters is configured to acquire only one point cloud data scanned by the lidar.

34. The parking control system of claim 32, wherein each of the lidars is configured to scan a predetermined monitoring area corresponding to at least two parking spaces, and each of the master controllers is configured to obtain only one point cloud data scanned by the lidar.

35. The parking control system of claim 32, wherein each of the lidars is configured to scan only a predetermined monitoring area corresponding to one parking space, and each of the masters is configured to obtain point cloud data obtained by scanning at least two of the lidars.

36. The parking control system of claim 32, wherein each of the lidars is configured to scan a predetermined monitoring area corresponding to at least two parking spaces, and each of the masters is configured to obtain point cloud data obtained by scanning at least two of the lidars.

37. The parking control system of claim 32, further comprising: and the V2X device is connected with the vehicle controller.

38. The parking control system of claim 32, further comprising: and the power supply equipment is used for supplying power to the master controller and/or the laser radar.

39. An automobile having the vehicle controller of claim 31 mounted thereon.

40. The vehicle of claim 39, wherein the vehicle controller is coupled to a steering system, a throttle control system, and a braking system of the vehicle.

41. The vehicle of claim 39, wherein said vehicle is provided with a vehicle-mounted V2X device connected to said vehicle controller.

42. The vehicle of claim 39, wherein the vehicle is provided with an onboard locating device.

43. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the parking control method according to any one of claims 1 to 23.

44. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the parking control method according to any one of claims 24 to 29.