High-precision map data processing method and device, medium, equipment and driving system

Abstract

The application discloses a high-precision map data processing method and device, a medium and equipment, and belongs to the technical field of electronic maps. The method mainly comprises the following steps: obtaining a high-precision road section matched with each trajectory point according to the absolute position of the trajectory point of a traditional navigation path in a traditional navigation map; obtaining a plurality of continuous high-precision road sections matched with a corresponding traditional navigation path according to a plurality of continuous trajectory points; checking whether a redundant high-precision road section exists in the plurality of continuous high-precision road sections according to the topological connection relationship between the plurality of continuous high-precision road sections, deleting the redundant high-precision road section if the redundant high-precision road section exists, and merging and connecting other related road sections in the plurality of continuous high-precision road sections; and obtaining a high-precision map matched with the corresponding traditional navigation path according to the plurality of continuous high-precision road sections. The application can improve the matching accuracy.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a high-precision map data processing method, apparatus, medium, equipment, and driving system. Background Technology

[0002] When existing autonomous driving products are deployed, high-precision maps cannot directly provide navigation functionality. It is necessary to match traditional navigation map products onto high-precision maps to determine which parts of the high-precision map should be activated on the vehicle for driver assistance and autonomous driving. Existing technologies using Hidden Markov Models to match high-precision maps suffer from low accuracy due to inaccurate positioning and the matching of numerous redundant road segments. Summary of the Invention

[0003] To address the problems existing in the prior art, this application mainly provides a high-precision map data processing method, apparatus, medium, and device. By checking whether there are redundant high-precision road segments among multiple consecutive high-precision road segments according to the topological connection relationship between them, and merging and connecting multiple consecutive high-precision road segments with redundancy, the matching accuracy is improved.

[0004] In a first aspect, embodiments of this application provide a high-precision map data processing method, which includes:

[0005] Based on the absolute position of trajectory points in a traditional navigation map, a high-precision road segment matching each trajectory point is obtained; multiple consecutive high-precision road segments matching the corresponding traditional navigation path are obtained based on multiple consecutive trajectory points; the topological connection relationship between the multiple consecutive high-precision road segments is used to check whether there are redundant high-precision road segments, and if so, the redundant high-precision road segments are deleted, and other related road segments in the multiple consecutive high-precision road segments are merged and connected; and a high-precision map matching the corresponding traditional navigation path is obtained based on the multiple consecutive high-precision road segments.

[0006] Secondly, embodiments of this application provide a high-precision map data processing apparatus, comprising:

[0007] The system comprises a matching module for obtaining a high-precision road segment matching each trajectory point based on the absolute position of the trajectory points in a traditional navigation path on a traditional navigation map; a first continuous processing module for obtaining multiple consecutive high-precision road segments matching the corresponding traditional navigation path based on multiple consecutive trajectory points; a second continuous processing module for checking whether there are redundant high-precision road segments among the multiple consecutive high-precision road segments based on the topological connection relationship between them, deleting the redundant high-precision road segments if they exist, and merging and connecting other related road segments among the multiple consecutive high-precision road segments; and a third continuous processing module for obtaining a high-precision map matching the corresponding traditional navigation path based on the multiple consecutive high-precision road segments.

[0008] Thirdly, embodiments of this application provide a driving system that includes the aforementioned high-precision map data processing device.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer instructions that are operated to perform the high-precision map data processing method described above.

[0010] Fifthly, embodiments of this application provide a computer device including a processor and a memory, the memory storing computer instructions that are operated to execute the high-precision map data processing method described above.

[0011] The beneficial effects achievable by the technical solution of this application are: a high-precision map data processing method, apparatus, medium, equipment, and driving system. This application, based on the topological connection relationship between multiple consecutive high-precision road segments matched with traditional navigation paths, checks whether redundant high-precision road segments exist among these multiple consecutive high-precision road segments, and merges and connects redundant consecutive high-precision road segments, thereby improving matching accuracy. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description exemplarily illustrate some embodiments of this application.

[0013] Figure 1 This is a schematic flowchart of a specific implementation method for a high-precision map data processing method according to this application;

[0014] Figure 2 This is a schematic diagram of continuous high-precision road segments in a specific embodiment of a high-precision map data processing method of this application;

[0015] Figure 3This is a schematic diagram of a high-precision map data processing method according to a specific embodiment of the present application, showing that there are redundant high-precision road segments and missing matching high-precision road segments in multiple consecutive high-precision road segments;

[0016] Figure 4 This is a schematic diagram of a high-precision map data processing method according to a specific embodiment of the present application, showing that there are redundant high-precision road segments and missing matching high-precision road segments in multiple consecutive high-precision road segments;

[0017] Figure 5 This is a schematic diagram of a specific embodiment of a high-precision map data processing device according to this application;

[0018] The accompanying drawings have illustrated specific embodiments of this disclosure, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this disclosure to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0019] The preferred embodiments of this application will now be described in detail with reference to the accompanying drawings, so that the advantages and features of this application can be more easily understood by those skilled in the art, thereby providing a clearer and more definite definition of the scope of protection of this application.

[0020] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0021] Compared to traditional electronic maps, high-precision maps offer higher accuracy and more data dimensions. Traditional electronic maps have meter-level accuracy, commercial GPS has 5-meter accuracy, while high-precision maps have centimeter-level accuracy. Traditional electronic maps only record road-level data: road shape, slope, curvature, paving, direction, etc. High-precision maps not only add lane-related data, such as lane line type and lane width, but also a large amount of target data such as elevated objects, guardrails, trees, road edge types, and roadside landmarks. High-precision maps can clearly distinguish details such as lane line types and roadside landmarks.

[0022] In the process of matching high-precision navigation maps with traditional navigation routes, existing technologies often result in inaccurate positioning, leading to the matching of numerous redundant road segments and thus lower accuracy of the high-precision maps.

[0023] This application matches relatively fixed road ranges in high-precision maps with navigation paths in traditional navigation maps. After obtaining multiple consecutive high-precision road segments based on continuous trajectory points on the traditional navigation path, it checks for redundant high-precision road segments based on their topological connectivity. Multiple redundant consecutive high-precision road segments are then merged and connected to improve matching accuracy.

[0024] The technical solutions of this application will now be described in detail with reference to specific embodiments and accompanying drawings. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0025] Figure 1 This application illustrates a specific embodiment of a high-precision map data processing method.

[0026] exist Figure 1 The specific implementation of the high-precision map data processing method of this application shown includes the following steps: Step S101: Based on the absolute position of the trajectory points of the traditional navigation path in the traditional navigation map, obtain a high-precision road segment matching each trajectory point; Step S102: Based on multiple consecutive trajectory points, obtain multiple consecutive high-precision road segments matching the corresponding traditional navigation path; Step S103: Based on the topological connection relationship between the multiple consecutive high-precision road segments, check whether there are redundant high-precision road segments among the multiple consecutive high-precision road segments. If so, delete the redundant high-precision road segments and merge and connect other related road segments among the multiple consecutive high-precision road segments; and Step S104: Based on the multiple consecutive high-precision road segments, obtain a high-precision map matching the corresponding traditional navigation path.

[0027] This application checks for redundant high-precision road segments among multiple consecutive high-precision road segments that match traditional navigation paths based on the topological connection relationship between them, and merges and connects multiple consecutive high-precision road segments with redundancy, thereby improving the matching accuracy.

[0028] Process S101 indicates that, based on the absolute position of the trajectory points of the traditional navigation path in the traditional navigation map, a high-precision road segment matching each trajectory point is obtained. This facilitates the combination of the matched high-precision road segments into a continuous high-precision road segment based on the continuous trajectory points on the traditional navigation path.

[0029] In an optional specific embodiment of this application, the process of obtaining a high-precision road segment matching each trajectory point based on the absolute position of the trajectory points of the traditional navigation path in the traditional navigation map includes obtaining a high-precision road segment matching each trajectory point based on the absolute position of the trajectory points of the traditional navigation path in the traditional navigation map and the road centerline of the high-precision map.

[0030] In an optional specific embodiment of this application, the process of obtaining a high-precision road segment matching each trajectory point based on the absolute position of the trajectory points of the traditional navigation path in the traditional navigation map includes: obtaining the high-precision road segment range of the high-precision road segment using the road boundary of each high-precision road segment in the high-precision map and the boundaries at the beginning and end of the high-precision road segment; and obtaining a high-precision road segment matching each trajectory point based on the absolute position of the trajectory points of the traditional navigation path in the traditional navigation map and the absolute position of multiple high-precision road segment ranges.

[0031] Compared to obtaining high-precision road segments that match each trajectory point based on the road centerline of a high-precision map, this embodiment obtains a fixed road range in a high-definition map, and then uses the road range of the high-definition map to match the trajectory points of the traditional navigation path. If the range of the trajectory point and the corresponding high-precision road segment meets a certain distance requirement, it means that the trajectory point matches the corresponding high-precision road segment. This effectively avoids mismatches and improves the matching accuracy during the matching process.

[0032] Process S102 represents the process of obtaining multiple consecutive high-precision road segments that match the corresponding traditional navigation path based on multiple consecutive trajectory points. This facilitates checking for any missing high-precision road segments based on the topological connection relationship between the multiple consecutive high-precision road segments.

[0033] In an optional specific embodiment of this application, the process of obtaining multiple consecutive high-precision road segments matching the corresponding traditional navigation path based on multiple consecutive trajectory points includes calculating, based on the direction of the navigation path, the distance between each trajectory point and the next trajectory point, and the angle between the road centerline in the traditional navigation map and the road centerline in the high-precision map, a topologically continuous high-precision road segment matching each of the above trajectory points.

[0034] In an optional specific embodiment of this application, the process of obtaining multiple consecutive high-precision road segments matching the corresponding traditional navigation path based on multiple consecutive trajectory points includes, according to the direction of the navigation path, sequentially calculating the continuous high-precision road segments that intersect the trajectory lines connecting each trajectory point and the next trajectory point on the traditional navigation path, and the high-precision road segments matching each trajectory point can be topologically connected.

[0035] In one specific embodiment of this application, the process of obtaining multiple consecutive high-precision road segments matching the corresponding traditional navigation paths based on multiple consecutive trajectory points of the traditional navigation paths includes, according to the direction of the navigation path, sequentially calculating consecutive high-precision road segments that intersect the trajectory lines connecting each trajectory point and the next trajectory point on the traditional navigation path, and whose high-precision road segments matching each trajectory point are topologically connectable. Specifically, as shown... Figure 2 As shown, high-precision road segment c is a continuous segment of high-precision road segment b.

[0036] When obtaining continuous high-precision road segments based on the distance between preceding and following trajectory points and the angle between the trajectory direction and the road centerline in traditional navigation paths, if some roads in the high-precision map are short and the distance between two adjacent trajectory points is far, the observation range of the two trajectory points cannot reach the road, resulting in missed observations of the corresponding high-precision map roads. Optimization can only be achieved by inserting observation points, thus increasing the number of observations and calculations. This embodiment, however, utilizes the intersection of the line connecting preceding and following trajectory points with the road segment to avoid missing road segments and eliminates the need to add observation points. Therefore, it improves observation efficiency without increasing computational load, thereby improving the efficiency of matching high-precision maps with traditional navigation paths.

[0037] Process S103 represents the process of checking whether there are redundant high-precision road segments among the multiple consecutive high-precision road segments according to the topological connection relationship between them. If there are, the redundant high-precision road segments are deleted, and other related road segments among the multiple consecutive high-precision road segments are merged and connected. This process can greatly improve the accuracy of traditional navigation path matching high-precision maps.

[0038] Specifically, in real-world scenarios, inaccurate positioning of trajectory points may lead to mismatches between estimated points and high-precision road segments. This results in redundant road segments being incorrectly matched among multiple consecutive high-precision road segments derived from continuous trajectory points along the navigation path. For example... Figure 3 As shown and Figure 4 As shown, this application greatly improves the matching accuracy by checking for any missing high-precision road segments and merging and connecting them accordingly.

[0039] In an optional embodiment of this application, the process of checking whether there are redundant high-precision road segments among multiple consecutive high-precision road segments based on the topological connection relationship between multiple consecutive high-precision road segments includes: merging and connecting multiple consecutive high-precision road segments according to the direction of the navigation path to obtain multiple high-precision road segment groups, wherein two adjacent high-precision road segments within a high-precision road segment group can be topologically connected; determining whether there is a topological connection relationship between each pair of high-precision road segments belonging to two adjacent high-precision road segment groups; if so, then there are redundant high-precision road segments among the multiple consecutive high-precision road segments; and obtaining redundant high-precision road segments based on the high-precision road segments belonging to two adjacent high-precision road segment groups that have a topological connection relationship.

[0040] In this specific embodiment, the process of merging and connecting other related road segments in multiple consecutive high-precision road segments includes merging and connecting high-precision road segments that belong to two adjacent high-precision road segment groups and have a topological connection relationship.

[0041] In this specific embodiment, redundant road segments within two adjacent high-precision road segment groups are deleted, and the high-precision road segments within the two adjacent high-precision road segment groups are merged and connected, which can improve the matching accuracy.

[0042] In a specific instance of this application, such as Figure 3 As shown in a specific embodiment of this application, such as Figure 3 As shown, there are six consecutive high-precision road segments "1, 2, 3, 4, 5, 6". High-precision road segments 1 and 2, and 2 and 3 can be topologically connected respectively; 4 and 5, and 5 and 6 can be topologically connected respectively; 3 and 4 cannot be topologically connected, thus resulting in two high-precision groupings: "1, 2, 3" and "4, 5, 6". Upon inspection, high-precision road segments 3 and 6, belonging to the two high-precision groupings "1, 2, 3" and "4, 5, 6" respectively, can be topologically connected. Therefore, there are redundant road segments among the six consecutive high-precision road segments "1, 2, 3, 4, 5, 6". Based on the topological connection positions of high-precision road segments 3 and 6, redundant high-precision road segments 4 and 5 are obtained. Redundant high-precision road segments 4 and 5 are deleted, and the topologically connected segments 3 and 6 are merged and connected.

[0043] In an optional specific embodiment of this application, the process of checking whether there are redundant high-precision road segments among multiple consecutive high-precision road segments based on the topological connection relationship between multiple consecutive high-precision road segments includes: merging and connecting multiple consecutive high-precision road segments according to the direction of the navigation path to obtain multiple high-precision road segment groups, wherein two adjacent high-precision road segments within a high-precision road segment group can be topologically connected; determining whether the road segment length of each high-precision road segment group is not greater than a predetermined first length threshold; if it is not greater, then there are redundant high-precision road segments among the multiple consecutive high-precision road segments, and the high-precision road segments within the corresponding high-precision road segment group are determined to be redundant high-precision road segments, and such redundant high-precision road segments are marked as dirty-matched high-precision road segments.

[0044] Optionally, the first length threshold mentioned above is 500m.

[0045] In a specific instance of this application, such as Figure 4 As shown, eight consecutive high-precision road segments "8, 9, 10, 11, 12, 13, 14, 15" are topologically connected. High-precision road segments 8 and 9, and 9 and 10 can be topologically connected respectively; 11 and 12 can be topologically connected; 13 and 14, and 14 and 15 can be topologically connected respectively. Therefore, three high-precision road segment groups are obtained: "8, 9, 10", "11, 12" and "13, 14, 15". After calculation, the length of the high-precision road segment group "11, 12" is not greater than the first length threshold. Therefore, high-precision road segments 11 and 12 are directly judged as dirty matching high-precision road segments.

[0046] In a specific example of this application, the process of merging and connecting other related road segments in multiple consecutive high-precision road segments includes,

[0047] In the grouping of multiple consecutive high-precision road segments after deleting dirty matching road segments, it is determined whether there is a topological connection relationship between each pair of high-precision road segments belonging to two adjacent high-precision road segment groups. If there is, there are redundant high-precision road segments among the multiple consecutive high-precision road segments. Based on the high-precision road segments belonging to two adjacent high-precision road segment groups that have a topological connection relationship, the redundant high-precision road segments are obtained, the redundant high-precision road segments are deleted, and the high-precision road segments belonging to two adjacent high-precision road segment groups that have a topological connection relationship are merged and connected.

[0048] In a specific example of this application, the process of merging and connecting other related road segments in multiple consecutive high-precision road segments includes, in the grouping of multiple consecutive high-precision road segments after removing redundancy, determining whether two adjacent high-precision road segments between two adjacent high-precision road segment groups can be connected by suspected missing-matching high-precision road segments where trajectory points of traditional navigation paths are not matched in the high-precision map, wherein the length of the suspected missing-matching high-precision road segment is not greater than a predetermined second length threshold; if so, the suspected missing-matching high-precision road segment is determined as a missing-matching high-precision road segment; otherwise, there is no missing-matching high-precision road segment.

[0049] Optionally, the second length threshold mentioned above is 500m.

[0050] Specifically, if the suspected missed high-precision road segment is long enough, then even if the trajectory points of the traditional navigation path deviate, there will be no missed match. Therefore, only when the length of the suspected missed high-precision road segment is insufficient, less than the predetermined second length threshold, will trajectory point deviation lead to a missed match.

[0051] In this specific embodiment, high-precision road segments with missing matching are used to merge and connect two adjacent high-precision road segments between two adjacent high-precision road segment groups.

[0052] In a specific example of this application, the grouping of two adjacent high-precision road segments after removing redundancy from multiple consecutive high-precision road segments includes, as follows: Figure 4 The six consecutive high-precision road segments shown are "8, 9, 10, 13, 14, 15". High-precision road segments 8 and 9, and 9 and 10 can be topologically connected respectively; 13 and 14, and 14 and 15 can be topologically connected respectively; 10 and 13 cannot be topologically connected. Therefore, we get two groups: "8, 9, 10" and "13, 14, 15". After inspection, the two groups "8, 9, 10" and "13, 14, 15" can be connected by high-precision road segment "16" that meets the length requirement. Therefore, there is a missing high-precision road segment among the above six consecutive high-precision road segments. High-precision road segment 16 is used to merge and connect the two groups "8, 9, 10" and "13, 14, 15".

[0053] In a specific example of this application, firstly, multiple consecutive high-precision road segments are merged and connected to obtain multiple high-precision road segment groups. Adjacent high-precision road segments within a high-precision road segment group can be topologically connected. It is then determined whether a topological connection exists between any two high-precision road segments belonging to adjacent high-precision road segment groups. If not, it is determined whether two adjacent high-precision road segments between adjacent high-precision road segment groups can be connected through suspected missing-match high-precision road segments in the high-precision map where trajectory points of traditional navigation paths are not matched. The length of the suspected missing-match high-precision road segment is not greater than a predetermined second length threshold. If so, the suspected missing-match high-precision road segment is identified as a missing-match high-precision road segment, and the missing-match high-precision road segment is used to merge and connect adjacent high-precision road segments between adjacent high-precision road segment groups.

[0054] Process S104 represents obtaining a high-precision map that matches the corresponding traditional navigation path based on multiple consecutive high-precision road segments, which can ultimately obtain a high-precision map that matches the corresponding traditional navigation path, so as to further open up the corresponding high-precision map products and provide services.

[0055] Figure 5This application illustrates a specific embodiment of a high-precision map data processing apparatus.

[0056] exist Figure 5 The specific embodiment of the high-precision map data processing device of this application shown includes: a matching module 501, used to obtain a high-precision road segment matching each trajectory point based on the absolute position of the trajectory points of the traditional navigation path in the traditional navigation map; a first continuous processing module 502, used to obtain multiple continuous high-precision road segments matching the corresponding traditional navigation path based on multiple consecutive trajectory points; a second continuous processing module 503, used to check whether there are redundant high-precision road segments among the multiple continuous high-precision road segments according to the topological connection relationship between them, and if so, delete the redundant high-precision road segments and merge and connect other related road segments among the multiple continuous high-precision road segments; and a third continuous processing module 504, used to obtain a high-precision map matching the corresponding traditional navigation path based on the multiple continuous high-precision road segments.

[0057] The device in this application checks for redundant high-precision road segments based on the topological connections between multiple consecutive high-precision road segments that match traditional navigation paths. It then merges and connects redundant high-precision road segments, thereby improving matching accuracy.

[0058] The matching module 501 is used to obtain high-precision road segments that match each trajectory point based on the absolute position of the trajectory points of the traditional navigation path in the traditional navigation map. It can easily form a continuous high-precision road segment based on the continuous trajectory points on the traditional navigation path.

[0059] This embodiment obtains a fixed road range in a high-definition map, and then matches the road range of the high-definition map with the trajectory points of traditional navigation paths. If the trajectory point and the range of the corresponding high-precision road segment meet a certain distance requirement, it means that the trajectory point matches the corresponding high-precision road segment. This can effectively avoid mismatches and improve the matching accuracy during the matching process.

[0060] The first continuous processing module 502 is used to obtain multiple continuous high-precision road segments that match the corresponding traditional navigation path based on multiple continuous trajectory points. It can easily check whether there are any missing high-precision road segments based on the topological connection relationship between the multiple continuous high-precision road segments.

[0061] The second continuous processing module 503 is used to check whether there are redundant high-precision road segments in multiple continuous high-precision road segments according to the topological connection relationship between multiple continuous high-precision road segments. If there are, the redundant high-precision road segments are deleted, and other related road segments in multiple continuous high-precision road segments are merged and connected. This can greatly improve the accuracy of traditional navigation path matching high-precision maps.

[0062] Specifically, in real-world scenarios, inaccurate positioning of trajectory points may lead to mismatches between estimated points and high-precision road segments. This results in redundant road segments being incorrectly matched among multiple consecutive high-precision road segments derived from continuous trajectory points along the navigation path. For example... Figure 3 As shown and Figure 4 As shown, this application greatly improves the matching accuracy by checking for any missing high-precision road segments and merging and connecting them accordingly.

[0063] The fourth continuous processing module 504 is used to obtain a high-precision map that matches the corresponding traditional navigation path based on multiple consecutive high-precision road segments. It can ultimately obtain a high-precision map that matches the corresponding traditional navigation path, so as to further develop the corresponding high-precision map product and provide services.

[0064] The high-precision map data processing apparatus provided in this application can be used to execute the high-precision map data processing method described in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0065] In one specific embodiment of this application, the functional modules of the high-precision map data processing device of this application can be directly in hardware, in software modules executed by a processor, or in a combination of both.

[0066] Software modules may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in this art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium.

[0067] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general-purpose processor can be a microprocessor, but alternatively, it can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors incorporating a DSP core, or any other such configuration. Alternatively, the storage medium can be integrated with the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in the user terminal. Alternatively, the processor and storage medium can reside as discrete components in the user terminal.

[0068] In another specific embodiment of this application: a driving system is provided, wherein the driving system includes a high-precision map data processing device, optionally, the image sensing and display device includes a processor and a memory, the processor and the memory being coupled; the high-precision map data processing device is used to execute the high-precision map data processing method in any of the above schemes.

[0069] In another specific embodiment of this application, a computer-readable storage medium is provided, which stores computer instructions that are operated to perform the high-precision map data processing method in any of the above schemes.

[0070] In another specific embodiment of this application, a computer device includes a processor and a memory, the memory storing computer instructions that are operated to perform the high-precision map data processing method in any of the above schemes.

[0071] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0072] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0073] The above are merely embodiments of this application and do not limit the scope of this patent application. Any equivalent structural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of this application.

Claims

1. A method for processing high-precision map data, characterized in that, include: Based on the absolute position of the trajectory points of the traditional navigation path in the traditional navigation map, a high-precision road segment matching each trajectory point is obtained; Based on multiple consecutive trajectory points, multiple consecutive high-precision road segments matching the corresponding traditional navigation paths are obtained; The system checks for redundant high-precision road segments based on their topological connections. Specifically, based on the direction of the navigation path, the multiple consecutive high-precision road segments are merged and connected to form multiple high-precision road segment groups. Adjacent high-precision road segments within a group can be topologically connected, while adjacent high-precision road segment groups cannot be topologically connected. The system determines whether there is a topological connection between any two high-precision road segments belonging to adjacent high-precision road segment groups. If such a connection exists, then a redundant high-precision road segment exists within the multiple consecutive high-precision road segments. The redundant high-precision road segment is identified based on the high-precision road segments belonging to adjacent high-precision road segment groups that have a topological connection. If redundant high-precision road segments exist, they are deleted, and other related road segments among the multiple consecutive high-precision road segments are merged and connected; and A high-precision map matching the corresponding traditional navigation path is obtained based on the multiple consecutive high-precision road segments.

2. The high-precision map data processing method according to claim 1, characterized in that, The process of merging and connecting other related road segments among the multiple consecutive high-precision road segments includes: High-precision road segments belonging to two adjacent high-precision road segment groups and having a topological connection relationship are merged and connected.

3. The high-precision map data processing method according to claim 1, characterized in that, The process of checking whether there are redundant high-precision road segments among the multiple consecutive high-precision road segments based on the topological connection relationship between them includes: The system determines whether the length of each high-precision road segment group is not greater than a predetermined first length threshold. If it is not greater, then the multiple consecutive high-precision road segments contain redundant high-precision road segments, and the high-precision road segments in the corresponding high-precision road segment group are determined to be redundant high-precision road segments.

4. The high-precision map data processing method according to claim 3, characterized in that, The process of merging and connecting other related road segments among the multiple consecutive high-precision road segments includes: In the grouping of the multiple consecutive high-precision road segments after removing redundancy, it is determined whether there is a topological connection relationship between each pair of high-precision road segments belonging to two adjacent high-precision road segment groups; if so, there is a redundant high-precision road segment among the multiple consecutive high-precision road segments. The redundant high-precision road segment is obtained based on the high-precision road segments belonging to two adjacent high-precision road segment groups that have a topological connection relationship. The redundant high-precision road segment is deleted, and the high-precision road segments belonging to two adjacent high-precision road segment groups that have a topological connection relationship are merged and connected. or In the grouping of the multiple consecutive high-precision road segments after removing redundancy, it is determined whether two adjacent high-precision road segments between two adjacent high-precision road segment groups can be connected by a suspected missing high-precision road segment where the trajectory point of the traditional navigation path is not matched in the high-precision map. The length of the suspected missing high-precision road segment is not greater than a predetermined length threshold. If possible, the suspected missing high-precision road segment is identified as the missing high-precision road segment; otherwise, there is no missing high-precision road segment.

5. The high-precision map data processing method according to claim 1, characterized in that, The process of obtaining a high-precision road segment matching each trajectory point based on the absolute position of the trajectory points in a traditional navigation path on a traditional navigation map includes: The roads in the high-precision map are segmented to obtain multiple high-precision road segments, and the range of multiple high-precision road segments is obtained by using the road edge line and the segmentation edge line of each high-precision road segment; as well as, Based on the absolute position of the trajectory points of the traditional navigation path in the traditional navigation map and the absolute position of the range of the multiple high-precision road segments, a high-precision road segment matching each trajectory point is obtained.

6. The high-precision map data processing method according to claim 1, characterized in that, The process of obtaining multiple consecutive high-precision road segments that match the corresponding traditional navigation path based on multiple consecutive trajectory points includes, Based on the direction of the navigation path, the continuous high-precision road segments that intersect with the trajectory lines connecting each trajectory point and the next trajectory point on the traditional navigation path and match each trajectory point are calculated sequentially.

7. A high-precision map data processing device, characterized in that, include, The matching module is used to obtain a high-precision road segment that matches each trajectory point based on the absolute position of the trajectory points of the traditional navigation path in the traditional navigation map. The first continuous processing module is used to obtain multiple continuous high-precision road segments that match the corresponding traditional navigation path based on multiple continuous trajectory points; The second continuous processing module is used to check whether there are redundant high-precision road segments among the multiple continuous high-precision road segments based on the topological connection relationship between them. If there are, the redundant high-precision road segments are deleted, and other related road segments among the multiple continuous high-precision road segments are merged and connected. Specifically, based on the direction of the navigation path, the multiple continuous high-precision road segments are merged and connected to obtain multiple high-precision road segment groups. Adjacent high-precision road segments within a high-precision road segment group can be topologically connected, while adjacent high-precision road segment groups cannot be topologically connected. The module determines whether there is a topological connection relationship between each pair of high-precision road segments belonging to two adjacent high-precision road segment groups. If such a relationship exists, then the multiple continuous high-precision road segments contain redundant high-precision road segments. The redundant high-precision road segments are obtained based on the high-precision road segments belonging to two adjacent high-precision road segment groups that have a topological connection relationship. as well as The third continuous processing module is used to obtain a high-precision map that matches the corresponding traditional navigation path based on the multiple continuous high-precision road segments.

8. A driving system, characterized in that, The driving system includes the high-precision map data processing device as described in claim 7.

9. A computer-readable storage medium storing computer instructions, characterized in that, When the computer instructions are executed, the computer performs the high-precision map data processing method according to any one of claims 1-6.

10. A computer device comprising a processor and a memory, the memory storing computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the high-precision map data processing method as described in any one of claims 1-6.

Images