A parking control method, device and system

Abstract

Embodiments of the present application provide a parking control method, device and system. The parking control method comprises: receiving a message sent by a vehicle controller that a vehicle to be parked requests to park; determining a parking space and sending an identifier of the parking space to the vehicle controller; obtaining point cloud data of a predetermined monitoring area corresponding to the parking space scanned by a laser radar; 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, 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 the vehicle controller controls a driving direction and a speed of the vehicle to be parked in real time according to the rotation matrix and the translation matrix and finally stops in the parking space. The parking control method has the advantages of high automation and high precision, and meets the needs of realizing automatic and accurate parking in parking spaces of multiple types and small spaces.

Description

[0001] This divisional application is a divisional application of Chinese patent application No. 2018116023105, filed on December 26, 2018, entitled "A Parking Control Method, Device and System". Technical Field

[0002] The embodiments of this application relate to the field of intelligent transportation technology, and more specifically, the embodiments of this application relate to a parking control method, device and system. Background Technology

[0003] This section is intended to provide background or context for the embodiments of this application as set forth in the claims. The description herein is not intended to be a prior art simply because it is included in this section.

[0004] With urbanization and the widespread use of passenger cars, parking has become a major challenge restricting the development of many cities. To address this issue, various types of parking spaces have emerged, such as automatically locking parking spaces, interlocking parking spaces, and multi-level parking spaces. Furthermore, to improve land utilization and parking management efficiency, the area of ​​each parking space is generally designed to accommodate exactly one car. However, regardless of the type of parking space or the limited space, a high degree of precision in parking is required. Summary of the Invention

[0005] To address the vehicle parking problem, some existing solutions include:

[0006] (1) Some technical solutions use vehicle GPS devices to collect vehicle location data to control vehicle parking. However, the positioning accuracy of GPS devices (generally reaching the meter level) cannot meet the requirements for accurate parking in parking spaces (accuracy needs to reach the centimeter level). In addition, most parking spaces in cities are located in underground parking lots, which are affected by above-ground buildings and their indoor equipment, and GPS signals are easily blocked, leading to positioning failure.

[0007] (2) Some technical solutions use vehicle cameras to visually locate parking lines to control vehicle parking. However, due to limitations in algorithms and computing power, this solution cannot currently achieve centimeter-level precise parking.

[0008] It is evident that most common vehicle parking methods currently rely on in-vehicle positioning devices or cameras to locate vehicles and parking spaces. However, this method suffers from drawbacks such as large errors and slow speed.

[0009] In view of the above problems, this application proposes a parking control method, device and system that overcomes or at least partially solves the above problems.

[0010] In a first aspect of the embodiments of this application, a parking control method applied to a master controller is provided, comprising:

[0011] Receives messages from the vehicle controller requesting the vehicle to stop.

[0012] A parking space is identified and its identifier is sent to the vehicle controller, so that the vehicle controller can control the vehicle to drive to the parking space;

[0013] Obtain point cloud data of the predetermined monitoring area corresponding to the parking space obtained by LiDAR scanning; the predetermined monitoring area includes the parking space and a preset area accessible to the parking space;

[0014] Clustering the point cloud data yields a set of point clouds for the vehicles to be parked;

[0015] The iterative nearest point (ICP) algorithm is used to calculate the point cloud set of the vehicles to be parked and the vehicle point cloud model to obtain the rotation matrix and translation matrix between the point cloud set of the vehicles to be parked and the vehicle point cloud model; wherein, the vehicle point cloud model is the point cloud set obtained in advance by scanning the vehicles parked in the parking space using a lidar.

[0016] The rotation matrix and translation matrix are sent so that the vehicle controller can control the driving direction and speed of the vehicle to be parked in real time according to the rotation matrix and translation matrix and finally stop it in the parking space.

[0017] In a second aspect of the embodiments of this application, a parking control method applied to a vehicle controller is provided, comprising:

[0018] Send a message to the vehicle waiting to be parked requesting to stop;

[0019] Receive the parking space identifier returned by the main controller and control the vehicle to be parked to drive to the parking space;

[0020] The receiver returns a rotation and translation matrix between the point cloud set of the vehicles to be parked and the vehicle point cloud model; wherein, the vehicle point cloud model is a point cloud set obtained by scanning the vehicles parked in the parking space using a lidar in advance.

[0021] The direction and speed of the vehicle to be parked are controlled in real time according to the rotation matrix and translation matrix so that the vehicle to be parked eventually stops at the parking space.

[0022] In a third aspect of the embodiments of this application, a master controller is provided, including a first processor, a first memory, and a computer program stored in the first memory and executable on the first processor. When the first processor runs the computer program, it executes the various steps of the aforementioned parking control method applied to the master controller.

[0023] In a fourth aspect of the embodiments of this application, a vehicle controller is provided, including a second processor, a second memory, and a computer program stored in the second memory and executable on the second processor. When the second processor runs the computer program, it performs the various steps of the parking control method applied to the vehicle controller as described above.

[0024] In a fifth aspect of the embodiments of this application, a parking control system is provided, including: a master controller as described above, a vehicle controller as described above, and a lidar.

[0025] In a sixth aspect of the embodiments of this application, an automobile is provided, which is equipped with a vehicle controller as described above.

[0026] In a seventh aspect of the embodiments of this application, a computer-readable storage medium is provided having a computer program stored thereon, the computer program being executed by a processor to implement the various steps of the parking control method applied to a master controller as described above.

[0027] In an eighth aspect of the embodiments of this application, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the various steps of the parking control method applied to a vehicle controller as described above.

[0028] Using the above technical solution, this application uses the ICP algorithm to calculate the rotation and translation of the vehicle waiting to be parked from the parking space, and controls the driving direction and speed of the vehicle waiting to be parked based on the rotation and translation, and finally controls the vehicle to stop accurately in the parking space. The entire parking process is completed automatically and can achieve centimeter-level accuracy, which can meet the needs of high-precision parking. Attached Figure Description

[0029] The above and other objects, features, and advantages of exemplary embodiments of this application will become readily apparent upon reading the following detailed description with reference to the accompanying drawings. Several embodiments of this application are illustrated in the drawings by way of example and not limitation, in which:

[0030] Figure 1 The application scenarios provided by the embodiments of this application are illustrated schematically;

[0031] Figure 2The flowchart of the parking control method provided in the embodiments of this application is illustrated schematically;

[0032] Figure 3 A preset area of ​​one embodiment of this application is schematically shown;

[0033] Figure 4 A preset area of ​​yet another embodiment of this application is schematically shown;

[0034] Figure 5 The configuration modes of the main controller, lidar, and predetermined monitoring area provided in the embodiments of this application are schematically illustrated.

[0035] Figure 6 The method for determining the initial translation matrix according to an embodiment of this application is illustrated schematically;

[0036] Figure 7 The flowchart of the parking control method applied to the main controller provided in the embodiments of this application is illustrated schematically;

[0037] Figure 8 The flowchart of the parking control method applied to a vehicle controller provided in the embodiments of this application is illustrated schematically;

[0038] Figure 9 The illustration schematically depicts a vehicle provided in an embodiment of this application;

[0039] Figure 10 The parking control system provided in the embodiments of this application is illustrated schematically.

[0040] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0041] The principles and spirit of this application will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are provided merely to enable those skilled in the art to better understand and implement this application, and are not intended to limit the scope of this application in any way. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of this disclosure to those skilled in the art.

[0042] Those skilled in the art will understand that the embodiments of this application can be implemented as a system, apparatus, device, method, or computer program product. Therefore, this disclosure can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0043] The number of any elements in the accompanying drawings of this application is for illustrative purposes only and not for limitation, and any naming is for distinction only and has no limiting meaning.

[0044] The principles and spirit of this application will be explained in detail below with reference to several representative embodiments. Invention Overview

[0046] Currently, common methods for parking vehicles using vehicle positioning devices or vehicle cameras suffer from drawbacks such as low accuracy and slow speed. To meet the need for automated and precise parking in various types of parking spaces with limited space, this application provides a parking control method. This method first uses LiDAR to scan vehicles already parked in parking spaces to obtain vehicle point cloud models. Then, when a vehicle requests to park, LiDAR is used to scan vehicles moving towards the parking space in real time to obtain their point cloud sets. Subsequently, the rotation and translation matrices between the point cloud sets of the vehicles to be parked and the vehicle point cloud models are calculated using the ICP algorithm. Since these rotation and translation matrices represent the rotation and translation amounts of the moving vehicle to the parking space, the driving direction and speed of the vehicle to be parked can be controlled in real time based on these rotation and translation matrices, so that the vehicle to be parked stops precisely in the parking space.

[0047] The parking control method proposed in this application has the advantages of high automation and high precision, achieving centimeter-level accuracy, which meets the need for automated and precise parking in various types of parking spaces with limited space.

[0048] Application Scenarios Overview

[0049] This application provides an example of an application scenario, such as... Figure 1 As shown, a lidar is installed above the parking space. The lidar is connected to the main controller, which acquires the point cloud data obtained by the lidar scanning.

[0050] The vehicle controller sends a message requesting the vehicle to stop. After receiving the message, the main controller allocates a parking space to the vehicle. As the vehicle moves toward the parking space, the main controller uses point cloud data acquired by the LiDAR to cluster and obtain a set of point clouds of the moving vehicle. It then uses the ICP algorithm to calculate the rotation and translation matrices between the point cloud set of the vehicle and the point cloud model of the vehicle corresponding to the parking space. The vehicle controller controls the driving direction and speed of the vehicle in real time based on the rotation and translation matrices to ensure that the vehicle stops precisely at the parking space.

[0051] It is important to note that Figure 1 The application scenarios shown are merely for the purpose of facilitating understanding of the spirit and principles of this application, and the implementation of this application is not limited in any way. On the contrary, the implementation of this application can be applied to any applicable scenario.

[0052] Exemplary methods

[0053] The following is combined Figure 1 Application scenarios, refer to Figure 2 This application describes the parking control method provided in its embodiments.

[0054] like Figure 2 As shown in the figure, this application provides a parking control method, including:

[0055] In step S100, the vehicle controller sends a message to the vehicle waiting to be stopped requesting to stop.

[0056] In practice, the vehicle controller and the main controller can send and receive messages via wireless communication methods such as Wi-Fi, V2X, and base stations; this application does not impose strict limitations on this. Considering signal stability, the main controller and the vehicle controller can send and receive messages via V2X technology. In some embodiments, the vehicle controller can broadcast a message from a waiting vehicle requesting to park in a parking space via a V2X device installed on the waiting vehicle.

[0057] In some embodiments, the vehicle controller may send a message only when it determines that a predetermined condition is met, for example:

[0058] (1) The vehicle controller sends a message after determining that a vehicle waiting to be parked has entered the parking lot; or,

[0059] (2) The vehicle controller sends a message after receiving a preset trigger signal (such as a trigger signal sent by a road card device set up at the entrance of the parking lot).

[0060] In some embodiments, the message sent by the vehicle controller may include one or more of the following information:

[0061] (1) Vehicle identification markings of vehicles waiting to be parked;

[0062] (2) The vehicle model of the vehicle to be parked;

[0063] (3) Positioning data collected by the on-board positioning equipment of the vehicle waiting to be parked;

[0064] (4) Communication connection identifier.

[0065] The communication connection identifier includes, but is not limited to, one or both of the following: the MAC address of the vehicle controller and the MAC address of the V2X communication device connected to the vehicle controller.

[0066] In step S200, the main controller receives a message from the vehicle controller requesting the vehicle to stop.

[0067] In some embodiments, the master controller can receive messages from the vehicle controller via a V2X device.

[0068] In step S300, the main controller identifies a parking space and sends the identifier of that parking space to the vehicle controller.

[0069] To ensure a stable communication connection between the master controller and the vehicle controller, in some embodiments, before step S300, the master controller parses a communication connection identifier from a message sent by the vehicle controller and establishes a communication connection with the vehicle controller using this communication connection identifier. In some embodiments, the communication connection identifier may be, but is not limited to, the MAC address of the vehicle controller, and / or the MAC address of the V2X communication device to which the vehicle controller is connected.

[0070] In some embodiments, the master controller can be used to manage vehicle parking operations for one or more parking spaces (such as all parking spaces in a parking lot). The master controller can locally store the identifiers and occupied status (i.e., whether a vehicle is already parked in the parking space) of all the parking spaces it manages. When the master controller receives a request from the vehicle controller for a vehicle to park, the master controller can determine an available parking space from all the parking spaces it manages and send its identifier to the vehicle controller.

[0071] In step S400, the vehicle controller determines the parking space based on the parking space identifier sent by the main controller and controls the vehicle to be parked to drive to the parking space.

[0072] In some embodiments, the parking space identifier may be the parking space number and / or location information. For example, the parking space number may be a serial number such as 1, 2, 3, or MN (indicating that the parking space is located in row M and column N of the parking lot). The location information of the parking space may be latitude and longitude coordinates, or row M and column N (indicating that the parking space is located in row M and column N of the parking lot), etc. This application does not make specific limitations in this regard.

[0073] In step S500, the main controller acquires point cloud data of the predetermined monitoring area corresponding to the parking space obtained by the LiDAR scan; wherein, the predetermined monitoring area includes the parking space and a preset area accessible to the parking space.

[0074] In some embodiments, the lidar is always in scanning mode. After the main controller sends the parking space identifier to the vehicle controller, it immediately begins to acquire the point cloud data obtained by the lidar scan at a preset frequency.

[0075] In order to calculate the rotation and translation of a moving vehicle waiting to stop to the parking space, the predetermined monitoring area should include the parking space and a pre-defined area accessible to that parking space.

[0076] In some embodiments, the preset area may be an area covered by extending a certain distance outward from the boundaries of the parking spaces, such as... Figure 3As shown, the preset area (shown by the dashed line) is the area covered by each boundary of the parking space extending 5 meters outwards.

[0077] In some embodiments, the preset area can be a rectangular area in the lane connecting the parking space (i.e., the area the vehicle passes through in the lane before entering the parking space). The length of this rectangular area can be set by the user, and its width is the same as the lane width. Figure 4 As shown, the preset area (shown by the dashed line) is a rectangular area in the lane connecting the parking space to the parking space, with a length of 15 meters and a width of 7 meters.

[0078] In some embodiments, the main controller will preprocess the point cloud data obtained by the LiDAR in real time. For example, if the scanning range of the LiDAR is larger than the predetermined monitoring area, the point cloud data outside the predetermined monitoring area can be deleted according to the location of the predetermined monitoring area, and only the point cloud data of the predetermined monitoring area can be retained.

[0079] The main controller and LiDAR are two independent devices with multiple connection modes, and there is a one-to-one correspondence between the designated monitoring area and the parking space. Considering these factors, in specific implementation, the main controller, LiDAR, and the designated monitoring area (parking space) can be configured as follows: Figure 5 The following configuration modes are shown:

[0080] (a) One main controller is connected to only one lidar, and one lidar is only responsible for scanning the predetermined monitoring area corresponding to one parking space;

[0081] (b) One main controller is connected to only one lidar, and one lidar is responsible for scanning the predetermined monitoring area corresponding to at least two parking spaces;

[0082] (c) A master controller is connected to at least two lidars, and each lidar is only responsible for scanning the designated monitoring area corresponding to one parking space;

[0083] (d) A master controller is connected to at least two lidars, and one lidar is responsible for scanning the predetermined monitoring area corresponding to at least two parking spaces.

[0084] In practice, the configuration mode can be determined by comprehensively considering information such as the number of lines and scanning range of the lidar. This application does not impose specific limitations on this.

[0085] Given that there are multiple configuration modes between the main controller, LiDAR, and parking space, in order to facilitate the main controller in determining the LiDAR responsible for scanning the predetermined monitoring area corresponding to the parking space, in some embodiments, after determining an available parking space for the vehicle to be parked, the main controller determines the LiDAR used to scan the predetermined monitoring area corresponding to the parking space based on the configuration relationship between the LiDAR and the parking space, thereby obtaining the point cloud data obtained by the LiDAR scan.

[0086] In step S600, the main controller clusters the point cloud data to obtain a set of point cloud data of vehicles to be parked.

[0087] Specifically, when a vehicle waiting to stop moves into the scanning range of the lidar, the laser beam will be directed at the vehicle and returned to be received by the lidar. The resulting point cloud data will contain the point cloud corresponding to the vehicle waiting to stop. By clustering the point cloud data, the point cloud set of the vehicle waiting to stop can be extracted.

[0088] This step can employ algorithms commonly used for clustering arbitrary shapes, such as WaveCluster, ROCK, CURE, K-Prototypes, DENCLUE, DBSCAN, etc.

[0089] Since the predetermined monitoring area may cover public areas within the parking lot (such as shared lanes for parking spaces) or other parking spaces, the acquired point cloud data may simultaneously contain point clouds corresponding to multiple vehicles (e.g., vehicles about to park in other parking spaces, or vehicles already parked in other parking spaces). In this case, clustering the point cloud data may result in a set of point clouds for multiple vehicles (including vehicles waiting to park and other vehicles). Considering this, to facilitate the main controller in clustering the point cloud data to obtain the set of point clouds for vehicles waiting to park, the embodiments of this application provide the following processing methods:

[0090] (1) In some embodiments, the main controller clusters the point cloud data to obtain point cloud sets of one or more vehicles, and determines the point cloud sets of vehicles corresponding to the driving state in these point cloud sets as the point cloud sets of the vehicles to be stopped.

[0091] In this type of embodiment, other parking spaces adjacent to the parking space requested by the vehicle waiting to park may already be occupied. Therefore, in the clustered point cloud set, only one corresponds to a vehicle in a driving state, while the others correspond to vehicles in a stationary state. These stationary vehicles may be vehicles that have already stopped in other parking spaces. In this case, there is no need to focus on this type of point cloud set, but only on the point cloud set corresponding to the vehicles in a driving state.

[0092] (2) In some embodiments, the vehicle controller sends a message containing the positioning data collected by the vehicle positioning device of the vehicle to be parked. The main controller clusters the point cloud data to obtain point cloud sets of one or more vehicles, and determines the point cloud sets containing the above positioning data as the point cloud sets of the vehicles to be parked.

[0093] In this type of embodiment, the positioning data collected by the vehicle positioning devices of different vehicles are the location information of different vehicles. Different vehicles can be distinguished by this positioning data. Therefore, 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.

[0094] In practice, vehicle-mounted positioning equipment can be GPS positioning equipment, carrier phase differential RTK positioning equipment, BeiDou satellite positioning system positioning equipment, GLONASS positioning system positioning equipment, Galileo positioning system positioning equipment, Global Navigation Satellite System GNSS positioning equipment, etc.

[0095] (3) In some embodiments, the vehicle controller sends a message containing the positioning data collected by the vehicle positioning device of the vehicle to be parked. The main controller extracts the point cloud data corresponding to the location of the above positioning data and the area within a preset length around it from the point cloud data, and clusters the extracted point cloud data to obtain the point cloud set of the vehicle to be parked.

[0096] In this type of embodiment, the positioning data collected by the vehicle's onboard positioning device corresponds to the vehicle's location information. The main controller can determine the vehicle's location based on this positioning data. However, since the location corresponding to the positioning data is a point location and cannot represent the location of all parts of the vehicle body, a preset length can be determined based on the length of most vehicles. This preset length is then used to determine the location corresponding to the positioning data and the surrounding area within that preset length, which can cover the entire vehicle body. The main controller extracts the point cloud data corresponding to this area from the point cloud data, which necessarily includes the point cloud corresponding to the vehicle to be parked. Clustering these points yields the point cloud set of the vehicle to be parked.

[0097] (4) In some embodiments, the vehicle controller includes the lane number of the vehicle to be stopped in the message it sends. The main controller extracts the point cloud data of the lane where the vehicle to be stopped is located from the point cloud data according to the lane number of the vehicle to be stopped and the known relative positions of each lane and the lidar. The point cloud data is clustered to obtain a point cloud set of one or more vehicles. The point cloud set in the point cloud set of the one or more vehicles that has an intersection with the point cloud data of the lane where the vehicle to be stopped is located is determined as the point cloud set of the vehicle to be stopped.

[0098] In this type of embodiment, once the location of the LiDAR is determined, the relative positions of each lane and the LiDAR can be determined and stored locally on the main controller as known information. The main controller can determine which lane the vehicle to be stopped is traveling in based on the lane number of the lane it is in. Combining the relative positional relationship between each lane and the LiDAR, the main controller can extract the point cloud data of the lane where the vehicle to be stopped is located from the point cloud data. After the main controller clusters the point cloud data to obtain point cloud sets of one or more vehicles, it finds the point cloud set that intersects with the point cloud data of the lane where the vehicle to be stopped is located. This point cloud set is the point cloud set of the vehicle to be stopped.

[0099] (5) In some embodiments, the vehicle controller includes the lane number of the vehicle to be stopped in the message it sends. The main controller extracts the point cloud data of the lane where the vehicle to be stopped is located from the point cloud data according to the lane number of the vehicle to be stopped and the known relative positions of each lane and the lidar. The extracted point cloud data is then clustered to obtain the point cloud set of the vehicle to be stopped.

[0100] In this type of embodiment, once the location of the lidar is determined, the relative positions of each lane and the lidar can be determined and stored locally on the main controller as known information; the main controller can determine which lane the vehicle to be stopped is traveling in based on the lane number of the lane it is in; combining the relative positional relationship between each lane and the lidar, the main controller can extract the point cloud data of the lane where the vehicle to be stopped is located from the point cloud data.

[0101] (6) In some embodiments, the vehicle controller includes in the message sent the positioning data collected by the vehicle positioning device of the vehicle to be stopped and the lane number of the lane it is in; the main controller extracts the point cloud data of the lane where the vehicle to be stopped is located from the point cloud data according to the lane number of the vehicle to be stopped and the known relative positions of each lane and the lidar; the main controller clusters the point cloud data to obtain point cloud sets of one or more vehicles, and determines the point cloud sets that contain the above positioning data and have an intersection with the extracted point cloud data of the lane where the vehicle to be stopped is located as the point cloud set of the vehicle to be stopped.

[0102] In this type of embodiment, the positioning data collected by the vehicle positioning devices of different vehicles are the location information of different vehicles. Generally, different vehicles can be distinguished by this positioning data. However, considering that the positioning data obtained by the vehicle positioning devices has a certain error and adjacent lanes may be close to each other, in order to distinguish vehicles with similar positioning data but located in different lanes, the point cloud set containing the above positioning data and having an intersection with the point cloud data of the lane where the vehicle to be stopped is located can be determined as the point cloud set of the vehicle to be stopped.

[0103] In step S700, the main controller uses the ICP algorithm to calculate the point cloud set of the vehicles to be parked and the vehicle point cloud model, and obtains and sends the rotation matrix and translation matrix between the point cloud set of the vehicles to be parked and the vehicle point cloud model; wherein, the vehicle point cloud model is the point cloud set obtained by scanning the vehicles parked in the parking space in advance.

[0104] The ICP algorithm can be used to calculate the translation and rotation matrices between different point sets. The point cloud set of the vehicle to be parked is the point set corresponding to the vehicle in motion, while the vehicle point cloud model is the point set of the vehicle precisely stopped in the parking space. Therefore, by using the ICP algorithm to calculate these two point sets, the translation and rotation matrices between the vehicle in motion and the vehicle precisely stopped in the parking space can be obtained. Furthermore, since the vehicle point cloud model is the point set of the vehicle precisely stopped in the parking space, the rotation and translation matrices between the point cloud set of the vehicle to be parked and the vehicle point cloud model correspond to the rotation and translation amounts of the vehicle to be parked from the parking space, respectively.

[0105] Considering that vehicles may have different models, the point cloud sets obtained by the LiDAR scanning different models of vehicles will also be different. Therefore, in some embodiments, multiple vehicle point cloud models can be obtained in advance by scanning multiple different vehicle models parked in the parking space using the LiDAR, and these vehicle point cloud models can be stored in a model library. Step S700 is executed according to the following process: the main controller determines the vehicle model of the vehicle to be parked, selects the vehicle point cloud model that matches the vehicle model of the vehicle to be parked in the model library, and uses the ICP algorithm to calculate the point cloud set of the vehicle to be parked and the vehicle point cloud model that matches the vehicle model of the vehicle to be parked.

[0106] For example, the model library includes multiple vehicle point cloud models a, b, c, d, e, f, and g, and the vehicle models corresponding to these vehicle point cloud models are A, B, C, D, E, F, and G, respectively. When the vehicle model of the vehicle to be parked is F, the main controller can determine the vehicle point cloud model f that matches the vehicle model of the vehicle to be parked by matching. Then, the ICP algorithm can be used to calculate the point cloud set of the vehicle to be parked and f.

[0107] Considering that for some vehicle models, the model library may not store a matching vehicle point cloud model, in some embodiments, the parking control method provided in this application further includes: determining whether the model library contains a vehicle point cloud model matching the vehicle model of the vehicle to be parked; if not, selecting an existing vehicle point cloud model from the model library as the matching vehicle point cloud model, and after the vehicle stops in the parking space, scanning the vehicle using a LiDAR and storing the obtained point cloud set in the model library. After this process, when a vehicle of the same model wants to park in the same parking space again, a matching vehicle point cloud model can be found in the model library.

[0108] In some embodiments, the vehicle controller includes the vehicle model of the vehicle to be stopped in the message it sends, and the master controller can parse the vehicle model of the vehicle to be stopped from the message after receiving it.

[0109] In some embodiments, the main controller may first obtain the vehicle identifier of the vehicle to be parked, and then determine the vehicle model of the vehicle to be parked based on the known correspondence between vehicle identifiers and vehicle models. The vehicle identifier may be a license plate number.

[0110] In some embodiments, the main controller can obtain the vehicle identification of the vehicle to be parked by photographing and recognizing its license plate. For example, the main controller uses a camera to photograph the license plate of the vehicle to be parked.

[0111] In some embodiments, the vehicle controller includes the vehicle identifier of the vehicle to be stopped in the message it sends, and the master controller can parse the vehicle identifier from it after receiving the message.

[0112] The ICP algorithm calculates the rotation and translation matrices between the point cloud set of the vehicle to be parked and the vehicle point cloud model in an iterative manner. During the iteration process of the ICP algorithm, the initial rotation and translation matrices used have a very important impact on the accuracy of the final calculated results.

[0113] In some embodiments, step S700 is performed according to the following procedure:

[0114] Step S702: Determine the first average center and the second average center, wherein the coordinates of the first average center are the average of the coordinates of a preset number of points in the point cloud set of the vehicle to be stopped that are located at the foremost position in the driving direction of the vehicle to be stopped; the coordinates of the second average center are the average of the coordinates of a preset number of points in the vehicle point cloud model that are located at the foremost position in the driving direction of the vehicle to be stopped.

[0115] Step S704: Determine the initial rotation matrix and the initial translation matrix; wherein, the initial rotation matrix is ​​the matrix used to rotate from the first average center to the second average center; the initial translation matrix is ​​the matrix used to translate from the first average center to the second average center;

[0116] Step S706: Using the initial rotation matrix and the initial translation matrix, iterative calculations are performed on the point cloud set of the vehicle to be parked and the vehicle point cloud model to obtain the rotation matrix and translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model.

[0117] like Figure 6 As shown, the point cloud set of the vehicles waiting to stop is located in coordinate system 1, and the vehicle point cloud model is located in coordinate system 2; the n foremost points (marked by dashed boxes) in the point cloud set of the vehicles waiting to stop along the driving direction of the vehicles are... , i =1,2,3...n, with the first mean center being... , , , In the vehicle point cloud model, the n foremost points (marked by dashed boxes) located in the direction of travel of the vehicle waiting to stop are: , i =1,2,3...n, the second mean center is , , , ; the first average center Rotate to the second average center The matrix used is determined as the initial rotation matrix; the first average center is... Translate to the second average center The matrix used is determined to be the initial translation matrix.

[0118] In some embodiments, step S700 is performed according to the following steps S708~S712:

[0119] Step S708: The main controller parses the positioning data collected by the on-board positioning device of the vehicle to be parked from the message sent by the vehicle controller.

[0120] Step S710: Determine the initial rotation matrix and the initial translation matrix respectively; wherein, the initial rotation matrix is ​​the matrix used to rotate the point corresponding to the positioning data to the reference positioning point; the initial translation matrix is ​​the matrix used to translate the point corresponding to the positioning data to the reference positioning point; the reference positioning point is the point corresponding to the positioning data obtained by the vehicle positioning device when the vehicle stops in the parking space during the process of determining the vehicle point cloud model.

[0121] Step S712: Using the initial rotation matrix and the initial translation matrix, iterative calculations are performed on the point cloud set of the vehicle to be parked and the vehicle point cloud model to obtain the rotation matrix and translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model.

[0122] In the process of determining the vehicle point cloud model, the vehicle used is equipped with an on-board positioning device. When the vehicle stops in a parking space, the point determined by the positioning data obtained by the on-board positioning device is the reference positioning point.

[0123] In such embodiments, the vehicle-mounted positioning device can 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, etc.

[0124] The vehicle point cloud model is the set of points of vehicles precisely parked in parking spaces, while the point cloud set of vehicles waiting to park, obtained through clustering, is the set of points of vehicles currently in motion. Therefore, by using the ICP algorithm to calculate the rotation and translation of a vehicle in motion from its point cloud set to the parking space, the rotation and translation of the vehicle can be obtained. In this process, the accuracy of the vehicle point cloud model directly affects the accuracy of the final calculation result. However, currently common LiDAR systems have a limited number of lines (e.g., 32 lines, 64 lines). When scanning stationary vehicles in parking spaces using a fixed-position LiDAR, the number and direction of the laser beams limit the area the laser beams can reach. The resulting point cloud data only reflects a small area of ​​the vehicle body, and the resulting point cloud set (i.e., the vehicle point cloud model) cannot accurately represent the position of the entire vehicle body, or even be obtained through clustering algorithms.

[0125] To overcome the above problems, in some embodiments, the vehicle point cloud model can be obtained according to steps S714~S718:

[0126] Step S714: Use lidar to scan for vehicles that are driving toward the parking space and eventually parking there.

[0127] Step S716: Convert the point cloud data when the vehicle has not reached the parking space to the coordinate system of the point cloud data when it has reached the parking space.

[0128] In practice, this process can utilize the ICP algorithm to convert point cloud data between different coordinate systems.

[0129] Step S718: Determine the point cloud set obtained after conversion as the vehicle point cloud model.

[0130] Steps S714 to S718 involve using a lidar to scan a moving vehicle. This method allows the laser beam to reach more areas of the vehicle body, resulting in more point cloud data and a more complete vehicle point cloud model. This better reflects the position of the entire vehicle body, meets the requirements of the ICP algorithm, and improves the accuracy of the calculation results.

[0131] In step S800, the vehicle controller controls the driving direction and speed of the vehicle in real time based on the rotation matrix and translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model, so that the vehicle to be parked stops in the parking space.

[0132] In some embodiments, the vehicle controller controls the steering system, throttle control system, and braking system of the vehicle to be stopped to achieve real-time control of the vehicle's direction and speed.

[0133] Since the rotation and translation matrices between the point cloud set of the vehicles waiting to be parked and the vehicle point cloud model are the rotation and translation amounts of the vehicles moving from the parking space, the driving direction and speed of the vehicles waiting to be parked can be controlled in real time based on the rotation and translation matrices calculated in real time, so that the vehicles can drive into the parking space.

[0134] In some embodiments, during step S600, the vehicle controller, in controlling the driving direction and speed of the vehicle to be parked, considers not only the rotation and translation matrices between the point cloud set of the vehicle to be parked and the vehicle point cloud model, but also obstacles around the parking space (such as stationary vehicles in adjacent parking spaces) to ensure that the parking process of the vehicle to be parked is safe and smooth.

[0135] In the parking control method proposed in this application, since the vehicle point cloud model is a set of point clouds obtained by scanning vehicles that are precisely stopped in parking spaces, the driving direction and speed of the vehicle to be parked are controlled according to the rotation matrix and translation matrix. This is equivalent to using the vehicle point cloud model as a target and performing rotation and translation operations on the point cloud set of the vehicle to be parked to make it coincide with the vehicle point cloud model, thereby achieving the goal of the vehicle to be parked precisely in the parking space. The parking control method proposed in this application has the advantages of high automation and high precision. It is applicable to various types of parking spaces, such as automatic locking parking spaces, intersecting parking spaces, and multi-level parking spaces. It helps to solve problems caused by non-standard parking, such as vehicle tilting (tire, door and other parts are easily damaged), being too close to adjacent parking spaces (door cannot be opened), and difficulty in leaving the parking space (time-consuming, requiring the vehicle to be moved from adjacent parking spaces).

[0136] Based on the same inventive concept, embodiments of this application provide a parking control method applied to a main controller, such as... Figure 7 As shown, it includes:

[0137] Step A100: Receive a message from the vehicle controller requesting the vehicle to stop.

[0138] Step A200: Identify a parking space and send the identifier of the parking space to the vehicle controller, so that the vehicle controller can control the vehicle to drive to the parking space;

[0139] Step A300: Obtain point cloud data of the predetermined monitoring area corresponding to the parking space obtained by LiDAR scanning; the predetermined monitoring area includes the parking space and a preset area accessible to the parking space;

[0140] Step A400: Cluster the point cloud data to obtain a set of point clouds of the vehicles to be parked;

[0141] Step A500: The iterative nearest point (ICP) algorithm is used to calculate the point cloud set of the vehicles to be parked and the vehicle point cloud model to obtain the rotation matrix and translation matrix between the point cloud set of the vehicles to be parked and the vehicle point cloud model; wherein, the vehicle point cloud model is a point cloud set obtained in advance by scanning the vehicles parked in the parking space using a lidar.

[0142] Step A600: Send the rotation matrix and translation matrix so that the vehicle controller can control the driving direction and speed of the vehicle to be parked in real time according to the rotation matrix and translation matrix and finally stop it in the parking space.

[0143] In some embodiments, receiving a message from a vehicle controller requesting to stop includes: receiving a message from a vehicle controller requesting to stop broadcast by the vehicle controller via a V2X device.

[0144] In some embodiments, before determining a parking space, the method further includes: parsing a communication connection identifier from the message; and establishing a communication connection with the vehicle controller through the communication connection identifier.

[0145] In some embodiments, the communication connection identifier includes one or both of the MAC address of the vehicle controller and the MAC address of the V2X communication device connected to the vehicle controller.

[0146] In some embodiments, determining a parking space includes: determining an available parking space from a preset plurality of parking spaces.

[0147] In some embodiments, the identifier of the parking space includes: the parking space number and / or location information.

[0148] In some embodiments, each lidar is used to scan only the predetermined monitoring area corresponding to a parking space, and each master controller is used to acquire point cloud data obtained from the lidar scan.

[0149] In some embodiments, each lidar is used to scan a predetermined monitoring area corresponding to at least two parking spaces, and each master controller is used to acquire point cloud data obtained from the scanning of one lidar.

[0150] In some embodiments, each lidar is used to scan only a predetermined monitoring area corresponding to a parking space, and each master controller is used to acquire point cloud data obtained from at least two lidar scans.

[0151] In some embodiments, each lidar is used to scan a predetermined monitoring area corresponding to at least two parking spaces, and each master controller is used to acquire point cloud data obtained from the scanning of at least two lidars.

[0152] In some embodiments, acquiring point cloud data of the predetermined monitoring area corresponding to the parking space obtained by lidar scanning includes:

[0153] Determine the lidar used to scan the predetermined monitoring area corresponding to the parking space;

[0154] Obtain the point cloud data obtained from the LiDAR scan.

[0155] In some embodiments, acquiring point cloud data of the predetermined monitoring area corresponding to the parking space obtained by lidar scanning further includes:

[0156] When it is determined that the scanning range of the lidar is greater than the predetermined monitoring area corresponding to the parking space, the point cloud data obtained by the lidar scan is preprocessed to obtain the point cloud data of the predetermined monitoring area corresponding to the parking space.

[0157] In some embodiments, clustering the point cloud data to obtain a set of point clouds of vehicles to be parked includes:

[0158] The point cloud data is clustered to obtain point cloud sets of one or more vehicles, and the point cloud set of the vehicle corresponding to the driving state in the point cloud set of the one or more vehicles is determined as the point cloud set of the vehicle to be stopped.

[0159] In some embodiments, clustering the point cloud data to obtain a set of point clouds of vehicles to be parked includes:

[0160] The location data collected by the vehicle positioning device of the vehicle to be parked is parsed from the message;

[0161] The point cloud data is clustered to obtain a point cloud set of one or more vehicles, and the point cloud set containing the positioning data in the point cloud set of the one or more vehicles is determined as the point cloud set of the vehicle to be parked.

[0162] In some embodiments, clustering the point cloud data to obtain a set of point clouds of vehicles to be parked includes:

[0163] The location data collected by the vehicle positioning device of the vehicle to be parked is parsed from the message;

[0164] The point cloud data corresponding to the location data and the area within a preset length around it is extracted from the point cloud data, and the extracted point cloud data is clustered to obtain the point cloud set of the vehicle to be parked.

[0165] In some embodiments, clustering the point cloud data to obtain a set of point clouds of vehicles to be parked includes:

[0166] Parse the lane number of the vehicle waiting to stop from the message;

[0167] Based on the lane number of the vehicle to be parked and the known relative positions of each lane to the lidar, the point cloud data of the lane where the vehicle to be parked is located is extracted from the point cloud data.

[0168] Clustering the point cloud data yields point cloud sets for one or more vehicles;

[0169] The point cloud set that intersects with the point cloud data of the lane where the vehicle to be stopped is located is determined as the point cloud set of the vehicle to be stopped.

[0170] In some embodiments, clustering the point cloud data to obtain a set of point clouds of vehicles to be parked includes:

[0171] Parse the lane number of the vehicle waiting to stop from the message;

[0172] Based on the lane number of the vehicle to be parked and the known relative positions of each lane to the lidar, the point cloud data of the lane where the vehicle to be parked is located is extracted from the point cloud data, and the extracted point cloud data is clustered to obtain the point cloud set of the vehicle to be parked.

[0173] In some embodiments, clustering the point cloud data to obtain a set of point clouds of vehicles to be parked includes:

[0174] The location data collected by the vehicle positioning device of the vehicle waiting to be parked and the lane number of the vehicle waiting to be parked are extracted from the message.

[0175] Based on the lane number of the vehicle to be parked and the known relative positions of each lane to the lidar, the point cloud data of the lane where the vehicle to be parked is located is extracted from the point cloud data.

[0176] The point cloud data is clustered to obtain point cloud sets of one or more vehicles. The point cloud set of the one or more vehicles that contains the positioning data and has an intersection with the point cloud data of the lane where the vehicle to be parked is located is determined as the point cloud set of the vehicle to be parked.

[0177] In some embodiments, the point cloud set and vehicle point cloud model of the vehicles to be parked are calculated using the ICP algorithm, including:

[0178] Determine the vehicle model of the vehicle to be parked;

[0179] Select a vehicle point cloud model from the model library that matches the vehicle model of the vehicle to be parked;

[0180] The ICP algorithm is used to calculate the point cloud set of the vehicles to be parked and the vehicle point cloud model that matches the vehicle model of the vehicles to be parked; wherein, the model library includes multiple vehicle point cloud models obtained in advance by scanning multiple different vehicle models parked in the parking space using LiDAR.

[0181] In some embodiments, determining the vehicle model of the vehicle to be parked includes: parsing the vehicle model of the vehicle to be parked from the message.

[0182] In some embodiments, determining the vehicle model of the vehicle to be parked includes: parsing the vehicle identifier of the vehicle to be parked from the message, and determining the vehicle model of the vehicle to be parked based on the known correspondence between vehicle identifiers and vehicle models.

[0183] In some embodiments, the parking control method applied to the main controller provided in this application further includes:

[0184] Determine whether the model library contains a vehicle point cloud model that matches the vehicle model of the vehicle to be parked;

[0185] If not included, an existing vehicle point cloud model is selected from the model library and determined as the vehicle point cloud model that matches the vehicle model of the vehicle to be parked. After the vehicle to be parked stops at the parking space, the LiDAR is used to scan the vehicle and the resulting point cloud set is stored in the model library.

[0186] In some embodiments, the ICP algorithm is used to calculate the rotation matrix and translation matrix between the point cloud set of the vehicles to be parked and the vehicle point cloud model, including:

[0187] A first average center and a second average center are determined, wherein the coordinates of the first average center are the average of the coordinates of a preset number of points in the point cloud set of the vehicle to be stopped that are located at the foremost position in the driving direction of the vehicle to be stopped; and the coordinates of the second average center are the average of the coordinates of the preset number of points in the vehicle point cloud model that are located at the foremost position in the driving direction of the vehicle to be stopped.

[0188] Determine an initial rotation matrix, which is the matrix used to rotate from the first average center to the second average center;

[0189] Determine an initial translation matrix, which is the matrix used to translate the first average center to the second average center;

[0190] Using the initial rotation matrix and the initial translation matrix, iterative calculations are performed on the point cloud set of the vehicle to be parked and the vehicle point cloud model to obtain the rotation matrix and translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model.

[0191] In some embodiments, the ICP algorithm is used to calculate the rotation matrix and translation matrix between the point cloud set of the vehicles to be parked and the vehicle point cloud model, including:

[0192] Parse the location data collected by the vehicle positioning device of the vehicle to be parked from the message;

[0193] Determine an initial rotation matrix, which is the matrix used to rotate the point corresponding to the positioning data to a reference positioning point. The reference positioning point is the point corresponding to the positioning data obtained by the vehicle positioning device when the vehicle stops at the parking space during the process of determining the vehicle point cloud model.

[0194] Determine an initial translation matrix, which is the matrix used to translate the point corresponding to the positioning data to the reference positioning point;

[0195] Using the initial rotation matrix and the initial translation matrix, iterative calculations are performed on the point cloud set of the vehicle to be parked and the vehicle point cloud model to obtain the rotation matrix and translation matrix between the point cloud set of the vehicle to be parked and the vehicle point cloud model.

[0196] In some embodiments, the vehicle point cloud model is determined as follows:

[0197] The system uses lidar to scan for vehicles that are heading toward and eventually park in the parking space.

[0198] The point cloud data of the vehicle before it reaches the parking space is converted to the coordinate system of the point cloud data when it reaches the parking space;

[0199] The point cloud set obtained after conversion is determined as the vehicle point cloud model.

[0200] Figure 7 The parking control method applied to the main controller shown is similar to Figure 2 The parking control method shown is based on the same inventive concept and has the same non-limiting implementation method, which can be referred to in the foregoing description. Figure 2 The parking control method shown will not be elaborated upon here.

[0201] Based on the same inventive concept, this application also provides a parking control method applied to a vehicle controller, such as... Figure 8 As shown, it includes:

[0202] Step B100: Send a message to the vehicle waiting to be parked requesting to stop.

[0203] Step B200: Receive the parking space identifier returned by the main controller and control the vehicle to be parked to drive towards the parking space;

[0204] Step B300: Receive the rotation and translation matrices between the point cloud set of the vehicles to be parked and the vehicle point cloud model returned by the main controller; wherein, the vehicle point cloud model is a point cloud set obtained in advance by scanning the vehicles parked in the parking space using a lidar.

[0205] Step B400: Control the driving direction and speed of the vehicle to be parked in real time according to the rotation matrix and translation matrix so that the vehicle to be parked eventually stops at the parking space.

[0206] In some embodiments, sending a message requesting a vehicle to park in a parking space includes broadcasting the message requesting a vehicle to park in a parking space via a V2X device.

[0207] In some embodiments, the message includes any one or more of the following information:

[0208] The vehicle identification of the vehicle to be parked;

[0209] The vehicle model of the vehicle to be parked;

[0210] The positioning data collected by the on-board positioning device of the vehicle to be parked;

[0211] Communication connection identifier.

[0212] In some embodiments, the communication connection identifier includes one or both of the MAC address of the vehicle controller and the MAC address of the V2X communication device connected to the vehicle controller.

[0213] In some embodiments, sending a message requesting the vehicle to stop includes:

[0214] The message is sent after the vehicle waiting to be parked enters the parking lot; or,

[0215] The message is sent after receiving a preset trigger signal.

[0216] In some embodiments, controlling the driving direction and speed of the vehicle to be stopped in real time according to the rotation matrix and translation matrix includes: controlling the driving direction and speed of the vehicle to be stopped in real time by controlling the steering system, throttle control system and braking system of the vehicle to be stopped according to the rotation matrix and translation matrix.

[0217] Figure 8 The parking control method applied to the vehicle controller shown is similar to Figure 2 The parking control method shown is based on the same inventive concept and has the same non-limiting implementation method, which can be referred to in the foregoing description. Figure 2 The parking control method shown will not be elaborated upon here.

[0218] Based on the same inventive concept, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which is executed by a processor to perform various steps in the parking control method applied to the main controller provided in embodiments of this application. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. 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), optical storage device, magnetic storage device, or any suitable combination thereof.

[0219] Based on the same inventive concept, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which is executed by a processor to perform various steps in the parking control method for a vehicle controller provided in embodiments of this application. This computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0220] Exemplary device

[0221] Based on the same inventive concept, embodiments of this application also provide a main controller, which includes a first processor, a first memory, and a computer program stored in the first memory and executable on the first processor. When the first processor runs the computer program, it executes... Figure 7 The parking control method applied to the main controller.

[0222] The method by which a computer program in the first memory is executed during runtime and Figure 2 The parking control method shown is based on the same inventive concept and has the same non-limiting implementation method, which can be referred to in the previous exemplary method. Figure 2 The parking control method shown will not be elaborated upon here.

[0223] Optionally, in this application, the first processor can be implemented by circuits, chips, 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 integrated circuits (ASICs), one or more digital signal processors (DSPs), one or more integrated circuits, etc.

[0224] Optionally, in this application, the first memory can be implemented by circuits, chips, or other electronic components. For example, the first memory may include one or more read-only memories (ROMs), random access memories (RAMs), flash memories, electrically programmable memories (EPROMs), electrically programmable and erasable memories (EEPROMs), embedded multimedia cards (eMMCs), hard disk drives, or any volatile or non-volatile media.

[0225] In this embodiment, the main controller can be a computer device in the form of an industrial computer, server, PC, portable computer, tablet computer, PDA, iMac, etc.

[0226] Based on the same inventive concept, this application also provides a vehicle controller, which includes a second processor, a second memory, and a computer program stored in the second memory and executable on the second processor. When the second processor runs the computer program, it executes... Figure 8 The parking control method applied to vehicle controllers.

[0227] The method by which a computer program in the second memory is executed during runtime is similar to... Figure 2 The parking control method shown is based on the same inventive concept and has the same non-limiting implementation method, which can be referred to in the previous exemplary method. Figure 2 The parking control method shown will not be elaborated upon here.

[0228] Optionally, in this application, the second processor can be implemented by circuits, chips, 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 integrated circuits (ASICs), one or more digital signal processors (DSPs), one or more integrated circuits, etc.

[0229] Optionally, in this application, the second memory can be implemented by circuits, chips, or other electronic components. For example, the second memory may include one or more read-only memories (ROMs), random access memories (RAMs), flash memories, electrically programmable memories (EPROMs), electrically programmable and erasable memories (EEPROMs), embedded multimedia cards (eMMCs), hard disk drives, or any volatile or non-volatile media.

[0230] In this application embodiment, the vehicle controller may be a DSP (Digital Signal Processor), FPGA (Field-Programmable Gate Array) controller, industrial computer, vehicle computer, ECU (Electronic Control Unit), ARM or VCU (Vehicle Control Unit), etc., and this application does not make specific limitations on it.

[0231] Based on the same inventive concept, this application also provides a car, such as... Figure 9As shown, the car is equipped with a vehicle controller. This vehicle controller sends a message requesting the vehicle to stop, receives the parking space identifier returned by the main controller, and controls the vehicle to drive towards the parking space; it also receives the rotation and translation matrices between the point cloud set of the vehicle to stop and the vehicle point cloud model returned by the main controller; and controls the driving direction and speed of the vehicle to stop in real time based on the rotation and translation matrices, so that the vehicle eventually stops at the parking space.

[0232] In some embodiments, the vehicle controller is connected to the vehicle's steering system, throttle control system, and braking system. That is, the vehicle controller indirectly achieves real-time control of the driving direction and speed of the vehicle waiting to stop by controlling the vehicle's steering system, throttle control system, and braking system.

[0233] In some embodiments, the vehicle is also equipped with a vehicle-to-everything (V2X) device connected to the vehicle controller.

[0234] The vehicle can be a traditional vehicle driven by humans (such as a passenger car, construction vehicle, fire truck, ambulance, etc.) or an autonomous vehicle. It can consume traditional energy sources such as gasoline and diesel, or it can consume new energy sources such as electricity and solar energy. Among them, autonomous vehicles refer to vehicles that utilize autonomous driving technology to have passenger (such as passenger cars, buses, etc.), cargo (such as ordinary trucks, box trucks, enclosed trucks, tank trucks, flatbed trucks, container trucks, dump trucks, special structure trucks, etc.) or special rescue functions (such as fire trucks, ambulances, etc.).

[0235] Exemplary System

[0236] Based on the same inventive concept, this application also provides a parking control system, such as... Figure 10 As shown, it includes: a main controller, a vehicle controller, and a lidar.

[0237] The working principle of this parking control system can be referenced as follows: Figure 2 The parking control method shown will not be described in detail here.

[0238] In this parking control system, the lidar can be 16-line, 32-line, or 64-line type. The more laser beams there are, the easier it is to cover the entire body of the vehicle being scanned with the point cloud data obtained from the scan. Correspondingly, the cost will also be higher. The hardware composition structure of the main controller and vehicle controller has been described in the exemplary device and will not be repeated here.

[0239] The parking control system and Figure 2 The parking control method shown is based on the same inventive concept and has the same non-limiting implementation method, which can be referred to in the previous exemplary method. Figure 2The parking control method shown will not be elaborated upon here.

[0240] To achieve the purpose of scanning the predetermined monitoring area (including parking spaces and the preset area of ​​driveable parking spaces) with lidar, lidar can be installed on the ceiling, wall, mechanical equipment or professional support frame of the parking lot.

[0241] In some embodiments, the main controller may be installed in the central control room of the parking lot or on the ceiling, wall, mechanical equipment or professional support frame of the parking lot, and connected to the lidar.

[0242] In some embodiments, the vehicle controller is mounted on the vehicle to be parked.

[0243] In some embodiments, the vehicle controller is a device mounted outside the vehicle to be parked, such as a device fixed in a certain location or a device mounted on any mobile device. In these embodiments, the vehicle controller controls the steering system, throttle control system and braking system of the vehicle to be parked through wireless communication methods such as base stations and WIFI, thereby indirectly controlling the vehicle to stop.

[0244] In some embodiments, such as Figure 5 As shown in (a), the main controller, lidar, and predetermined monitoring area (parking space) are set to the following mode: each lidar is used to scan only one predetermined monitoring area, and each main controller is used to acquire real-time point cloud data obtained from one lidar scan.

[0245] In some embodiments, such as Figure 5 As shown in (b), the master controller, lidar, and predetermined monitoring areas are set to the following mode: each lidar is used to scan at least two predetermined monitoring areas, and each master controller is used to acquire real-time point cloud data obtained from one lidar scan.

[0246] In some embodiments, such as Figure 5 As shown in (c), the master controller, lidar, and predetermined monitoring area are set to the following mode: each lidar is used to scan only one predetermined monitoring area, and each master controller is used to acquire real-time point cloud data obtained from at least two lidar scans.

[0247] In some embodiments, such as Figure 5 As shown in (d), the master controller, lidar, and predetermined monitoring areas are set to the following mode: each lidar is used to scan at least two predetermined monitoring areas, and each master controller is used to acquire real-time point cloud data obtained from the scanning of at least two lidars.

[0248] In some embodiments, such as Figure 10As shown, the parking control system also includes: a V2X device connected to the main controller, and a V2X device connected to the vehicle controller.

[0249] In some embodiments, such as Figure 10 As shown, the parking control system also includes a power supply device for powering the main controller and / or the lidar.

[0250] In some embodiments, the parking control system further includes an uninterruptible power supply (UPS) for supplying power to the main controller and / or lidar when the power supply equipment is interrupted.

[0251] The purpose, technical solution and beneficial effects of this application have been described in detail above. It should be understood that the above description is only a specific embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this application should be included within the scope of protection of this application.

[0252] It should be noted that although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0253] Those skilled in the art will also understand that the various illustrative logical blocks, units, and steps listed in the embodiments of this application can be implemented by electronic hardware, computer software, or a combination of both. To clearly demonstrate the interchangeability of hardware and software, the functions of the various illustrative components, units, and steps described above have been generally described. Whether such functionality is implemented through hardware or software depends on the specific application and the overall system design requirements. Those skilled in the art can implement the described functions using various methods for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of this application.

[0254] The various illustrative logic blocks, units, or devices described in the embodiments of this application can be implemented or operate the described functions using a general-purpose processor, digital signal processor, application-specific integrated circuit (ASIC), field-programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. The general-purpose processor can be a microprocessor; alternatively, it can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented using a combination of computing devices, such as a digital signal processor and a microprocessor, multiple microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration.

[0255] The steps of the methods or algorithms described in the embodiments of this application can be directly embedded in hardware, a software module executed by a processor, or a combination of both. The software module can be stored in RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from and write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and storage medium can be housed in an ASIC, which can be housed in a user terminal. Optionally, the processor and storage medium can also be housed in different components of the user terminal.

[0256] In one or more exemplary designs, the functions described in the embodiments of this application can be implemented in hardware, software, firmware, or any combination of these three. If implemented in software, these functions can be stored on a computer-readable medium or transmitted on a computer-readable medium in the form of one or more instructions or code. Computer-readable media includes computer storage media and communication media that facilitate the transfer of computer programs from one place to another. Storage media can be any available media that can be accessed by a general-purpose or special-purpose computer. For example, such computer-readable media can 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 can be used to carry or store program code in the form of instructions or data structures and other forms that can be read by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Furthermore, any connection can be suitably defined as a computer-readable medium, for example, if the software is transmitted from a website, server or other remote resource via a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wirelessly, such as infrared, wireless and microwave, it is also included in the defined computer-readable medium. The disks and discs mentioned include compressed disks, laser discs, optical discs, DVDs, floppy disks, and Blu-ray discs. Disks typically copy data magnetically, while discs typically copy data optically using lasers. Combinations of the above can also be contained in computer-readable media.

Claims

1. A parking control method, characterized in that, include: Receives messages from the vehicle controller requesting the vehicle to stop. A parking space is identified and its identifier is sent to the vehicle controller, so that the vehicle controller can control the vehicle to drive to the parking space; Obtain point cloud data of the predetermined monitoring area corresponding to the parking space obtained by lidar scanning; The predetermined monitoring area includes the parking space and a preset area accessible to the parking space; Clustering the point cloud data yields a set of point clouds for the vehicles to be parked; The iterative nearest point (ICP) algorithm is used to calculate the point cloud set of the vehicles to be parked and the vehicle point cloud model to obtain the rotation matrix and translation matrix between the point cloud set of the vehicles to be parked and the vehicle point cloud model; wherein, the vehicle point cloud model is the point cloud set obtained in advance by scanning the vehicles parked in the parking space using a lidar. The rotation matrix and translation matrix are sent so that the vehicle controller can control the driving direction and speed of the vehicle to be parked in real time according to the rotation matrix and translation matrix and finally stop it in the parking space.

2. The parking control method according to claim 1, characterized in that, Receive messages from the vehicle controller requesting to stop from vehicles waiting to be parked, including: receiving messages broadcast by the vehicle controller requesting to stop from vehicles waiting to be parked via the V2X device.

3. The parking control method according to claim 1, characterized in that, Before determining a parking space, the process also includes: parsing a communication connection identifier from the message; and establishing a communication connection with the vehicle controller through the communication connection identifier.

4. The parking control method according to claim 3, characterized in that, The communication connection identifier includes one or both of the MAC address of the vehicle controller and the MAC address of the V2X communication device connected to the vehicle controller.

5. The parking control method according to claim 1, characterized in that, Identifying a parking space includes: selecting an available parking space from a set of preset parking spaces.

6. The parking control method according to claim 1, characterized in that, The identification of the parking space includes: the parking space number and / or location information.

7. The parking control method according to claim 1, characterized in that, Each lidar is used to scan only the designated monitoring area corresponding to one parking space, and each main controller is used to acquire point cloud data obtained from the lidar scan.

8. The parking control method according to claim 1, characterized in that, Each lidar is used to scan the predetermined monitoring area corresponding to at least two parking spaces, and each master controller is used to acquire point cloud data obtained from the scan of one lidar.

9. The parking control method according to claim 1, characterized in that, Each lidar is used to scan only the designated monitoring area corresponding to one parking space, and each main controller is used to acquire point cloud data obtained from at least two lidar scans.

10. The parking control method according to claim 1, characterized in that, Each lidar is used to scan the predetermined monitoring area corresponding to at least two parking spaces, and each master controller is used to acquire point cloud data obtained from the scans of at least two lidars.

11. The parking control method according to claim 1, characterized in that, Acquire point cloud data of the predetermined monitoring area corresponding to the parking space obtained by lidar scanning, including: Determine the lidar used to scan the predetermined monitoring area corresponding to the parking space; Obtain the point cloud data obtained from the LiDAR scan.

12. The parking control method according to claim 11, characterized in that, Acquiring point cloud data of the predetermined monitoring area corresponding to the parking space obtained by lidar scanning also includes: When it is determined that the scanning range of the lidar is greater than the predetermined monitoring area corresponding to the parking space, the point cloud data obtained by the lidar scan is preprocessed to obtain the point cloud data of the predetermined monitoring area corresponding to the parking space.

13. The parking control method according to claim 1, characterized in that, Clustering the point cloud data yields a set of point clouds containing the vehicles waiting to stop, including: The point cloud data is clustered to obtain point cloud sets of one or more vehicles, and the point cloud set of the vehicle corresponding to the driving state in the point cloud set of the one or more vehicles is determined as the point cloud set of the vehicle to be stopped.

14. The parking control method according to claim 1, characterized in that, Clustering the point cloud data yields a set of point clouds containing the vehicles waiting to stop, including: The location data collected by the vehicle positioning device of the vehicle to be parked is parsed from the message; The point cloud data is clustered to obtain a point cloud set of one or more vehicles, and the point cloud set containing the positioning data in the point cloud set of the one or more vehicles is determined as the point cloud set of the vehicle to be parked.

15. The parking control method according to claim 1, characterized in that, Clustering the point cloud data yields a set of point clouds containing the vehicles waiting to stop, including: The location data collected by the vehicle positioning device of the vehicle to be parked is parsed from the message; The point cloud data corresponding to the location data and the area within a preset length around it is extracted from the point cloud data, and the extracted point cloud data is clustered to obtain the point cloud set of the vehicle to be parked.

16. The parking control method according to claim 1, characterized in that, Clustering the point cloud data yields a set of point clouds containing the vehicles waiting to stop, including: Parse the lane number of the vehicle waiting to stop from the message; Based on the lane number of the vehicle to be parked and the known relative positions of each lane to the lidar, the point cloud data of the lane where the vehicle to be parked is located is extracted from the point cloud data. Clustering the point cloud data yields point cloud sets for one or more vehicles; The point cloud set that intersects with the point cloud data of the lane where the vehicle to be stopped is located is determined as the point cloud set of the vehicle to be stopped.

17. The parking control method according to claim 1, characterized in that, Clustering the point cloud data yields a set of point clouds containing the vehicles waiting to stop, including: Parse the lane number of the vehicle waiting to stop from the message; Based on the lane number of the vehicle to be parked and the known relative positions of each lane to the lidar, the point cloud data of the lane where the vehicle to be parked is located is extracted from the point cloud data, and the extracted point cloud data is clustered to obtain the point cloud set of the vehicle to be parked.

18. The parking control method according to claim 1, characterized in that, Clustering the point cloud data yields a set of point clouds containing the vehicles waiting to stop, including: The location data collected by the vehicle positioning device of the vehicle waiting to be parked and the lane number of the vehicle waiting to be parked are extracted from the message. Based on the lane number of the vehicle to be parked and the known relative positions of each lane to the lidar, the point cloud data of the lane where the vehicle to be parked is located is extracted from the point cloud data. The point cloud data is clustered to obtain point cloud sets of one or more vehicles. The point cloud set of the one or more vehicles that contains the positioning data and has an intersection with the point cloud data of the lane where the vehicle to be parked is located is determined as the point cloud set of the vehicle to be parked.

19. The parking control method according to claim 1, characterized in that, The point cloud set and vehicle point cloud model of the vehicles to be parked are calculated using the ICP algorithm, including: Determine the vehicle model of the vehicle to be parked; Select a vehicle point cloud model from the model library that matches the vehicle model of the vehicle to be parked; The ICP algorithm is used to calculate the point cloud set of the vehicles to be parked and the vehicle point cloud model that matches the vehicle model of the vehicles to be parked; wherein, the model library includes multiple vehicle point cloud models obtained in advance by scanning multiple different vehicle models parked in the parking space using LiDAR.

20. The parking control method according to claim 19, characterized in that, Determining the vehicle model of the vehicle to be parked includes: parsing the vehicle model of the vehicle to be parked from the message.

21. The parking control method according to claim 19, characterized in that, Determining the vehicle model of the vehicle to be parked includes: parsing the vehicle identifier of the vehicle to be parked from the message, and determining the vehicle model of the vehicle to be parked based on the known correspondence between vehicle identifiers and vehicle models.

22. The parking control method according to claim 19, characterized in that, Also includes: Determine whether the model library contains a vehicle point cloud model that matches the vehicle model of the vehicle to be parked; If not included, an existing vehicle point cloud model is selected from the model library and determined as the vehicle point cloud model that matches the vehicle model of the vehicle to be parked. After the vehicle to be parked stops at the parking space, the LiDAR is used to scan the vehicle and the resulting point cloud set is stored in the model library.

23. The parking control method according to claim 1, characterized in that, The vehicle point cloud model is determined as follows: The system uses lidar to scan for vehicles that are heading toward and eventually park in the parking space. The point cloud data of the vehicle before it reaches the parking space is converted to the coordinate system of the point cloud data when it reaches the parking space; The point cloud set obtained after conversion is determined as the vehicle point cloud model.

24. A parking control method, characterized in that, include: Send a message to the vehicle waiting to be parked requesting to stop; Receive the parking space identifier returned by the main controller and control the vehicle to be parked to drive to the parking space; The receiver returns a rotation and translation matrix between the point cloud set of the vehicles to be parked and the vehicle point cloud model; wherein, the vehicle point cloud model is a point cloud set obtained by scanning the vehicles parked in the parking space using a lidar in advance. The direction and speed of the vehicle to be parked are controlled in real time according to the rotation matrix and translation matrix so that the vehicle to be parked eventually stops at the parking space.

25. The parking control method according to claim 24, characterized in that, Sending messages to vehicles waiting to park, including: broadcasting messages to vehicles waiting to park in parking spaces via V2X devices.

26. The parking control method according to claim 24, characterized in that, The message contains one or more of the following information: The vehicle identification of the vehicle to be parked; The vehicle model of the vehicle to be parked; The positioning data collected by the on-board positioning device of the vehicle to be parked; Communication connection identifier.

27. The parking control method according to claim 26, characterized in that, The communication connection identifier includes one or both of the MAC address of the vehicle controller and the MAC address of the V2X communication device connected to the vehicle controller.

28. The parking control method according to claim 24, characterized in that, Send a message to the vehicle waiting to stop requesting to stop, including: The message is sent after the vehicle waiting to be parked enters the parking lot; or, The message is sent after receiving a preset trigger signal.

29. The parking control method according to claim 24, characterized in that, Real-time control of the driving direction and speed of the vehicle to be stopped according to the rotation matrix and translation matrix includes: controlling the driving direction and speed of the vehicle to be stopped in real time by controlling the steering system, throttle control system and braking system of the vehicle to be stopped according to the rotation matrix and translation matrix.

30. A master controller, comprising a first processor, a first memory, and a computer program stored in the first memory and executable on the first processor, characterized in that, When the first processor runs the computer program, it executes each step of the parking control method according to any one of claims 1 to 23.

31. A vehicle controller, comprising a second processor, a second memory, and a computer program stored in the second memory and executable on the second processor, characterized in that, When the second processor runs the computer program, it executes each step of the parking control method according to any one of claims 24 to 29.

32. A parking control system, characterized in that, include: The main controller as claimed in claim 30, the vehicle controller as claimed in claim 31, and the lidar.

33. The parking control system according to claim 32, characterized in that, Each of the aforementioned lidars is used to scan only the predetermined monitoring area corresponding to one parking space, and each of the aforementioned main controllers is used to acquire point cloud data obtained from the scanning of one of the lidars.

34. The parking control system according to claim 32, characterized in that, Each of the lidars is used to scan a predetermined monitoring area corresponding to at least two parking spaces, and each master controller is used to acquire point cloud data obtained from the scanning of one lidar.

35. The parking control system according to claim 32, characterized in that, Each of the lidars is used to scan only the predetermined monitoring area corresponding to a parking space, and each of the main controllers is used to acquire point cloud data obtained from the scans of at least two lidars.

36. The parking control system according to claim 32, characterized in that, Each of the lidar is used to scan a predetermined monitoring area corresponding to at least two parking spaces, and each of the main controllers is used to acquire point cloud data obtained from the scans of at least two lidars.

37. The parking control system according to claim 32, characterized in that, Also includes: The vehicle-to-everything (V2X) device connected to the main controller, and the V2X device connected to the vehicle controller.

38. The parking control system according to claim 32, characterized in that, Also includes: Power supply equipment for powering the main controller and / or the lidar.

39. A car, characterized in that, The vehicle is equipped with a vehicle controller as described in claim 31.

40. The automobile according to claim 39, characterized in that, The vehicle controller is connected to the vehicle's steering system, throttle control system, and braking system.

41. The automobile according to claim 39, characterized in that, The vehicle is equipped with a vehicle-to-everything (V2X) device that is connected to the vehicle controller.

42. The automobile according to claim 39, characterized in that, The vehicle is equipped with an on-board positioning device.

43. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when executed by a processor, implements each step of the parking control method according to any one of claims 1 to 23.

44. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when executed by a processor, implements each step of the parking control method according to any one of claims 24 to 29.

Images