Automatic parking method and vehicle

Abstract

The present application discloses an automatic parking method and a vehicle, and belongs to the field of vehicle technology. Through the technical solution provided by the embodiment of the present application, when the vehicle turns on automatic parking and searches for a target parking space, it is determined whether there is a target vehicle around the target parking space that has not yet parked in the parking space, and the target vehicle is a vehicle that may park in the target parking space. In the case that the target vehicle exists, it is determined whether the target vehicle has the intention to park in the target parking space, that is, the probability of the target vehicle parking in the target parking space is further determined. In the case that the target vehicle has the intention to park in the target parking space, the vehicle is controlled to partially park in the target parking space in the target parking manner, that is, the vehicle quickly occupies the target parking space, thereby preventing the target parking space from being parked by other vehicles, and improving the success rate of automatic parking.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and more specifically, to an automatic parking method and a vehicle in the field of vehicle technology. Background Art

[0002] With the development of vehicle technology, more and more vehicles are equipped with automatic parking functions. After the user starts the automatic parking function, the vehicle can automatically find a parking space and complete parking.

[0003] In the related art, during the process of automatic parking, in order to ensure that the vehicle can be successfully parked in a parking space, the vehicle will perform multiple pre-adjustments during the automatic parking process to find a suitable initial parking position and parking angle.

[0004] However, since the pre-adjustment takes a long time, the target parking space to be parked may be occupied by other vehicles during the pre-adjustment process, resulting in failure of automatic parking. Summary of the invention

[0005] The present application embodiment provides an automatic parking method and a vehicle, which can improve the success rate of automatic parking. The technical solution is as follows:

[0006] In one aspect, an automatic parking method is provided, the method comprising:

[0007] When the vehicle starts automatic parking and searches for a target parking space, determining whether there is a target vehicle that is not in the parking space around the target parking space;

[0008] In the case where the target vehicle exists, determining whether the target vehicle has a parking intention to park in the target parking space;

[0009] In a case where the target vehicle has a parking intention to park in the target parkable space, the vehicle is controlled to partially park in the target parkable space in a target parking manner, where the target parking manner is a parking manner for quickly entering the parkable space.

[0010] In a possible implementation manner, when the vehicle starts automatic parking and searches for a target parking space, determining whether there is a target vehicle that is not in the parking space around the target parking space includes:

[0011] When the vehicle starts automatic parking and searches for a target available parking space, the area around the target available parking space is divided into a parking space area and a lane area, and it is determined whether there are other vehicles around the target available parking space, wherein the parking space area is an area including parking spaces around the target available parking space;

[0012] In a case where there are other vehicles around the target parking space and the other vehicles are in the lane area, determining that the target vehicle exists and the target vehicle is the other vehicle;

[0013] In a case where there are other vehicles around the target parking space and the other vehicles are in the parking space area, or there are no other vehicles around the target parking space, it is determined that the target vehicle does not exist.

[0014] In a possible implementation manner, when the vehicle starts automatic parking and searches for a target parking space, dividing the area around the target parking space into a parking space area and a lane area and determining whether there are other vehicles around the target parking space includes:

[0015] When the vehicle starts automatic parking and searches for a target available parking space, obtaining environmental information around the target available parking space;

[0016] Based on the environmental information, a local map around the target parking space is generated, wherein the local map includes a parking space area and a lane area;

[0017] Based on the environmental information, it is determined whether there are other vehicles around the target parking space.

[0018] In a possible implementation manner, generating a local map around the target parking space based on the environmental information includes:

[0019] Performing map element recognition on the environmental information to obtain a plurality of map elements in the environmental information;

[0020] Based on the plurality of map elements and the relative positional relationship between the map elements, generating an initial local map around the target parking space;

[0021] Based on the element type of each map element, a parking space area and a lane area are marked in the initial local map to obtain a local map around the target parking space.

[0022] In a possible implementation manner, determining whether there are other vehicles around the target parking space based on the environmental information includes:

[0023] Extracting features from the environmental information to obtain environmental information features of the environmental information;

[0024] Target detection is performed based on the environmental information features to determine whether there are other vehicles around the target parking space.

[0025] In a possible implementation manner, when the target vehicle exists, determining whether the target vehicle has a parking intention to park in the target parking space includes:

[0026] In the case where the target vehicle exists, obtaining vehicle motion information and vehicle position of the target vehicle, wherein the vehicle motion information includes a vehicle motion state and a vehicle motion direction;

[0027] Based on the vehicle motion information and vehicle position of the target vehicle and parking space information of the target parking space, it is determined whether the target vehicle has a parking intention to park in the target parking space, wherein the parking space information includes a parking space position and a parking space orientation.

[0028] In a possible implementation manner, the determining whether the target vehicle has a parking intention to park in the target parking space based on the vehicle motion information, the vehicle position of the target vehicle and the parking space information of the target parking space includes:

[0029] Based on the vehicle position of the target vehicle and the parking space position of the target parking space, determining a relative position relationship between the target vehicle and the target parking space, wherein the relative position relationship includes a distance and a direction;

[0030] Based on the vehicle motion information of the target vehicle, the relative position relationship, and the parking space orientation, it is determined whether the target vehicle has a parking intention to park in the target parking space.

[0031] In a possible implementation manner, determining whether the target vehicle has a parking intention to park in the target parking space based on the vehicle motion information of the target vehicle, the relative position relationship, and the parking space orientation includes:

[0032] Determining a parking parameter for the target vehicle to park in the target parking space based on the vehicle motion information of the target vehicle, the relative position relationship, and the parking space orientation, wherein the parking parameter is used to indicate the size of the parking possibility;

[0033] When the parking parameter is greater than or equal to a parking parameter threshold, determining that the target vehicle has a parking intention to park in the target parking space;

[0034] When the parking parameter is less than the parking parameter threshold, it is determined that the target vehicle has no parking intention to park in the target parking space.

[0035] In a possible implementation manner, when the target vehicle has a parking intention to park in the target parkable space, controlling the vehicle to partially park in the target parkable space in a target parking manner includes:

[0036] If the target vehicle intends to park in the target available parking space, generating a first target parking path corresponding to the target parking method based on the vehicle position, vehicle orientation and parking space information of the target available parking space, wherein the parking space information includes a parking space position and a parking space orientation;

[0037] Based on the first target parking path, the vehicle is controlled to be partially parked in the target parking space.

[0038] In a possible implementation manner, when the target vehicle has a parking intention to park in the target parking space, generating a first target parking path corresponding to the target parking method based on the vehicle position, vehicle orientation and parking space information of the target parking space includes:

[0039] Based on the vehicle position and vehicle orientation of the vehicle, and the parking position and parking orientation of the target parking space, a plurality of candidate parking paths are generated, wherein different parking paths do not completely overlap;

[0040] The shortest parking path among the plurality of candidate parking paths is determined as a first target parking path corresponding to the target parking method.

[0041] In a possible implementation manner, controlling the vehicle to partially park into the target parking space based on the first target parking path includes:

[0042] Controlling the vehicle to travel according to the first target parking path and determining whether there is an obstacle ahead of the vehicle in the direction of travel;

[0043] If there is an obstacle ahead of the vehicle in the driving direction, determine whether the vehicle can avoid the obstacle; if the vehicle can avoid the obstacle, perform path correction on the first target parking path based on obstacle information of the obstacle to obtain a reference parking path, wherein the obstacle information includes the position and size of the obstacle; and control the vehicle to partially park in the target parking space based on the reference parking path;

[0044] When there is no obstacle ahead of the vehicle in the driving direction, the vehicle is controlled to continue driving along the first target parking path so as to partially park in the target parking space.

[0045] In a possible implementation, the method further includes:

[0046] In the case that the vehicle cannot avoid the obstacle, the vehicle is controlled to stop parking in the target parking space and to search for a parking space again.

[0047] In a possible implementation manner, when the target vehicle has a parking intention to park in the target parkable space, after controlling the vehicle to partially park in the target parkable space in a target parking manner, the method further includes:

[0048] generating a second target parking path based on parking space information of the target parkable space, the vehicle position, the vehicle orientation, and parking assistance information of the vehicle when the vehicle is partially parked in the target parkable space, the parking space information including the parking space position, the parking space orientation, and parking space obstacle information, the parking assistance information including at least one of driving and occupancy distribution information and trunk opening information, the trunk opening information being used to indicate whether the trunk needs to be opened after the vehicle completes parking;

[0049] Based on the second target parking path, the vehicle is controlled to be completely parked in the target parking space.

[0050] In a possible implementation manner, when the vehicle starts automatic parking and searches for a target parking space, before determining whether there is a target vehicle that is not in the parking space around the target parking space, the method further includes:

[0051] When the vehicle enters the parking area, start automatic parking and search for a parking space;

[0052] Determining whether to enable the target parking mode based on the number of searched available parking spaces and the number of all searched parking spaces, or the duration of the parking space search;

[0053] When the target parking mode is enabled, it is determined whether the target parking space is found.

[0054] In a possible implementation manner, determining whether to enable the target parking mode based on the number of searched available parking spaces and the number of all searched parking spaces, or the duration of the parking space search, includes:

[0055] When the ratio between the number of searched available parking spaces and the number of all searched parking spaces is less than or equal to a preset ratio, determining to enable the target parking mode; when the ratio between the number of searched available parking spaces and the number of all searched parking spaces is greater than the preset ratio, determining not to enable the target parking mode;

[0056] Alternatively, when the parking space search time is greater than or equal to a preset time, it is determined that the target parking mode is enabled; when the parking space search time is less than the preset time, it is determined that the target parking mode is not enabled.

[0057] In one aspect, an automatic parking device is provided, the device comprising:

[0058] A target vehicle determination module, for determining whether there is a target vehicle that is not in the parking space around the target parking space when the vehicle starts automatic parking and searches for the target parking space;

[0059] a parking intention determination module, for determining, when the target vehicle exists, whether the target vehicle has a parking intention to park in the target parking space;

[0060] The parking control module is used to control the vehicle to partially park into the target available parking space in a target parking manner when the target vehicle intends to park into the target available parking space, wherein the target parking manner is a parking manner for quickly entering the available parking space.

[0061] In a possible implementation manner, the target vehicle determination module is used to, when the vehicle turns on automatic parking and searches for a target available parking space, divide the area around the target available parking space into a parking space area and a lane area and determine whether there are other vehicles around the target available parking space, the parking space area being an area including parking spaces around the target available parking space; when there are other vehicles around the target available parking space and the other vehicles are in the lane area, determine that the target vehicle exists and the target vehicle is the other vehicle; when there are other vehicles around the target available parking space and the other vehicles are in the parking space area, or when there are no other vehicles around the target available parking space, determine that the target vehicle does not exist.

[0062] In a possible implementation, the target vehicle determination module is used to, when the vehicle turns on automatic parking and searches for a target parking space, obtain environmental information around the target parking space; based on the environmental information, generate a local map around the target parking space, the local map including a parking space area and a lane area; based on the environmental information, determine whether there are other vehicles around the target parking space.

[0063] In a possible implementation, the target vehicle determination module is configured to perform map element recognition on the environmental information to obtain a plurality of map elements in the environmental information; generate an initial local map around the target parking space based on the plurality of map elements and the relative positional relationship between the map elements; and mark parking space areas and lane areas in the initial local map based on the element type of each map element to obtain a local map around the target parking space.

[0064] In a possible implementation, the target vehicle determination module is configured to perform feature extraction on the environmental information to obtain environmental information features of the environmental information; and perform target detection based on the environmental information features to determine whether there are other vehicles around the target parking space.

[0065] In a possible implementation, the parking intention determination module is used to obtain vehicle motion information and vehicle position of the target vehicle when the target vehicle exists, the vehicle motion information including vehicle motion state and vehicle motion direction; and determine whether the target vehicle has a parking intention to park in the target parking space based on the vehicle motion information, vehicle position and parking space information of the target parking space, the parking space information including parking space position and parking space orientation.

[0066] In a possible implementation, the parking intention determination module is used to determine a relative position relationship between the target vehicle and the target parking space based on the vehicle position of the target vehicle and the parking space position of the target parking space, wherein the relative position relationship includes a distance and a direction; and to determine whether the target vehicle has a parking intention to park in the target parking space based on the vehicle motion information of the target vehicle, the relative position relationship and the parking space orientation.

[0067] In a possible implementation manner, the parking intention determination module is configured to determine a parking parameter for the target vehicle to park in the target available parking space based on the vehicle motion information of the target vehicle, the relative position relationship, and the parking space orientation, the parking parameter being used to indicate the magnitude of parking possibility; when the parking parameter is greater than or equal to a parking parameter threshold, determine that the target vehicle has a parking intention to park in the target available parking space; and when the parking parameter is less than the parking parameter threshold, determine that the target vehicle does not have a parking intention to park in the target available parking space.

[0068] In a possible implementation, the parking control module is configured to generate a first target parking path corresponding to the target parking method based on the vehicle position, vehicle orientation and parking space information of the target parking space when the target vehicle has an intention to park in the target available parking space, the parking space information including the parking space position and parking space orientation; and control the vehicle to partially park in the target available parking space based on the first target parking path.

[0069] In a possible implementation manner, the parking control module is configured to generate a plurality of candidate parking paths based on the vehicle position, the vehicle orientation, and the parking position and parking orientation of the target parking space, wherein different parking paths do not completely overlap; and determine the shortest parking path among the plurality of candidate parking paths as a first target parking path corresponding to the target parking method.

[0070] In a possible implementation manner, the parking control module is configured to control the vehicle to travel along the first target parking path and determine whether there is an obstacle ahead of the vehicle in the direction of travel; if there is an obstacle ahead of the vehicle in the direction of travel, determine whether the vehicle can avoid the obstacle; if the vehicle can avoid the obstacle, perform path correction on the first target parking path based on obstacle information of the obstacle to obtain a reference parking path, wherein the obstacle information includes an obstacle position and an obstacle size; control the vehicle to partially park into the target available parking space based on the reference parking path; and if there is no obstacle ahead of the vehicle in the direction of travel, control the vehicle to continue traveling along the first target parking path to partially park into the target available parking space.

[0071] In a possible implementation manner, the parking control module is further configured to control the vehicle to stop parking in the target available parking space and to search for an available parking space again when the vehicle cannot avoid the obstacle.

[0072] In a possible implementation manner, the parking control module is further configured to, when the vehicle is partially parked in the target parkable space, generate a second target parking path based on parking space information of the target parkable space, the vehicle position, the vehicle orientation, and parking assistance information of the vehicle, the parking space information including the parking space position and the parking space orientation as well as parking space obstacle information, the parking assistance information including at least one of driving and occupancy distribution information and trunk opening information, the trunk opening information being used to indicate whether the trunk needs to be opened after the vehicle completes parking; based on the second target parking path, control the vehicle to be completely parked in the target parkable space.

[0073] In a possible implementation, the device further includes:

[0074] The parking space search module is used to start automatic parking and search for parking spaces when the vehicle enters the parking area; determine whether to enable the target parking mode based on the number of searched available parking spaces and the number of all searched parking spaces, or the duration of the parking space search; and determine whether the target available parking space is found when the target parking mode is enabled.

[0075] In a possible implementation, the parking space search module is used to determine that the target parking mode is enabled when the ratio between the number of searched available parking spaces and the number of all searched parking spaces is less than or equal to a preset ratio; determine that the target parking mode is not enabled when the ratio between the number of searched available parking spaces and the number of all searched parking spaces is greater than the preset ratio; or determine that the target parking mode is enabled when the duration of the parking space search is greater than or equal to the preset duration; and determine that the target parking mode is not enabled when the duration of the parking space search is less than the preset duration.

[0076] On the one hand, a vehicle is provided, comprising one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the program code is loaded and executed by the one or more processors to implement the operations performed by the automatic parking method.

[0077] In one aspect, a computer-readable storage medium is provided, wherein at least one program code is stored in the computer-readable storage medium, and the program code is loaded and executed by a processor to implement the operations performed by the automatic parking method. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 is a schematic diagram of an implementation environment of an automatic parking method provided in an embodiment of the present application;

[0079] Figure 2 is a flow chart of an automatic parking method provided by an embodiment of the present application;

[0080] Figure 3 is a flow chart of another automatic parking method provided by an embodiment of the present application;

[0081] Figure 4 is a structural schematic diagram of an automatic parking device provided in an embodiment of the present application;

[0082] Figure 5 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0083] The technical solution in the present application will be described clearly and in detail below in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0084] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features reflected. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0085] Automatic parking: Automatic parking means that the car automatically parks itself without manual control. Car manufacturers developed cars that can park themselves because they realized the needs of consumers. Automatic parking can help drivers park their cars more easily. The automatic parking system can automatically control the steering wheel, accelerator and brake when the vehicle is parked to help the driver park the vehicle into the parking space. The system uses sensors and cameras to sense the environment around the vehicle, calculate the parking path, and park the vehicle accurately.

[0086] Path planning: Path planning refers to planning an optimal path from a starting point to a destination for a robot or other mobile device in a given environment. Path planning is an important research direction in the fields of robotics, automation, computer science, etc. It has a wide range of applications, including autonomous driving, logistics distribution, robot navigation, etc. The main goal of path planning is to find an optimal path so that a robot or other mobile device can reach the destination in the shortest time, with the least energy consumption, and while avoiding obstacles.

[0087] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain better results.

[0088] Machine Learning (ML) is a multi-disciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, etc. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge sub-models to continuously improve their performance.

[0089] The implementation environment of the embodiment of the present application is introduced below. Figure 1 The implementation environment of the automatic parking method provided in the embodiment of the present application includes a vehicle-mounted terminal 101 and an intelligent driving controller 102.

[0090] The vehicle terminal 101 is a terminal installed on the vehicle, and has the ability to collect and process data. The vehicle terminal 101 is connected to multiple component controllers and multiple sensors of the vehicle by wire. The vehicle terminal 101 can control multiple component controllers of the vehicle, and different component controllers can control different vehicle components. The sensors can collect environmental information around the vehicle, and the environmental information is environmental information related to automatic parking. In the embodiment of the present application, the multiple component controllers include an intelligent driving controller 102, and the intelligent driving controller 102 is used to control the intelligent driving process of the vehicle. In the embodiment of the present application, it refers to controlling the automatic parking process of the vehicle.

[0091] After introducing the implementation environment of the embodiment of the present application, the application scenario of the technical solution provided by the embodiment of the present application is introduced below. The technical solution provided by the embodiment of the present application can be applied to various types of vehicles with automatic driving functions. After adopting the technical solution provided by the embodiment of the present application, when the vehicle turns on automatic parking and searches for the target parking space, it is determined whether there is a target vehicle that is not in the parking space around the target parking space, that is, it is determined whether there is a target vehicle that has not been parked in the parking space around the target parking space, and the target vehicle is a vehicle that may be parked in the target parking space. In the case of the presence of the target vehicle, it is determined whether the target vehicle has the intention to park in the target parking space, that is, it is further determined the probability of the target vehicle parking in the target parking space. In the case of the target vehicle having the intention to park in the target parking space, the vehicle is controlled to partially park in the target parking space in the target parking mode, that is, the vehicle quickly occupies the target parking space, thereby preventing the target parking space from being parked by other vehicles and improving the success rate of automatic parking.

[0092] After introducing the implementation environment and application scenarios of the embodiments of the present application, the technical solutions provided by the embodiments of the present application are introduced below. Figure 2 , taking the execution subject as an intelligent driving controller as an example, the method includes the following steps.

[0093] 201. When the vehicle starts automatic parking and searches for a target parking space, the intelligent driving controller determines whether there is a target vehicle that is not in the parking space around the target parking space.

[0094] The target parking space refers to the parking space selected by the automatic parking system, and the area around the target parking space refers to the area within a certain range around the target parking space. The target vehicle refers to the vehicle that is located around the target parking space and is not in other parking spaces. In the embodiment of the present application, the target vehicle is a vehicle that has the possibility of being parked in the target parking space.

[0095] 202. When the target vehicle exists, the intelligent driving controller determines whether the target vehicle has an intention to park in the target parking space.

[0096] Among them, the target vehicle has a parking intention to park in the target parking space, which means that the probability that the target vehicle will park in the target parking space is high; the target vehicle does not have a parking intention to park in the target parking space, which means that the probability that the target vehicle will park in the target parking space is low.

[0097] 203. When the target vehicle has an intention to park in the target parking space, the intelligent driving controller controls the vehicle to partially park in the target parking space in a target parking manner, where the target parking manner is a parking manner for quickly entering the parking space.

[0098] Among them, the vehicle partially parking into the target parking space refers to the vehicle partially entering the target parking space, that is, the vehicle is not completely parked into the target parking space, so as to occupy the target parking space; the target parking method refers to the parking method of controlling the vehicle to occupy the parking space, that is, the parking method of controlling the vehicle to quickly partially enter the parking space.

[0099] Through the technical solution provided by the embodiment of the present application, when the vehicle starts automatic parking and searches for the target parking space, it is determined whether there is a target vehicle that is not in the parking space around the target parking space, that is, it is determined whether there is a target vehicle that has not parked in the parking space around the target parking space, and the target vehicle is a vehicle that may park in the target parking space. In the case of the presence of the target vehicle, it is determined whether the target vehicle has the intention to park in the target parking space, that is, the probability of the target vehicle parking in the target parking space is further determined. In the case of the target vehicle having the intention to park in the target parking space, the vehicle is controlled to partially park in the target parking space in the target parking manner, that is, the vehicle quickly occupies the target parking space, thereby preventing the target parking space from being parked by other vehicles and improving the success rate of automatic parking.

[0100] It should be noted that the above steps 201-203 are a simple description of the automatic parking method provided in the embodiment of the present application. The automatic parking method provided in the embodiment of the present application will be described in more detail below with reference to some examples. Figure 3 , taking the execution subject as an intelligent driving controller as an example, the method includes the following steps.

[0101] 301. When the vehicle enters the parking area, the intelligent driving controller starts automatic parking and searches for a parking space.

[0102] The parking area is an area where parking spaces exist, for example, a parking lot or other area where parking spaces exist. Automatic parking is a function provided by the vehicle, and turning on automatic parking means turning on the automatic parking function. Parking space search refers to the process of finding a parking space in the parking area. Parking space search is the basis of automatic parking. After turning on automatic parking, parking space search will be automatically performed.

[0103] In a possible implementation, when the vehicle enters the parking area, the intelligent driving controller starts the automatic parking function. When the automatic parking function is started, the intelligent driving controller obtains environmental information around the vehicle. The intelligent driving controller controls the vehicle to travel based on the environmental information and continuously obtains environmental information around the vehicle. The intelligent driving controller searches for a parking space based on the environmental information around the vehicle.

[0104] Among them, the automatic parking function can be automatically turned on by the intelligent driving controller when it recognizes the parking area, or turned on in response to a start command, and the start command is triggered by a voice command or a key command. The vehicle is equipped with an environmental sensor, through which the environmental information can be obtained. In some embodiments, the environmental sensor includes a visual sensor, for example, the visual sensor includes a camera and a radar. Accordingly, in the case where the environmental sensor includes a camera and a radar, the environmental information includes an environmental image.

[0105] In this embodiment, when the vehicle enters the parking area, the automatic parking function is activated. In the case of the automatic parking function, the collected environmental information is used to control the vehicle driving and search for parking spaces, which is more efficient.

[0106] For example, when a vehicle enters a parking area, the intelligent driving controller activates the automatic parking function. When the automatic parking function is activated, the intelligent driving controller obtains an environmental image around the vehicle. The intelligent driving controller performs path planning based on the environmental image to obtain an initial path. The intelligent driving controller uses the initial path to control the vehicle to travel. During the driving of the vehicle, the environmental image around the vehicle is continuously obtained, and the parking space is recognized on the environmental image to determine whether there is a parking space around the vehicle.

[0107] In order to explain the above example more clearly, the method of performing parking space recognition based on the environment image in the above example is explained below.

[0108] In some embodiments, the intelligent driving controller inputs the environment image into a parking space recognition model, extracts features of the environment image through the parking space recognition model, and obtains environment image features of the environment image. The intelligent driving controller recognizes the environment image based on the environment image features through the parking space recognition model to realize parking space recognition, so as to determine whether there is a parking space around the vehicle.

[0109] Among them, the parking space recognition model is a target detection model, which is trained using multiple sample environment images and annotation information corresponding to each sample environment image. The annotation information is used to indicate whether there is a parking space in the corresponding sample environment image and, if there is a parking space, the position of the parking space in the sample environment image.

[0110] It should be noted that the above description is based on an example in which the environmental information includes an environmental image. In other possible implementations, the environmental information may also include other visual information that can describe the environment, for example, the environmental information also includes an environmental point cloud.

[0111] 302. The intelligent driving controller determines whether to enable the target parking method based on the number of searched available parking spaces and the number of all searched parking spaces, or the duration of the parking space search.

[0112] Among them, a parking space refers to a parking space where no vehicle is parked. In the above step 301, during the parking space search process, when a parking space is identified, it is further determined whether the parking space is a parking space. The target parking method is a parking method for quickly entering a parking space. In other words, the target parking method refers to a parking method for controlling the vehicle to occupy a parking space, that is, a parking method for controlling the vehicle to quickly partially enter a parking space. When the target parking method is activated, the vehicle will reduce the number of pre-adjustments as quickly as possible during the automatic parking process, so as to occupy the parking space as quickly as possible, and does not pursue the parking effect. The target parking method focuses on speed; when the target parking method is not activated, the vehicle will park in the parking space according to the original parking method during the automatic parking process, that is, it will perform multiple pre-adjustments, focusing on the parking effect.

[0113] In a possible implementation, when the ratio between the number of searched available parking spaces and the number of all searched parking spaces is less than or equal to a preset ratio, the intelligent driving controller determines to enable the target parking mode. When the ratio between the number of searched available parking spaces and the number of all searched parking spaces is greater than the preset ratio, the intelligent driving controller determines not to enable the target parking mode.

[0114] The number of available parking spaces and the number of all parking spaces searched are determined during the parking space search process. If the ratio between the number of available parking spaces searched and the number of all parking spaces searched is less than or equal to the preset ratio, it means that the number of available parking spaces in the current parking area is small, so it is necessary to enable the target parking method to seize the available parking spaces; if the ratio between the number of available parking spaces searched and the number of all parking spaces searched is greater than the preset ratio, it means that the number of available parking spaces in the current parking area is large, so it is not necessary to enable the target parking method to seize the available parking spaces. The preset ratio is set by the technician according to the actual situation, and the embodiments of the present application do not limit this.

[0115] In this implementation, the ratio between the number of searched available parking spaces and the number of all searched parking spaces is compared with a preset ratio to determine whether to activate the target parking mode. The activation judgment of the target parking mode matches the actual situation of the parking area and has high accuracy.

[0116] In a possible implementation, when the duration of the parking space search is greater than or equal to a preset duration, the intelligent driving controller determines to enable the target parking mode. When the duration of the parking space search is less than the preset duration, the intelligent driving controller determines not to enable the target parking mode.

[0117] The longer the parking space search time is, that is, the parking space search time is greater than or equal to the preset time, it means that it is not easy to search for available parking spaces, and the number of available parking spaces in the parking area is smaller; the shorter the parking space search time is, that is, the parking space search time is less than the preset time, it means that it is easier to search for available parking spaces, and the number of available parking spaces in the parking area is larger. The preset time is set by technicians according to actual conditions, and the embodiments of the present application do not limit this.

[0118] In this implementation, the duration of the parking space search is compared with the preset duration to determine whether to activate the target parking mode. The activation judgment of the target parking mode matches the actual situation of the parking area and has high accuracy.

[0119] 303. When the target parking mode is enabled, the intelligent driving controller determines whether the target parking space is found.

[0120] The target parking space refers to the parking space selected by the automatic parking system. Generally speaking, the target parking space is an empty space that the vehicle can park in. Parking means that the size of the parking space matches the vehicle. Therefore, searching for the target parking space means searching for the parking space that the vehicle can park in. The target parking space is identified by the recognition algorithm built into the intelligent driving controller, and the embodiments of the present application are not limited thereto.

[0121] 304. When the vehicle starts automatic parking and searches for a target parking space, the intelligent driving controller determines whether there is a target vehicle that is not in the parking space around the target parking space.

[0122] The target parking space surrounding refers to an area within a certain range near the target parking space. The target vehicle refers to a vehicle located around the target parking space and not in other parking spaces. In the embodiment of the present application, the target vehicle is a vehicle that has the possibility of parking in the target parking space.

[0123] In a possible implementation, when the vehicle turns on automatic parking and searches for a target parking space, the intelligent driving controller divides the area around the target parking space into a parking space area and a lane area and determines whether there are other vehicles around the target parking space, and the parking space area is an area including parking spaces around the target parking space. When there are other vehicles around the target parking space and the other vehicles are in the lane area, the intelligent driving controller determines that the target vehicle exists and the target vehicle is the other vehicle. When there are other vehicles around the target parking space and the other vehicles are in the parking space area, or when there are no other vehicles around the target parking space, the intelligent driving controller determines that the target vehicle does not exist.

[0124] The parking space area is the area where the parking space is located in the parking area, and the lane area is the area excluding the parking space in the parking area, for example, the area where the lane next to the parking space is located.

[0125] In this embodiment, when the vehicle starts automatic parking and searches for a target parking space, the area around the target parking space is divided into the parking space area and the lane area, and it is determined whether there are other vehicles around the target parking space. The determination of whether the target vehicle exists is based on whether there are other vehicles and whether the other vehicles are in the parking space area or the lane area, and the accuracy of the target vehicle determination is high.

[0126] In order to explain the above embodiment more clearly, the following describes the manner in which the intelligent driving controller in the above embodiment divides the area around the target parking space into a parking space area and a lane area and determines whether there are other vehicles around the target parking space.

[0127] In a possible implementation, when the vehicle starts automatic parking and searches for a target parking space, the intelligent driving controller obtains environmental information around the target parking space. Based on the environmental information, the intelligent driving controller generates a local map around the target parking space, where the local map includes a parking space area and a lane area. Based on the environmental information, the intelligent driving controller determines whether there are other vehicles around the target parking space.

[0128] The local map around the target parking space is used to describe the environment around the target parking space.

[0129] In this embodiment, the acquired environmental information around the target parking space is used to generate a local map around the target parking space, and the local map can be used to distinguish the parking space area from the lane area. In addition, the acquired environmental information can also be used to determine whether there are other vehicles around the target parking space, thereby making full use of the environmental information.

[0130] In order to explain the above implementation more clearly, the above implementation is explained in two parts below.

[0131] Part 1: When the vehicle turns on automatic parking and searches for a target parking space, the intelligent driving controller obtains environmental information around the target parking space.

[0132] In a possible implementation, when the vehicle turns on automatic parking and searches for a target parking space, the intelligent driving controller obtains an environmental image around the target parking space through an environmental sensor.

[0133] Among them, the environmental sensor is a binocular camera.

[0134] It should be noted that the above description is based on an example in which the environmental information includes an environmental image. In other possible implementations, the environmental information may also include other visual information that can describe the environment, for example, the environmental information also includes an environmental point cloud.

[0135] In the second part, the intelligent driving controller generates a local map around the target parking space based on the environmental information.

[0136] In a possible implementation, the intelligent driving controller performs map element recognition on the environmental information to obtain multiple map elements in the environmental information. The intelligent driving controller generates an initial local map around the target parking space based on the multiple map elements and the relative position relationship between the map elements. The intelligent driving controller marks the parking space area and the lane area in the initial local map based on the element type of each map element to obtain a local map around the target parking space.

[0137] Map elements refer to elements that can be used to generate maps, such as lane lines, parking space lines, obstacles (pillars, ice cream cones, etc.), and lane signs. The relative position relationship between each map element can represent the distribution of each map element around the target parking space. The element types of map elements contained in the parking area and the lane area are different, so the element types of map elements can be used to distinguish between the parking area and the lane area.

[0138] For example, the intelligent driving controller performs map element recognition on the two environmental images captured by the binocular camera to obtain multiple map elements in each environmental image. The intelligent driving controller performs element matching on the multiple map elements in the two environmental images to obtain the correspondence between the map elements in the two environmental images. The intelligent driving controller generates an initial local map around the target parking space based on the correspondence between the map elements in the two environmental images, the relative position relationship between the map elements, the position of the map elements in the environmental images, and the positions of the two cameras of the binocular camera on the vehicle. The intelligent driving controller marks the area where the map elements of the first type of element in the initial local map are located as the parking space area, and marks the area where the map elements of the second type of element are located as the lane area, to obtain a local map around the target parking space.

[0139] Among them, the first type includes parking space lines and obstacles, and the second type includes lane lines and lane markings, etc.

[0140] In order to more clearly illustrate the technical solution provided in the above example, the method of generating the initial local map in the above example is explained below.

[0141] In some embodiments, the intelligent driving controller determines the position of each map element around the target parking space based on the correspondence between the map elements in the two environment images, the relative position relationship between each map element, the position of each map element in the environment image, and the positions of the two cameras of the binocular camera on the vehicle. The intelligent driving controller generates an initial local map around the target parking space based on the position of each map element around the target parking space.

[0142] Part 3: The intelligent driving controller determines whether there are other vehicles around the target parking space based on the environmental information.

[0143] In a possible implementation, the intelligent driving controller extracts features from the environmental information to obtain environmental information features of the environmental information. The intelligent driving controller performs target detection based on the environmental information features to determine whether there are other vehicles around the target parking space.

[0144] For example, the intelligent driving controller extracts features from the environment image to obtain environment information features of the environment image. The intelligent driving controller divides the environment information features into multiple sub-environment information features, and one environment information feature corresponds to a part of the environment image. The intelligent driving controller fully connects and normalizes each sub-environment information feature to obtain a classification value for each sub-environment information feature. When the classification value of any sub-environment information feature is greater than or equal to the classification value threshold, the intelligent driving controller determines that there are other vehicles around the target parking space, and the other vehicles are located in the part corresponding to the sub-environment information feature. When the classification values ​​of each sub-environment information feature are less than the classification value threshold, the intelligent driving controller determines that there are no other vehicles around the target parking space.

[0145] 305. When the target vehicle exists, the intelligent driving controller determines whether the target vehicle has an intention to park in the target parking space.

[0146] The target vehicle has a parking intention to park in the target parking space, which means that the probability that the target vehicle will park in the target parking space is high. The target vehicle does not have a parking intention to park in the target parking space, which means that the probability that the target vehicle will park in the target parking space is low.

[0147] In a possible implementation, when the target vehicle exists, the intelligent driving controller obtains the vehicle motion information and vehicle position of the target vehicle, where the vehicle motion information includes the vehicle motion state and the vehicle motion direction. The intelligent driving controller determines whether the target vehicle has a parking intention to park in the target parking space based on the vehicle motion information, vehicle position and parking space information of the target parking space, where the parking space information includes the parking space position and parking space orientation.

[0148] The vehicle motion state includes stationary and moving.

[0149] In this embodiment, when the target vehicle exists, the vehicle motion information, vehicle position and parking space information of the target parking space are used to determine whether the target vehicle has the intention to park in the target parking space, and the accuracy of the parking intention is relatively high.

[0150] In order to explain the above implementation more clearly, the above implementation will be explained in several parts below.

[0151] Part 1: When the target vehicle exists, the intelligent driving controller obtains the vehicle motion information and vehicle position of the target vehicle.

[0152] In a possible implementation, when the target vehicle exists, the intelligent driving controller performs motion information recognition and vehicle position recognition on the target vehicle through an environmental image or an environmental point cloud to obtain the vehicle motion state, vehicle motion direction and vehicle position of the target vehicle.

[0153] Among them, both the environmental image and the environmental point cloud are collected by the environmental sensor of the vehicle. For example, when the environmental information is an environmental image, the environmental sensor is a binocular camera, and accordingly, the environmental image is an image collected by the binocular camera; when the environmental information is an environmental point cloud, the environmental sensor is a radar, and accordingly, the environmental point cloud is a point cloud collected by the radar.

[0154] In this implementation, the vehicle motion information and vehicle position of the target vehicle are identified using an environmental image or an environmental point cloud with high accuracy.

[0155] In order to explain the above embodiment more clearly, the above embodiment is described below by using two examples.

[0156] Example 1: When the target vehicle exists and the environmental information is an environmental image, the intelligent driving controller determines the vehicle motion state and vehicle motion direction of the target vehicle through multiple environmental images collected at adjacent moments. The intelligent driving controller determines the vehicle position of the target vehicle based on the environmental image collected at the most recent moment.

[0157] Example 2: When the target vehicle exists and the environmental information is an environmental point cloud, the intelligent driving controller determines the vehicle motion state and vehicle motion direction of the target vehicle through multiple environmental point clouds collected at adjacent times. The intelligent driving controller determines the vehicle position of the target vehicle based on the environmental point cloud collected at the most recent time.

[0158] Part 2: The intelligent driving controller determines whether the target vehicle has an intention to park in the target parking space based on the vehicle motion information, the vehicle position and the parking space information of the target parking space.

[0159] In a possible implementation, the intelligent driving controller determines the relative position relationship between the target vehicle and the target parking space based on the vehicle position of the target vehicle and the parking space position of the target parking space, wherein the relative position relationship includes a distance and a direction. The intelligent driving controller determines whether the target vehicle has a parking intention to park in the target parking space based on the vehicle motion information of the target vehicle, the relative position relationship, and the parking space orientation.

[0160] For example, the intelligent driving controller determines the distance and direction between the target vehicle and the target parking space based on the vehicle position of the target vehicle and the parking space position of the target parking space. The intelligent driving controller determines the parking parameter of the target vehicle in the target parking space based on the vehicle motion information of the target vehicle, the relative position relationship and the parking space orientation, and the parking parameter is used to indicate the size of the parking possibility. When the parking parameter is greater than or equal to the parking parameter threshold, the intelligent driving controller determines that the target vehicle has the intention to park in the target parking space. When the parking parameter is less than the parking parameter threshold, the intelligent driving controller determines that the target vehicle does not have the intention to park in the target parking space.

[0161] In order to more clearly illustrate the technical solution provided by the above example, the method of determining the parking parameters of the target parking space in the above example is explained below.

[0162] In some embodiments, the intelligent driving controller inputs the vehicle motion information, the relative position relationship, and the parking space orientation of the target vehicle into a parking parameter determination model, and extracts features of the vehicle motion information, the relative position relationship, and the parking space orientation through the parking parameter determination model to obtain parking parameter features. The intelligent driving controller fully connects and normalizes the parking parameter features through the parking parameter determination model to obtain parking parameters for the target vehicle to park in the target available parking space.

[0163] The parking parameter determination model is a regression model that can determine the parking parameters according to the input vehicle motion information, the relative position relationship and the parking space orientation. The parking parameter determination model is trained based on multiple sample vehicle motion information, multiple sample relative position relationships and multiple sample parking space orientations and corresponding annotated parking parameters.

[0164] 306. When the target vehicle has an intention to park in the target parking space, the intelligent driving controller controls the vehicle to partially park in the target parking space in a target parking manner.

[0165] Among them, the vehicle partially parks in the target parking space means that the vehicle partially enters the target parking space, that is, it is not completely parked in the target parking space, so as to seize the target parking space. In some embodiments, the vehicle partially enters the target parking space means that the front or rear of the vehicle is parked in the target parking space at a preset ratio, and the preset ratio is set by the technician according to the actual situation, for example, the preset ratio is set to 1 / 3, etc., and the embodiments of the present application do not limit this. After the vehicle partially parks in the target parking space, it is also necessary to adjust the position of the vehicle in the target parking space.

[0166] In a possible implementation, when the target vehicle intends to park in the target parking space, the intelligent driving controller generates a first target parking path corresponding to the target parking method based on the vehicle position, vehicle orientation, and parking space information of the target parking space. Based on the first target parking path, the intelligent driving controller controls the vehicle to partially park in the target parking space.

[0167] The first target parking path is a parking path for occupying the target available parking space. When the first target parking path is used for parking, the vehicle can be partially parked in the target available parking space with priority, thereby occupying the target available parking space.

[0168] For example, the intelligent driving controller generates multiple candidate parking paths based on the vehicle position, vehicle orientation, parking position and parking orientation of the target parking space, and different parking paths do not completely overlap. The intelligent driving controller determines the shortest parking path among the multiple candidate parking paths as the first target parking path corresponding to the target parking method. The intelligent driving controller controls the vehicle to travel according to the first target parking path and determines whether there is an obstacle in front of the vehicle's driving direction. In the case where there is an obstacle in front of the vehicle's driving direction, the intelligent driving controller determines whether the vehicle can avoid the obstacle. In the case that the vehicle can avoid the obstacle, the intelligent driving controller corrects the path of the first target parking path based on the obstacle information of the obstacle to obtain a reference parking path, and the obstacle information includes the obstacle position and obstacle size. The intelligent driving controller controls the vehicle to partially park in the target parking space based on the reference parking path. In the case that there is no obstacle in front of the vehicle's driving direction, the intelligent driving controller controls the vehicle to continue to travel according to the first target parking path to partially park in the target parking space. In addition, when the vehicle cannot avoid the obstacle, the vehicle is controlled to stop parking in the target parking space and search for a parking space again.

[0169] Among them, based on the vehicle position, vehicle orientation, parking position and parking orientation of the target parking space, a plurality of candidate parking paths are generated by using a path planning method in the relevant technology, which is not limited in the embodiments of the present application. After obtaining the first target parking path, the intelligent driving controller can also update the first target parking path in real time according to the obstacle information collected from the obstacles, thereby ensuring the safety of the vehicle. In some embodiments, obstacles include pedestrians, other vehicles and other objects that can hinder the parking of the vehicle, which is not limited in the embodiments of the present application.

[0170] Optionally, after step 306 , the intelligent driving controller can also execute the following step 307 .

[0171] 307. When the vehicle is partially parked in the target parking space, the intelligent driving controller generates a second target parking path based on the parking space information of the target parking space, the vehicle position, the vehicle orientation and the parking assistance information of the vehicle, wherein the parking space information includes the parking space position, the parking space orientation and the parking space obstacle information, and the parking assistance information includes at least one of the driving and occupancy distribution information and the trunk opening information, and the trunk opening information is used to indicate whether the trunk needs to be opened after the vehicle completes parking.

[0172] The second target parking path is a parking path for controlling the vehicle to be completely parked in the target parking space. The driving and passenger distribution information is used to indicate the distribution of passengers in the vehicle, and the trunk opening information is used to indicate whether there is a need to open the trunk after parking is completed.

[0173] In a possible implementation, when the vehicle is partially parked in the target parking space, the intelligent driving controller generates a second target parking path based on the parking space information of the target parking space, the vehicle position, the vehicle orientation and parking assistance information of the vehicle, the parking space information including the parking space position, the parking space orientation and the parking space obstacle information, and the parking assistance information including the driving and occupancy distribution information.

[0174] Among them, the driving and occupancy distribution information can control whether the vehicle is parked on the left or right side of the target parking space after parking is completed. For example, when the driving and occupancy distribution information indicates that the drivers and passengers in the vehicle are all on the right side of the vehicle, the vehicle can be parked on the left side of the target parking space to facilitate the drivers and passengers to get off; when the driving and occupancy distribution information indicates that the drivers and passengers in the vehicle are all on the left side of the vehicle, the vehicle can be parked on the right side of the target parking space to facilitate the drivers and passengers to get off. In some embodiments, the driving and occupancy distribution information is obtained by the intelligent driving controller after recognizing the image of the driver and passenger.

[0175] In this implementation, the driving and passenger distribution information is combined in the process of generating the second target parking path, so that the second target parking path is more closely matched with the passenger distribution in the vehicle. After the vehicle is parked using the second target parking path, the passengers in the vehicle can get off the vehicle more conveniently.

[0176] For example, when the vehicle is partially parked in the target parking space, the intelligent driving controller performs path planning based on the parking space information of the target parking space, the vehicle position, vehicle orientation and driver and passenger distribution information of the vehicle to obtain the second target parking path.

[0177] In a possible implementation, when the vehicle is partially parked in the target parking space, the intelligent driving controller generates a second target parking path based on the parking space information of the target parking space, the vehicle position, the vehicle orientation and parking assistance information of the vehicle, the parking space information including the parking space position, the parking space orientation and the parking space obstacle information, and the parking assistance information including the trunk opening information.

[0178] Among them, the driver and passenger distribution information can control whether the vehicle is parked in front or in the back of the target parking space after parking is completed. For example, if the trunk opening information indicates that there is no need to open the trunk, the vehicle can be parked in the back of the target parking space to ensure that the vehicle is fully parked in the target parking space; if the trunk opening information indicates that there is a need to open the trunk, the vehicle can be parked in the front of the target parking space to facilitate the driver and passenger to open the trunk after getting off the vehicle. In some embodiments, the trunk opening information is triggered by the operation of the driver and passenger.

[0179] In this implementation, the trunk opening information is combined in the process of generating the second target parking path, so that the second target parking path matches whether the vehicle needs to open the trunk. After the vehicle is parked with the second target parking path, the trunk can be opened more conveniently.

[0180] For example, when the vehicle is partially parked in the target parking space, the intelligent driving controller performs path planning based on the parking space information of the target parking space, the vehicle position, vehicle orientation and trunk opening information of the vehicle to obtain the second target parking path.

[0181] 308. The intelligent driving controller controls the vehicle to completely park in the target parking space based on the second target parking path.

[0182] Wherein, completely parking into the target available parking space means that the vehicle is completely parked into the target available parking space.

[0183] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0184] Through the technical solution provided by the embodiment of the present application, when the vehicle starts automatic parking and searches for the target parking space, it is determined whether there is a target vehicle that is not in the parking space around the target parking space, that is, it is determined whether there is a target vehicle that has not parked in the parking space around the target parking space, and the target vehicle is a vehicle that may park in the target parking space. In the case of the presence of the target vehicle, it is determined whether the target vehicle has the intention to park in the target parking space, that is, the probability of the target vehicle parking in the target parking space is further determined. In the case of the target vehicle having the intention to park in the target parking space, the vehicle is controlled to partially park in the target parking space in the target parking manner, that is, the vehicle quickly occupies the target parking space, thereby preventing the target parking space from being parked by other vehicles and improving the success rate of automatic parking.

[0185] Figure 4 is a schematic diagram of the structure of an automatic parking device provided in an embodiment of the present application, see Figure 4 The device includes: a target vehicle determination module 401, a parking intention determination module 402 and a parking control module 403.

[0186] The target vehicle determination module 401 is used to determine whether there is a target vehicle that is not in the parking space around the target parking space when the vehicle starts automatic parking and searches for the target parking space.

[0187] The parking intention determination module 402 is used to determine whether the target vehicle has the parking intention to park in the target parking space when the target vehicle exists.

[0188] The parking control module 403 is used to control the vehicle to partially park into the target available parking space in a target parking manner when the target vehicle intends to park into the target available parking space. The target parking manner is a parking manner for quickly entering the available parking space.

[0189] In a possible implementation, the target vehicle determination module 401 is used to, when the vehicle starts automatic parking and searches for a target parking space, divide the area around the target parking space into a parking space area and a lane area and determine whether there are other vehicles around the target parking space, wherein the parking space area is an area including parking spaces around the target parking space. When there are other vehicles around the target parking space and the other vehicles are in the lane area, it is determined that the target vehicle exists and the target vehicle is the other vehicle. When there are other vehicles around the target parking space and the other vehicles are in the parking space area, or when there are no other vehicles around the target parking space, it is determined that the target vehicle does not exist.

[0190] In a possible implementation, the target vehicle determination module 401 is used to obtain environmental information around the target available parking space when the vehicle starts automatic parking and searches for the target available parking space. Based on the environmental information, a local map around the target available parking space is generated, and the local map includes a parking space area and a lane area. Based on the environmental information, it is determined whether there are other vehicles around the target available parking space.

[0191] In a possible implementation, the target vehicle determination module 401 is used to perform map element recognition on the environmental information to obtain multiple map elements in the environmental information. Based on the multiple map elements and the relative position relationship between each map element, an initial local map around the target parking space is generated. Based on the element type of each map element, the parking space area and the lane area are marked in the initial local map to obtain a local map around the target parking space.

[0192] In a possible implementation, the target vehicle determination module 401 is used to extract features from the environmental information to obtain environmental information features of the environmental information, and perform target detection based on the environmental information features to determine whether there are other vehicles around the target parking space.

[0193] In a possible implementation, the parking intention determination module 402 is used to obtain the vehicle motion information and vehicle position of the target vehicle when the target vehicle exists, and the vehicle motion information includes the vehicle motion state and the vehicle motion direction. Based on the vehicle motion information, vehicle position of the target vehicle and the parking space information of the target parking space, it is determined whether the target vehicle has the parking intention to park in the target parking space, and the parking space information includes the parking space position and the parking space orientation.

[0194] In a possible implementation, the parking intention determination module 402 is used to determine the relative position relationship between the target vehicle and the target parking space based on the vehicle position of the target vehicle and the parking space position of the target parking space, wherein the relative position relationship includes a distance and a direction. Based on the vehicle motion information of the target vehicle, the relative position relationship and the parking space orientation, it is determined whether the target vehicle has a parking intention to park in the target parking space.

[0195] In a possible implementation, the parking intention determination module 402 is used to determine a parking parameter for the target vehicle to park in the target available parking space based on the vehicle motion information of the target vehicle, the relative position relationship, and the parking space orientation, wherein the parking parameter is used to indicate the size of the parking possibility. When the parking parameter is greater than or equal to a parking parameter threshold, it is determined that the target vehicle has a parking intention to park in the target available parking space. When the parking parameter is less than the parking parameter threshold, it is determined that the target vehicle does not have a parking intention to park in the target available parking space.

[0196] In a possible implementation, the parking control module 403 is configured to generate a first target parking path corresponding to the target parking method based on the vehicle position, vehicle orientation, and parking space information of the target parking space when the target vehicle intends to park in the target parking space, the parking space information including the parking space position and parking space orientation. Based on the first target parking path, control the vehicle to partially park in the target parking space.

[0197] In a possible implementation, the parking control module 403 is configured to generate a plurality of candidate parking paths based on the vehicle position, vehicle orientation, and the parking position and parking orientation of the target parking space, wherein different parking paths do not completely overlap, and determine the shortest parking path among the plurality of candidate parking paths as the first target parking path corresponding to the target parking method.

[0198] In a possible implementation, the parking control module 403 is used to control the vehicle to travel along the first target parking path and determine whether there is an obstacle ahead of the vehicle in the direction of travel. If there is an obstacle ahead of the vehicle in the direction of travel, determine whether the vehicle can avoid the obstacle. If the vehicle can avoid the obstacle, the first target parking path is corrected based on the obstacle information of the obstacle to obtain a reference parking path, and the obstacle information includes the obstacle position and obstacle size. Based on the reference parking path, the vehicle is controlled to partially park in the target parking space. If there is no obstacle ahead of the vehicle in the direction of travel, the vehicle is controlled to continue traveling along the first target parking path to partially park in the target parking space.

[0199] In a possible implementation manner, the parking control module 403 is further configured to control the vehicle to stop parking in the target available parking space and search for an available parking space again when the vehicle cannot avoid the obstacle.

[0200] In a possible implementation, the parking control module 403 is further configured to generate a second target parking path based on parking space information of the target parking space, the vehicle position, vehicle orientation, and parking assistance information of the vehicle when the vehicle is partially parked in the target parking space, the parking space information including the parking space position, parking space orientation, and parking space obstacle information, the parking assistance information including at least one of the driving and occupancy distribution information and trunk opening information, the trunk opening information being used to indicate whether the trunk needs to be opened after the vehicle completes parking. Based on the second target parking path, the vehicle is controlled to be fully parked in the target parking space.

[0201] In a possible implementation, the device further includes:

[0202] The parking space search module is used to start automatic parking and search for parking spaces when the vehicle enters the parking area. Based on the number of searched available parking spaces and the number of all searched parking spaces, or the duration of the parking space search, determine whether to enable the target parking mode. If the target parking mode is enabled, determine whether the target available parking space is found.

[0203] In a possible implementation, the parking space search module is used to determine that the target parking mode is enabled when the ratio between the number of searched available parking spaces and the number of searched total parking spaces is less than or equal to a preset ratio. When the ratio between the number of searched available parking spaces and the number of searched total parking spaces is greater than the preset ratio, determine that the target parking mode is not enabled. Alternatively, when the duration of the parking space search is greater than or equal to a preset duration, determine that the target parking mode is enabled. When the duration of the parking space search is less than the preset duration, determine that the target parking mode is not enabled.

[0204] It should be noted that: the automatic parking device provided in the above embodiment is only illustrated by the division of the above functional modules when performing automatic parking. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the automatic parking device provided in the above embodiment and the automatic parking method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0205] Through the technical solution provided by the embodiment of the present application, when the vehicle starts automatic parking and searches for the target parking space, it is determined whether there is a target vehicle that is not in the parking space around the target parking space, that is, it is determined whether there is a target vehicle that has not parked in the parking space around the target parking space, and the target vehicle is a vehicle that may park in the target parking space. In the case of the presence of the target vehicle, it is determined whether the target vehicle has the intention to park in the target parking space, that is, the probability of the target vehicle parking in the target parking space is further determined. In the case of the target vehicle having the intention to park in the target parking space, the vehicle is controlled to partially park in the target parking space in the target parking manner, that is, the vehicle quickly occupies the target parking space, thereby preventing the target parking space from being parked by other vehicles and improving the success rate of automatic parking.

[0206] The embodiment of the present application also provides a vehicle, Figure 5 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application.

[0207] Typically, the vehicle 500 includes: one or more processors 501 and one or more memories 502 .

[0208] The processor 501 may include one or more processing cores, such as a 4-core processor, a 5-core processor, etc. The processor 501 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 501 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 501 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 501 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0209] The memory 502 may include one or more computer-readable storage media, which may be non-transitory. The memory 502 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 502 is used to store at least one computer program, which is used to be executed by the processor 501 to implement the automatic parking method provided in the method embodiment of the present application.

[0210] Those skilled in the art will understand that Figure 5 The structure shown in the figure does not constitute a limitation on the vehicle 500, and the vehicle 500 may include more or less components than those shown in the figure, or combine certain components, or adopt a different arrangement of components.

[0211] In addition, the device provided in the embodiments of the present application may specifically be a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute an automatic parking method provided in the above embodiments.

[0212] This embodiment also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement an automatic parking method provided in the above embodiment.

[0213] This embodiment also provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement an automatic parking method provided in the above embodiment.

[0214] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0215] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0216] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0217] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An automatic parking method, characterized in that: The method comprises: When the vehicle enters the parking area, turn on automatic parking and search for parking spaces; In the case where the ratio between the number of searched available parking spaces and the number of all searched parking spaces is less than or equal to a preset ratio, it is determined that the target parking mode is enabled; in the case where the ratio between the number of searched available parking spaces and the number of all searched parking spaces is greater than the preset ratio, it is determined that the target parking mode is not enabled, and the target parking mode is a parking mode that reduces the number of pre-adjustments to quickly occupy available parking spaces; or, in the case where the duration of the parking space search is greater than or equal to a preset duration, it is determined that the target parking mode is enabled; in the case where the duration of the parking space search is less than the preset duration, it is determined that the target parking mode is not enabled; When the target parking mode is enabled, determining whether a target parking space is found, the target parking space being an empty space where the vehicle can be parked; When the vehicle starts automatic parking and searches for a target parking space, determining whether there is a target vehicle that is not in the parking space around the target parking space; In the case where the target vehicle exists, determining whether the target vehicle has a parking intention to park in the target parking space; In a case where the target vehicle has a parking intention to park in the target parkable space, the vehicle is controlled to partially park in the target parkable space in a target parking manner.

2. The method according to claim 1, characterized in that When the vehicle starts automatic parking and searches for a target parking space, determining whether there is a target vehicle that is not in the parking space around the target parking space includes: When the vehicle starts automatic parking and searches for a target available parking space, the area around the target available parking space is divided into a parking space area and a lane area, and it is determined whether there are other vehicles around the target available parking space, wherein the parking space area is an area including parking spaces around the target available parking space; In a case where there are other vehicles around the target parking space and the other vehicles are in the lane area, determining that the target vehicle exists and the target vehicle is the other vehicle; In a case where there are other vehicles around the target parking space and the other vehicles are in the parking space area, or there are no other vehicles around the target parking space, it is determined that the target vehicle does not exist.

3. The method according to claim 2, characterized in that When the vehicle starts automatic parking and searches for a target parking space, dividing the area around the target parking space into a parking space area and a lane area and determining whether there are other vehicles around the target parking space includes: When the vehicle starts automatic parking and searches for a target available parking space, obtaining environmental information around the target available parking space; Based on the environmental information, a local map around the target parking space is generated, wherein the local map includes a parking space area and a lane area; Based on the environmental information, it is determined whether there are other vehicles around the target parking space.

4. The method according to claim 3, characterized in that The generating a local map around the target parking space based on the environmental information includes: Performing map element recognition on the environmental information to obtain a plurality of map elements in the environmental information; Based on the plurality of map elements and the relative positional relationship between the map elements, generating an initial local map around the target parking space; Based on the element type of each map element, a parking space area and a lane area are marked in the initial local map to obtain a local map around the target parking space.

5. The method according to claim 3, characterized in that: The determining, based on the environmental information, whether there are other vehicles around the target parking space includes: Extracting features from the environmental information to obtain environmental information features of the environmental information; Target detection is performed based on the environmental information features to determine whether there are other vehicles around the target parking space.

6. The method according to claim 1, characterized in that The step of determining whether the target vehicle has an intention to park in the target parking space when the target vehicle exists includes: In the case where the target vehicle exists, obtaining vehicle motion information and vehicle position of the target vehicle, wherein the vehicle motion information includes a vehicle motion state and a vehicle motion direction; Based on the vehicle motion information and vehicle position of the target vehicle and parking space information of the target parking space, it is determined whether the target vehicle has a parking intention to park in the target parking space, wherein the parking space information includes a parking space position and a parking space orientation.

7. The method according to claim 6, characterized in that The determining whether the target vehicle has a parking intention to park in the target parking space based on the vehicle motion information, the vehicle position and the parking space information of the target parking space includes: Based on the vehicle position of the target vehicle and the parking space position of the target parking space, determining a relative position relationship between the target vehicle and the target parking space, wherein the relative position relationship includes a distance and a direction; Based on the vehicle motion information of the target vehicle, the relative position relationship, and the parking space orientation, it is determined whether the target vehicle has a parking intention to park in the target parking space.

8. The method according to claim 7, characterized in that The determining whether the target vehicle has a parking intention to park in the target parking space based on the vehicle motion information of the target vehicle, the relative position relationship, and the parking space orientation includes: Determining a parking parameter for the target vehicle to park in the target parking space based on the vehicle motion information of the target vehicle, the relative position relationship, and the parking space orientation, wherein the parking parameter is used to indicate the size of the parking possibility; When the parking parameter is greater than or equal to a parking parameter threshold, determining that the target vehicle has a parking intention to park in the target parking space; When the parking parameter is less than the parking parameter threshold, it is determined that the target vehicle has no parking intention to park in the target parking space.

9. The method according to claim 1, characterized in that: When the target vehicle has a parking intention to park in the target parking space, controlling the vehicle to partially park in the target parking space in a target parking manner includes: If the target vehicle intends to park in the target available parking space, generating a first target parking path corresponding to the target parking method based on the vehicle position, vehicle orientation and parking space information of the target available parking space, wherein the parking space information includes a parking space position and a parking space orientation; Based on the first target parking path, the vehicle is controlled to be partially parked in the target parking space.

10. The method according to claim 9, characterized in that The step of generating a first target parking path corresponding to the target parking method based on the vehicle position, vehicle orientation and parking space information of the target parking space when the target vehicle intends to park in the target parking space includes: Based on the vehicle position, the vehicle orientation, and the parking position and parking orientation of the target parking space, a plurality of candidate parking paths are generated, wherein different parking paths do not completely overlap; The shortest parking path among the plurality of candidate parking paths is determined as a first target parking path corresponding to the target parking method.

11. The method according to claim 9, characterized in that The controlling the vehicle to partially park into the target parking space based on the first target parking path includes: Controlling the vehicle to travel according to the first target parking path and determining whether there is an obstacle ahead of the vehicle in the direction of travel; If there is an obstacle ahead of the vehicle in the driving direction, determine whether the vehicle can avoid the obstacle; if the vehicle can avoid the obstacle, perform path correction on the first target parking path based on obstacle information of the obstacle to obtain a reference parking path, wherein the obstacle information includes the position and size of the obstacle; and control the vehicle to partially park in the target parking space based on the reference parking path; When there is no obstacle ahead of the vehicle in the driving direction, the vehicle is controlled to continue driving along the first target parking path so as to partially park in the target parking space.

12. The method according to claim 11, characterized in that The method further comprises: In the case that the vehicle cannot avoid the obstacle, the vehicle is controlled to stop parking in the target parking space and to search for a parking space again.

13. The method according to claim 1, characterized in that After controlling the vehicle to partially park in the target parking space in a target parking manner when the target vehicle intends to park in the target parking space, the method further includes: generating a second target parking path based on parking space information of the target parkable space, the vehicle position, the vehicle orientation, and parking assistance information of the vehicle when the vehicle is partially parked in the target parkable space, the parking space information including the parking space position, the parking space orientation, and parking space obstacle information, the parking assistance information including at least one of driving and occupancy distribution information and trunk opening information, the trunk opening information being used to indicate whether the trunk needs to be opened after the vehicle completes parking; Based on the second target parking path, the vehicle is controlled to be completely parked in the target parking space.

14. A vehicle, characterized in that: The vehicle comprises: A memory for storing executable program codes; A processor, configured to call and run the executable program code from the memory, so that the vehicle executes the automatic parking method as described in any one of claims 1 to 13.

Images