Map proximity element query method and device, intelligent vehicle, and storage medium

Abstract

The application provides a map proximity element query method, device, intelligent vehicle and storage medium. The query method comprises the following steps: acquiring a high-precision map of an area where a vehicle is located, dividing road data of the high-precision map into multiple zone layers, and establishing a KD-tree according to a topological relationship between the multiple zone layers; acquiring a current latitude and longitude of the vehicle, and retrieving m to-be-confirmed zone layers adjacent to the current latitude and longitude in the KD-tree according to the current latitude and longitude; when m>1, acquiring multiple historical latitudes and longitudes of the vehicle, and screening and determining a current zone layer from the m to-be-confirmed zone layers according to the multiple historical latitudes and longitudes, wherein the current zone layer comprises n lane layers; and when n>1, screening and determining a current lane layer from the n lane layers according to the multiple historical latitudes and longitudes. The application solves the problem that the technical solution in the related art cannot inhibit the interference of overlapping high-precision map elements in a multi-layer geographic scene, and provides a proximity element query near a vehicle coordinate in a high-precision map according to the latitude and longitude coordinates of the vehicle.

Description

Technical Field

[0001] This invention relates to the field of map navigation and data processing technology, and more specifically, to a method, apparatus, intelligent vehicle, and storage medium for querying nearby elements on a map. Background Technology

[0002] High-precision maps are a key component for achieving autonomous driving. As an effective supplement to onboard sensors, they provide vehicles with more reliable perception capabilities and a larger spatial scale. While utilizing high-precision maps to provide driving assistance information such as road data with centimeter-level accuracy and data on fixed objects around lanes, how to efficiently retrieve various high-precision map elements for driving assistance from the vast amount of map data based on the vehicle's latitude and longitude coordinates has become a pressing technical problem that needs to be solved.

[0003] On the other hand, due to the requirements of national geographic data security, high-precision maps cannot contain elevation information, which leads to the problem of overlapping high-precision map data of geographic elements at different heights in multi-layered geographic scenarios such as elevated roads and tunnels. Therefore, an effective high-precision map neighbor element query method also needs to include the filtering and optimization design of elements at different heights of neighboring latitude and longitude coordinates.

[0004] Therefore, it can be seen that the problem with the related technologies is that the technical solutions in the related technologies cannot suppress the interference of overlapping high-precision map elements in multi-layered geographical scenes, and provide a query for nearby elements near the vehicle coordinates in the high-precision map based on the vehicle's latitude and longitude coordinates. Summary of the Invention

[0005] The problem solved by this invention is that the technical solutions in related technologies cannot suppress the interference of overlapping high-precision map elements in multi-layered geographical scenes, and provide a query for nearby elements near the vehicle coordinates in the high-precision map based on the vehicle's latitude and longitude coordinates.

[0006] To address the aforementioned problems, the primary objective of this invention is to provide a method for querying nearby elements on a high-precision map based on latitude and longitude.

[0007] The second objective of this invention is to provide a device for querying nearby elements on a high-precision map based on latitude and longitude.

[0008] A third objective of this invention is to provide an intelligent vehicle.

[0009] A fourth objective of this invention is to provide a readable storage medium.

[0010] To achieve the first objective of this invention, embodiments of this invention provide a method for querying nearby elements in a high-precision map based on latitude and longitude. The query method includes: acquiring a high-precision map of the area where the vehicle is located; dividing the road data of the high-precision map into multiple layers; establishing a KD-tree based on the topological relationships between the multiple layers; acquiring the vehicle's current latitude and longitude; retrieving m layers in the KD-tree that are adjacent to the current latitude and longitude for confirmation based on the current latitude and longitude; when m > 1, acquiring multiple historical latitude and longitudes of the vehicle; selecting and determining the current layer from the m layers for confirmation based on the multiple historical latitude and longitudes; the current layer including n lane layers; when n > 1, selecting and determining the current lane layer from the n lane layers based on the multiple historical latitude and longitudes; providing the vehicle with a map element query for the current lane layer; wherein m is a natural number, n is a positive integer, and each lane layer includes one lane and the map element data of that lane.

[0011] Compared with existing technologies, the technical effects achieved by this solution are as follows: the offline preprocessing stage of KD-tree retrieval results in shorter computation time and higher efficiency when using the online element query function; the invention divides the high-precision map into zone and lane layers, and in practical applications, the zone layer where the vehicle is located is queried first, followed by the specific lane layer, effectively increasing the efficiency and speed of the query method and reducing computation time; the query method of this invention can provide a query for nearby elements near the vehicle coordinates in the high-precision map based on the vehicle's latitude and longitude coordinates.

[0012] In one embodiment of the present invention, multiple historical latitude and longitude coordinates are recorded by the vehicle during the current journey, and when the vehicle passes through multiple historical latitude and longitude coordinates and the current latitude and longitude coordinates in chronological order, the vehicle travels the same distance between each two latitude and longitude coordinates.

[0013] Compared with existing technologies, the technical effects achieved by this solution are as follows: When a vehicle is stuck in traffic for a long time or waiting at a red light, its latitude and longitude coordinates remain stationary for a certain period of time. If the historical latitude and longitude coordinates of the vehicle are obtained at the same time interval, the obtained coordinates may not accurately reflect the vehicle's driving trajectory. The historical latitude and longitude coordinates obtained by the method of this invention are obtained at equal intervals, which can more accurately reflect the historical driving trajectory of the vehicle, thereby making the subsequent query method more accurate.

[0014] In one embodiment of the present invention, when m > 1, multiple historical latitude and longitude coordinates of the vehicle are obtained. Based on the multiple historical latitude and longitude coordinates, the current zone is determined from m unconfirmed zones. The current zone includes n lane layers. The process includes: determining at least one candidate zone from the m unconfirmed zones based on the multiple historical latitude and longitude coordinates; obtaining the heading of the center shape point set of the candidate zone; determining the heading of the historical coordinate point set based on the multiple historical latitude and longitude coordinates; comparing the deviation between the heading of the center shape point set and the heading of the historical coordinate point set, and selecting the candidate zone with the smallest deviation as the current zone.

[0015] Compared with existing technologies, the technical effects achieved by adopting this technical solution are as follows: The method of this invention can reduce the amount of calculation and improve the accuracy of discrimination by using the connection query method of the central shape point set; the addition of historical latitude and longitude discrimination to the query method effectively suppresses the problem of high-precision map element data overlap in multi-layer geographical environments and enhances the robustness of high-precision map data query for autonomous vehicles.

[0016] In one embodiment of the present invention, determining at least one candidate layer from m unconfirmed layers based on multiple historical latitude and longitude coordinates includes: determining multiple historical layers based on multiple historical latitude and longitude coordinates; and selecting layers from the m unconfirmed layers that are the same as or have a topological relationship with any of the multiple historical layers as candidate layers.

[0017] Compared with existing technologies, the technical effects achieved by adopting this technical solution are as follows: The method of this embodiment can accurately determine the candidate region layer, thereby effectively improving the stability and reliability of subsequent query methods.

[0018] In one embodiment of the present invention, when n > 1, the current lane layer is determined from n lane layers based on multiple historical latitude and longitude coordinates, including: using a bisection method of first and last secant projection to search the center shape point set of the current zone layer to obtain the lane layer to be confirmed; determining multiple historical lane layers based on multiple historical latitude and longitude coordinates; and determining whether the lane layer to be confirmed is the current lane layer based on the topological connection relationship between the multiple historical lane layers and the lane layer to be confirmed.

[0019] Compared with the prior art, the technical effect achieved by adopting this technical solution is that the method of this embodiment can accurately determine the current lane layer where the vehicle is located, effectively increasing the reliability of the query method of the present invention.

[0020] In one embodiment of the present invention, the query method includes: when m=1, the layer to be confirmed is the current layer.

[0021] In one embodiment of the present invention, the query method includes: when n=1, the lane layer is the current lane layer.

[0022] To achieve the second objective of this invention, embodiments of this invention provide a high-precision map neighbor element query device based on latitude and longitude. The query device includes: a first acquisition module, used to acquire a high-precision map of the area where the vehicle is located, divide the road data of the high-precision map into multiple layers, and establish a KD-tree based on the topological relationship between the multiple layers; a second acquisition module, used to acquire the current latitude and longitude of the vehicle, and based on the current latitude and longitude, retrieve m layers to be confirmed in the KD-tree that are adjacent to the current latitude and longitude; a first control module, used when m > 1, to acquire multiple historical latitude and longitudes of the vehicle, and based on the multiple historical latitude and longitudes, filter and determine the current layer from the m layers to be confirmed, the current layer including n lane layers; a second control module, used when n > 1, used when n > 1, filter and determine the current lane layer from the n lane layers; and a query module, used to provide the vehicle with a map element query for the current lane layer; wherein, m is a natural number, n is a positive integer, and each lane layer includes one lane and the map element data of that lane.

[0023] The high-precision map neighbor element query device based on latitude and longitude in this embodiment of the invention implements the steps of the query method as in any embodiment of the invention, and therefore has all the beneficial effects of the query method as in any embodiment of the invention, which will not be repeated here.

[0024] To achieve the third objective of the present invention, an embodiment of the present invention provides an intelligent vehicle, which includes: a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein when the program or instructions are executed by the processor, the steps of the query method as described in any embodiment of the present invention are implemented.

[0025] The intelligent vehicles of this invention implement the steps of the query method as described in any embodiment of this invention, and therefore have all the beneficial effects of the query method as described in any embodiment of this invention, which will not be repeated here.

[0026] To achieve the fourth objective of the present invention, embodiments of the present invention provide a readable storage medium on which a program or instruction is stored, and when the program or instruction is executed by a processor, it implements the steps of the query method as described in any embodiment of the present invention.

[0027] The readable storage medium of this invention implements the steps of the query method as described in any embodiment of this invention, and therefore has all the beneficial effects of the query method as described in any embodiment of this invention, which will not be repeated here. Attached Figure Description

[0028] Figure 1 This is a flowchart illustrating the steps of a high-precision map neighbor element query method based on latitude and longitude according to some embodiments of the present invention. Detailed Implementation

[0029] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0030] See Figure 1 This embodiment provides a method for querying nearby elements on a high-precision map based on latitude and longitude. The query method includes:

[0031] S100: Obtain a high-precision map of the area where the vehicle is located, divide the road data of the high-precision map into multiple layers, and establish a KD-tree based on the topological relationship between the multiple layers;

[0032] S200: Obtain the vehicle's current latitude and longitude, and based on the current latitude and longitude, retrieve the m unconfirmed regions in the KD-tree that are adjacent to the current latitude and longitude.

[0033] S300: When m>1, obtain multiple historical latitude and longitude coordinates of the vehicle, and based on the multiple historical latitude and longitude coordinates, filter and determine the current zone from m unconfirmed zones. The current zone includes n lane layers.

[0034] S400: When n>1, the current lane layer is determined by filtering from n lane layers based on multiple historical latitude and longitude coordinates.

[0035] S500: Provides vehicles with a query of map elements for the current lane layer;

[0036] Where m is a natural number and n is a positive integer, each lane layer includes one lane and the map element data of that lane.

[0037] It should be noted that the various element data in the high-precision map are stored in order of geographic coordinates. In this invention, the high-precision map data can be simply divided into area layers and lane layers for data retrieval. Different high-precision maps may have different or more detailed divisions of area layers or lane layers, but the processing method for searching nearby elements is the same. In this invention, the high-precision map data will be simplified to a data structure of area layers and lane layers.

[0038] The layer in this invention includes at least one lane layer. When the layer includes multiple lane layers, it also includes the topological relationships between these lane layers. A lane layer is a single lane and includes map element data for that lane. The layer is established by enlarging the area on the road plane along a direction perpendicular to the center road to form a rectangular region. Preferably, the width of the rectangular region is the sum of the widths of all lanes along the direction perpendicular to the center road. When establishing the layer, the rectangular regions of layers that are not topologically connected do not overlap. It should be noted that if the lanes of two layers are interconnected, then these two layers are topologically connected.

[0039] Furthermore, in S100, a high-precision map of the area where the vehicle is located is acquired. The road data of the high-precision map is divided into multiple layers, and a KD-tree is built based on the topological relationships between the multiple layers. The construction of the KD-tree is carried out during the vehicle offline preprocessing stage. After dividing the road data of the high-precision map into multiple layers, a KD-tree is gradually built based on the topological relationships between the interconnections between the layers and the left-hand relationships of the boundaries of each layer, thus completing the map data element query preprocessing.

[0040] Further, in S200, the vehicle's current latitude and longitude are obtained. Based on the current latitude and longitude, m unconfirmed regions in the KD-tree are retrieved, meaning the unconfirmed region contains the current latitude and longitude or is adjacent to the region containing the current latitude and longitude. Preferably, the m unconfirmed regions are obtained using the KNN nearest neighbor algorithm based on the KD-tree.

[0041] Furthermore, in S300, when m>1, multiple historical latitude and longitude coordinates of the vehicle are obtained. Based on the multiple historical latitude and longitude coordinates, the current zone is determined from m unconfirmed zones. The current zone includes n lane layers.

[0042] Furthermore, in S400, when n>1, the current lane layer is determined by filtering from n lane layers based on multiple historical latitude and longitude coordinates.

[0043] Furthermore, in S500, map element queries for the current lane layer are provided for the vehicle; the current lane layer is the lane layer where the vehicle is currently located. At this time, map element query services for the current lane layer can be provided for the vehicle based on the actual latitude and longitude of the vehicle.

[0044] Understandably, the process of building a KD-tree in the offline preprocessing stage has a short computation time and high efficiency when using the online element query function. This invention divides the high-precision map into zone layers and lane layers. In practical applications, the zone layer where the vehicle is located is queried first, and then the specific lane layer is queried, which effectively increases the efficiency and speed of the query method of this invention and reduces the computation time. The query method of this invention can provide a query of nearby elements near the vehicle coordinates in the high-precision map based on the vehicle's latitude and longitude coordinates.

[0045] Furthermore, multiple historical latitude and longitude coordinates are recorded by the vehicle during the current journey, and when the vehicle passes through multiple historical latitude and longitude coordinates and the current latitude and longitude coordinates in chronological order, the vehicle travels the same distance between each two latitude and longitude coordinates.

[0046] For example, when multiple historical latitude and longitude coordinates of a vehicle are arranged sequentially according to the vehicle's travel time, the travel distance between every two historical latitude and longitude coordinates is 50m.

[0047] Understandably, when a vehicle is stuck in traffic for a long time or waiting at a red light, its latitude and longitude coordinates remain stationary for a certain period of time. If the historical latitude and longitude coordinates of the vehicle are obtained at the same time interval, the obtained coordinates may not accurately reflect the vehicle's driving trajectory. The historical latitude and longitude coordinates obtained by the method of the present invention are obtained at equal intervals, which can more accurately reflect the historical driving trajectory of the vehicle, thereby making the subsequent query method more accurate.

[0048] Furthermore, when m > 1, multiple historical latitude and longitude coordinates of the vehicle are obtained. Based on these coordinates, the current zone is determined from m unconfirmed zones. The current zone includes n lane layers, including:

[0049] S310: Based on multiple historical latitude and longitude coordinates, determine at least one candidate layer from m unconfirmed layers;

[0050] S320: Obtain the heading of the center shape point set of the candidate region;

[0051] S330: Determine the course of a set of historical coordinate points based on multiple historical latitude and longitude coordinates;

[0052] S340: Compare the deviations between the heading of the center shape point set and the heading of the historical coordinate point set, and select the candidate layer with the smallest deviation as the current layer.

[0053] Furthermore, in S320, the heading of the center shape point set of the candidate region is obtained. The candidate region is rectangular, and the heading of the center shape point set of the candidate region is the direction of its inner lane.

[0054] Furthermore, in S330, the heading of the historical coordinate point set is determined based on multiple historical latitude and longitude coordinates. The heading of the historical coordinate point set can be approximated as the direction of travel with the highest probability at the current time point calculated based on the vehicle's multiple historical latitude and longitude coordinates.

[0055] Furthermore, in S340, the deviation between the heading of the center shape point set and the heading of the historical coordinate point set is compared, and the candidate layer with the smallest deviation is selected as the current layer; the headings of the center shape point sets of multiple candidate layers are compared with the headings of the historical coordinate point sets, and the candidate layer with the smallest deviation is the current layer of the vehicle.

[0056] It should be noted that when there is a road fork at the current latitude and longitude coordinates, the current zone calculated at this time may have errors. In this case, it is necessary to wait for the vehicle to travel a certain distance and then correct it again based on the vehicle's real-time latitude and longitude coordinates to determine the correct current zone of the vehicle.

[0057] Understandably, the method of the present invention can reduce the amount of computation and improve the accuracy of discrimination by using the connection query method of the central shape point set; by adding the discrimination of historical latitude and longitude to the query method, the problem of high-precision map element data overlap in multi-layer geographical environment is effectively suppressed, and the robustness of high-precision map data query for autonomous vehicles is enhanced.

[0058] Furthermore, based on multiple historical latitude and longitude coordinates, at least one candidate layer is identified from the m unconfirmed layers, including:

[0059] S311: Based on multiple historical latitude and longitude coordinates, multiple historical strata are determined;

[0060] S312: Select candidate layers from m layers to be confirmed that have the same topological relationship as any layer in the multiple historical layers or have mutual connections.

[0061] Furthermore, in S311, multiple historical strata are determined based on multiple historical latitude and longitude coordinates; the strata where the historical latitude and longitude coordinates are located are the historical strata.

[0062] Understandably, the method in this embodiment can accurately determine the candidate region layer, thereby effectively improving the stability and reliability of subsequent query methods.

[0063] Furthermore, when n > 1, the current lane layer is determined from n lane layers based on multiple historical latitude and longitude coordinates, including:

[0064] S410: Use the bisection method of the first and last secant projection to search the center shape point set of the current layer to obtain the lane layer to be confirmed;

[0065] S420: Multiple historical lane layers are determined based on multiple historical latitude and longitude coordinates;

[0066] S430: Determine whether the lane layer to be confirmed is the current lane layer based on the topological connection relationship between multiple historical lane layers and the lane layer to be confirmed.

[0067] In this embodiment, the lane layer to be confirmed that has a topological connection with multiple historical lane layers is the current lane layer.

[0068] Understandably, the method of this embodiment can accurately determine the current lane layer where the vehicle is located, effectively increasing the reliability of the query method of the present invention.

[0069] Furthermore, the query methods include:

[0070] When m=1, the layer to be confirmed is the current layer.

[0071] In this embodiment, when m=1, it means that only one layer needs to be confirmed to meet the requirements, and this layer is the current layer.

[0072] Furthermore, the query methods include:

[0073] When n=1, the lane layer is the current lane layer.

[0074] In this embodiment, when n=1, only one lane layer is determined to meet the requirements, and this lane layer is the current lane layer.

[0075] Furthermore, this embodiment provides a device for querying nearby elements on a high-precision map based on latitude and longitude. The query device includes:

[0076] The first acquisition module is used to acquire a high-precision map of the area where the vehicle is located, divide the road data of the high-precision map into multiple layers, and establish a KD-tree based on the topological relationship between the multiple layers.

[0077] The second acquisition module is used to acquire the current latitude and longitude of the vehicle, and based on the current latitude and longitude, to retrieve the m unconfirmed regions in the KD-tree that are adjacent to the current latitude and longitude.

[0078] The first control module is used to obtain multiple historical latitude and longitude coordinates of the vehicle when m>1, and to filter and determine the current zone from m unconfirmed zone layers based on the multiple historical latitude and longitude coordinates. The current zone layer includes n lane layers.

[0079] The second control module is used to select and determine the current lane layer from n lane layers based on multiple historical latitude and longitude coordinates when n>1.

[0080] The query module is used to provide vehicles with map element queries for the current lane layer;

[0081] Where m is a natural number and n is a positive integer, each lane layer includes one lane and the map element data of that lane.

[0082] The high-precision map neighbor element query device based on latitude and longitude in this embodiment of the invention implements the steps of the query method as in any embodiment of the invention, and therefore has all the beneficial effects of the query method as in any embodiment of the invention, which will not be repeated here.

[0083] Furthermore, this embodiment provides an intelligent vehicle, which includes: a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the steps of the query method as described in any embodiment of the present invention.

[0084] The intelligent vehicles of this invention implement the steps of the query method as described in any embodiment of this invention, and therefore have all the beneficial effects of the query method as described in any embodiment of this invention, which will not be repeated here.

[0085] Furthermore, this embodiment provides a readable storage medium on which a program or instruction is stored, and when the program or instruction is executed by a processor, it implements the steps of the query method as described in any embodiment of the present invention.

[0086] The readable storage medium of this invention implements the steps of the query method as described in any embodiment of this invention, and therefore has all the beneficial effects of the query method as described in any embodiment of this invention, which will not be repeated here.

[0087] While the present invention has been disclosed above, it is not limited thereto. Any person skilled in the art can make various modifications and alterations without departing from the spirit and scope of the invention; therefore, the scope of protection of the present invention should be determined by the scope defined in the claims.

Claims

1. A method for querying high-precision map proximate elements based on latitude and longitude, characterized in that, The query method includes: Obtain a high-precision map of the area where the vehicle is located, divide the road data of the high-precision map into multiple layers, and establish a KD-tree based on the topological relationship between the multiple layers. Obtain the current latitude and longitude of the vehicle, and based on the current latitude and longitude, retrieve the m unconfirmed regions in the KD-tree that are adjacent to the current latitude and longitude; When m > 1, multiple historical latitude and longitude coordinates of the vehicle are obtained. Based on the multiple historical latitude and longitude coordinates, the current zone is determined from the m zones to be confirmed. The current zone includes n lane layers. When n > 1, the current lane layer is determined from the n lane layers based on the multiple historical latitude and longitude coordinates, including: using a bisection method of first and last secant projection to search the center shape point set of the current zone layer to obtain the lane layer to be confirmed; determining multiple historical lane layers based on the multiple historical latitude and longitude coordinates; and determining whether the lane layer to be confirmed is the current lane layer based on the topological connection relationship between the multiple historical lane layers and the lane layer to be confirmed. Provide the vehicle with a map element query for the current lane layer; Where m is a natural number and n is a positive integer, each lane layer includes one lane and map element data for that lane.

2. The query method of claim 1, wherein, The multiple historical latitude and longitude coordinates are recorded by the vehicle during the current journey, and when the vehicle passes through multiple historical latitude and longitude coordinates and the current latitude and longitude coordinates in chronological order, the distance traveled by the vehicle between each two latitude and longitude coordinates is the same.

3. The query method of claim 2, wherein, When m > 1, multiple historical latitude and longitude coordinates of the vehicle are obtained. Based on these multiple historical latitude and longitude coordinates, the current zone is determined from m unconfirmed zones. The current zone includes n lane layers, including: Based on the multiple historical latitude and longitude coordinates, at least one candidate layer is determined from the m layers to be confirmed; Obtain the heading of the center shape point set of the candidate region layer; Determine the course of the historical coordinate point set based on multiple historical latitude and longitude coordinates; The deviations between the headings of the central shape point set and the headings of the historical coordinate point set are compared, and the candidate layer with the smallest deviation is selected as the current layer.

4. The query method of claim 3, wherein, The step of determining at least one candidate region from m unconfirmed regions based on multiple historical latitude and longitude coordinates includes: Multiple historical strata are determined based on the aforementioned historical latitude and longitude coordinates; From the m layers to be confirmed, layers that are the same as or have a topological relationship with any of the multiple historical layers are selected as candidate layers.

5. The query method of any one of claims 1 to 4, characterized in that, The query method includes: When m=1, the layer to be confirmed is the current layer.

6. The query method of any one of claims 1 to 4, wherein, The query method includes: When n=1, the lane layer is the current lane layer.

7. A device for querying a high-precision map proximity element based on latitude and longitude, characterized in that, The query device includes: The first acquisition module is used to acquire a high-precision map of the area where the vehicle is located, divide the road data of the high-precision map into multiple layers, and establish a KD-tree according to the topological relationship between the multiple layers. The second acquisition module is used to acquire the current latitude and longitude of the vehicle, and based on the current latitude and longitude, retrieve and acquire m unconfirmed regions in the KD-tree that are adjacent to the current latitude and longitude. The first control module is used to obtain multiple historical latitude and longitude coordinates of the vehicle when m>1, and to filter and determine the current zone layer from m zones to be confirmed based on the multiple historical latitude and longitude coordinates, wherein the current zone layer includes n lane layers. The second control module is used to determine the current lane layer from n lane layers based on multiple historical latitude and longitude coordinates when n > 1. This includes: using a bisection method of first and last secant projection to search the center shape point set of the current lane layer to obtain the lane layer to be confirmed; determining multiple historical lane layers based on the multiple historical latitude and longitude coordinates; and determining whether the lane layer to be confirmed is the current lane layer based on the topological connection relationship between the multiple historical lane layers and the lane layer to be confirmed. The query module is used to provide the vehicle with a map element query for the current lane layer; Where m is a natural number and n is a positive integer, each lane layer includes one lane and map element data for that lane.

8. An intelligent vehicle, characterized by The intelligent vehicle includes: a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the query method as described in any one of claims 1 to 6.

9. A readable storage medium, characterized by, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the query method as described in any one of claims 1 to 6.

Images