Parking method, device, vehicle and storage medium

Abstract

The application provides a parking method and device, a vehicle and a storage medium. The method comprises: continuously acquiring information of a plurality of parked vehicles within a preset range of the vehicle when the vehicle is in a parking scene; determining a combined feature based on the information of the plurality of parked vehicles, and performing map construction according to the combined feature to obtain a target map, wherein the combined feature is used to indicate the positional relationship between the plurality of parked vehicles and the vehicle features of the plurality of parked vehicles; and performing parking based on the target map in response to a parking instruction. The application can determine the information of the plurality of parked vehicles in the parking lot where the vehicle is located to determine the combined feature for map construction, so that the combined feature for constructing the map is more stable, the target map is more accurate, and the accuracy of parking is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, and in particular, to a parking method and device, a vehicle, and a storage medium. BACKGROUND

[0002] With the rapid development of science and technology, automatic parking driving is increasingly used in daily life. In automatic parking, memory parking is one of the important functions, and map construction and positioning of a parking scene are indispensable steps in the memory parking function. Currently, the map construction and positioning technology in the parking scene is only applicable to parking scenes close to city centers and with relatively standardized management. The above technology makes the map construction and positioning of the parking scene less accurate under conditions such as no map provider support and invalidation of real-time dynamic measurement technology (GPS, etc.). How to improve the accuracy of map construction and positioning of the parking scene is a problem to be solved. SUMMARY

[0003] In view of this, the embodiments of the present application provide a parking method and device, an electronic device, and a storage medium to improve the above problems.

[0004] According to an aspect of the embodiments of the present application, a parking method is provided, applied to a vehicle, and the method comprises: continuously acquiring information of a plurality of parked vehicles within a preset range from the vehicle when the vehicle is in a parking scene; determining a combined feature based on the information of the plurality of parked vehicles, and performing map construction according to the combined feature to obtain a target map, wherein the combined feature is used to indicate a positional relationship between the plurality of parked vehicles and vehicle features of the plurality of parked vehicles; and performing parking based on the target map in response to a parking instruction.

[0005] According to an aspect of the embodiments of the present application, a parking device is provided, and the device comprises: a parked vehicle information acquisition module, configured to continuously acquire information of a plurality of parked vehicles within a preset range from the vehicle when the vehicle is in a parking scene; a target map construction module, configured to determine a combined feature based on the information of the plurality of parked vehicles, and perform map construction according to the combined feature to obtain a target map, wherein the combined feature is used to indicate a positional relationship between the plurality of parked vehicles and vehicle features of the plurality of parked vehicles; and a parking module, configured to perform parking based on the target map in response to a parking instruction.

[0006] According to an aspect of the embodiments of the present application, a vehicle is provided, comprising: a processor; a memory having computer readable instructions stored thereon, wherein the computer readable instructions are executed by the processor to implement the above parking method.

[0007] According to an aspect of the embodiments of the present application, a computer readable storage medium is provided, and the computer readable storage medium stores computer readable instructions. When the computer readable instructions are executed by a processor, the computer readable instructions implement the parking method as described above.

[0008] In the scheme of the present application, when the vehicle is in a parking scenario, the combined features for map construction are determined by continuously obtaining information of a plurality of parked vehicles within a preset range of the vehicle. In this way, the combined features indicating the positional relationship between the plurality of parked vehicles and the vehicle features of the plurality of parked vehicles can be determined according to the information of the plurality of parked vehicles, and then the vehicle can perform map construction according to the combined features to obtain a target map, and finally the vehicle can park according to the target map. The present application determines the combined features for target map construction by determining the information of the plurality of parked vehicles within the preset range of the vehicle, so that the information for constructing the map is more stable, avoiding the interference of the same vehicle changing position on the constructed map in extreme cases, and under the condition that real-time dynamic measurement fails and the parking scenario lacks effective fixed structures for extracting features, the vehicle can successfully park according to the constructed target map.

[0009] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0010] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application. It is apparent that the accompanying drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0011] Figure 1 is a flowchart of the parking method according to an embodiment of the present application.

[0012] Figure 2 is a flowchart of the specific steps of step 120 according to an embodiment of the present application.

[0013] Figure 3 is a flowchart of the specific steps of step 130 according to an embodiment of the present application.

[0014] Figure 4 is a flowchart of the specific steps after step 138 according to another embodiment of the present application.

[0015] Figure 5 is a block diagram of the parking device according to an embodiment of the present application.

[0016] Figure 6 is a hardware structure diagram of an electronic device according to an embodiment of the present application.

[0017] The specific embodiments have been shown and described in considerable detail in order to explain the present application and to enable one skilled in the art to practice the application. Therefore, to the extent there are any inconsistencies, contradictions or other discrepancies, they are intended to be specifically addressed by the teachings herein. DETAILED DESCRIPTION

[0018] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations may, however, be implemented in many different forms and should not be construed as limited to the examples set forth herein; rather, these implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the example implementations to those skilled in the art. Like reference numerals may refer to like elements throughout the description of the figures.

[0019] It should be noted that the terms "first", "second", and the like, used in the description and the claims of the present application as well as above-mentioned drawings of the application, are used to distinguish similar objects and are not necessarily used to describe a specific sequential or chronological order. It should be understood that the use of these terms is arbitrary and made solely for the sake of ease of description and that the scope of the application is not limited to a given order of steps described herein. Further, use of the terms "include," "have," and "comprise" and variations thereof, are intended to be inclusive and are used to indicate that the item being described may include additional items not specifically recited. Further, the term "comprise" is used in the sense of include, and should not be used in the sense of consist or consist essentially.

[0020] Further, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the technology can be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, devices, implementations, and operations have not been shown or described in detail to avoid obscuring aspects of the application.

[0021] The block diagrams shown in the drawings are merely functional entities and do not necessarily have to correspond to physically independent entities. That is, the functional entities can be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices. The flowcharts shown in the drawings are merely exemplary and do not necessarily include all contents and operations / steps, nor are they necessarily executed in the order described. For example, some operations / steps can be further divided, and some operations / steps can be combined or partially combined, so that the actual execution order can be changed according to actual conditions.

[0022] Please refer to Figure 1 , Figure 1 A parking method provided by an embodiment of the present application is shown, in a specific embodiment, the parking method can be applied to a parking device 400 as shown in Figure 5 and a vehicle 500 configured with the parking device 400. Figure 6 The specific flow of the embodiment will be described below, of course, it can be understood that the method can also be executed by an electronic device with computing processing capability, such as a desktop computer, a notebook computer, a vehicle terminal, a terminal device such as a car machine large screen, the method can also be executed by a processing system including a server and a terminal; the method can also be performed by a domain controller. The flow shown in Figure 1 will be described in detail below, the parking method can specifically include the following steps:

[0023] Step 110, when the vehicle is in a parking scene, continuously acquiring information of a plurality of parked vehicles within a preset range of the vehicle.

[0024] As one way, when the vehicle enters a parking area (i.e. the vehicle is in a parking scene), the information of a plurality of parked vehicles within a preset range of the vehicle can be collected by the image collection device of the vehicle. Optionally, whether the vehicle is in a parking scene can be determined by the current position information of the vehicle. For example, when the current position information of the vehicle is located at a preset distance from the entrance of a parking lot, it can be determined that the vehicle is in a parking scene. Optionally, whether the vehicle is in a parking scene can also be determined according to the image collected by the image collection device of the vehicle. For example, whether there is parking lot corresponding identification information in the image collected by the image collection device can be determined, if there is, it is determined that the vehicle is in a parking scene.

[0025] As a manner, the vehicle continuously moves to find a parking space in a parking scenario, and information of a plurality of parked vehicles within a preset range of the vehicle is continuously collected in the process, so as to facilitate map construction according to the information of the plurality of parked vehicles. Alternatively, the information of the plurality of parked vehicles within the preset range of the vehicle can be continuously acquired by an information acquisition device. The information acquisition device can be a radar detector, a driving recorder, a camera, or the like of the vehicle. Alternatively, the information of all vehicles within the effective detection range of the vehicle can be continuously detected by the radar detector of the vehicle.

[0026] As a manner, when the vehicle is in a parking scenario, the vehicle can continuously acquire information of a plurality of parked vehicles within a preset range of the vehicle in response to a mapping request. The mapping request can be a request generated in response to the user selecting an automatic parking function on a large screen of a vehicle machine or an electronic device in communication connection with the vehicle. Alternatively, when the user controls the vehicle to enter a parking lot, the user can select to start the automatic parking function of the vehicle by touch, click, or drag operation, and map construction of the parking scenario is an indispensable step of the automatic parking function. When the user selects to start the automatic parking function, the vehicle generates a mapping request correspondingly, and sends the mapping request to a main control system of the vehicle. The main control system of the vehicle continuously acquires information of a plurality of parked vehicles within a preset range of the vehicle based on the mapping request after receiving the mapping request, and then constructs a map according to the acquired information.

[0027] In step 120, a combined feature is determined based on the information of the plurality of parked vehicles, and a map is constructed according to the combined feature to obtain a target map. The combined feature is used to indicate the positional relationship between the plurality of parked vehicles and the vehicle features of the plurality of parked vehicles.

[0028] As a manner, after the information of the plurality of parked vehicles within the preset range of the vehicle is acquired, based on the characteristic that most vehicles are continuously arranged in a parking scenario, a plurality of continuously arranged vehicles can be selected by using the idea of a sliding window, and a combined feature is determined according to the information of all parked vehicles in the window.

[0029] In some embodiments, the information of the plurality of parked vehicles at least includes a feature map of the plurality of parked vehicles abstracted by a neural network model, vehicle type information of the plurality of parked vehicles, orientation information of the plurality of parked vehicles, and angle information between the plurality of parked vehicles; and a feature descriptor of the combined feature includes a long vector spliced from the feature map of the plurality of parked vehicles, and the vehicle type of the plurality of parked vehicles, the orientation information of the plurality of parked vehicles, and the angle information between the plurality of parked vehicles.

[0030] Optionally, the neural network can be an identification neural network for identifying the feature map according to the images of the plurality of parked vehicles collected by the image collection device of the vehicle. Optionally, the identification neural network can be composed of any one or more of a convolutional neuron, a recurrent neuron, a long short-term memory neuron, and a feedforward neuron.

[0031] In some other embodiments, the plurality of parked vehicles are a plurality of continuously arranged parked vehicles, a plurality of parked vehicles arranged with special structures in between, or a plurality of parked vehicles arranged with empty parking spaces in between; the information of the plurality of parked vehicles further comprises special structure information between the plurality of parked vehicles and / or empty parking space information between the plurality of parked vehicles; and the feature descriptor of the combined feature further comprises the special structure information between the plurality of parked vehicles and / or the empty parking space information between the plurality of parked vehicles.

[0032] In some other embodiments, the information of the plurality of parked vehicles comprises image information of the plurality of parked vehicles; and the image feature descriptor of the combined feature comprises the image information of the plurality of parked vehicles.

[0033] Optionally, the combined feature can be determined by extracting reference vehicles in the sliding window, performing feature extraction on the images corresponding to the reference vehicles based on the vehicle detection model to obtain feature vectors corresponding to the reference vehicles respectively, and splicing the feature vectors corresponding to the reference vehicles respectively into a long vector as the feature descriptor of the combined feature; determining the vehicle types, vehicle orientations, and other information of the reference vehicles by identifying the images corresponding to the reference vehicles through the vehicle detection model, and adding the vehicle types, vehicle orientations, and other information of the reference vehicles to the feature descriptor of the combined feature as flag bits; determining the geometric relationship information between the reference vehicles by identifying the images corresponding to the reference vehicles through the vehicle detection model, and adding the geometric relationship information to the feature descriptor of the combined feature, wherein the geometric relationship information can be angle information between the reference vehicles; and additionally, the image feature descriptor or license plate information can be added to the feature descriptor of the combined feature by aligning the vehicles detected by the external parameter alignment radar detector and the vehicle information detected in the images of the other vehicles of the parking lot collected by the image collection device. Therefore, the combined feature determined according to the plurality of reference vehicles not only identifies the positional relationship between the plurality of reference vehicles, but also represents the specific features corresponding to the plurality of reference vehicles respectively.

[0034] As another way, when the radar detector detects that multiple parked vehicles within a preset range are not arranged continuously, i.e., there is no adjacent vehicle on both sides (front and back) of a vehicle, it indicates that the vehicle is adjacent to a special structure (wall, column) or a parking space (which indicates that the parking space is currently not parked with a vehicle); if adjacent to a special structure, the special structure is taken as part of the combined feature; if adjacent to a parking space, the parking space is recorded.

[0035] As a way, after the combined feature is determined, the parked vehicles are determined according to the combined feature to form a size-specific road sign, and a two-dimensional parking map is established according to the continuous road sign positions. The two-dimensional parking map can be determined as the target map. Optionally, the road sign information, route indication information, and special structure (wall, column, etc.) of the parking lot where the vehicle is located can also be added to the combined feature as a combined feature, and then the target map is established according to the combined feature, so that the target map is more accurate. Optionally, an initial map can be determined according to the special structure in the combined feature and the driving information of the vehicle, which is a rough map of the parking lot, and then the target map is obtained by matching and adding the information of each parking space in the combined feature and the driving information of the vehicle.

[0036] Optionally, the position of the ego vehicle in the map can also be updated based on the relationship between the vehicle road sign that has been constructed and the road sign detected by the ego vehicle driving to a new position, and the map road sign element is updated, so as to update the target map.

[0037] In some embodiments, as shown in FIG. 1, step 120 includes: Figure 2

[0038] Step 121, determining attribute information of a road sign of the target map according to the combined feature, the road sign corresponding to the multiple parked vehicles in the parking scene.

[0039] As a way, since the combined feature is determined according to the information of the multiple parked vehicles collected by the vehicle, the attribute information of the multiple parked vehicles can be determined according to the combined feature. Optionally, the attribute information of the road sign can be information about whether there is an empty parking space between the multiple parked vehicles, as well as orientation information of the multiple parked vehicles, geometric relationship information between the multiple parked vehicles, etc., or information about whether the multiple parked vehicles are adjacent to a special structure. The attribute information of the road sign can be set according to actual needs, which is not limited here.

[0040] Step 122, determining size information of the road sign according to the size information of the multiple parked vehicles, and constructing the target map according to the attribute information of the road sign and the size information of the road sign.

[0041] ​As a manner, the vehicle can recognize images of multiple parked vehicles collected by the vehicle to determine size information of the multiple parked vehicles, and then determine size information of the road sign according to the size information of the multiple parked vehicles.

[0042] Optionally, a map scale of the target map can be determined in advance, and then the size information of the road sign is proportionally reduced according to the map scale, so that the road sign in the target map is more consistent with the actual situation.

[0043] Please continue to refer to Figure 1 , step 130, in response to the parking instruction, parking is performed based on the target map.

[0044] As a manner, after the target map is determined, the current position of the vehicle can be used to query an empty parking space in the target map, and then the vehicle is controlled to park according to the position information of the empty parking space.

[0045] In the embodiments of the present application, when the vehicle is in a parking scene, the combined features for map construction are determined by continuously acquiring information of multiple parked vehicles within a preset range of the vehicle, so that the position relationship between the multiple parked vehicles and the combined features of the vehicle features of the multiple parked vehicles can be determined according to the information of the multiple parked vehicles, and then the vehicle can construct a target map according to the combined features, and finally the vehicle can park according to the target map. The present application determines the information of the multiple parked vehicles within the preset range of the vehicle to determine the combined features for constructing the target map, so that the information for constructing the map is more stable, avoiding the interference of the same vehicle changing position on the constructed map in extreme cases, and under the condition that real-time dynamic measurement fails and the parking scene lacks effective fixed structures for extracting features, the vehicle can successfully park according to the constructed target map.

[0046] In some embodiments, as shown in Figure 3 , step 130 includes:

[0047] Step 131, in response to the parking instruction, determining the current position of the vehicle.

[0048] As a manner, the parking instruction can be a parking instruction triggered by the control system of the vehicle after determining that the target map has been constructed. Optionally, the parking instruction can also be a parking instruction generated by the main control system of the vehicle according to the user's selection after the user selects a position in the target map that he wants to park in. Optionally, the parking instruction can be a parking instruction generated by the user after selecting a parking space that he wants to park in. Optionally, the parking instruction can also be an instruction triggered by the main control system of the vehicle when the automatic parking function of the vehicle is in an open state after obtaining the target map.

[0049] As a way, the current position of the vehicle can be determined by acquiring information of a plurality of parked vehicles around the current position of the vehicle, and then matching the information of the plurality of parked vehicles around the current position of the vehicle with the combined features in the target map.

[0050] In step 132, a target parking space is determined based on the current position and the target map; the target parking space is the closest empty parking space to the current position marked on the target map.

[0051] As a way, when the vehicle reaches the best drop-off position of the driver or the passenger, the target parking space closest to the vehicle is searched in the target map according to the current position information of the vehicle, wherein the target parking space indicates a parking space determined to be empty during the construction of the target map. Optionally, during the construction of the target map, the parking spaces can be marked in advance, and then the closest mark is determined in the target map according to the current position information of the vehicle, and the target parking space is determined based on the mark.

[0052] As another way, when it is determined that there is a parking space around the vehicle, the parking space can be marked first, and when the vehicle reaches the best drop-off position of the driver or the passenger, the vehicle enters the automatic parking or assisted parking mode, and the mark of the parking space is searched back in the map within the range of the constructed map, and then parking is performed. Optionally, the control information of the vehicle can be the wheel speed information, the driving route information, and the driving speed information of the vehicle, and then the driving path of the vehicle is determined based on the information, and then the parking space is marked on the driving path, so that the parking space can be clearly displayed during the subsequent construction of the target map, and the parking space is determined as the target parking space.

[0053] In some embodiments, after step 131, the method further comprises: determining the current position information of the target vehicle, determining whether there is a reference vehicle in the target map based on the current position information; if it is determined that there is a reference vehicle and the number of the reference vehicles is greater than or equal to a number threshold, determining the positional relationship between the plurality of reference vehicles in the target map; if it is determined that there are at least two target vehicles with a distance greater than a first distance threshold in the reference vehicles according to the positional relationship, determining the parking space between the at least two target vehicles as the target parking space; and parking according to the target parking space.

[0054] As a manner, the reference vehicle refers to the vehicle parked in series, and the reference vehicle is determined by using the feature that the vehicles are adjacent in the parking scene, and the vehicle parked in series is taken as the reference vehicle in the vehicle parked in the parking lot. Optionally, the reference vehicle is taken as the information with real scale, and then whether the parking space exists is determined by using the information, so that the determination of the parking space is more accurate.

[0055] As a manner, the quantity threshold indicates the saturation degree of the parked vehicles in the parking lot in a certain area range, and when the number of the parked vehicles in the parking lot in a certain area range is greater than or equal to the quantity threshold, it is determined that the parked vehicles in the current parking lot are more, and then the positional relationship between the multiple reference vehicles is determined to determine whether the parking space exists.

[0056] Optionally, the positional relationship between the multiple reference vehicles can include the distance relationship between the multiple vehicles, and whether the parking space exists between the multiple reference vehicles is determined by using the distance relationship.

[0057] As a manner, when it is determined according to the positional relationship that at least two target vehicles exist in the reference vehicles and the distance between the target vehicles is greater than a first distance threshold, it is determined that an area in which no vehicle is parked exists between the two target vehicles, and then the area in which no vehicle is parked is taken as the target parking space. Optionally, the positional relationship further indicates that the area size of the area between the at least two target vehicles in the reference vehicles is greater than a preset area size, and the preset area size indicates that the vehicle can be safely parked.

[0058] In some embodiments, the method further includes: if it is determined that the reference vehicle exists and the number of the multiple reference vehicles is less than the quantity threshold, determining multiple parking spaces in the target map; and determining the parking space closest to the current position from the multiple parking spaces as the target parking space according to the current position.

[0059] As a manner, when it is determined that the reference vehicle exists and the number of the multiple reference vehicles is less than the quantity threshold, it is determined that the parked vehicles around the current position of the vehicle are not saturated, that is, the parked vehicles around the current position are less, and then it is determined that multiple parking spaces exist around the current position. In order to facilitate the user to park, the parking space closest to the current position of the vehicle is taken as the target parking space.

[0060] As a manner, when it is determined that the multiple parking spaces exist, the positional information of the parking space in which no vehicle is parked is determined by using the image corresponding to the current position collected by the vehicle, and then the distance between the parking space in which no vehicle is parked and the current position of the vehicle is calculated to determine the target parking space.

[0061] Step 133, controlling the vehicle to move to the target parking space.

[0062] As a way, the vehicle can be controlled to move to the target parking space by the automatic parking module of the vehicle. Alternatively, after determining the target parking space, the automatic parking module of the vehicle can plan a route according to the current position of the vehicle and the position of the target parking space, so as to determine the moving route of the vehicle, and then control the vehicle to move to the target parking space according to the moving route.

[0063] Step 134, during the movement of the vehicle to the target parking space, information of a plurality of parked vehicles within a preset range from the vehicle is acquired.

[0064] As a way, since there may be a situation that the vehicle is parked when the target map is constructed, but the vehicle has now left during the movement of the vehicle, it is necessary to acquire the information of a plurality of parked vehicles around the vehicle when the vehicle moves to the target parking space.

[0065] Step 135, determining whether the road mark corresponding to the plurality of parked vehicles in the parking scene changes according to the information of the plurality of parked vehicles and attribute information of the road mark within the preset range in the target map, the attribute information of the road mark being determined according to the combined features when the target map is constructed.

[0066] As a way, there may be a situation that the previously parked vehicle has now left the parking lot during the movement of the vehicle, at this time, the vehicle can directly stop in the parking space without parked vehicles, therefore, it is necessary to compare the information of the plurality of parked vehicles collected during the movement of the vehicle with the attribute information of the road mark in the target map, so as to determine whether the road mark changes. Alternatively, the attribute information of the road mark in the target map can be the positional relationship between the plurality of vehicles, the license plate information of the plurality of vehicles, etc. Alternatively, the attribute information of the road mark can also be the lane line information of the parking space where the plurality of vehicles are respectively located, etc.

[0067] Step 136, if it is determined that the road mark changes, determining that an effective parking space is generated in the target map.

[0068] As a way, when it is determined that the information of the plurality of currently collected parked vehicles is different from the attribute information of the corresponding road mark in the target map, it can be determined that the road mark changes, that is, it can be determined that there is a discontinuous arrangement of vehicles between the plurality of currently collected parked vehicles, so as to determine that an effective parking space is generated in the target map. Alternatively, the effective parking space can be determined among the discontinuous arrangement of vehicles between the plurality of parked vehicles.

[0069] Step 137, parking according to the effective parking space, and updating the target map.

[0070] As a manner, when it is determined that the effective parking space is generated in the target map, in order to enable the user to park as soon as possible, the effective parking space is taken as the target parking space, so that the vehicle can be parked according to the target parking space. Alternatively, the position corresponding to the position where the effective parking space is determined can be determined according to the attribute information of the road sign in the target map and the information of the plurality of parked vehicles collected by the vehicle during movement, and then the driving route of the vehicle is re-planned according to the effective parking space and the current position of the vehicle, and then the vehicle is controlled to park according to the re-planned driving route, so as to enable the vehicle to park in the effective parking space.

[0071] As a manner, the target map can be updated according to the current position of the vehicle and the position of the effective parking space where the vehicle parks, so as to facilitate the user to drive out of the parking lot according to the updated target map.

[0072] In step 138, if it is determined that the road sign has not changed, the vehicle is controlled to continue moving to the target parking space.

[0073] As a manner, if it is determined that the road sign has not changed, it can be determined that there is no effective parking space at present, that is, the vehicle continues to drive according to the driving route planned according to the target parking space, so as to facilitate the vehicle to park in the target parking space. Alternatively, whether the road sign has changed can be determined according to whether the attribute information of the road sign in the target map is the same as the information of the plurality of parked vehicles collected by the vehicle during movement.

[0074] In some embodiments, as shown in Figure 4 After step 138, the method further includes:

[0075] In step 210, when the distance between the vehicle and the target parking space is not greater than a preset distance threshold, the information of a plurality of parked vehicles within a preset range from the vehicle is acquired.

[0076] As a manner, when the vehicle approaches the target parking space, it is necessary to determine whether the target parking space is currently a parking space, that is, it is necessary to determine in advance whether the target parking space is currently parked by a vehicle, so as to avoid the parking failure caused by the determination that the target parking space cannot be parked when the vehicle is ready to park. Alternatively, when the distance between the vehicle and the target parking space is not greater than a preset distance threshold (i.e. when the vehicle approaches the target parking space), the information of a plurality of parked vehicles within a preset range from the vehicle is acquired. Alternatively, the distance within the preset range from the vehicle can be the effective detection range of the detection device of the vehicle, or can be other self-defined range, which can be set according to actual needs, and is not limited here.

[0077] Step 220: Determine whether the target parking space is a parking space based on the information of the multiple parked vehicles.

[0078] Step 230: If the target parking space is a parking space available, park the car according to the target parking space.

[0079] As one approach, if the information of multiple parked vehicles corresponding to the target parking space collected by the current vehicle is found to be the same as the attribute information of the corresponding road sign in the target map, then the target parking space can be determined to be a parking space. At this time, the vehicle can be controlled to park according to the driving route with the target parking space as the destination, thereby parking the vehicle into the target parking space and completing the parking process.

[0080] Step 240: If the target parking space is not a parking space, update the target map according to the vehicle information parked in the target parking space, and redetermine the target parking space according to the updated target map, and control the vehicle to move to the redetermined target parking space.

[0081] As one approach, if the information of multiple parked vehicles corresponding to the target parking space collected by the current vehicle is different from the attribute information of the corresponding road sign in the target map, it can be determined that other vehicles are parked in the target parking space. In this case, the target parking space is a non-parking space.

[0082] Optionally, when different parking spaces are identified as target parking spaces, the target map is updated based on the information of multiple parked vehicles corresponding to the target parking space collected by the vehicle, and the current position of the vehicle is reacquired. Then, based on the current position of the vehicle, an available parking space is determined in the updated target map as the target parking space, and the vehicle is controlled to move towards the target parking space according to the newly determined target parking space. Optionally, during the process of the vehicle moving towards the new target parking space, step 131 and the steps after step 131 are repeated until the vehicle is parked.

[0083] In this embodiment, as the vehicle approaches the target parking space, information on multiple parked vehicles within a preset range is collected. This information is used to determine whether the target parking space is available. If the target parking space is available, the vehicle is controlled to park. If the target parking space is not available, the target map is updated, and a new target parking space is determined on the updated map to facilitate successful parking and improve the parking success rate.

[0084] Figure 5 This is a block diagram of a parking device according to an embodiment of this application, such as... Figure 5 As shown, the parking device 400 includes: a parking vehicle information acquisition module 410, a target map construction module 420, and a parking module 430.

[0085] The parking vehicle information acquisition module 410 is configured to continuously acquire information of a plurality of parked vehicles within a preset range of the vehicle when the vehicle is in a parking scene; the target map construction module 420 is configured to determine a combined feature based on the information of the plurality of parked vehicles, and construct a target map according to the combined feature, wherein the combined feature is used to indicate a positional relationship between the plurality of parked vehicles and vehicle features of the plurality of parked vehicles; and the parking module 430 is configured to perform parking based on the target map in response to a parking instruction.

[0086] In some embodiments, the information of the plurality of parked vehicles at least includes feature maps of the plurality of parked vehicles, vehicle type information of the plurality of parked vehicles, orientation information of the plurality of parked vehicles, and angle information between the plurality of parked vehicles; and the feature descriptor of the combined feature includes a long vector spliced from the feature maps of the plurality of parked vehicles, and the vehicle types of the plurality of parked vehicles, the orientation information of the plurality of parked vehicles, and the angle information between the plurality of parked vehicles.

[0087] In some embodiments, the plurality of parked vehicles are a plurality of continuously arranged parked vehicles, a plurality of parked vehicles arranged with special structures in between, or a plurality of parked vehicles arranged with empty parking spaces in between; the information of the plurality of parked vehicles further includes special structure information between the plurality of parked vehicles and / or empty parking space information between the plurality of parked vehicles; and the feature descriptor of the combined feature further includes the special structure information between the plurality of parked vehicles and / or the empty parking space information between the plurality of parked vehicles.

[0088] In some embodiments, the information of the plurality of parked vehicles includes image information of the plurality of parked vehicles; and the image feature descriptor of the combined feature includes the image information of the plurality of parked vehicles.

[0089] In some embodiments, the information of the plurality of parked vehicles includes license plate information of the plurality of parked vehicles; and the unified descriptor of the combined feature includes the license plate information of the plurality of parked vehicles.

[0090] In some embodiments, the target map construction module 420 includes an attribute information determination unit configured to determine attribute information of a road mark of the target map according to the combined feature, the road mark corresponding to the plurality of parked vehicles in the parking scene; and a target map construction unit configured to determine size information of the road mark according to size information of the plurality of parked vehicles, and construct the target map according to the attribute information of the road mark and the size information of the road mark.

[0091] In some embodiments, the parking module 430 comprises: a current position determining unit configured to determine a current position of the vehicle in response to a parking instruction; a target parking space determining unit configured to determine a target parking space based on the current position and the target map, the target parking space being an empty parking space closest to the current position in the target map; a first control unit configured to control the vehicle to move to the target parking space; a first acquisition unit configured to acquire information of a plurality of parked vehicles within a preset range of the vehicle during movement of the vehicle to the target parking space; a landmark determining unit configured to determine whether a landmark changes according to the information of the plurality of parked vehicles and attribute information of the landmark within the preset range in the target map, the landmark corresponding to the plurality of parked vehicles in a parking scenario, the attribute information of the landmark being determined according to the combined features when the target map is constructed; an effective parking space determining unit configured to determine an effective parking space in the target map if it is determined that the landmark changes; an updating unit configured to park according to the effective parking space and update the target map; and a second control unit configured to control the vehicle to continue moving to the target parking space if it is determined that the landmark does not change.

[0092] In some embodiments, the parking module 430 further comprises: a second acquisition unit configured to acquire information of a plurality of parked vehicles within a preset range of the vehicle when a distance between the vehicle and the target parking space is not greater than a preset distance threshold; a parking space determining unit configured to determine whether the target parking space is a parking space according to the information of the plurality of parked vehicles; a parking unit configured to park according to the target parking space if the target parking space is a parking space; and a third control unit configured to update the target map according to vehicle information of a vehicle parked in the target parking space if the target parking space is not a parking space, and to determine a target parking space again according to the updated target map and control the vehicle to move to the determined target parking space.

[0093] According to an aspect of some embodiments of the present application, a computer program product or computer program is provided, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method in any of the above embodiments.

[0094] According to an aspect of some embodiments of the present application, a vehicle is also provided, which comprises the above parking module 430. Figure 6As shown, the vehicle 500 includes a processor 510 and one or more memories 520 for storing program instructions for execution by the processor 510, which implements the object recognition method described above.

[0095] Further, the processor 510 can include one or more processing cores. The processor 510 runs or executes instructions, programs, code sets or instruction sets stored in the memory 520, and calls data stored in the memory 520. Alternatively, the processor 510 can be implemented in at least one of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 510 can be integrated with a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU is mainly used to process the operating system, user interface and application programs, etc.; the GPU is used to render and draw the display content; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor, but be realized by a separate communication chip.

[0096] According to an aspect of the present application, the present application also provides a computer readable storage medium, which can be included in the electronic device described in the above embodiments, or can exist separately and not be assembled into the electronic device. The above-mentioned computer readable storage medium carries computer readable instructions, which, when executed by the processor, realize the method in any of the above embodiments.

[0097] It should be noted that the computer readable medium shown in the embodiments of the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present application, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, or the like, or any suitable combination of the above.

[0098] The units described in the embodiments of the present application can be implemented in software, or in hardware, or in a combination of software and hardware. The units described can also be arranged in a processor. In some cases, the names of the units do not constitute a limitation on the units themselves.

[0099] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, such division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into a plurality of modules or units.

[0100] The computer program product of the present application can be a computer program product, which is a machine-readable medium (media) having exact sequences of instructions, program, code segments, or routines, written in any of a variety of languages. Such a machine-readable medium (media) is a tangible, non-transitory, storage medium that is non-transitory and tangible, such as a floppy diskette, a hard disk, a CD-ROM, a DVD, a memory stick, a memory card, a memory, a tape, a cassette, or the like, which is further analogous to the human brain or a computer processor (or the like), having the exact sequences of instructions, program, code segments, or routines, written in any of a variety of languages. Such a machine-readable medium (media) is a tangible, non-transitory, storage medium that is non-transitory and tangible, such as a floppy diskette, a hard disk, a CD-ROM, a DVD, a memory stick, a memory card, a memory, a tape, a cassette, or the like, which is further analogous to the human brain or a computer processor (or the like), having the exact sequences of instructions, program, code segments, or routines, written in any of a variety of languages. Note that the computer program product of the present application can be implemented using software, hardware, or a combination thereof.

[0101] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. It is intended that the present application cover any and all variations of the present application comprising modifications and / or additions of detail as long as such variations fall within the scope of the present application. It is intended that the scope of the present application be defined by the following claims and their equivalents.

[0102] It is to be understood that the application is not limited to the precise construction described and as shown in the accompanying drawings, and that various modifications and changes can be effected thereon without departing from the scope of the application. The scope of the application is to be limited only by the appended claims.

Claims

1. A parking method applied to a vehicle, characterized by, The method comprises: continuously acquiring information of a plurality of parked vehicles within a preset range of the vehicle when the vehicle is in a parking scene; determining a combined feature based on the information of the plurality of parked vehicles, wherein the combined feature is used to indicate a positional relationship between the plurality of parked vehicles and vehicle features of the plurality of parked vehicles; determining attribute information of a road sign corresponding to the plurality of parked vehicles in the parking scene according to the combined feature; determining size information of the road sign according to size information of the plurality of parked vehicles, and constructing a target map according to the attribute information of the road sign and the size information of the road sign; performing parking based on the target map in response to a parking instruction.

2. The method of claim 1, wherein, The information of the plurality of parked vehicles at least comprises feature maps of the plurality of parked vehicles, vehicle type information of the plurality of parked vehicles, orientation information of the plurality of parked vehicles, and angle information between the plurality of parked vehicles, which are abstracted by a neural network model. The feature descriptor of the combined feature comprises a long vector spliced from the feature maps of the plurality of parked vehicles, and the vehicle types of the plurality of parked vehicles, the orientation information of the plurality of parked vehicles, and the angle information between the plurality of parked vehicles.

3. The method of claim 1, wherein, The plurality of parked vehicles are a plurality of continuously arranged parked vehicles, a plurality of parked vehicles arranged with special structures in between, or a plurality of parked vehicles arranged with empty parking spaces in between; and the information of the plurality of parked vehicles further comprises special structure information between the plurality of parked vehicles and / or empty parking space information between the plurality of parked vehicles. The feature descriptor of the combined feature further comprises the special structure information between the plurality of parked vehicles and / or the empty parking space information between the plurality of parked vehicles.

4. The method of claim 1, wherein, The information of the plurality of parked vehicles comprises image information of the plurality of parked vehicles; and an image feature descriptor of the combined feature comprises the image information of the plurality of parked vehicles.

5. The method of claim 1, wherein, The information of the plurality of parked vehicles comprises license plate information of the plurality of parked vehicles; and a unified descriptor of the combined feature comprises the license plate information of the plurality of parked vehicles.

6. The method of claim 1, wherein performing parking based on the target map in response to a parking instruction comprises: determining a current position of the vehicle in response to a parking instruction; determining a target parking space based on the current position and the target map; the target parking space is an empty parking space closest to the current position marked on the target map; controlling the vehicle to move to the target parking space; acquiring information of a plurality of parked vehicles within a preset range of the vehicle during the movement of the vehicle to the target parking space; determining whether a road sign corresponding to the plurality of parked vehicles in the parking scene has changed according to the information of the plurality of parked vehicles and attribute information of the road sign within the preset range in the target map, the attribute information of the road sign being determined according to the combined feature when the target map is constructed; if it is determined that the road sign has changed, determining that an effective parking space is generated in the target map; performing parking according to the effective parking space, and updating the target map. If it is determined that the landmark has not changed, the vehicle is controlled to continue moving towards the target parking space. 7.The method of claim 6, after the vehicle is controlled to continue moving towards the target parking space, further comprising: obtaining information of a plurality of parked vehicles within a preset range of the vehicle when a distance between the vehicle and the target parking space is not greater than a preset distance threshold; determining whether the target parking space is a parking space based on the information of the plurality of parked vehicles; parking according to the target parking space if the target parking space is a parking space; updating the target map based on information of a vehicle parked in the target parking space if the target parking space is not a parking space, and determining a new target parking space based on the updated target map, and controlling the vehicle to move towards the new target parking space.

8. A parking device, characterized in that The apparatus comprises: a parked vehicle information obtaining module configured to continuously obtain information of a plurality of parked vehicles within a preset range of the vehicle when the vehicle is in a parking scenario; a target map constructing module configured to determine a combination feature based on the information of the plurality of parked vehicles, determine attribute information of a landmark based on the combination feature, the landmark corresponding to the plurality of parked vehicles in the parking scenario, determine size information of the landmark based on size information of the plurality of parked vehicles, and construct a target map based on the attribute information of the landmark and the size information of the landmark, wherein the combination feature is used to indicate a positional relationship between the plurality of parked vehicles and vehicle features of the plurality of parked vehicles; a parking module configured to park based on the target map in response to a parking instruction.

9. A vehicle characterized by comprising: The vehicle comprises: a processor; a memory having computer readable instructions stored thereon, the computer readable instructions being executed by the processor to implement the method of any one of claims 1 to 7.

10. A computer readable storage medium, characterized in that, The computer readable storage medium has program code stored therein, the program code being executable by the processor to implement the method of any one of claims 1 to 7.

Images