Method, device and equipment for verifying integrity of high-precision map, medium and vehicle

Abstract

The embodiment of the invention discloses an integrity checking method, device and equipment for a high-precision map, a medium and a vehicle, the method comprises the following steps: matching each target traditional navigation path with the high-precision map of a to-be-checked region, the matching content comprising road label information, road position information and road angle information; the map area corresponding to the set of each target traditional navigation path comprises a to-be-verified area; in the matching process, if each target traditional navigation path is successfully matched with the high-precision map, determining that the high-precision map of the to-be-verified region is completely established; if unmatched road sections exist in the target traditional navigation path, a map area corresponding to the unmatched road sections serves as a high-precision map area where mapping is not completed in the high-precision map, and the skeleton line is a traditional map used for creating the high-precision map. By adopting the technical scheme, the checking efficiency of the integrity of the high-precision map is improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of autonomous driving technology, and more specifically, to a method, device, equipment, medium and vehicle for verifying the integrity of a high-precision map. Background Art

[0002] In the process of making high-precision maps, incomplete mapping is often caused by problems in the production process.

[0003] In the related art, the integrity check of the map is usually done manually, specifically by overlaying the base map of the map with the newly created high-precision map. The human can check the missing areas in the newly created high-precision map by the difference in colors displayed between the base map and the newly created high-precision map. This manual review method takes a lot of time and effort and is relatively inefficient. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, equipment, medium and vehicle for verifying the integrity of a high-precision map, thereby improving the efficiency of verifying the integrity of a high-precision map.

[0005] The specific technical solutions are as follows:

[0006] In a first aspect, an embodiment of the present invention provides a method for checking the integrity of a high-precision map, comprising:

[0007] Matching each target traditional navigation path with a high-precision map of the area to be verified, wherein the matching content includes road label information, road position information and road angle information; the map area corresponding to the set of each target traditional navigation path includes the area to be verified;

[0008] During the matching process, if all the traditional navigation paths of the target are successfully matched with the high-precision map, it is determined that the high-precision map of the area to be verified is complete;

[0009] If there are unmatched road sections in the target traditional navigation path, the map area corresponding to the unmatched road sections will be used as the high-precision map area in which mapping is not completed in the high-precision map, where the target traditional navigation path is a path provided by the traditional navigation map, or a path split from a skeleton line; the skeleton line is a traditional map obtained through open source map production for creating high-precision maps.

[0010] It can be seen from the above scheme that the embodiment of the present invention adopts an automated method when checking the integrity of the high-precision map. By matching each target traditional navigation path with the high-precision map of the area to be checked, the map area corresponding to the target traditional navigation path that does not have a matching object in the matching process can be used as the incompletely mapped area in the high-precision map. Compared with the method of manually checking the integrity of the map in the related art, the automatic verification method of the integrity of the high-precision map provided by the embodiment of the present invention effectively improves the verification efficiency and accuracy.

[0011] Optionally, when the target traditional navigation path is provided by a traditional navigation map, the target traditional navigation path is determined by:

[0012] Acquire multiple traditional navigation paths from a traditional navigation map, and match each traditional navigation path with a skeleton line of the area to be verified, and obtain the road number of each section in the skeleton line that successfully matches each traditional navigation path, wherein the map area corresponding to the set of each traditional navigation path includes the area to be verified;

[0013] The road numbers corresponding to different traditional navigation paths are sorted in descending order according to the number of numbers, and the traditional navigation path with the largest total number of road numbers and the road numbers that are successfully matched are temporarily stored from the sorted road numbers;

[0014] The temporarily stored road numbers are deleted from the road numbers corresponding to the unstored traditional navigation paths, and after the deletion operation is completed, the operation of sorting the road numbers corresponding to different traditional navigation paths in order of the number from large to small is returned, until the ratio of the number of temporarily stored road numbers to the total number of roads in the area to be verified reaches a preset ratio, and each temporarily stored traditional navigation path is used as the target traditional navigation path to be matched with the high-precision map of the area to be verified.

[0015] Through the above technical solution, it can be seen that by selecting as few target traditional navigation paths as possible from the traditional navigation paths covering the map to be verified, the problem of large number of matches and long matching time caused by too many repeated traditional navigation paths during the integrity verification of the high-precision map is avoided.

[0016] Optionally, the method provided by the embodiment of the present invention further includes:

[0017] Remap the unfinished high-precision map areas, and use the remapped high-precision map of the area to be verified as the new high-precision map to be verified. Return to perform the operation of matching the target traditional navigation path with the new high-precision map to be verified until the high-precision maps of the area to be verified are all completed.

[0018] Optionally, the high-precision map is constructed according to the granularity of cells, there are overlapping areas between adjacent cells, and each cell is divided according to different high-precision road sections in the high-precision map;

[0019] Accordingly, before matching each target traditional navigation path with the high-precision map of the area to be verified, the method provided by the embodiment of the present invention further includes:

[0020] The connectivity of the high-precision map in each cell is checked. If there are no missing sections in the connectivity of the high-precision map in each cell, the cells belonging to the area to be checked are merged according to the overlapping sections to obtain the high-precision map corresponding to the area to be checked.

[0021] Optionally, merging the cells belonging to the area to be verified according to overlapping sections includes:

[0022] For each overlapping road section between each cell, determine the number of lanes corresponding to each candidate position point on each overlapping road section, and use each candidate position point whose number of lanes is consistent within a preset range as a position point to be merged;

[0023] Merge the overlapping road segments corresponding to the locations to be merged into the same road segment.

[0024] Through the above technical solution, it can be known that, under the premise that the high-precision map is constructed according to the cell granularity, for the high-precision map of the map to be verified, each cell can be merged according to the repeated sections between cells after the construction of each cell is completed, so as to form a high-precision map of the area to be verified. In the process of merging each cell, a straight road section with a non-fork road and a set distance and lane number that is consistent can be identified, and the cells can be merged in the straight road section to ensure the accuracy of the cell merging.

[0025] Optionally, determining the number of lanes corresponding to each candidate position point on each overlapping road segment includes:

[0026] For each candidate position point on each overlapping road segment, the normal line of the candidate position point is extended to both sides of the road until it reaches the lane edge line of the road;

[0027] The total number of lane lines intersecting the normal line is determined, and the number of lanes corresponding to the candidate position point is determined based on the total number of lane lines obtained.

[0028] Optionally, after verifying the connectivity of the high-precision map in each cell and before merging multiple cells belonging to the area to be verified according to overlapping sections, the method provided by the embodiment of the present invention further includes:

[0029] For each road in each cell, the outermost road edge line of the road is determined, and the roads that do not belong to the outermost road edge line are deleted.

[0030] Through the above technical solution, it can be seen that for each road in each cell, by deleting the roads that do not belong to the outermost road edge line of the road, it is possible to filter the miscellaneous lines appearing in the high-precision map to avoid these miscellaneous lines interfering with the matching results.

[0031] In a second aspect, an embodiment of the present invention further provides a high-precision map integrity verification device, comprising:

[0032] A matching module is configured to match each target traditional navigation path with a high-precision map of the area to be verified, wherein the matching content includes road label information, road position information and road angle information; the map area corresponding to the set of each target traditional navigation path includes the area to be verified;

[0033] The integrity verification module is configured to, during the matching process, if all target traditional navigation paths are successfully matched with the high-precision map, determine that the high-precision map construction of the area to be verified is complete; if there are unmatched sections in the target traditional navigation path, the map area corresponding to the unmatched sections will be used as the high-precision map area in which the mapping is not completed in the high-precision map, wherein the target traditional navigation path is a path provided by the traditional navigation map, or a path split from the skeleton line; the skeleton line is a traditional map obtained through open source map production for creating high-precision maps.

[0034] Optionally, when the target traditional navigation path is provided by a traditional navigation map, the apparatus provided in this embodiment further includes:

[0035] The target traditional navigation path determination module is specifically configured as follows:

[0036] Acquire multiple traditional navigation paths from a traditional navigation map, and match each traditional navigation path with a skeleton line of the area to be verified, to obtain the road number of each section in the skeleton line successfully matched with each traditional navigation path, wherein the map area corresponding to the set of each traditional navigation path includes the area to be verified;

[0037] The road numbers corresponding to different traditional navigation paths are sorted in descending order according to the number of numbers, and the traditional navigation path with the largest total number of road numbers and the road numbers that are successfully matched are temporarily stored from the sorted road numbers;

[0038] The temporarily stored road numbers are deleted from the road numbers corresponding to the unstored traditional navigation paths, and after the deletion operation is completed, the operation of sorting the road numbers corresponding to different traditional navigation paths in order of the number from large to small is returned, until the ratio of the number of temporarily stored road numbers to the total number of roads in the area to be verified reaches a preset ratio, and each temporarily stored traditional navigation path is used as a target traditional navigation path to be matched with the high-precision map of the area to be verified.

[0039] Optionally, the device provided by the embodiment of the present invention further includes:

[0040] The mapping module is used to remap the high-precision map area that has not been completed, and use the remapped high-precision map of the area to be verified as the new high-precision map to be verified, and return to execute the operation of matching the target traditional navigation path with the new high-precision map to be verified until the high-precision map of the area to be verified is fully mapped.

[0041] Optionally, the high-precision map is constructed according to the granularity of cells, there are overlapping areas between adjacent cells, and each cell is divided according to different high-precision road sections in the high-precision map;

[0042] Accordingly, before matching each target traditional navigation path with the high-precision map of the area to be verified, the device provided in this embodiment further includes:

[0043] A connectivity verification module is configured to verify the connectivity of the high-precision map in each cell;

[0044] The map merging module is configured to merge the cells belonging to the area to be verified according to the overlapping sections if there are no missing connectivity sections of the high-precision map in each cell, so as to obtain a high-precision map corresponding to the area to be verified.

[0045] Optional, map merging module, including:

[0046] The lane number determination unit is configured to determine the number of lanes corresponding to each candidate position point on each overlapping road segment between each cell if there is no missing connectivity road segment in the high-precision map in each cell;

[0047] A to-be-merged position point determination unit is configured to select candidate position points whose number of lanes is consistent within a preset range as to-be-merged position points;

[0048] The merging unit is configured to merge the overlapping road sections corresponding to the to-be-merged position points into a same road section.

[0049] Optionally, the lane number determination unit is specifically configured as follows:

[0050] For each candidate position point on each overlapping road segment, the normal line of the candidate position point is extended to both sides of the road until it reaches the lane edge line of the road;

[0051] The total number of lane lines intersecting the normal line is determined, and the number of lanes corresponding to the candidate position point is determined based on the total number of lane lines obtained.

[0052] Optionally, after verifying the connectivity of the high-precision map in each cell and before merging the multiple cells belonging to the area to be verified according to overlapping sections, the apparatus provided by the embodiment of the present invention further includes:

[0053] For each road in each cell, the outermost road edge line of the road is determined, and the roads that do not belong to the outermost road edge line are deleted.

[0054] In a third aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0055] one or more processors;

[0056] a storage device for storing one or more programs,

[0057] When the one or more programs are executed by the one or more processors, the one or more processors implement the high-precision map integrity verification method provided by any embodiment of the present invention.

[0058] In a fourth aspect, an embodiment of the present invention provides a storage medium on which a computer program is stored, characterized in that when the program is executed by a processor, a high-precision map integrity verification method as provided in any embodiment of the present invention is implemented.

[0059] In a fifth aspect, an embodiment of the present invention provides a vehicle, which includes the integrity verification device for a high-precision map provided by any embodiment of the present invention, or includes the electronic device provided by any embodiment of the present invention.

[0060] In a sixth aspect, an embodiment of the present invention provides a computer program, which includes program instructions, and when the program instructions are executed by a computer, implements a high-precision map integrity verification method as provided in any embodiment of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0062] Figure 1 A flowchart of a method for checking the integrity of a high-precision map provided in the first embodiment of the present invention;

[0063] Figure 2 A flowchart of a method for checking the integrity of a high-precision map provided in Embodiment 2 of the present invention;

[0064] Figure 3 A structural block diagram of a high-precision map integrity verification device provided in Embodiment 3 of the present invention;

[0065] Figure 4 A structural block diagram of an electronic device provided in Embodiment 4 of the present invention;

[0066] Figure 5 A schematic diagram of a vehicle provided in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] It should be noted that the terms "including" and "having" and any variations thereof in the embodiments of the present invention and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0069] In the description of the embodiment of the present invention, the term "traditional navigation map" generally has an accuracy of meter level, which only records road level data, such as road shape, slope, curvature, paving, direction, etc. The users of "traditional navigation map" are mainly drivers.

[0070] In the description of the embodiments of the present invention, the term "Open Street Map (OSM)" refers to a map drawn by a user based on a handheld GPS (Global Positioning System) device, aerial photography or other free content or even local knowledge alone, and is freely available to other users.

[0071] In the description of the embodiment of the present invention, the term "skeleton line" refers to the map route obtained through the production of open source maps, which uses thin curves consistent with the original shape connectivity and topological structure to represent the spatial data of the features in the map. The road network in the skeleton line is spatially coherent, and its accuracy is generally at the meter level, in which only road-level data is recorded, such as road shape, slope, curvature, paving, direction, etc. The "high-precision map" in this embodiment is created based on the skeleton line.

[0072] In the description of the embodiments of the present invention, the term "high-precision map" has an accuracy of centimeters. In addition to the road-level data in the above-mentioned "traditional navigation map", the "high-precision map" also adds data related to lane attributes (lane line type, lane width, etc.), such as overhead objects, guardrails, trees, road edge types, and roadside landmarks. The main user of the "high-precision map" is the car's automatic driving system.

[0073] The embodiments of the present invention disclose a method, device, equipment, medium and vehicle for checking the integrity of a high-precision map, which are described in detail below.

[0074] Embodiment 1

[0075] Figure 1 This is a flowchart of a method for checking the integrity of a high-precision map provided in the first embodiment of the present invention. The method can be applied to the integrity check scenario after the high-precision map of a certain area is created. The method provided in this embodiment can be executed by a map loading device, which can be implemented in software and / or hardware. Figure 1 As shown, the method provided in this embodiment specifically includes:

[0076] S110, matching each target traditional navigation path with a high-precision map of the area to be verified.

[0077] In this embodiment, a high-precision map can be created in units of regions, for example, a high-precision map corresponding to Beijing, a high-precision map corresponding to Shanghai, or a high-precision map corresponding to Tianjin, etc. is created. After a high-precision map is created, it is usually necessary to verify the integrity of the map. In this embodiment, the high-precision map of the area to be verified is a map that needs to be verified for integrity after the high-precision map of a certain area is created.

[0078] In this embodiment, the map area corresponding to the set of each target traditional navigation path includes the area to be verified. If the traditional navigation map can be obtained, the target traditional navigation path covering the area to be verified can be obtained from the traditional navigation map. If the traditional navigation map cannot be obtained, the target traditional navigation path covering the area to be verified can be extracted from the skeleton line.

[0079] In this embodiment, when matching each target traditional navigation path with the high-precision map of the map to be verified, the trajectory points of the target traditional navigation path can be matched with the road center line of the high-precision road section in the high-precision map to be verified. Alternatively, in order to avoid mismatching or missed matching caused by changes in the specifications of the road center line and not being in the middle of the road, this embodiment can also adopt a method of matching the trajectory points of the target traditional navigation path with the road range of the high-precision road section to improve the accuracy of the matching results.

[0080] Specifically, when the target traditional navigation path is provided by a traditional navigation map, in order to avoid duplication of traditional navigation paths, as few target traditional navigation paths as possible can be extracted from multiple traditional navigation paths covering the area to be verified. Specifically, each target traditional navigation path can be obtained in the following manner:

[0081] A. Obtain multiple traditional navigation paths covering the area to be verified from the traditional navigation map, and match each traditional navigation path with the skeleton line of the area to be verified, and obtain the road number of each section in the skeleton line that successfully matches each traditional navigation path.

[0082] The map area corresponding to the set of each traditional navigation path includes the area to be verified. The content of matching each traditional navigation path with the skeleton line of the area to be verified includes road label information, road position information and road angle information.

[0083] B. Sorting the road numbers corresponding to different traditional navigation paths in descending order of number, and temporarily storing the traditional navigation path with the largest total number of road numbers and the road numbers that it successfully matches from the sorted road numbers.

[0084] C. Delete the temporarily stored road numbers from the road numbers corresponding to the unstored traditional navigation paths, and after the deletion operation is completed, return to execute the sorting operation of the road numbers corresponding to different traditional navigation paths in order of the number from large to small, until the ratio of the number of temporarily stored road numbers to the total road data of the area to be verified reaches a preset ratio, and then use each temporarily stored traditional navigation path as the target traditional navigation path to be matched with the high-precision map of the area to be verified.

[0085] Among them, the road number of each section in the skeleton line can be represented by Arabic numerals, for example, the road numbers of each section in the skeleton line that successfully matches the traditional navigation path 1 are 1, 2, 3, 4, 5, 6, and 7; the road numbers of each section in the skeleton line that successfully matches the traditional navigation path 2 are 1, 2, 3, 8, and 9; the road numbers of each section in the skeleton line that successfully matches the traditional navigation path 3 are 10, 11, and 12; the road numbers of each section in the skeleton line that successfully matches the traditional navigation path 4 are 3, 6, and 7; the road numbers of each section in the skeleton line that successfully matches the traditional navigation path 5 are 8, 9, 10, 11, and 12; the road number of each section in the skeleton line that successfully matches the traditional navigation path 6 is 15. Among them, the number of road numbers corresponding to the traditional navigation path 1 is 7, the number of road numbers corresponding to the traditional navigation path 2 and the traditional navigation path 5 are both 5, the number of road numbers corresponding to the traditional navigation path 3 and the traditional navigation path 4 are both 3, and the number of road numbers corresponding to the traditional navigation path 6 is 1. The road numbers corresponding to different traditional navigation paths are sorted in descending order of number:

[0086] Traditional navigation path 1: 1, 2, 3, 4, 5, 6, 7;

[0087] Traditional navigation path 2: 1, 2, 3, 8, 9;

[0088] Traditional navigation path 5: 8, 9, 10, 11, 12;

[0089] Traditional navigation path 3: 10, 11, 12;

[0090] Traditional navigation path 4: 3, 6, 7;

[0091] Traditional navigation path 6:15

[0092] Among them, since the traditional navigation path with the largest total number of numbers is traditional navigation path 1, traditional navigation path 1 and the road numbers (1, 2, 3, 4, 5, 6, 7) that it successfully matches are temporarily stored, and the temporarily stored road numbers (1, 2, 3) are deleted from the road numbers (1, 2, 3, 8, 9) corresponding to the traditional navigation path 2 that are not temporarily stored, and the temporarily stored road numbers (3, 6, 7) are deleted from the road numbers (3, 6, 7) corresponding to the traditional navigation path 4 that are not temporarily stored. After the deletion operation is completed, the road numbers corresponding to each unstored traditional navigation path are sorted in order from large to small according to the number of numbers, and the sorting result is:

[0093] Traditional navigation path 5: 8, 9, 10, 11, 12;

[0094] Traditional navigation path 3: 10, 11, 12;

[0095] Traditional navigation path 2: 8, 9;

[0096] Traditional navigation path 6:15.

[0097] After the sorting is completed, the traditional navigation path 5 and its corresponding road numbers (8, 9, 10, 11, 12) are selected from the sorted traditional navigation paths for temporary storage, and then the temporarily stored road numbers (10, 11, 12) are deleted from the road numbers (10, 11, 12) corresponding to the traditional navigation path 3 that have not been temporarily stored, and the road numbers (8, 9) corresponding to the traditional navigation path 2 that have not been temporarily stored are deleted. After the deletion operation is complete, since only one traditional navigation path 6 remains, the traditional navigation path 6 and its corresponding road number (15) are temporarily stored.

[0098] Finally, when the ratio of the number of temporarily stored road numbers to the total road data of the area to be verified reaches a preset ratio, for example, when it reaches 99%, the temporarily stored traditional navigation path 1, traditional navigation path 5 and traditional navigation path 6 can all be used as target traditional navigation paths to match the high-precision map of the area to be verified.

[0099] By adopting the above-mentioned setting, this embodiment avoids the problem of too many matching times and long matching time caused by too many repeated traditional navigation paths during the integrity verification of the high-precision map. On the premise of meeting the path recall rate, the target traditional navigation paths covering the area to be verified can be obtained in the smallest possible number.

[0100] S120. During the matching process, if all target traditional navigation paths are successfully matched with the high-precision map, it is determined that the high-precision map construction of the area to be verified is complete; if there are unmatched sections in the target traditional navigation path, the map area corresponding to the unmatched sections is used as the high-precision map area in the high-precision map where the mapping is not completed.

[0101] In this embodiment, during the matching process, the matching content includes road label information, road position information and road angle information. For any traditional navigation path, if each track point of the traditional navigation path successfully matches each matching content of the corresponding high-precision road section, it means that the traditional navigation path successfully matches the corresponding high-precision road section. If each traditional navigation path successfully matches the high-precision map of the corresponding position, it can be determined that the high-precision map of the area to be verified is complete.

[0102] Those skilled in the art will appreciate that, during the matching process, when the high-precision map is fully mapped, each section in the target traditional navigation path has a corresponding matching object. If there are unmatched sections in the target traditional navigation path, that is, if one or several sections in the traditional navigation path do not have corresponding matching objects, the map area corresponding to the unmatched sections will be used as the high-precision map area in which mapping is not completed in the high-precision map. For example, if sections 6 and 7 of sections 1 to 8 of the target traditional navigation path are not involved in the matching, that is, there are no matching objects, and other sections 1 to 5 and section 8 all have high-precision sections that are successfully matched, then the map area corresponding to sections 6 and 7 in the target traditional navigation path will be used as the high-precision map area in which mapping is not completed in the high-precision map.

[0103] In this embodiment, when checking the integrity of the high-precision map, an automated method is used. By matching each target traditional navigation path with the high-precision map of the area to be checked, the map area corresponding to the target traditional navigation path that is not matched during the matching process can be used as the incompletely mapped area in the high-precision map. Compared with the method of manually checking the integrity of the map in the related art, the automatic checking method of the integrity of the high-precision map provided by the embodiment of the present invention effectively improves the checking efficiency and accuracy.

[0104] Embodiment 2

[0105] Figure 2 This is a flow chart of a method for checking the integrity of a high-precision map provided in the second embodiment of the present invention. Based on the above embodiment, when the high-precision map is constructed according to the granularity of cells, this embodiment refines the process of obtaining the high-precision map of the area to be checked, such as Figure 2 As shown, the method provided in this embodiment includes:

[0106] S210. Verify the connectivity of the high-precision map in each cell. If there are no missing connectivity sections in the high-precision map in each cell, merge multiple cells belonging to the area to be verified according to the overlapping sections to obtain a high-precision map corresponding to the area to be verified.

[0107] In this embodiment, the high-precision map is constructed according to the granularity of the cell. Different cells are divided according to the road sections in the high-precision map, and there are overlapping areas between adjacent cells. That is, the high-precision map to be constructed can be divided into multiple cells according to different road sections, and then each cell can be mapped separately. In this embodiment, after the high-precision maps of each cell belonging to the area to be verified are created, each cell can be merged according to the overlapping road sections, so as to obtain the high-precision map corresponding to the area to be verified.

[0108] It should be noted that after the high-precision map construction of each cell is completed, before the cells are merged, the connectivity of each cell needs to be checked. The connectivity verification process is to verify whether there are any missing road connection sections in the high-precision map. If a road connection section is missing, it means that the connectivity of the high-precision map to be verified is missing; if a road connection section is not missing, it means that the connectivity of the high-precision map to be verified is not missing, and there are other sections at both ends of the road connection section that are topologically connected to the road connection section. Specifically, when performing connectivity verification, the road centerline of the high-precision map to be verified can be extracted, and the road centerline can be matched with the skeleton line of the corresponding position, wherein the matching content includes road label information, road position information and road angle information. Specifically, the matching results of each skeleton line segment in the road centerline, that is, the road numbers of the matched skeleton line segments, can be unioned, and then it can be checked which sections in the skeleton line have not been matched, that is, there are no corresponding matching objects. For example, if there are eight sections to be matched in the skeleton line, and the roads of the matched high-precision sections are numbered 1 to 8, a total of eight sections, then it can be shown that the road connectivity of the high-precision map is complete; and if the road numbers of the matched high-precision sections are 1 to 6, that is, there are two sections in the skeleton line that have not been matched, if these two sections are road-connected sections, it means that the road-connected sections are missing in the high-precision map, that is, there is a lack of road connectivity; if the two missing sections are not road-connected sections, it means that there is no lack of road connectivity in the high-precision map.

[0109] Furthermore, after verifying the connectivity of the high-precision map in each cell and before merging multiple cells belonging to the area to be verified according to overlapping road sections, the outermost road edge line of each road in each cell is determined, and the roads that do not belong to the outermost road edge line are deleted, thereby filtering out the miscellaneous lines appearing in the high-precision map to prevent these miscellaneous lines from affecting the accuracy of subsequent matching results.

[0110] In this embodiment, after completing the verification of the road connectivity of each cell, each cell belonging to the area to be verified can be merged. It should be noted that in order to ensure the accuracy of road merging, the location for road segment merging must be a straight road segment rather than a fork road segment, or a road segment with a lane number change within a preset range (e.g., 5 to 20 meters) before and after. Among them, the fork road segment can also be determined by the number of lanes.

[0111] Specifically, the cells belonging to the area to be verified may be merged according to the overlapping sections in the following manner, including:

[0112] For each overlapping road section between cells, the number of lanes corresponding to each candidate position point on each overlapping road section is determined, and each candidate position point whose number of lanes remains consistent within a preset range is used as a position point to be merged, and the overlapping road sections corresponding to the position points to be merged are merged into the same road section.

[0113] The number of lanes corresponding to the candidate position point can be determined by the following method:

[0114] For each candidate position point on each overlapping road segment, the normal line of the candidate position point is extended to both sides of the road until it extends to the lane edge line of the road, and the total number of lane lines intersecting with the normal line is determined, and the number of lanes corresponding to the candidate position point is determined based on the total number of lane lines obtained. The normal line of the candidate position point is a straight line that is perpendicular to the tangent line at the point and passes through the point.

[0115] Number of lanes = total number of lane lines - 1.

[0116] S220, matching each target traditional navigation path with a high-precision map of the area to be verified.

[0117] The matching content includes road label information, road position information and road angle information, and the map area corresponding to the set of each target traditional navigation path includes the area to be verified.

[0118] S230. During the matching process, if each target traditional navigation path is successfully matched with the high-precision map, it is determined that the high-precision map of the area to be verified is complete; if there are unmatched sections in the target traditional navigation path, the map area corresponding to the unmatched sections is used as the high-precision map area in the high-precision map where mapping is not completed.

[0119] Among them, the target traditional navigation path is a path provided by a traditional navigation map, or a path split from a skeleton line, and the skeleton line is a traditional map obtained by producing an open source map for creating the high-precision map.

[0120] S240, re-map the high-precision map area that has not been mapped, and use the re-mapped high-precision map of the area to be verified as a new high-precision map to be verified, and return to execute the operation of matching the target traditional navigation path with the new high-precision map to be verified until the high-precision map of the area to be verified is fully mapped.

[0121] In this embodiment, under the premise that the high-precision map is constructed according to the cell granularity, for the high-precision map of the map to be verified, each cell can be merged according to the repeated sections between cells after the mapping of each cell is completed to form a high-precision map of the area to be verified. In the process of merging each cell, a straight road section with a non-fork road and a consistent number of non-lanes within a set distance can be identified, and the cells are merged in the straight road section to ensure the accuracy of the cell merging.

[0122] Embodiment 3

[0123] Figure 3 A structural block diagram of a high-precision map integrity verification device provided in Embodiment 3 of the present invention, such as Figure 3 As shown, the device includes: a matching module 310 and an integrity checking module 320, wherein:

[0124] The matching module 310 is configured to match each target traditional navigation path with a high-precision map of the area to be verified, wherein the matching content includes road label information, road position information and road angle information; the map area corresponding to the set of each target traditional navigation path includes the area to be verified;

[0125] The integrity verification module 320 is configured to, during the matching process, if all target traditional navigation paths are successfully matched with the high-precision map, determine that the high-precision map construction of the area to be verified is complete; if there are unmatched sections in the target traditional navigation path, the map area corresponding to the unmatched sections will be used as the high-precision map area in which the mapping is not completed in the high-precision map, wherein the target traditional navigation path is a path provided by the traditional navigation map, or a path split from the skeleton line; the skeleton line is a traditional map obtained through open source map production for creating high-precision maps.

[0126] Optionally, when the target traditional navigation path is provided by a traditional navigation map, the apparatus provided in this embodiment further includes:

[0127] The target traditional navigation path determination module is specifically configured as follows:

[0128] Acquire multiple traditional navigation paths from a traditional navigation map, and match each traditional navigation path with a skeleton line of the area to be verified, to obtain the road number of each section in the skeleton line successfully matched with each traditional navigation path, wherein the map area corresponding to the set of each traditional navigation path includes the area to be verified;

[0129] The road numbers corresponding to different traditional navigation paths are sorted in descending order according to the number of numbers, and the traditional navigation path with the largest total number of road numbers and the road numbers that are successfully matched are temporarily stored from the sorted road numbers;

[0130] The temporarily stored road numbers are deleted from the road numbers corresponding to the unstored traditional navigation paths, and after the deletion operation is completed, the operation of sorting the road numbers corresponding to different traditional navigation paths in order of the number from large to small is returned, until the ratio of the number of temporarily stored road numbers to the total number of roads in the area to be verified reaches a preset ratio, and each temporarily stored traditional navigation path is used as a target traditional navigation path to be matched with the high-precision map of the area to be verified.

[0131] Optionally, the device provided by the embodiment of the present invention further includes:

[0132] The mapping module is used to remap the high-precision map area that has not been completed, and use the remapped high-precision map of the area to be verified as the new high-precision map to be verified, and return to execute the operation of matching the target traditional navigation path with the new high-precision map to be verified until the high-precision map of the area to be verified is fully mapped.

[0133] Optionally, the high-precision map is constructed according to the granularity of cells, there are overlapping areas between adjacent cells, and each cell is divided according to different high-precision road sections in the high-precision map;

[0134] Accordingly, before matching each target traditional navigation path with the high-precision map of the area to be verified, the device provided in this embodiment further includes:

[0135] A connectivity verification module is configured to verify the connectivity of the high-precision map in each cell;

[0136] The map merging module is configured to merge the cells belonging to the area to be verified according to the overlapping sections if there are no missing connectivity sections of the high-precision map in each cell, so as to obtain a high-precision map corresponding to the area to be verified.

[0137] Optional, map merging module, including:

[0138] The lane number determination unit is configured to determine the number of lanes corresponding to each candidate position point on each overlapping road segment between each cell if there is no missing connectivity road segment in the high-precision map in each cell;

[0139] A to-be-merged position point determination unit is configured to select candidate position points whose number of lanes is consistent within a preset range as to-be-merged position points;

[0140] The merging unit is configured to merge the overlapping road sections corresponding to the to-be-merged position points into a same road section.

[0141] Optionally, the lane number determination unit is specifically configured as follows:

[0142] For each candidate position point on each overlapping road segment, the normal line of the candidate position point is extended to both sides of the road until it reaches the lane edge line of the road;

[0143] The total number of lane lines intersecting the normal line is determined, and the number of lanes corresponding to the candidate position point is determined based on the total number of lane lines obtained.

[0144] Optionally, after verifying the connectivity of the high-precision map in each cell and before merging the multiple cells belonging to the area to be verified according to overlapping sections, the apparatus provided by the embodiment of the present invention further includes:

[0145] For each road in each cell, the outermost road edge line of the road is determined, and the roads that do not belong to the outermost road edge line are deleted.

[0146] The high-precision map integrity verification device provided in the embodiment of the present invention can execute the high-precision map integrity verification method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not described in detail in the above embodiments, please refer to the high-precision map integrity verification method provided in any embodiment of the present invention.

[0147] Embodiment 4

[0148] Figure 4 A structural block diagram of an electronic device provided in Embodiment 4 of the present invention, such as Figure 4 As shown, the electronic device includes:

[0149] A memory 510 storing executable program codes;

[0150] a processor 520 coupled to the memory 510;

[0151] The processor 520 calls the executable program code stored in the memory 510 to execute the integrity verification method of the high-precision map provided by any embodiment of the present invention.

[0152] Embodiment 5

[0153] Based on the above embodiments, another embodiment of the present invention provides a vehicle, wherein the vehicle includes the device as described in any of the above embodiments, or includes the electronic device as described above.

[0154] Figure 5 This is a schematic diagram of a vehicle provided in Embodiment 5 of the present invention. Figure 5 As shown, the vehicle includes a speed sensor 61, an ECU (Electronic Control Unit) 62, a GPS (Global Positioning System) positioning device 63, and a T-Box (Telematics Box) 64. The speed sensor 61 is used to measure the vehicle speed and use the vehicle speed as the empirical speed for model training; the GPS positioning device 63 is used to obtain the current geographic location of the vehicle; the T-Box 64 can communicate with the server as a gateway; and the ECU 62 can execute the integrity verification method of the high-precision map.

[0155] In addition, the vehicle may also include: a V2X (Vehicle-to-Everything) module 65, a radar 66 and a camera 67. The V2X module 65 is used to communicate with other vehicles, roadside equipment, etc.; the radar 66 or the camera 67 is used to sense the road environment information in the front and / or other directions to obtain original point cloud data; the radar 66 and / or the camera 67 can be configured at the front and / or rear of the vehicle body.

[0156] Based on the above method embodiments, another embodiment of the present invention provides a storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement the high-precision map integrity verification method as described in any of the above embodiments.

[0157] Those skilled in the art can understand that the accompanying drawings are only schematic diagrams of an embodiment, and the modules or processes in the accompanying drawings are not necessarily required to implement the present invention.

[0158] Those skilled in the art can understand that the modules in the device in the embodiment can be distributed in the device in the embodiment according to the description of the embodiment, or can be changed accordingly and located in one or more devices different from the embodiment. The modules in the above embodiment can be combined into one module, or can be further divided into multiple sub-modules.

[0159] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for checking the integrity of a high-precision map, characterized in that: include: Matching each target traditional navigation path with a high-precision map of the area to be verified, wherein the matching content includes road label information, road position information and road angle information; the map area corresponding to the set of each target traditional navigation path includes the area to be verified; During the matching process, if each target traditional navigation path is successfully matched with the high-precision map, it is determined that the high-precision map of the area to be verified is complete; If there are unmatched road sections in the target traditional navigation path, the map area corresponding to the unmatched road sections will be used as the high-precision map area for which mapping is not completed in the high-precision map, wherein the target traditional navigation path is a path provided by the traditional navigation map, or a path split from a skeleton line; the skeleton line is a traditional map obtained through open source map production for creating the high-precision map.

2. The method according to claim 1, characterized in that In the case where the target traditional navigation path is provided by a traditional navigation map, the target traditional navigation path is determined in the following manner: Acquire multiple traditional navigation paths from a traditional navigation map, and match each traditional navigation path with a skeleton line of the area to be verified, to obtain the road number of each road section in the skeleton line that successfully matches each traditional navigation path, wherein the map area corresponding to the set of each traditional navigation path includes the area to be verified; The road numbers corresponding to different traditional navigation paths are sorted in descending order according to the number of numbers, and the traditional navigation path with the largest total number of road numbers and the road numbers that are successfully matched are temporarily stored from the sorted road numbers; The temporarily stored road numbers are deleted from the road numbers corresponding to the unstored traditional navigation paths, and after the deletion operation is completed, the operation of sorting the road numbers corresponding to different traditional navigation paths in order of the number from large to small is returned, until the ratio of the number of temporarily stored road numbers to the total number of roads in the area to be verified reaches a preset ratio, and each temporarily stored traditional navigation path is used as a target traditional navigation path to be matched with the high-precision map of the area to be verified.

3. The method according to claim 1, characterized in that The method further comprises: The high-precision map area that has not been completed is remapped, and the high-precision map of the area to be verified after the remap is used as a new high-precision map to be verified, and the operation of matching the target traditional navigation path with the new high-precision map to be verified is returned to execute until the high-precision map of the area to be verified is fully mapped.

4. The method according to any one of claims 1 to 3, characterized in that: The high-precision map is constructed according to the granularity of the cell, there is an overlapping area between adjacent cells, and each cell is divided according to different high-precision road sections in the high-precision map; Accordingly, before matching each target traditional navigation path with the high-precision map of the area to be verified, the method further includes: The connectivity of the high-precision map in each cell is checked. If there are no missing sections in the connectivity of the high-precision map in each cell, the cells belonging to the area to be checked are merged according to the overlapping sections to obtain the high-precision map corresponding to the area to be checked.

5. The method according to claim 4, characterized in that The merging of cells belonging to the area to be verified according to overlapping sections includes: For each overlapping road section between each cell, determine the number of lanes corresponding to each candidate position point on each overlapping road section, and use each candidate position point whose number of lanes is consistent within a preset range as a position point to be merged; The overlapping road sections corresponding to the to-be-merged position points are merged into the same road section.

6. The method according to claim 5, characterized in that The determining of the number of lanes corresponding to each candidate position point on each overlapping road section includes: For each candidate position point on each overlapping road segment, the normal line of the candidate position point is extended to both sides of the road until it reaches the lane edge line of the road; The total number of lane lines intersecting the normal line is determined, and the number of lanes corresponding to the candidate position point is determined according to the total number of lane lines obtained.

7. The method according to claim 4, characterized in that After verifying the connectivity of the high-precision map in each cell and before merging the multiple cells belonging to the area to be verified according to the overlapping sections, the method further includes: For each road in each cell, the outermost road edge line of the road is determined, and the roads that do not belong to the outermost road edge line are deleted.

8. A high-precision map integrity verification device, characterized in that: include: A matching module is configured to match each target traditional navigation path with a high-precision map of the area to be verified, wherein the matching content includes road label information, road position information and road angle information; the map area corresponding to the set of each target traditional navigation path includes the area to be verified; The integrity verification module is configured to, during the matching process, if all target traditional navigation paths are successfully matched with the high-precision map, determine that the high-precision map construction of the area to be verified is complete; if there are unmatched sections in the target traditional navigation path, then use the map area corresponding to the unmatched sections as the high-precision map area in which the mapping is not completed in the high-precision map, wherein the target traditional navigation path is a path provided by the traditional navigation map, or a path split from a skeleton line; the skeleton line is a traditional map obtained through open source map production for creating the high-precision map.

9. The device according to claim 8, characterized in that In the case where the target traditional navigation path is provided by a traditional navigation map, the device further includes: The target traditional navigation path determination module is specifically configured as follows: Acquire multiple traditional navigation paths from a traditional navigation map, and match each traditional navigation path with a skeleton line of the area to be verified, to obtain the road number of each road section in the skeleton line that successfully matches each traditional navigation path, wherein the map area corresponding to the set of each traditional navigation path includes the area to be verified; The road numbers corresponding to different traditional navigation paths are sorted in descending order according to the number of numbers, and the traditional navigation path with the largest total number of road numbers and the road numbers that are successfully matched are temporarily stored from the sorted road numbers; The temporarily stored road numbers are deleted from the road numbers corresponding to the unstored traditional navigation paths, and after the deletion operation is completed, the operation of sorting the road numbers corresponding to different traditional navigation paths in order of the number from large to small is returned, until the ratio of the number of temporarily stored road numbers to the total number of roads in the area to be verified reaches a preset ratio, and each temporarily stored traditional navigation path is used as a target traditional navigation path to be matched with the high-precision map of the area to be verified.

10. The device according to claim 8, characterized in that The device also includes: The mapping module is used to remap the high-precision map area that has not been completed, and use the remapped high-precision map of the area to be verified as a new high-precision map to be verified, and return to perform the operation of matching the target traditional navigation path with the new high-precision map to be verified until the high-precision map of the area to be verified is fully mapped.

11. The device according to any one of claims 7 to 10, characterized in that: The high-precision map is constructed according to the granularity of the cell, there is an overlapping area between adjacent cells, and each cell is divided according to different high-precision road sections in the high-precision map; Accordingly, before matching each target traditional navigation path with the high-precision map of the area to be verified, the device further includes: A connectivity verification module is configured to verify the connectivity of the high-precision map in each cell; The map merging module is configured to merge the cells belonging to the area to be verified according to the overlapping sections if there are no missing connectivity sections of the high-precision map in each cell, so as to obtain a high-precision map corresponding to the area to be verified.

12. The device according to claim 11, characterized in that The map merging module comprises: The lane number determination unit is configured to determine the number of lanes corresponding to each candidate position point on each overlapping road segment between each cell if there is no missing connectivity road segment in the high-precision map in each cell; A to-be-merged position point determination unit is configured to select candidate position points whose number of lanes is consistent within a preset range as to-be-merged position points; The merging unit is configured to merge the overlapping road sections corresponding to the to-be-merged position points into a same road section.

13. The device according to claim 12, characterized in that The lane number determination unit is specifically configured as follows: For each candidate position point on each overlapping road segment, extending the normal line of the candidate position point to both sides of the road until it reaches the lane edge line of the road; The total number of lane lines intersecting the normal line is determined, and the number of lanes corresponding to the candidate position point is determined according to the total number of lane lines obtained.

14. The device according to claim 11, characterized in that After verifying the connectivity of the high-precision map in each cell and before merging the multiple cells belonging to the area to be verified according to the overlapping sections, the device further includes: For each road in each cell, the outermost road edge line of the road is determined, and the roads that do not belong to the outermost road edge line are deleted.

15. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

16. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

17. A vehicle, characterized in that: The vehicle comprises the device as claimed in any one of claims 8 to 14, or comprises the electronic device as claimed in claim 15.

Images