Positioning initialization method and device and electronic equipment

Abstract

The invention discloses a positioning initialization method and device and electronic equipment, and the method comprises the steps: screening out a plurality of rough matching maps from a plurality of initial maps based on a current positioning signal and pre-obtained positioning signals corresponding to the plurality of initial maps in response to a condition that a first star searching number is greater than a preset number threshold value; in response to the fact that the second star searching number is not larger than the number threshold value, screening out a plurality of maps to be finely matched from a plurality of rough matching maps based on the second position and positions of points on an underground parking lot map line of the plurality of rough matching maps obtained in advance; and determining a target precise matching map and an initial pose of the vehicle in the target precise matching map based on the current environment characteristics of the vehicle and the plurality of maps to be precisely matched. In the autonomous parking stage, the driving path of the vehicle entering the entrance of the underground parking lot to the map starting point does not need to be completely consistent with the driving path in the mapping stage.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a positioning initialization method, device and electronic equipment. Background Art

[0002] Home-zone Parking Assist (HPA) or Home-zone Parking Pilot (HPP) refers to a technology that can park the car in a designated parking space on behalf of the user in certain specific scenarios. Memory parking is a key technology for intelligent driving assistance and is also a popular research direction today. The HPA parking process is mainly divided into two stages, the route learning and mapping stage (hereinafter referred to as the mapping stage) and the route playback autonomous parking stage (hereinafter referred to as the parking stage). In the mapping stage, the vehicle learns, records and stores the starting position of the map, the parking location, the parking path, and the environmental feature map information during the driving process through its own sensors. In the parking stage, when the vehicle is near the starting point of the map again, it realizes repositioning (also called positioning initialization). After the user turns on the HPA function, the vehicle automatically drives to the designated parking space according to the learned path and completes the parking.

[0003] Positioning initialization is a very important step in memory parking technology. Only after completing positioning initialization and knowing the current vehicle's position and posture in the map (describing the position and posture of an object in a specified coordinate system, position: positioning in space, posture: orientation in space), can autonomous parking begin; the accuracy of positioning initialization will also affect the accuracy of positioning in the subsequent parking process, and even be the key factor in determining whether the vehicle can successfully park in the designated parking space.

[0004] In the related art, memory parking positioning initialization is achieved through a path matching method. The path matching method is to record the path of the vehicle from the entrance of the underground parking lot (the HPA function is mostly aimed at underground parking lots) to the starting point of the map, such as how many times the vehicle turns left and right. In the autonomous parking stage, if the vehicle's driving path is basically consistent with the path recorded during the learning map, it is considered to have arrived near the starting point of the map. The current real-time map is used to associate data with the map saved during the learning map stage, and the optimization target is constructed. The current vehicle's posture is calculated to complete the positioning initialization.

[0005] However, this path matching method requires that the driving path of the vehicle from the entrance of the underground parking lot to the starting point of the map (i.e. the starting point of the map building) during the autonomous parking phase must be completely consistent with the driving path during the map building phase, otherwise the path matching will fail. In order to improve the robustness of this method, it is sometimes required that only one route can be learned in an underground parking lot. Summary of the invention

[0006] The purpose of the embodiments of the present application is to provide a method, device and electronic device for positioning initialization, so as to solve the problem in the prior art that the driving path of a vehicle entering the entrance of an underground parking lot to reach the starting point of a map during the autonomous parking stage must be completely consistent with the driving path during the mapping stage, otherwise the path matching will fail.

[0007] In a first aspect, an embodiment of the present application provides a method for positioning initialization, including: Obtaining the first search satellite number and the current positioning signal when the vehicle travels to the first position; In response to the first search satellite number being greater than a preset number threshold, a plurality of rough matching maps are screened out from the plurality of initial maps based on the current positioning signal and pre-acquired positioning signals corresponding to the plurality of initial maps respectively; wherein a difference between the positioning signal corresponding to the rough matching map and the current positioning signal is less than a preset first signal threshold; Obtain the second satellite search number when the vehicle travels to the second position; In response to the second search star number being not greater than the quantity threshold, based on the second position and the positions of each point on the map route of the underground parking lot of the plurality of pre-acquired rough matching maps, a plurality of maps to be refined matching are screened out from the plurality of rough matching maps; wherein among the positions of each point on the map route of the map to be refined matching, there is a point position whose distance from the second position is less than a preset first distance threshold; Obtain the current environmental characteristics of the vehicle; Based on the current environmental characteristics of the vehicle and a plurality of maps to be precisely matched, a target precisely matched map and an initial position and posture of the vehicle in the target precisely matched map are determined.

[0008] In some embodiments, it also includes: In response to the second search star number being greater than a quantity threshold, a plurality of maps to be refined matching are screened out from the plurality of rough matching maps based on a current positioning signal and pre-acquired positioning signals corresponding to the plurality of rough matching maps respectively; wherein a difference between the positioning signal corresponding to the map to be refined matching and the current positioning signal is less than a preset second signal threshold; and the first signal threshold is greater than the second signal threshold.

[0009] In some embodiments, based on the current environmental features of the vehicle and a plurality of maps to be accurately matched, determining a target accurate matching map and an initial position of the vehicle in the target accurate matching map includes: Based on the current environmental features of the vehicle and the multiple maps to be refined, determine the position and posture of the vehicle in the multiple maps to be refined, and output multiple matching scores; If the matching score is greater than a preset threshold score, the to-be-refined matching map and the vehicle's position and posture in the to-be-refined matching map corresponding to the matching score greater than the threshold score are respectively determined as the target fine matching map and the initial position and posture of the vehicle in the target fine matching map.

[0010] In some embodiments, based on the current positioning signal and the pre-acquired positioning signals corresponding to the multiple initial maps, a plurality of coarse matching maps are screened out from the multiple initial maps, including: For each of the multiple positioning signals corresponding to the multiple initial maps, the following steps are performed: calculating the longitude difference between the longitude of the current positioning signal and the longitude of each positioning signal, and the latitude difference between the latitude of the current positioning signal and the latitude of each positioning signal; Based on the longitude difference and the latitude difference, determining whether the initial map is a rough matching map; If, among the positioning signals corresponding to the initial map, there are positioning signals whose longitude difference is less than a preset longitude threshold and whose latitude difference is less than a preset latitude threshold, the initial map is determined to be a coarse matching map; The first signal threshold includes: a longitude threshold and a latitude threshold.

[0011] In some embodiments, the method further includes: obtaining an initial map and a positioning signal corresponding to the initial map, including: From the start of the vehicle, obtain the third search satellite number and positioning signal of the vehicle at the current position; If the third search number is greater than the threshold, the positioning signal is recorded and saved; In response to a mapping instruction, a map of the ground parking lot is created with the current position of the vehicle as the starting point of the ground mapping, and the positioning signals of each point on the ground map route are saved; wherein the initial map includes: a map of the ground parking lot; the positioning signals corresponding to the initial map are the positioning signals on the route passed by the vehicle from the start of the vehicle to the end of the mapping.

[0012] In some embodiments, the method further includes: obtaining an initial map, a positioning signal corresponding to the initial map, and locations of each point on the underground parking lot map route, including: From the start of the vehicle, obtain the third search satellite number and positioning signal of the vehicle at the current position; If the third search number is greater than the threshold, the positioning signal is recorded and saved; When the number of satellites searched for the third time is not greater than the threshold value during the vehicle's movement, the vehicle's position at this moment is regarded as the entrance to the underground parking lot, and the recording of positioning signals is stopped; When a vehicle enters the underground parking lot from the entrance, in response to a mapping instruction, a map of the underground parking lot is created with the current position of the vehicle as the starting point of the underground mapping, and the position of each point on the underground parking lot map route relative to the starting point of the underground mapping is saved; wherein, the initial map includes: a map of the underground parking lot; the positioning signal corresponding to the initial map is: the positioning signal on the route passed by the vehicle from the start of the vehicle to when the third search number is not greater than the quantity threshold.

[0013] In some embodiments, each point on the underground parking lot map route includes an underground mapping starting point. Based on the second position and the positions of each point on the underground parking lot map route of the pre-acquired multiple rough matching maps, multiple maps to be refined matching are selected from the multiple rough matching maps, including: Obtaining the positions of the underground mapping starting points of multiple rough matching maps relative to the entrance of the underground parking lot; Based on the second position and the positions of the underground mapping starting points of the plurality of rough matching maps relative to the entrance of the underground parking lot, a plurality of maps to be refined matching are screened out from the plurality of rough matching maps.

[0014] In some embodiments, obtaining the positions of the underground mapping starting points of the plurality of coarse matching maps relative to the entrance of the underground parking lot includes: Obtain the vehicle's trajectory from the entrance of the underground parking lot to the starting point of underground mapping; Based on the trajectory before the starting point, the position of the underground mapping starting point relative to the entrance of the underground parking lot is obtained.

[0015] In some embodiments, based on the second position and the positions of each point on the underground parking lot map route of the pre-acquired multiple rough matching maps, multiple maps to be refined matching are selected from the multiple rough matching maps, including: The positions of the underground mapping starting points of the multiple rough matching maps relative to the underground parking entrance are obtained; and the positions of each point on the underground parking map line relative to the underground mapping starting point are obtained, and the positions of each point on the underground parking map line relative to the underground parking entrance are obtained through position conversion; Based on the second position and the position of each point on the underground parking lot map route relative to the underground parking lot entrance, a plurality of maps to be refined matching are screened out from the plurality of coarse matching maps.

[0016] In a second aspect, an embodiment of the present application provides a device for positioning initialization, including: A first acquisition module is configured to acquire a first search satellite number and a current positioning signal when the vehicle travels to a first position; The rough matching module is configured to, in response to the first search star number being greater than a preset number threshold, screen out a plurality of rough matching maps from the plurality of initial maps based on the current positioning signal and the pre-acquired positioning signals corresponding to the plurality of initial maps respectively; wherein, among the point positions on the map route of the map to be precisely matched, there is a point position whose distance to the second position is less than a preset first distance threshold; A second acquisition module is configured to acquire a second satellite search number when the vehicle travels to a second position; The first fine matching module is configured to, in response to the second search number being not greater than a quantity threshold, screen out a plurality of maps to be finely matched from a plurality of rough matching maps based on the second position and the positions of each point on the map route of the underground parking lot of the plurality of rough matching maps acquired in advance; wherein the distance between the second position and the positions of each point on the map route of the map to be finely matched is less than a preset first distance threshold; A third acquisition module is configured to acquire current environmental characteristics of the vehicle; The posture determination module is configured to determine a target precise matching map and an initial posture of the vehicle in the target precise matching map based on the current environmental characteristics of the vehicle and a plurality of maps to be precisely matched.

[0017] The method for positioning initialization provided in the embodiment of the present application, during the vehicle's movement, first uses the number of star searches to determine whether the vehicle is located above ground or underground, based on the current positioning signal and the pre-acquired positioning signals corresponding to the multiple initial maps, multiple rough matching maps are screened out from the multiple initial maps, and then it is determined whether the vehicle has reached the vicinity of the parking lot where the route has been learned, and then the number of star searches is used again to determine whether the vehicle is located above ground or underground, and based on the second number of star searches being no greater than the quantity threshold, it is determined that the vehicle has reached the underground parking lot, based on the second position and the positions of each point on the underground parking lot map route of the pre-acquired multiple rough matching maps, multiple maps to be finely matched are screened out from the multiple rough matching maps, and then it is determined whether the vehicle is near the underground parking lot map route. Only when the vehicle reaches the vicinity of the underground parking lot map route, map feature matching is started, and then positioning initialization can be performed at any position close to the underground parking lot map route, rather than only at the map construction starting point, thereby improving the user experience.

[0018] In the present application, during the parking phase, it is only necessary to compare the distance between the second position of the vehicle and the positions of each point on the map route. When there is a point position among the positions of each point on the map route whose distance from the second position is less than the preset first distance threshold, it proves that the vehicle has arrived near the map route, and then the positioning initialization can be performed. It can be seen from this that the positioning initialization completed using the method of the present invention does not depend on the starting point of the map, and does not focus on the driving trajectory of the vehicle arriving near the map route. The vehicle can complete the positioning initialization at any position close to the map route; therefore, the driving path of the vehicle entering the underground parking lot entrance to the starting point of the map does not have to be completely consistent with the driving path in the mapping phase, and there is no need to find the starting point of the map, as long as the vehicle arrives near the map route. For example, if the vehicle turns around in the underground parking lot, it is different from the driving path learned before, but as long as the vehicle arrives near the map route, the positioning initialization can be performed. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1A flowchart of a positioning initialization method according to an embodiment of the present application; Figure 2 A schematic block diagram of a positioning initialization method according to an embodiment of the present application; Figure 3 A schematic diagram of a rough matching process in the underground parking stage of an embodiment of the present application; Figure 4 A schematic diagram of a precise matching process in the underground parking stage of an embodiment of the present application; Figure 5a A schematic diagram of a ground parking lot mapping stage in an embodiment of the present application; Figure 5b A schematic diagram of an underground parking lot mapping stage in an embodiment of the present application; Figure 6 A schematic diagram of the structure of a positioning initialization device according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] Various aspects and features of the present application are described herein with reference to the accompanying drawings.

[0021] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but only as an example of an embodiment. Other modifications within the scope and spirit of the present application will occur to those skilled in the art.

[0022] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0023] These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0024] It should also be understood that although the present application has been described with reference to some specific examples, those skilled in the art will be able to readily implement many other equivalent forms of the present application.

[0025] The above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.

[0026] Specific embodiments of the present application are described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments applied for are merely examples of the present application, which may be implemented in a variety of ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that obscure the present application. Therefore, the specific structural and functional details applied for herein are not intended to be limiting, but merely serve as a basis and representative basis for the claims to teach those skilled in the art to use the present application in a variety of ways with substantially any suitable detailed structure.

[0027] This specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," all of which may refer to one or more of the same or different embodiments according to the present application.

[0028] See also Figure 2 ,HPA (Home-zone Parking Assist, memory parking technology) is divided into two stages, mapping stage and parking stage. Positioning initialization is also divided into these two stages (mapping stage and parking stage) for explanation.

[0029] In the map building stage, the initial map information is saved and the generated initial map (i.e. Figure 2 The land in Figure 1 ,land Figure 2 ,land Figure 3 , ..., map n) are added to the initial map list. Optionally, the initial map is a map that is pre-learned and stored based on the user's selection. For example, it can be the parking lot of the community where the user's home is located, the parking lot where the office is located, or the parking lot of the shopping mall or supermarket that the user often visits.

[0030] In the parking phase, in the first phase (coarse matching), the positioning signal is used to determine whether the vehicle has reached the vicinity of the parking lot where the route has been learned, and the initial map with successful coarse matching is selected from the initial map list, and the initial map with successful coarse matching is determined as the coarse matching map (i.e. Figure 2 Map i, map j, ..., map k) in are added to the coarse matching list.

[0031] In the parking stage, the second stage (fine matching) determines whether the vehicle has reached the vicinity of a certain map route based on the second position and the positions of each point on the underground parking lot map route of the pre-acquired multiple rough matching maps. If so, the target fine matching map and the initial position of the vehicle in the target fine matching map are obtained through the current environmental features of the vehicle (i.e., Figure 2 The target precise matching map and the initial position of the vehicle in the target precise matching map are added to the precise matching list to complete the positioning initialization.

[0032] like Figure 2 As shown, (i,j,...,k)∈[1,2,3,...,n]; (x,y)∈[i,j,...,k].

[0033] The method for initializing positioning provided in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0034] See also Figure 1 As shown, Figure 1 The present invention is a flowchart of a method for initializing positioning according to an embodiment of the present application. The present invention provides a method for initializing positioning according to an embodiment of the present application, including: S10, obtaining a first search satellite number and a current positioning signal when the vehicle travels to a first position; Exemplarily, the positioning signal can be a GPS signal, a Beidou satellite signal, etc. The number of satellites searched refers to the value of the satellites searched by the device. Generally, this value is greater than 0 outdoors, and the value of the GPS signal is correct; once you enter the underground or tunnel, the signal is blocked, and no satellite can be found, and the number of satellites searched is 0. For the convenience of description, the various embodiments of the present application are described below using the positioning signal as a GPS signal as an example.

[0035] S20, in response to the first search satellite number being greater than a preset number threshold, based on the current positioning signal and pre-acquired positioning signals corresponding to the multiple initial maps, screening out multiple coarse matching maps from the multiple initial maps; wherein the difference between the positioning signal corresponding to the coarse matching map and the current positioning signal is less than a preset first signal threshold; In some embodiments, there is at least one positioning signal in the positioning signals corresponding to the coarse matching map whose difference with the current positioning signal is less than a preset first signal threshold. Optionally, there are multiple positioning signals corresponding to the initial map. When there is at least one positioning signal whose difference with the current positioning signal is less than a preset first signal threshold, the initial map corresponding to the positioning signal is screened as the coarse matching map.

[0036] Exemplarily, the preset quantity threshold is 0. The positioning signal corresponding to the initial map refers to the positioning signal saved in the mapping stage, which may be a plurality of positioning signals, for example, 3000 GPS signals, 5000 GPS signals, etc. The number of GPS signals stored is different based on the size of the storage space.

[0037] Optionally, the positioning signals corresponding to the initial map may be stored as soon as the vehicle is started. When a certain number of positioning signals are stored, a first-in-first-out method may be used to store them, taking into account the size of the storage space, so that a fixed number of positioning signals are always stored in the storage space.

[0038] S30, obtaining a second satellite search number when the vehicle travels to a second position; Exemplarily, the number of satellite searches is obtained in real time from the time the vehicle is started to the time the vehicle is moving.

[0039] S40a, in response to the second search number being not greater than the quantity threshold, based on the second position and the positions of each point on the map route of the underground parking lot of the plurality of pre-acquired rough matching maps, a plurality of maps to be refined matching are screened out from the plurality of rough matching maps; wherein among the positions of each point on the map route of the maps to be refined matching, there is a point position whose distance from the second position is less than a preset first distance threshold; For example, if the second search number is not greater than a preset threshold, it can be determined that the vehicle has entered the underground parking lot for parking. Optionally, based on the second position and the positions of each point on the underground parking lot map routes of the rough matching maps, it can be determined whether there is a point on each map route that is close to the second position (the distance between the two is less than the first distance threshold), and if so, it proves that the vehicle is near the map route.

[0040] S50, obtaining the current environmental characteristics of the vehicle; Exemplarily, the current environment features may include point cloud features, semantic features, and the like.

[0041] S60: Determine a target precise matching map and an initial position and posture of the vehicle in the target precise matching map based on the current environmental characteristics of the vehicle and the multiple maps to be precisely matched.

[0042] Exemplarily, the initial map includes pre-acquired environmental features, so the coarse matching map and the map to be finely matched selected from the initial map also include environmental characteristics, such as point cloud features, semantic features, and the like.

[0043] In the present application, based on the current environmental characteristics of the vehicle and multiple maps to be precisely matched, a target precise matching map can be screened out from the multiple maps to be precisely matched, and the initial position of the vehicle in the target precise matching map can be determined to complete the positioning initialization of the vehicle memory parking.

[0044] The method for positioning initialization provided in the embodiment of the present application, during the vehicle's movement, first uses the number of star searches to determine whether the vehicle is located above ground or underground, based on the current positioning signal and the pre-acquired positioning signals corresponding to the multiple initial maps, multiple rough matching maps are screened out from the multiple initial maps, and then it is determined whether the vehicle has reached the vicinity of the parking lot where the route has been learned, and then the number of star searches is used again to determine whether the vehicle is located above ground or underground, and based on the second number of star searches being no greater than the quantity threshold, it is determined that the vehicle has reached the underground parking lot, based on the second position and the positions of each point on the underground parking lot map route of the pre-acquired multiple rough matching maps, multiple maps to be finely matched are screened out from the multiple rough matching maps, and then it is determined whether the vehicle is near the underground parking lot map route. Only when the vehicle reaches the vicinity of the underground parking lot map route, map feature matching is started, and then positioning initialization can be performed at any position close to the underground parking lot map route, rather than only at the map construction starting point, thereby improving the user experience.

[0045] In the present application, during the parking phase, it is only necessary to compare the distance between the second position of the vehicle and the positions of each point on the map route. When there is a point position among the positions of each point on the map route whose distance from the second position is less than the preset first distance threshold, it proves that the vehicle has arrived near the map route, and then the positioning initialization can be performed. It can be seen from this that the positioning initialization completed using the method of the present invention does not depend on the starting point of the map, and does not focus on the driving trajectory of the vehicle arriving near the map route. The vehicle can complete the positioning initialization at any position close to the map route; therefore, the driving path of the vehicle entering the underground parking lot entrance to the starting point of the map does not have to be completely consistent with the driving path in the mapping phase, and there is no need to find the starting point of the map, as long as the vehicle arrives near the map route. For example, if the vehicle turns around in the underground parking lot, it is different from the driving path learned before, but as long as the vehicle arrives near the map route, the positioning initialization can be performed.

[0046] In some embodiments, see Figure 1 As shown, when the second search number is greater than the threshold value, it indicates that the vehicle is located on the ground, and memory parking in the ground parking lot needs to be completed. The positioning initialization method further includes: S40b, in response to the second search star number being greater than a quantity threshold, based on the current positioning signal and pre-acquired positioning signals corresponding to the multiple rough matching maps, a plurality of maps to be refined matching are screened out from the multiple rough matching maps; wherein a difference between the positioning signal corresponding to the map to be refined matching and the current positioning signal is less than a preset second signal threshold; and the first signal threshold is greater than the second signal threshold.

[0047] The embodiment of the present application is aimed at the situation of ground parking lots. It uses the current positioning signal and the pre-acquired positioning signals corresponding to multiple rough matching maps, and further performs precision matching on multiple rough matching maps by setting the first signal threshold to be greater than the second signal threshold, so that the screened map to be precisely matched has a point position that is closer to the second position, that is, the current positioning signal and the pre-acquired positioning signals corresponding to multiple rough matching maps are used to determine whether the vehicle is infinitely close to the map route or on the map route. If so, subsequent positioning initialization is performed. In the present application, by retaining the positioning signal corresponding to the map during the mapping stage, memory parking is not limited to underground parking scenarios, but is also applicable to ground parking scenarios.

[0048] In some embodiments, based on the current positioning signal and the pre-acquired positioning signals corresponding to the multiple initial maps, a plurality of coarse matching maps are screened out from the multiple initial maps, including: For each of the multiple positioning signals corresponding to the multiple initial maps, the following steps are performed: calculating the longitude difference between the longitude of the current positioning signal and the longitude of each positioning signal, and the latitude difference between the latitude of the current positioning signal and the latitude of each positioning signal; Based on the longitude difference and the latitude difference, determining whether the initial map is a rough matching map; If, among the positioning signals corresponding to the initial map, there are positioning signals whose longitude difference is less than a preset longitude threshold and whose latitude difference is less than a preset latitude threshold, the initial map is determined to be a coarse matching map; wherein the first signal threshold includes: a longitude threshold and a latitude threshold.

[0049] Exemplarily, the positioning signal corresponding to an initial map may be a plurality of positioning signals, for example, may include a plurality of GPS signals, and the number of GPS signals may be determined according to a preset storage space size or based on calculation accuracy or based on user settings. For example, an initial map may correspond to 5000 GPS signals. The current GPS signal acquired needs to be compared with the 5000 GPS signals one by one in terms of longitude and latitude, and 5000 longitude differences and latitude differences are obtained respectively. If there is at least one (for example, as long as there is only one) longitude difference and latitude difference that meet the preset conditions, it is determined that the coarse match is successful, and the initial map is determined to be a coarse match map.

[0050] The process of making a difference between the current GPS signal and a GPS signal is as follows, wherein a GPS signal is recorded as a first GPS signal.

[0051] Specifically, the longitude of the current GPS signal is subtracted from the longitude of the first GPS signal to obtain a longitude difference; Subtract the latitude of the current GPS signal from the latitude of the first GPS signal to obtain a latitude difference; When the longitude difference is smaller than a preset longitude threshold, and the latitude difference is smaller than a preset latitude threshold, the initial map corresponding to the first GPS signal is determined as a coarse matching map.

[0052] The following takes underground parking scene parking as an example to illustrate the positioning initialization method provided by this application.

[0053] In a specific embodiment, see Figure 3 , Figure 3 This is a schematic diagram of a rough matching process for an underground parking scenario in an embodiment of the present application. First, a rough matching list is set to store a rough matching map of successful rough matching. The rough matching list is initially empty.

[0054] After the vehicle is started, determine whether the first star search number (current GPS star search number) is greater than 0 (preset number threshold). If the first star search number is greater than 0, clear the rough match list and recalculate. For example, determine whether the first star search number (current GPS star search number) is greater than 0. If it is greater than 0, calculate the difference between the vehicle's current positioning signal and the positioning signals corresponding to multiple initial maps. If the difference is less than the first signal threshold, the rough match is successful, and the rough match map is added to the rough match list; the next moment, determine again whether the first star search number (current GPS star search number) is greater than 0. If the first star search number is still greater than 0, clear the rough match list and recalculate. Repeat the above process until the first star search number is equal to 0, and retain the saved rough match list.

[0055] See also Figure 4 As shown, Figure 4 The following is a flow chart of an underground parking scene precision matching process of an embodiment of the present application. First, a precision matching list is set to store a target precision matching map with successful precision matching and the initial position of the current vehicle in the target precision matching map. The precision matching list is initially empty.

[0056] When the vehicle is moving, when the first star search number is equal to 0, determine whether the coarse matching list is empty. If so, the positioning initialization fails and exits; otherwise, continue to determine whether the second star search number (the current GPS star search number) is greater than 0. If the second star search number (the current GPS star search number) is equal to 0, it is determined that the current vehicle is underground, and all coarse matching maps in the coarse matching map list are traversed to calculate the distance between the current position of the vehicle and each point position on the map route of multiple coarse matching maps. If there is a point position on the map route of multiple coarse matching maps whose distance to the current position of the vehicle is less than the first distance threshold, the coarse matching map corresponding to the point position is screened as the map to be refined.

[0057] Based on the current environmental characteristics of the vehicle and the multiple maps to be finely matched, a target fine matching map and an initial position and posture of the vehicle in the target fine matching map are determined, and the target fine matching map and the initial position and posture of the vehicle in the target fine matching map are added to a fine matching list.

[0058] In some embodiments, based on the current environmental features of the vehicle and a plurality of maps to be accurately matched, determining a target accurate matching map and an initial position of the vehicle in the target accurate matching map includes: Based on the current environmental features of the vehicle and the multiple maps to be refined, determine the position and posture of the vehicle in the multiple maps to be refined, and output multiple matching scores; If the matching score is greater than a preset threshold score, the to-be-refined matching map and the vehicle's position and posture in the to-be-refined matching map corresponding to the matching score greater than the threshold score are respectively determined as the target fine matching map and the initial position and posture of the vehicle in the target fine matching map.

[0059] For example, the current environmental features of the vehicle may be detected by sensors, and then map feature matching may be performed based on the current environmental features of the vehicle and a plurality of maps to be matched accurately to calculate the position and posture of the current vehicle in the maps to be matched accurately.

[0060] The types of maps to be precisely matched may include point cloud maps, semantic maps, etc. Different map feature matching methods may be selected according to the types of maps to be precisely matched.

[0061] In one embodiment, the map to be precisely matched in the embodiment of the present application is a point cloud map, and the corresponding point cloud map feature matching algorithm may include ICP (Iterative Closest Point), NDT (Normal Distributions Transform), etc., which are all commonly used point cloud map feature matching algorithms. The point cloud map feature matching algorithm can output the position and posture of the current vehicle in the map to be precisely matched, and give a matching score. According to the matching score and the threshold score, it is judged whether the map feature matching is successful.

[0062] If the matching score is greater than the preset threshold score, the map feature is determined to be matched successfully, and the matching posture is recorded and used as the initial posture for positioning. The to-be-fine-matched map and the posture (matching posture) of the vehicle in the to-be-fine-matched map corresponding to the matching score greater than the threshold score are respectively determined as the target fine matching map and the initial posture (matching posture) of the vehicle in the target fine matching map, and the target fine matching map and the initial posture of the vehicle in the target fine matching map are added to the fine matching list.

[0063] The precise matching list is the result of positioning initialization, which outputs the target precise matching map and the initial position of the vehicle in the target precise matching map.

[0064] Exemplarily, the number of target precise matching maps is greater than or equal to 1, that is, the precise matching list may include at least one target precise matching map and the initial position of the vehicle in the corresponding target precise matching map.

[0065] If the number of target precise matching maps in the precise matching list is greater than 1, the user can independently select which target precise matching map to park according to.

[0066] The following describes the mapping process of the ground parking lot and the mapping process of the underground parking lot respectively: 1. The process of mapping the ground parking lot; In some embodiments, obtaining an initial map and a positioning signal corresponding to the initial map includes: From the start of the vehicle, obtain the third search satellite number and positioning signal of the vehicle at the current position; If the third search number is greater than the threshold, the positioning signal is recorded and saved; In response to a mapping instruction, a map of the ground parking lot is created with the current position of the vehicle as the starting point of the ground mapping, and the positioning signals of each point on the ground map route are saved; wherein the initial map includes: a map of the ground parking lot; the positioning signals corresponding to the initial map are the positioning signals on the route passed by the vehicle from the start of the vehicle to the end of the mapping.

[0067] In some embodiments, during the mapping stage of the ground parking lot, the positioning signal (GPS signal) is recorded and saved to a preset storage space from the start of the vehicle. Considering factors such as the storage space size, positioning efficiency, or human settings, the positioning signal in the preset storage space can be updated in a first-in-first-out manner.

[0068] like Figure 5aAs shown, the vehicle has been recording GPS signals since it was started until it receives a mapping instruction. The current position of the vehicle is used as the starting point of the ground mapping to create a map of the ground parking lot. The GPS signal recorded before the starting point of the mapping can be called the "GPS signal before the starting point", and the GPS signal recorded between the starting point and the end point of the mapping can be called the "map line GPS signal". The positioning signal corresponding to the initial map on the ground is the "GPS signal before the starting point" plus the "map line GPS signal", that is, for the creation of the ground parking lot, the GPS positioning signal must be recorded from the start of the vehicle to the end of the vehicle mapping. In summary, for each ground parking lot map, there is a "GPS signal before the starting point" plus a "map line GPS signal" corresponding to the ground parking lot map. Optionally, in addition to the above information, the created map also includes environmental features and other information, where environmental features such as point cloud features, semantic features, etc.

[0069] For a ground parking lot, the embodiment of the present application can complete positioning initialization based on any point on the map route between the mapping start point and the mapping end point.

[0070] (ii) The process of mapping underground parking lots; In some embodiments, obtaining the initial map, the positioning signal corresponding to the initial map, and the positions of each point on the underground parking lot map route includes: From the start of the vehicle, obtain the third search satellite number and positioning signal of the vehicle at the current position; If the third search star number is greater than the quantity threshold, recording and saving the positioning signal; When the number of satellites searched for the third time is not greater than the threshold value during the vehicle's movement, the vehicle's position at this moment is regarded as the entrance to the underground parking lot, and the recording of positioning signals is stopped; When a vehicle enters the underground parking lot from the entrance, in response to a mapping instruction, a map of the underground parking lot is created with the current position of the vehicle as the starting point of the underground mapping, and the position of each point on the underground parking lot map route relative to the starting point of the underground mapping is saved; wherein, the initial map includes: a map of the underground parking lot; the positioning signal corresponding to the initial map is: the positioning signal on the route passed by the vehicle from the start of the vehicle to when the third search number is not greater than the quantity threshold.

[0071] In some embodiments, Figure 5bAs shown in the figure, after the vehicle is started, when it is judged that the third search number is greater than 0, it means that the vehicle is on the ground at this time, and the positioning signal of the vehicle from the start to the stage when the third search number is greater than 0 is saved and recorded in real time. When the third search number is equal to 0, the position of the vehicle at this moment is regarded as the entrance of the underground parking lot, and the recording of positioning signals is stopped. The positioning signal of the vehicle before the entrance of the underground parking lot (before the third search number is 0) is called "GPS signal before the parking lot entrance" (see Figure 5b ).

[0072] When a vehicle enters the underground parking lot entrance, in response to a mapping instruction, a map of the underground parking lot is created with the current position of the vehicle as the underground mapping starting point, and the position and posture of each point on the underground parking lot map line relative to the underground mapping starting point are saved. Optionally, the vehicle's pre-starting trajectory from the underground parking lot entrance to the underground mapping starting point is also saved, that is, the position and posture of each point on the pre-starting trajectory relative to the underground parking lot entrance is saved.

[0073] In summary, for each underground parking map, there is a "GPS signal before the parking entrance", a trajectory before the starting point, and the position of each point on the underground parking map route relative to the underground map starting point corresponding to the underground parking map. Optionally, in addition to the above information, the created map also includes environmental features, such as point cloud features, semantic features, etc.

[0074] In the underground parking lot parking scenario, since the positions of each point on the underground parking lot map route of multiple rough matching maps include the positions of each point including the starting point of the map, the positioning initialization method provided by this application can complete the positioning initialization based on the starting point of the map, and can also complete the positioning initialization based on any point on the map. The following is an explanation of two situations: In the first case, positioning initialization is completed based on the starting point of mapping.

[0075] In some embodiments, each point on the underground parking lot map route includes an underground mapping starting point; Based on the second position and the positions of each point on the underground parking lot map route of the pre-acquired multiple rough matching maps, multiple maps to be refined matching are selected from the multiple rough matching maps, including: Obtaining the positions of the underground mapping starting points of multiple rough matching maps relative to the entrance of the underground parking lot; Based on the second position and the positions of the underground mapping starting points of the plurality of rough matching maps relative to the entrance of the underground parking lot, a plurality of maps to be refined matching are screened out from the plurality of rough matching maps.

[0076] In some embodiments, obtaining the positions of the underground mapping starting points of the plurality of coarse matching maps relative to the entrance of the underground parking lot includes: Obtain the vehicle's trajectory from the entrance of the underground parking lot to the starting point of underground mapping; Based on the trajectory before the starting point, the position of the underground mapping starting point relative to the entrance of the underground parking lot is obtained.

[0077] In some embodiments, since the trajectory of the vehicle from the underground parking lot entrance to the underground mapping starting point is saved during the underground parking lot mapping process, the position of the underground mapping starting point relative to the underground parking lot entrance can be obtained.

[0078] During the actual parking phase of the vehicle, the real-time position of the vehicle during the movement can be obtained, that is, the position of the second position relative to the entrance of the underground parking lot. That is, the starting point of the map and the second position are both relative to the entrance of the underground parking lot. By comparing whether the distance between the starting point of the map and the second position is less than the preset first distance threshold, it is determined whether the rough matching map corresponding to the starting point of the map can be screened as the map to be finely matched. After the map to be finely matched is screened in the above manner, the target fine matching map and the initial posture of the vehicle in the target fine matching map are determined.

[0079] The above method is suitable for when the vehicle just enters the parking lot and is very close to the starting point of mapping. The starting point of mapping can be found quickly. Since only the distance between the second position and the starting point of mapping needs to be calculated, the amount of calculation is small, the time for initialization positioning is short, the efficiency is high, and the user experience is good.

[0080] In the second case, positioning initialization is completed based on the position of any point on the map line.

[0081] In some embodiments, based on the second position and the positions of each point on the underground parking lot map route of the pre-acquired multiple rough matching maps, multiple maps to be refined matching are selected from the multiple rough matching maps, including: The positions of the underground mapping starting points of the multiple rough matching maps relative to the underground parking entrance are obtained; and the positions of each point on the underground parking map line relative to the underground mapping starting point are obtained, and the positions of each point on the underground parking map line relative to the underground parking entrance are obtained through position conversion; Based on the second position and the position of each point on the underground parking lot map route relative to the underground parking lot entrance, a plurality of maps to be refined matching are screened out from the plurality of coarse matching maps.

[0082] In one embodiment, the distances between the second position of the vehicle and all points P on the map route from the starting point to the end point of mapping are calculated to determine whether the vehicle is on the map route or infinitely close to the map route. If so, the map corresponding to the point P close to the second position is used as the map to be precisely matched.

[0083] The above method is applicable to the situation where the trajectory of the vehicle after entering the underground parking lot is different from the trajectory during the mapping, so the starting point of the mapping cannot be found quickly. At this time, any point position on the map route whose distance from the second position is less than the preset first distance threshold can be found, and then the positioning initialization can be completed based on the point position. That is, the positioning initialization method provided by the present application does not depend on the driving trajectory in the parking phase being the same as the driving trajectory in the mapping phase, nor does it depend on finding the starting point of the mapping. As long as the vehicle is close to any point on the map route (that is, there is a point position on the map route whose distance from the second position is less than the preset first distance threshold), the positioning initialization can be completed based on the arbitrary point. The parking application scenarios are increased and the user experience is improved.

[0084] Based on the same inventive concept, the present application embodiment provides a device for positioning initialization, see Figure 6 As shown, Figure 6 This is a schematic diagram of the structure of a positioning initialization device according to an embodiment of the present application. The positioning initialization device includes: The first acquisition module 10 is configured to acquire a first search satellite number and a current positioning signal when the vehicle travels to a first position; The rough matching module 20 is configured to select a plurality of rough matching maps from the plurality of initial maps based on the current positioning signal and the pre-acquired positioning signals respectively corresponding to the plurality of initial maps in response to the first search star number being greater than a preset number threshold; wherein the difference between the positioning signal corresponding to the rough matching map and the current positioning signal is less than a preset first signal threshold; The second acquisition module 30 is configured to acquire a second satellite search number when the vehicle travels to a second position; The first fine matching module 40a is configured to, in response to the second search number being not greater than a quantity threshold, screen out a plurality of maps to be finely matched from a plurality of rough matching maps based on the second position and the positions of each point on the map route of the underground parking lot of the plurality of rough matching maps acquired in advance; wherein, among the positions of each point on the map route of the map to be finely matched, there is a point position whose distance from the second position is less than a preset first distance threshold; The third acquisition module 50 is configured to acquire the current environmental characteristics of the vehicle; The posture determination module 60 is configured to determine a target precise matching map and an initial posture of the vehicle in the target precise matching map based on the current environmental characteristics of the vehicle and a plurality of maps to be precisely matched.

[0085] In some embodiments, the positioning initialization device further includes: The second fine matching module 40b is configured to, in response to the second search star number being greater than a quantity threshold, screen out a plurality of maps to be finely matched from a plurality of coarse matching maps based on a current positioning signal and pre-acquired positioning signals corresponding to a plurality of coarse matching maps, wherein a difference between a positioning signal corresponding to the map to be finely matched and the current positioning signal is less than a preset second signal threshold; and the first signal threshold is greater than the second signal threshold.

[0086] In some embodiments, the posture determination module 60 is specifically configured to: Based on the current environmental features of the vehicle and the multiple maps to be refined, determine the position and posture of the vehicle in the multiple maps to be refined, and output multiple matching scores; If the matching score is greater than a preset threshold score, the to-be-refined matching map and the vehicle's position and posture in the to-be-refined matching map corresponding to the matching score greater than the threshold score are respectively determined as the target fine matching map and the initial position and posture of the vehicle in the target fine matching map.

[0087] In some embodiments, the coarse matching module 20 is specifically configured as follows: For each of the multiple positioning signals corresponding to the multiple initial maps, the following steps are performed: calculating the longitude difference between the longitude of the current positioning signal and the longitude of each positioning signal, and the latitude difference between the latitude of the current positioning signal and the latitude of each positioning signal; Based on the longitude difference and the latitude difference, determining whether the initial map is a rough matching map; If, among the positioning signals corresponding to the initial map, there are positioning signals whose longitude difference is less than a preset longitude threshold and whose latitude difference is less than a preset latitude threshold, the initial map is determined to be a coarse matching map; The first signal threshold includes: a longitude threshold and a latitude threshold.

[0088] In some embodiments, the positioning initialization device further includes a first mapping module, and the first mapping module is configured to: From the start of the vehicle, obtain the third search satellite number and positioning signal of the vehicle at the current position; If the third search number is greater than the threshold, the positioning signal is recorded and saved; In response to a mapping instruction, a map of the ground parking lot is created with the current position of the vehicle as the starting point of the ground mapping, and the positioning signals of each point on the ground map route are saved; wherein the initial map includes: a map of the ground parking lot; the positioning signals corresponding to the initial map are the positioning signals on the route passed by the vehicle from the start of the vehicle to the end of the mapping.

[0089] In some embodiments, the positioning initialization device further includes a second mapping module, and the second mapping module is configured to: From the start of the vehicle, obtain the third search satellite number and positioning signal of the vehicle at the current position; If the third search number is greater than the threshold, the positioning signal is recorded and saved; When the number of satellites searched for the third time is not greater than the threshold value during the vehicle's movement, the vehicle's position at this moment is regarded as the entrance to the underground parking lot, and the recording of positioning signals is stopped; When a vehicle enters the underground parking lot from the entrance, in response to a mapping instruction, a map of the underground parking lot is created with the current position of the vehicle as the starting point of the underground mapping, and the position of each point on the underground parking lot map route relative to the starting point of the underground mapping is saved; wherein, the initial map includes: a map of the underground parking lot; the positioning signal corresponding to the initial map is: the positioning signal on the route passed by the vehicle from the start of the vehicle to when the third search number is not greater than the quantity threshold.

[0090] In some embodiments, the first fine matching module 40a is specifically configured as follows: Based on the second position and the positions of each point on the underground parking lot map route of the pre-acquired multiple rough matching maps, a plurality of maps to be refined matching are selected from the multiple rough matching maps, including: Obtaining the positions of the underground mapping starting points of multiple rough matching maps relative to the entrance of the underground parking lot; Based on the second position and the positions of the underground mapping starting points of the plurality of rough matching maps relative to the entrance of the underground parking lot, a plurality of maps to be refined matching are screened out from the plurality of rough matching maps.

[0091] In some embodiments, the first fine matching module 40a is further specifically configured as follows: Obtain the vehicle's trajectory from the entrance of the underground parking lot to the starting point of underground mapping; Based on the trajectory before the starting point, the position of the underground mapping starting point relative to the entrance of the underground parking lot is obtained.

[0092] In some embodiments, the first fine matching module 40a is further specifically configured as follows: The positions of the underground mapping starting points of the multiple rough matching maps relative to the underground parking entrance are obtained; and the positions of each point on the underground parking map line relative to the underground mapping starting point are obtained, and the positions of each point on the underground parking map line relative to the underground parking entrance are obtained through position conversion; Based on the second position and the position of each point on the underground parking lot map route relative to the underground parking lot entrance, a plurality of maps to be refined matching are screened out from the plurality of coarse matching maps.

[0093] The method of this application has the following beneficial effects: 1. The embodiment of the present application first uses GPS signals to determine whether the vehicle has arrived near a parking lot where the route has been learned. If it is a ground parking lot, the GPS signal is continued to be used to determine whether the vehicle is infinitely close to the map route or is located on the map route; if it is an underground parking lot, the current position of the vehicle and the positions of each point on the map route are used to determine whether the vehicle is infinitely close to the map route or is located on the map route. Map feature matching is only started when the vehicle arrives at or is near the map route, which significantly reduces the amount of calculation and improves positioning speed and accuracy.

[0094] 2. For underground parking scenarios, since it is only necessary to determine the current position of the vehicle and the positions of each point on the map route, a point position that is infinitely close to the current position of the vehicle can be found on the map route, thereby completing the positioning initialization based on the point position. Therefore, the trajectory of entering the underground parking lot when parking does not have to be completely consistent with that when building the map, and there is no need to find the starting point of the map, as long as the vehicle can walk to the vicinity of any point on the map route. Currently, many memory parking positioning initializations can only be completed at the starting point of the map, but the embodiments of the present application can also achieve positioning initialization at any point on the map route from the starting point to the end point of the map.

[0095] 3. Since the driving trajectory of the application during the parking phase does not have to be consistent with the trajectory during map building, and there is no need to find a starting point for map building, multiple different routes can be learned in the same parking lot at different times, or after learning a route, the user can continue to learn the second route without leaving the parking lot, which is more flexible and practical.

[0096] 4. By storing the positioning signal (GPS signal) corresponding to the map during the mapping stage, it can be applied to both ground parking lots and underground parking lots, without being limited to underground parking lots.

[0097] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a method as described in any of the above embodiments when executing the computer program.

[0098] An embodiment of the present application further provides a storage medium, wherein the storage medium carries one or more computer programs, and when the one or more computer programs are executed by a processor, the steps of the method described above are implemented.

[0099] An embodiment of the present application also provides a computer program product, including a computer program / instruction, which implements the steps of the above method when the computer program / instruction is executed by a processor.

[0100] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. A method for positioning initialization, characterized in that: include: Obtaining the first search satellite number and the current positioning signal when the vehicle travels to the first position; In response to the first search star number being greater than a preset number threshold, based on the current positioning signal and pre-acquired positioning signals corresponding to the multiple initial maps, a plurality of coarse matching maps are screened out from the multiple initial maps; wherein the difference between the positioning signal corresponding to the coarse matching map and the current positioning signal is less than a preset first signal threshold; Obtaining a second satellite search number when the vehicle travels to a second position; In response to the second search star number being not greater than the quantity threshold, based on the second position and the positions of each point on the map route of the underground parking lot of the plurality of pre-acquired rough matching maps, a plurality of maps to be refined matching are screened out from the plurality of rough matching maps; wherein among the positions of each point on the map route of the map to be refined matching, there is a point position whose distance from the second position is less than a preset first distance threshold; Acquiring current environmental characteristics of the vehicle; Based on the current environmental features of the vehicle and the plurality of maps to be finely matched, a target finely matched map and an initial position and posture of the vehicle in the target finely matched map are determined.

2. The method according to claim 1, characterized in that: Also includes: In response to the second search star number being greater than the quantity threshold, based on the current positioning signal and pre-acquired positioning signals corresponding to the multiple rough matching maps, a plurality of maps to be refined matching are screened out from the multiple rough matching maps; wherein the difference between the positioning signal corresponding to the map to be refined matching and the current positioning signal is less than a preset second signal threshold; and the first signal threshold is greater than the second signal threshold.

3. The method according to claim 1, characterized in that Determining a target precise matching map and an initial position of the vehicle in the target precise matching map based on the current environmental features of the vehicle and the plurality of maps to be precisely matched includes: Based on the current environmental features of the vehicle and the multiple maps to be refined, determine the position and posture of the vehicle in the multiple maps to be refined, and output multiple matching scores; If the matching score is greater than a preset threshold score, the to-be-refined matching map corresponding to the matching score greater than the threshold score and the position and posture of the vehicle in the to-be-refined matching map are respectively determined as the target fine matching map and the initial position and posture of the vehicle in the target fine matching map.

4. The method according to claim 1, characterized in that Based on the current positioning signal and the pre-acquired positioning signals corresponding to the multiple initial maps, a plurality of coarse matching maps are selected from the multiple initial maps, including: For each of the multiple positioning signals corresponding to the multiple initial maps, the following steps are performed: calculating a longitude difference between the longitude of the current positioning signal and the longitude of each positioning signal, and a latitude difference between the latitude of the current positioning signal and the latitude of each positioning signal; Based on the longitude difference and the latitude difference, determining whether the initial map is a rough matching map; If, among the positioning signals corresponding to the initial map, there are positioning signals whose longitude difference is less than a preset longitude threshold and whose latitude difference is less than a preset latitude threshold, then determining that the initial map is a coarse matching map; The first signal threshold includes: the longitude threshold and the latitude threshold.

5. The method according to claim 2, characterized in that: Acquiring an initial map and a positioning signal corresponding to the initial map, including: From the start of the vehicle, obtain the third search satellite number and positioning signal of the vehicle at the current position; If the third search star number is greater than the quantity threshold, recording and saving the positioning signal; In response to a mapping instruction, a map of the ground parking lot is created with the current position of the vehicle as the starting point of ground mapping, and the positioning signals of each point on the ground map route are saved; wherein the initial map includes: a map of the ground parking lot; and the positioning signals corresponding to the initial map are positioning signals on the route passed by the vehicle from the start of the vehicle to the end of mapping.

6. The method according to claim 1, characterized in that Obtaining an initial map, a positioning signal corresponding to the initial map, and locations of each point on the underground parking lot map route, including: From the start of the vehicle, obtain the third search satellite number and positioning signal of the vehicle at the current position; If the third search star number is greater than the quantity threshold, recording and saving the positioning signal; When the third number of satellite searches is not greater than the threshold value during the vehicle's movement, the vehicle's position at this moment is regarded as the entrance to the underground parking lot, and the recording of the positioning signal is stopped; When the vehicle enters the underground parking lot from the entrance, in response to the mapping instruction, a map of the underground parking lot is created with the current position of the vehicle as the starting point of the underground mapping, and the position of each point on the underground parking lot map route relative to the starting point of the underground mapping is saved; wherein, the initial map includes: the map of the underground parking lot; the positioning signal corresponding to the initial map is: the positioning signal on the route passed by the vehicle from the start of the vehicle to when the third search number is not greater than the quantity threshold.

7. The method according to claim 6, characterized in that Each point on the underground parking lot map route includes the underground map starting point; Based on the second position and the positions of each point on the underground parking lot map route of the pre-acquired multiple rough matching maps, a plurality of maps to be refined matching are selected from the multiple rough matching maps, including: Obtaining the positions of the underground mapping starting points of multiple rough matching maps relative to the entrance of the underground parking lot; Based on the second position and the positions of the underground mapping starting points of the plurality of rough matching maps relative to the entrance of the underground parking lot, a plurality of maps to be refined matching are screened out from the plurality of rough matching maps.

8. The method according to claim 7, characterized in that The positions of the underground mapping starting points of multiple rough matching maps relative to the entrance of the underground parking lot are obtained, including: Obtaining a trajectory of the vehicle from the entrance of the underground parking lot to the starting point of underground mapping; Based on the trajectory before the starting point, the position of the underground mapping starting point relative to the entrance of the underground parking lot is obtained.

9. The method according to claim 6, characterized in that Based on the second position and the positions of each point on the underground parking lot map route of the pre-acquired multiple rough matching maps, a plurality of maps to be refined matching are selected from the multiple rough matching maps, including: Obtaining the positions of the underground mapping starting points of the plurality of rough matching maps relative to the underground parking entrance; and the positions of each point on the underground parking map route relative to the underground mapping starting point, and obtaining the position of each point on the underground parking map route relative to the underground parking entrance through position conversion; Based on the second position and the position of each point on the underground parking lot map route relative to the underground parking lot entrance, a plurality of maps to be refined matched are screened out from the plurality of coarse matched maps.

10. A positioning initialization device, characterized in that: include: A first acquisition module is configured to acquire a first search satellite number and a current positioning signal when the vehicle travels to a first position; The coarse matching module is configured to, in response to the first search star number being greater than a preset number threshold, screen out a plurality of coarse matching maps from the plurality of initial maps based on a current positioning signal and pre-acquired positioning signals respectively corresponding to the plurality of initial maps; wherein a difference between the positioning signal corresponding to the coarse matching map and the current positioning signal is less than a preset first signal threshold; A second acquisition module is configured to acquire a second satellite search number when the vehicle travels to a second position; A first fine matching module is configured to, in response to the second search number being not greater than the quantity threshold, screen out a plurality of maps to be finely matched from the plurality of rough matching maps based on the second position and the positions of each point on the map route of the underground parking lot of the plurality of rough matching maps acquired in advance; wherein among the positions of each point on the map route of the plurality of maps to be finely matched, there is a point position whose distance from the second position is less than a preset first distance threshold; A third acquisition module is configured to acquire current environmental characteristics of the vehicle; The posture determination module is configured to determine a target precise matching map and an initial posture of the vehicle in the target precise matching map based on the current environmental characteristics of the vehicle and the plurality of maps to be precisely matched.

Images