A high-precision map updating method, device and equipment

Abstract

Embodiments of the present specification disclose a high-precision map updating method, device and equipment. The scheme can include: obtaining historical lane line data at a first lane and target lane line data at a second lane, wherein the historical lane line data is to-be-updated lane line data at the first lane in a high-precision map, and the target lane line data is lane line data generated according to collected road perception data at the second lane. According to at least one same type of data in the historical lane line data and the target lane line data, it is judged whether the historical lane line data and the target lane line data belong to the same lane. If the historical lane line data and the target lane line data belong to the same lane, the target lane line data is used to update the historical lane line data in the high-precision map to obtain an updated high-precision map. The scheme can improve the accuracy and real-time performance of updating the lane line in the high-precision map.

Description

Technical Field

[0001] This application relates to the field of electronic map technology, and in particular to a high-precision map updating method, apparatus and equipment. Background Technology

[0002] Autonomous vehicles primarily rely on road information from high-definition maps for autonomous driving, and the timeliness of this road data plays a crucial role in their safe operation. Therefore, it is essential to update the road data in high-definition maps in real time to ensure their freshness and improve the safety of autonomous vehicles during operation.

[0003] Currently, when updating high-precision maps, after acquiring new lane line data for each lane, it is necessary to manually annotate the target lanes in the high-precision map database to find the corresponding new lane line data. Then, the original lane line data at the target lane is updated with the new lane line data. Manual annotation inevitably leads to annotation errors and is time-consuming, resulting in poor real-time performance of high-precision map updates.

[0004] Therefore, how to improve the accuracy and real-time performance of updating high-precision maps has become an urgent technical problem to be solved. Summary of the Invention

[0005] This specification provides a high-precision map updating method, apparatus, and device to solve the technical problems of low accuracy and poor real-time performance when updating high-precision maps in the prior art.

[0006] To solve the above-mentioned technical problems, the embodiments in this specification are implemented as follows:

[0007] A high-precision map update method, including,

[0008] The historical lane line data of the first lane and the target lane line data of the second lane are acquired. The historical lane line data is the lane line data to be updated of the first lane in the high-precision map, and the target lane line data is the lane line data generated based on the road perception data of the second lane.

[0009] Based on at least one type of data of the same type as the historical lane line data and the target lane line data, determine whether the historical lane line data and the target lane line data belong to the same lane, and obtain the determination result.

[0010] If the determination result indicates that the historical lane line data and the target lane line data belong to the same lane, then the historical lane line data in the high-precision map is updated using the target lane line data to obtain the updated high-precision map.

[0011] A high-precision map updating device, comprising,

[0012] The acquisition module is used to acquire historical lane line data of the first lane and target lane line data of the second lane; the historical lane line data is the lane line data to be updated of the first lane in the high-precision map, and the target lane line data is the lane line data generated based on the road perception data of the second lane collected.

[0013] The judgment module is used to determine whether the historical lane line data and the target lane line data belong to the same lane based on at least one type of data of the same type as the historical lane line data, and to obtain a judgment result.

[0014] An update module is used to update the historical lane line data in the high-precision map using the target lane line data if the judgment result indicates that the historical lane line data and the target lane line data belong to the same lane, thereby obtaining an updated high-precision map.

[0015] A high-precision map updating device includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the above-described method.

[0016] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method.

[0017] At least one embodiment provided in this specification can achieve the following beneficial effects:

[0018] In existing technologies, updating high-precision maps requires manually annotating lanes to retrieve the target lanes corresponding to the new lane line data from the high-precision map database. The original lane line data at the target lane is then updated based on the new lane line data. This approach suffers from low accuracy and poor real-time performance in updating high-precision maps. This solution automatically determines whether historical and target lane line data belong to the same lane based on characteristic data of at least some similar data types, eliminating the need for manual analysis and querying. If the historical and target lane line data belong to the same lane, the target lane line data can be used to update the historical lane line data, thus improving the accuracy and real-time performance of high-precision map updates. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating a high-precision map updating method provided in an embodiment of this specification;

[0021] Figure 2 A schematic diagram of a lane line consisting of 10 coordinate points, provided for an embodiment of this specification;

[0022] Figure 3 A schematic diagram of a lane line endpoint buffer zone provided for an embodiment of this specification;

[0023] Figure 4 This is a schematic diagram showing the slope of the lane line at various points provided in the embodiments of this specification;

[0024] Figure 5 A schematic diagram showing the distance between the coordinates of points with the same serial number between historical lane lines and target lane lines provided in the embodiments of this specification;

[0025] Figure 6 A flowchart illustrating the process of determining whether lane line feature data of the first type is within a first preset range, as provided in the embodiments of this specification.

[0026] Figure 7 This is a schematic diagram showing the vertical distances from various points on the target lane line to the historical lane line provided in the embodiments of this specification.

[0027] Figure 8 A flowchart illustrating the process of determining whether lane line feature data of the second type is within a second preset range, provided in an embodiment of this specification.

[0028] Figure 9 The embodiments provided in this specification correspond to Figure 1 A schematic diagram of the structure of a high-precision map updating device;

[0029] Figure 10 The embodiments provided in this specification correspond to Figure 1 A schematic diagram of the structure of a high-precision map updating device. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of one or more embodiments of this specification clearer, the technical solutions of one or more embodiments of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of one or more embodiments of this specification.

[0031] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0032] Figure 1 This is a flowchart illustrating a high-precision map updating method provided in an embodiment of this specification. From a programming perspective, the entity executing this process can be a device updating the high-precision map, or an application program installed on the device updating the high-precision map. Figure 1 As shown, the process may include the following steps:

[0033] Step 102: Obtain historical lane line data for the first lane and target lane line data for the second lane; the historical lane line data is the lane line data to be updated for the first lane in the high-precision map, and the target lane line data is the lane line data generated based on the road perception data collected for the second lane.

[0034] In this embodiment, the first lane can be any lane in a high-precision map, and the historical lane line data can be the original lane line data obtained from the high-precision map database for that first lane. The second lane can be the lane most similar to the first lane, and the target lane line data can be the new lane line data obtained from the database storing new lane line data for that second lane. The new lane line data is generated based on newly collected road perception data, and the road perception data used to generate the target lane line data was collected later than the road perception data used to generate the historical lane line data.

[0035] Step 104: Based on at least one type of data of the same type in the historical lane line data and the target lane line data, determine whether the historical lane line data and the target lane line data belong to the same lane, and obtain the determination result.

[0036] In the embodiments of this specification, data of the same type between historical lane line data and target lane line data may include: combinations of the length of historical lane lines and the length of target lane lines, combinations of the center point coordinates of historical lane lines and the center point coordinates of target lane lines, combinations of the set of coordinates of historical lane lines and the set of coordinates of target lane lines, combinations of the endpoint buffers of historical lane lines and the endpoint buffers of target lane lines, and combinations of the average slope of historical lane lines and the average slope of target lane lines. Based on one or more of the same types of data between historical lane line data and target lane line data, it is determined whether the historical lane line data and target lane line data belong to the same lane.

[0037] Step 106: If the judgment result indicates that the historical lane line data and the target lane line data belong to the same lane, then the historical lane line data in the high-precision map is updated using the target lane line data to obtain the updated high-precision map.

[0038] In the embodiments of this specification, when it is determined, based on one or more similar types of data between historical lane line data and target lane line data, that both historical and target lane line data belong to the same lane, the historical lane line data in the high-precision map database is updated using the target lane line data, thereby obtaining an updated high-precision map. If it is determined that the historical and target lane line data do not belong to the same lane, the historical lane line data in the high-precision map database cannot be updated using the target lane line data.

[0039] In the embodiments of this specification, the system can automatically determine whether the historical lane line data and the target lane line data belong to the same lane based on the same type of data between them. When it is determined that the historical lane line data and the target lane line data belong to the same lane, the historical lane line data in the high-precision map database can be updated using the target lane line data to improve the accuracy and real-time performance of updating the high-precision map.

[0040] based on Figure 1 In addition to the method described in the embodiments of this specification, some specific implementation schemes of the method are also provided, which will be described below.

[0041] In the embodiments of this specification, when it can be determined that the original data information of the historical lane line data is completely consistent with the original data information of the target lane line data, it means that the historical lane line data and the target lane line data are completely consistent. This proves that the historical lane line data in the high-precision map database does not need to be updated, and therefore, there is no need to update the historical lane line data in the high-precision map. The original data information in the historical lane line data may include: historical lane line type, historical lane line length, coordinates of the center point of the historical lane line, and a set of coordinates of the historical lane line points. The original data information in the target lane line data may include: target lane line type, target lane line length, coordinates of the center point of the target lane line, and a set of coordinates of the target lane line points. Specifically, the lane line type may include: highway lane lines, national highway lane lines, provincial highway lane lines, county road lane lines, township road lane lines, village road lane lines, etc. The set of coordinates of the lane line points may refer to the coordinate set composed of the coordinates of the points that constitute the lane line, such as... Figure 2 As shown, a lane line consists of 10 coordinate points. The set of coordinates from coordinate 1 to coordinate 10 is the set of lane line coordinate points.

[0042] In the embodiments of this specification, when it cannot be determined that the original data information of the historical lane line data is completely consistent with the original data information of the target lane line data, that is, there is a partial or complete inconsistency in the original data information. However, whether the target lane line data can be used to update the historical lane line data depends on whether the target lane line data and the historical lane line data belong to the same lane. If the target lane line data and the historical lane line data do not belong to the same lane, the target lane line data cannot be used to update the historical lane line data; if the target lane line data and the historical lane line data belong to the same lane, the target lane line data can be used to update the historical lane line data. Therefore, whether the target lane line data can be used to update the historical lane line data in the high-precision map database depends first on whether the historical lane line data and the target lane line data belong to the same lane.

[0043] When determining whether historical lane line data and target lane line data belong to the same lane, the judgment can be made based on the similarity of data types between the two. To improve the accuracy of the judgment, multiple similar data types can be used in a progressive manner to sequentially determine whether the historical lane line data and target lane line data belong to the same lane. Therefore, step 104: Based on at least one similar data type between the historical lane line data and the target lane line data, determine whether the historical lane line data and target lane line data belong to the same lane, and obtain the judgment result. This may include:

[0044] Based on at least one type of data of the same type from the historical lane line data and the target lane line data, lane line feature data of the first type is calculated.

[0045] Determine whether the lane line feature data of the first type is within a first preset range, and obtain a first determination result.

[0046] If the historical lane line data and the target lane line data are not identified as belonging to different lanes according to the first judgment result, then a second type of lane line feature data is calculated based on at least one data of the same type in the historical lane line data and the target lane line data; the feature calculation complexity of the second type of lane line feature data is higher than that of the first type of lane line feature data, and / or the lane identification accuracy of the second type of lane line feature data is higher than that of the first type of lane line feature data.

[0047] Determine whether the lane line feature data of the second type is within a second preset range to obtain a second determination result reflecting whether the historical lane line data and the target lane line data belong to the same lane.

[0048] In this embodiment, the first type of lane line feature data can be feature data that can be directly calculated from the original lane line data. The original data may include: lane line length, lane line center point coordinates, and a set of lane line point coordinates. If the first type of lane line feature data is not within a first preset range, it means that according to the first judgment result, the historical lane line data and the target lane line data belong to different lanes, and therefore the target lane line data cannot be used to update the historical lane line data in the high-precision map database. This allows for a jump to the end, saving server computing resources and improving the efficiency of determining whether the target lane line data can be used to update the historical lane line data. If the first type of lane line feature data is within the first preset range, it means that according to the first judgment result, the historical lane line data and the target lane line data cannot be identified as belonging to different lanes, meaning that the historical lane line data and the target lane line data may belong to the same lane or not. Therefore, deeper lane line feature data is needed for further judgment. It should be noted that using the first type of lane line feature data to determine whether the historical lane line data and the target lane line data belong to the same lane can be achieved by using multiple lane line feature data to sequentially determine whether the historical lane line data and the target lane line data belong to the same lane.

[0049] In the embodiments of this specification, the second type of lane line feature data can be feature data calculated based on preprocessed data obtained after processing the original lane line data. The preprocessed data obtained after processing the original lane line data can include: endpoint buffer ranges obtained by drawing buffers for the endpoints of the lane lines, average lane line slopes obtained by calculating the slopes of each point of the lane lines, and data such as the perpendicular lines from each point of the target lane line to the historical lane lines or the perpendicular lines from each point of the historical lane lines to the target lane lines.

[0050] In the embodiments of this specification, the endpoint buffer may include a start buffer and an end buffer. The start buffer may be a circle drawn with the start point as the center and a preset buffer radius, and the end buffer may also be a circle drawn with the end point as the center and a preset buffer radius. For example... Figure 3 As shown, circle 11 is the starting buffer drawn with the starting point 1 as the center, and circle 12 is the ending buffer drawn with the ending point 10 as the center.

[0051] In the embodiments of this specification, the average slope of the lane line refers to the average slope obtained by calculating the slope of each point constituting the lane line separately, and then averaging the slopes of each point. For example... Figure 4 As shown, a lane line consists of 7 points. The slope of each point is calculated from point 1 to point 7. The average slope of the lane line is then calculated by averaging the slopes from point 1 to point 7.

[0052] In this embodiment, if the second type of lane line feature data is not within the second preset range, it means that according to the second judgment result, the historical lane line data and the target lane line data belong to different lanes, and therefore the target lane line data cannot be used to update the historical lane line data in the high-precision map database. This allows for a jump to the end, saving server computing resources and improving the efficiency of determining whether the target lane line data can be used to update the historical lane line data. If the second type of lane line feature data is within the second preset range, it means that according to the second judgment result, the historical lane line data and the target lane line data belong to the same lane, and therefore the target lane line data can be used to update the historical lane line data in the high-precision map database.

[0053] It should be noted that the first type of lane line feature data is calculated based on the original lane line data, while the second type is calculated based on preprocessed data obtained after processing the original lane line data. Therefore, the computational complexity of the second type of lane line feature data is higher than that of the first type. The accuracy of identifying whether historical lane line data and target lane line data belong to the same lane using the second type of lane line feature data is also higher than that using the first type of lane line feature data.

[0054] Specifically, in the above embodiments, the lane line feature data of the first type may include: lane line length difference, lane line center point distance value, lane line point coordinate quantity difference, and lane line point coordinate average distance value.

[0055] The step of determining whether the lane line feature data of the first type is within a first preset range, and obtaining a first determination result, may include:

[0056] Determine whether the difference in lane line lengths is less than or equal to a first preset threshold to obtain a third determination result.

[0057] If the third judgment result indicates that the difference in lane line length is less than or equal to the first preset threshold, then it is determined whether the distance value of the center point of the lane line is less than or equal to the second preset threshold, and a fourth judgment result is obtained.

[0058] If the fourth judgment result indicates that the distance value of the center point of the lane line is less than or equal to the second preset threshold, then it is determined whether the difference in the number of coordinates of the lane line points is less than or equal to the third preset threshold, and a fifth judgment result is obtained.

[0059] If the fifth judgment result indicates that the difference in the number of lane line point coordinates is less than or equal to the third preset threshold, then it is determined whether the average distance value of the lane line point coordinates is less than or equal to the fourth preset threshold, and the first judgment result is obtained; wherein, when the average distance value of the lane line point coordinates is less than or equal to the fourth preset threshold, the first judgment result indicates that the historical lane line data and the target lane line data do not belong to different lanes.

[0060] In the embodiments of this specification, the lane line length difference can be the difference between the historical lane line length in the historical lane line data and the target lane line length in the target lane line data. The lane line center point distance value can be the distance between the coordinates of the historical lane line center point in the historical lane line data and the coordinates of the target lane line center point in the target lane line data. The lane line point coordinate quantity difference can be the difference between the number of coordinates in the historical lane line point coordinate set in the historical lane line data and the set of coordinates in the target lane line data. The average lane line point coordinate distance value can be the average distance between the historical lane line point coordinate set in the historical lane line data and the set of coordinates in the target lane line data.

[0061] In the embodiments of this specification, when calculating the average distance value of lane line point coordinates, the coordinates of each point in the historical lane line point coordinate set can be continuously sorted in ascending order according to the lane line driving direction, for example, they can be sorted from 1 to n from the start point to the end point; at the same time, the coordinates of each point in the target lane line point coordinate set can also be continuously sorted in ascending order according to the lane line driving direction. The distances between points with the same coordinate index are calculated for both the historical and target lane line point coordinate sets, obtaining the distances between points with the same index. Then, the average value of these distances is calculated to obtain the average distance value between the historical and target lane line point coordinates.

[0062] It should be noted that if some coordinates in the historical lane line coordinate set do not have corresponding coordinates in the target lane line coordinate set, then no coordinate distance calculation will be performed on those coordinates in the historical lane line coordinate set. Similarly, if some coordinates in the target lane line coordinate set do not have corresponding coordinates in the historical lane line coordinate set, then no coordinate distance calculation will be performed on those coordinates in the target lane line coordinate set.

[0063] In the embodiments described in this specification, such as Figure 5 As shown, the historical lane line coordinate set for historical lane line 111 contains 10 coordinate points numbered 1 to 10, while the target lane line coordinate set for target lane line 222 contains 11 coordinate points numbered 1 to 11. When calculating the average distance between the historical and target lane line coordinate sets, distance calculations are performed only for coordinate points with the same number, such as coordinates 1 to 10. However, no distance calculation is performed for coordinate point 11 in target lane line 222.

[0064] In the embodiments of this specification, the judgment process for determining whether lane line feature data of the first type is within a first preset range can be a judgment process based on data such as lane line length difference, lane line center point distance, lane line point coordinate quantity difference, and lane line point coordinate average distance, taken in a progressive manner. Figure 6 The diagram illustrates a process for determining whether lane line feature data of the first type falls within a first preset range. Specifically, it includes steps 601 to 607:

[0065] Step 601: Determine whether the difference in lane line lengths is less than or equal to the first preset threshold.

[0066] If the difference in lane line lengths is greater than a first preset threshold, it indicates that the historical lane line data and the target lane line data belong to different lanes. This means the target lane line data cannot be used to update the historical lane line data in the high-precision map database, and the process can proceed to the end. This saves server computing resources and improves the efficiency of determining whether the target lane line data can be used to update the historical lane line data. If the difference in lane line lengths is not greater than the first preset threshold, it indicates that the historical lane line data and the target lane line data cannot be determined to belong to different lanes. Therefore, it is necessary to continue identifying whether they belong to the same lane to ensure the accuracy of updating the high-precision map.

[0067] Step 603: Determine whether the distance value between the center point of the lane line is less than or equal to the second preset threshold.

[0068] If the distance between the center points of the lane lines is greater than the second preset threshold, it indicates that the historical lane line data and the target lane line data belong to different lanes. This means the target lane line data cannot be used to update the historical lane line data in the high-precision map database, and the process can proceed to the end. This saves server computing resources and improves the efficiency of determining whether the target lane line data can be used to update the historical lane line data. If the distance between the center points of the lane lines is not greater than the second preset threshold, it indicates that the historical lane line data and the target lane line data cannot be determined to belong to different lanes. Therefore, it is necessary to continue identifying whether they belong to the same lane to ensure the accuracy of updating the high-precision map.

[0069] Step 605: Determine whether the difference in the number of lane line point coordinates is less than or equal to the third preset threshold.

[0070] If the difference in the number of lane line coordinates is greater than the third preset threshold, it indicates that the historical lane line data and the target lane line data belong to different lanes. This means the target lane line data cannot be used to update the historical lane line data in the high-precision map database, and the process can proceed to the end. This saves server computing resources and improves the efficiency of determining whether the target lane line data can be used to update the historical lane line data. If the difference in the number of lane line coordinates is not greater than the third preset threshold, it indicates that the historical lane line data and the target lane line data cannot be determined to belong to different lanes. Therefore, it is necessary to continue identifying whether they belong to the same lane to ensure the accuracy of updating the high-precision map.

[0071] Step 607: Determine if the average distance between lane line point coordinates is less than or equal to the fourth preset threshold. If the average distance between lane line point coordinates is greater than the fourth preset threshold, it indicates that the historical lane line data and the target lane line data belong to different lanes. This means the target lane line data cannot be used to update the historical lane line data in the high-precision map database, and the process can proceed to the end. This saves server computing resources and improves the efficiency of determining whether the target lane line data can be used to update the historical lane line data. If the average distance between lane line point coordinates is not greater than the fourth preset threshold, it indicates that the historical lane line data and the target lane line data cannot be determined to belong to different lanes. Therefore, it is necessary to continue identifying whether they belong to the same lane to ensure the accuracy of updating the high-precision map.

[0072] It should be noted that the progressive continuous judgment of the difference in lane line length, the distance between lane line center points, the difference in the number of lane line point coordinates, and the average distance between lane line point coordinates can be performed in any order. Figure 6 The order of judgments in this document is merely an implementation method proposed to facilitate understanding of this solution by those skilled in the art, and is not a specific limitation on the order of judgments.

[0073] By determining whether the first type of lane line feature data is within a first preset range, target lane line data that does not belong to the same lane as historical lane line data can be eliminated, thereby improving the accuracy of updating historical lane line data in the high-precision map database. However, when the first type of lane line feature data is within the first preset range, it indicates that the historical lane line data and the target lane line data have not been identified as belonging to different lanes. To determine whether the historical lane line data and the target lane line data belong to the same lane, further judgment is needed based on the second type of lane line feature data. The second type of lane line feature data can be preprocessed data obtained by processing the original lane line data. Specifically, the second type of lane line feature data includes: the overlapping area of ​​lane line endpoint buffer zones, the average slope difference of lane lines, and the average vertical distance between lane lines.

[0074] The step of determining whether the second type of lane line feature data is within a second preset range, and obtaining a second determination result reflecting whether the historical lane line data and the target lane line data belong to the same lane, may include:

[0075] Determine whether the overlapping area of ​​the lane line endpoint buffer zone is less than or equal to the fifth preset threshold to obtain the sixth determination result.

[0076] If the sixth judgment result indicates that the overlapping area of ​​the lane line endpoint buffer zone is less than or equal to the fifth preset threshold, then it is determined whether the average slope difference of the lane lines is less than or equal to the sixth preset threshold, and a seventh judgment result is obtained.

[0077] If the seventh judgment result indicates that the average slope difference of the lane lines is less than or equal to the sixth preset threshold, then it is determined whether the average vertical distance between the lane lines is less than or equal to the seventh preset threshold, and the second judgment result is obtained; wherein, when the second judgment result indicates that the average vertical distance between the lane lines is less than or equal to the seventh preset threshold, it reflects that the historical lane line data and the target lane line data belong to the same lane.

[0078] In the embodiments of this specification, the overlapping area of ​​lane line endpoint buffers can be the overlapping area between the endpoint buffers of historical lane lines in historical lane line data and the endpoint buffers of target lane lines in target lane line data. The average lane line slope difference can be the difference between the average slope of historical lane lines in historical lane line data and the average slope of target lane lines in target lane line data. The average vertical distance between lane lines can be the average vertical distance between historical lane lines in historical lane line data and target lane lines in target lane line data.

[0079] In the embodiments of this specification, the average vertical distance between the historical lane line and the target lane line can be calculated by averaging the vertical distances from each point on the historical lane line to the target lane line. Alternatively, it can be calculated by averaging the vertical distances from each point on the target lane line to the historical lane line. Figure 7 As shown, these are the vertical distances from each point on the target lane line 222 to the historical lane line 111.

[0080] In the embodiments of this specification, the judgment process for determining whether the lane line feature data of the second type is within the second preset range can be a judgment process based on data such as the overlapping area of ​​the lane line endpoint buffer zone, the average slope difference of the lane lines, and the average vertical distance between lane lines, taken in a progressive manner. Figure 8 The diagram illustrates a process for determining whether lane line feature data of the second type falls within a second preset range. Specifically, it includes steps 801 to 805:

[0081] Step 801: Determine whether the overlapping area of ​​the lane line endpoint buffer zone is less than or equal to the fifth preset threshold.

[0082] The overlapping area of ​​lane line endpoint buffers can include the overlapping area of ​​lane line start-up buffers and lane line end-up buffers. It is determined whether the first overlapping area of ​​the start-up buffer of the historical lane line and the start-up buffer of the target lane line is less than or equal to a preset threshold A, and whether the second overlapping area of ​​the end-up buffer of the historical lane line and the end-up buffer of the target lane line is less than or equal to a preset threshold B. If the first overlapping area is greater than the preset threshold A and / or the second overlapping area is greater than the preset threshold B, it indicates that the historical lane line data and the target lane line data belong to different lanes. That is, the target lane line data cannot be used to update the historical lane line data in the high-precision map database, and the process can proceed to the end, saving server computing resources and improving the efficiency of determining whether the target lane line data can be used to update the historical lane line data. If the first overlapping area is not greater than the preset threshold A and the second overlapping area is not greater than the preset threshold B, it indicates that the historical lane line data and the target lane line data cannot be determined to belong to different lanes. Therefore, it is necessary to continue identifying whether they belong to the same lane to ensure the accuracy of updating the high-precision map.

[0083] Step 803: Determine whether the average slope difference of the lane lines is less than or equal to the sixth preset threshold.

[0084] If the average slope difference of the lane lines is greater than the sixth preset threshold, it indicates that the historical lane line data and the target lane line data belong to different lanes. This means the target lane line data cannot be used to update the historical lane line data in the high-precision map database, and the process can proceed to the end. This saves server computing resources and improves the efficiency of determining whether the target lane line data can be used to update the historical lane line data. If the average slope difference of the lane lines is not greater than the sixth preset threshold, it indicates that the historical lane line data and the target lane line data cannot be determined to belong to different lanes. Therefore, it is necessary to continue identifying whether they belong to the same lane to ensure the accuracy of updating the high-precision map.

[0085] Step 805: Determine whether the average vertical distance between lane lines is less than or equal to the seventh preset threshold.

[0086] If the average vertical distance between lane lines is greater than the seventh preset threshold, it indicates that the historical lane line data and the target lane line data belong to different lanes. This means the target lane line data cannot be used to update the historical lane line data in the high-precision map database, and the process can proceed to the end. This saves server computing resources and improves the efficiency of determining whether the target lane line data can be used to update the historical lane line data. If the average vertical distance between lane lines is not greater than the seventh preset threshold, it indicates that the historical lane line data and the target lane line data belong to the same lane. This means the target lane line data can be used to update the historical lane line data in the high-precision map database.

[0087] It should be noted that the progressive continuous judgment of the overlapping area of ​​the lane line endpoint buffer zone, the average slope difference of the lane lines, and the average vertical distance between lane lines can be performed in any order. Figure 8 The order of judgments in this document is merely an implementation method proposed to facilitate understanding of this solution by those skilled in the art, and is not a specific limitation on the order of judgments.

[0088] In this embodiment of the specification, the process of determining whether historical lane line data and target lane line data belong to the same lane utilizes a comprehensive judgment method that determines whether first-type lane line feature data is within a first preset range and whether second-type lane line feature data is within a second preset range. The first-type lane line feature data includes multiple features such as lane line length difference, lane line center point distance, difference in the number of lane line point coordinates, and average distance between lane line point coordinates. The second-type lane line feature data includes multiple features such as the overlapping area of ​​lane line endpoint buffer zones, average lane line slope difference, and average vertical distance between lane lines. Only after all feature data has been judged, and if the final judgment result indicates that the historical lane line data and target lane line data belong to the same lane, will the historical lane line data be updated using the target lane line data. This improves the accuracy of updating the historical lane line data.

[0089] Step 106: Updating the historical lane line data in the high-precision map using the target lane line data to obtain the updated high-precision map may include:

[0090] Obtain the starting coordinates and ending coordinates of the lane line from the target lane line data.

[0091] In the high-precision map database where the historical lane line data is located, a first coordinate matching the starting coordinate of the lane line and a second coordinate matching the ending coordinate of the lane line are determined.

[0092] The starting coordinates of the lane line are updated to the first coordinates, and the ending coordinates of the lane line are updated to the second coordinates to obtain the updated target lane line data.

[0093] Based on the updated target lane line data, the historical lane line data between the first coordinate and the second coordinate in the high-precision map database is updated to obtain the updated high-precision map.

[0094] In this embodiment, a starting buffer zone at the starting coordinates of the target lane line in the target lane line data is determined, wherein the buffer radius of the starting buffer zone is a first preset radius. In the high-precision map database containing the historical lane line data, each first coordinate buffer zone within the coverage area of ​​the starting coordinates of the target lane line is determined. The coverage area of ​​the starting coordinates of the target lane line can be represented as the area covered by a circle or other shape centered on the starting point of the target lane line with a second preset radius. Each first coordinate buffer zone is matched with the starting buffer zone at the starting point of the target lane line. The first coordinate corresponding to the first coordinate buffer zone with the largest overlapping area with the starting buffer zone is determined as the first coordinate matching the starting coordinates of the target lane line. It should be noted that the buffer radius of each first coordinate buffer zone is consistent with the first preset radius of the starting buffer zone. The method for determining the second coordinate matching the ending coordinates of the target lane line can refer to the method for determining the first coordinate matching the starting coordinates of the target lane line, and will not be repeated here.

[0095] In this embodiment, after determining the first coordinate matching the starting coordinates of the target lane line and the second coordinate matching the ending coordinates of the target lane line, the starting coordinates of the target lane line are updated to the first coordinate, and the ending coordinates of the target lane line are updated to the second coordinate, resulting in updated target lane line data. Then, the updated target lane line data is used to update the historical lane line data between the first and second coordinates in the high-precision map database. Simultaneously, if the lane line type in the target lane line data is inconsistent with the lane line type in the historical lane line data, the lane line type in the historical lane line data also needs to be updated to the lane line type in the target lane line data. This results in an updated high-precision map.

[0096] In the embodiments of this specification, after generating the target lane line data, the method described above can automatically determine whether the target lane line data and historical lane line data belong to the same lane. Once it is determined that the target lane line data and historical lane line data belong to the same lane, the historical lane line data can be updated using the target lane line data to obtain an updated high-precision map. This eliminates the need for manual annotation to query historical lane line data belonging to the same lane as the target lane line data. Therefore, the time spent updating the high-precision map can be reduced, improving the real-time performance of high-precision map updates.

[0097] Step 102: Obtain historical lane line data for the first lane and target lane line data for the second lane, which may include:

[0098] Obtain lane line data for any lane line in any historical map sheet stored in the first database to obtain the historical lane line data for the first lane.

[0099] Based on the map sheet number of any historical map sheet, a target map sheet with the map sheet number is determined in the second database; the data collection time used to generate the target map sheet is later than the data collection time used to generate the historical map sheet.

[0100] Obtain the lane line data at the lane line with the shortest vertical distance to the center point coordinates of any lane line contained in the target map area, and obtain the target lane line data at the second lane.

[0101] In this embodiment, the first database can be a database storing high-precision map data. The high-precision map can be a map composed of multiple map sheets, each of which covers a certain area. The first lane can be any lane in any map sheet of the high-precision map. Historical lane line data for the first lane is obtained from the first database.

[0102] In this embodiment of the specification, the second database can be a database that stores target lane line data generated from road perception data collected for the coverage area of ​​the high-precision map. In the second database, the target lane line data can also be stored in regions according to map sheet size.

[0103] In the embodiments of this specification, each historical map sheet in the first database containing historical lane line data has a one-to-one correspondence with each target map sheet in the second database containing target lane line data. The historical map sheet with the same map sheet number covers the same area as the target map sheet. The data used to generate the target map sheet was collected at a later time than the data used to generate the historical map sheet.

[0104] In this embodiment of the specification, the target map sheet with the map sheet number to which the historical lane line data of the first lane belongs is determined according to the map sheet number. The target lane line with the shortest distance to the center point of the historical lane line at the first lane is determined in the target map sheet. The lane line data corresponding to the target lane line is determined as the target lane line data at the second lane.

[0105] In determining whether historical lane line data and target lane line data belong to the same lane, the values ​​of various thresholds significantly impact the accuracy of the judgment. Therefore, to improve the accuracy of the judgment, it is necessary to reasonably select the value range of each threshold. Based on this, both the first preset range and the second preset range are numerical ranges determined according to the target threshold; the target threshold includes the first preset threshold, the second preset threshold, the third preset threshold, the fourth preset threshold, the fifth preset threshold, the sixth preset threshold, and the seventh preset threshold.

[0106] The method may further include:

[0107] Obtain the factor values ​​of each influencing factor of the target threshold; the influencing factors include at least: a first type of influencing factor in the road scene dimension, a second type of influencing factor in the lane density dimension, and a third type of influencing factor in the scale information dimension for drawing high-precision maps.

[0108] Determine the weight values ​​for each of the aforementioned influencing factors.

[0109] The target threshold is obtained by performing a weighted summation calculation based on the weight values ​​and factor values ​​of each of the influencing factors.

[0110] In the embodiments of this specification, any target threshold can be determined based on corresponding influencing factors. These influencing factors may include a first type of influencing factor based on the road scene dimension, a second type of influencing factor based on the lane density dimension, and a third type of influencing factor based on the scale information dimension for drawing the high-precision map. Other types of influencing factors may also be included. The road scene dimension can be the actual road type, such as highways, national highways, provincial highways, etc. The lane density dimension can be the actual number of lanes on the road. The scale information dimension can be the scale information used when drawing the high-precision map, such as 1:10000.

[0111] In the embodiments of this specification, the factor value of any influencing factor used to determine the target threshold can be determined according to the actual scenario. Assuming the target threshold is the spacing range between lane lines, the value of the spacing range between lane lines in the road scene dimension can be related to the road type; for example, the spacing range between lane lines in a highway scenario can be higher than that in other road scenarios. The value of the spacing range between lane lines in the lane density dimension can be related to the number of lanes; the more lanes, the smaller the spacing range between lane lines can be. The value of the spacing range between lane lines in the scale information dimension can be related to the scale size; the smaller the scale, the smaller the spacing range between lane lines can be.

[0112] In the embodiments of this specification, the weight value of the influence factor can represent the proportion of the corresponding influence factor in determining the target threshold. The larger the proportion, the higher the importance of the influence factor in determining the target threshold, that is, the larger the corresponding weight can be.

[0113] In the embodiments of this specification, after determining the factor values ​​and weight values ​​of each influencing factor used in calculating the target threshold, the corresponding target threshold can be calculated by weighted summation.

[0114] In the embodiments of this specification, each target threshold can be a threshold calculated based on multiple corresponding influencing factors, rather than determined by a single data point based on human experience. This can improve the accuracy of the judgment results on whether historical lane line data and target lane line data belong to the same lane, and thus improve the accuracy of updating high-precision maps.

[0115] Based on the same idea, embodiments of this specification also provide apparatus corresponding to the above methods. Figure 9 The embodiments provided in this specification correspond to Figure 1 A schematic diagram of the structure of a high-precision map updating device. (See diagram below.) Figure 9 As shown, the device may include:

[0116] The acquisition module 902 is used to acquire historical lane line data at the first lane and target lane line data at the second lane; the historical lane line data is the lane line data to be updated at the first lane in the high-precision map, and the target lane line data is lane line data generated based on the road perception data collected at the second lane;

[0117] The judgment module 904 is used to determine whether the historical lane line data and the target lane line data belong to the same lane based on at least one type of data of the same type as the historical lane line data, and to obtain a judgment result;

[0118] The update module 906 is used to update the historical lane line data in the high-precision map using the target lane line data if the judgment result indicates that the historical lane line data and the target lane line data belong to the same lane, thereby obtaining an updated high-precision map.

[0119] Optionally, the determination module 904 may include:

[0120] The first calculation unit is used to calculate lane feature data of a first type based on at least one type of data of the same type from the historical lane line data and the target lane line data.

[0121] The first judgment unit is used to determine whether the lane line feature data of the first type is within a first preset range, and to obtain a first judgment result;

[0122] The second calculation unit is configured to, if the historical lane line data and the target lane line data are not identified as belonging to different lanes according to the first judgment result, calculate lane line feature data of a second type based on at least one type of data of the same kind in the historical lane line data and the target lane line data; the feature calculation complexity of the second type of lane line feature data is higher than that of the first type of lane line feature data, and / or the lane identification accuracy of the second type of lane line feature data is higher than that of the first type of lane line feature data.

[0123] The second judgment unit is used to determine whether the lane line feature data of the second type is within a second preset range, and to obtain a second judgment result reflecting whether the historical lane line data and the target lane line data belong to the same lane.

[0124] Optionally, the lane line feature data of the first type includes: lane line length difference, lane line center point distance value, lane line point coordinate quantity difference, and lane line point coordinate average distance value.

[0125] The first determination unit may include:

[0126] The first judgment subunit is used to determine whether the difference in lane line length is less than or equal to a first preset threshold, and to obtain a third judgment result.

[0127] The second judgment subunit is used to determine whether the distance value of the center point of the lane line is less than or equal to the second preset threshold if the third judgment result indicates that the difference in lane line length is less than or equal to the first preset threshold, and to obtain the fourth judgment result.

[0128] The third judgment subunit is used to determine whether the difference in the number of lane line point coordinates is less than or equal to the third preset threshold if the fourth judgment result indicates that the distance value of the center point of the lane line is less than or equal to the second preset threshold, and to obtain the fifth judgment result.

[0129] The fourth judgment subunit is used to determine whether the average distance value of the lane line coordinates is less than or equal to the fourth preset threshold if the fifth judgment result indicates that the difference in the number of lane line coordinates is less than or equal to the third preset threshold, and to obtain the first judgment result; wherein, the first judgment result indicates that the historical lane line data and the target lane line data do not belong to different lanes when the average distance value of the lane line coordinates is less than or equal to the fourth preset threshold.

[0130] Optionally, the lane line feature data of the second type includes: the overlapping area of ​​lane line endpoint buffer zones, the average slope difference of lane lines, and the average vertical distance between lane lines.

[0131] The second determination unit may include:

[0132] The fifth judgment subunit is used to determine whether the overlapping area of ​​the lane line endpoint buffer zone is less than or equal to the fifth preset threshold, and to obtain the sixth judgment result.

[0133] The sixth judgment subunit is used to determine whether the average slope difference of the lane lines is less than or equal to the sixth preset threshold if the sixth judgment result indicates that the overlapping area of ​​the lane line endpoint buffer is less than or equal to the fifth preset threshold, and to obtain the seventh judgment result.

[0134] The seventh judgment subunit is used to determine whether the average vertical distance between the lane lines is less than or equal to the seventh preset threshold if the seventh judgment result indicates that the average slope difference of the lane lines is less than or equal to the sixth preset threshold, and to obtain the second judgment result; wherein, the second judgment result reflects that the historical lane line data and the target lane line data belong to the same lane when the average vertical distance between the lane lines is less than or equal to the seventh preset threshold.

[0135] Optionally, the update module 906 may include:

[0136] The first acquisition unit is used to acquire the starting coordinates and ending coordinates of the lane line in the target lane line data.

[0137] The first determining unit is used to determine, in the high-precision map database where the historical lane line data is located, a first coordinate that matches the starting coordinate of the lane line and a second coordinate that matches the ending coordinate of the lane line.

[0138] The first update unit is used to update the starting coordinate of the lane line to the first coordinate and update the ending coordinate of the lane line to the second coordinate to obtain the updated target lane line data.

[0139] The second update unit is used to update the historical lane line data between the first coordinate and the second coordinate in the high-precision map database according to the updated target lane line data, so as to obtain the updated high-precision map.

[0140] Optionally, the acquisition module 902 may include:

[0141] The second acquisition unit is used to acquire lane line data at any lane line in any historical map sheet stored in the first database, and obtain the historical lane line data at the first lane.

[0142] The second determining unit is used to determine a target map sheet with the map sheet number in the second database based on the map sheet number of any historical map sheet; the data collection time used to generate the target map sheet is later than the data collection time used to generate the historical map sheet;

[0143] The third acquisition unit is used to acquire lane line data at the lane line with the shortest vertical distance to the center point coordinates of any lane line contained in the target map sheet, and to obtain the target lane line data at the second lane.

[0144] Optionally, both the first preset range and the second preset range are numerical ranges determined based on a target threshold; the target threshold includes the first preset threshold, the second preset threshold, the third preset threshold, the fourth preset threshold, the fifth preset threshold, the sixth preset threshold, and the seventh preset threshold. The device may further include:

[0145] The first acquisition module is used to acquire the factor values ​​of each influencing factor of the target threshold. The influencing factors include at least: a first type of influencing factor in the road scene dimension, a second type of influencing factor in the lane density dimension, and a third type of influencing factor in the scale information dimension for drawing high-precision maps.

[0146] The determination module is used to determine the weight values ​​of each of the influencing factors.

[0147] The calculation module is used to perform a weighted summation calculation based on the weight values ​​of each of the influencing factors and the factor values ​​to obtain the target threshold.

[0148] Based on the same idea, this specification also provides devices corresponding to the above methods in its embodiments.

[0149] Figure 10 The embodiments provided in this specification correspond to Figure 1 A schematic diagram of the structure of a high-precision map updating device. (See diagram below.) Figure 10 As shown, device 1000 may include: at least one processor 1010; and,

[0150] Memory 1030 communicatively connected to the at least one processor; wherein,

[0151] The memory 1030 stores instructions 1020 that can be executed by the at least one processor 1010, which are executed by the at least one processor 1010 to enable the at least one processor 1010 to execute the instructions to implement the above-described method.

[0152] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method.

[0153] It should be understood that in the methods described in one or more embodiments of this specification, the order of some steps may be adjusted according to actual needs, or some steps may be omitted.

[0154] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, for... Figure 10 As the device shown is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0155] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A high-precision map update method, characterized in that, include: Acquire historical lane line data for the first lane and target lane line data for the second lane; the historical lane line data is the lane line data to be updated for the first lane in the high-precision map, and the target lane line data is lane line data generated based on the road perception data collected for the second lane; Based on at least one type of data of the same kind in the historical lane line data and the target lane line data, lane line feature data of the first type is calculated. Based on the first type of lane line feature data, it is determined whether the historical lane line data and the target lane line data belong to the same lane, and a first determination result is obtained. If so, based on at least one type of data of the same kind in the historical lane line data and the target lane line data, lane line feature data of the second type is calculated. Based on the second type of lane line feature data, it is determined whether the historical lane line data and the target lane line data belong to the same lane, and a second determination result is obtained. The second type of lane line feature data includes: the overlapping area of ​​lane line endpoint buffer zones, the average slope difference of lane lines, and the average vertical distance between lane lines. If the second determination result indicates that the historical lane line data and the target lane line data belong to the same lane, then the historical lane line data in the high-precision map is updated using the target lane line data to obtain the updated high-precision map.

2. The method as described in claim 1, characterized in that, The step of determining whether the historical lane line data and the target lane line data belong to the same lane based on the first type of lane line feature data, and obtaining a first determination result, includes: Determine whether the lane line feature data of the first type is within a first preset range, and obtain a first determination result; The step of determining whether the historical lane line data and the target lane line data belong to the same lane based on the second type of lane line feature data, and obtaining a second determination result, includes: The feature computation complexity of the second type of lane line feature data is higher than that of the first type of lane line feature data, and / or the lane identification accuracy of the second type of lane line feature data is higher than that of the first type of lane line feature data. Determine whether the lane line feature data of the second type is within a second preset range to obtain a second determination result reflecting whether the historical lane line data and the target lane line data belong to the same lane.

3. The method as described in claim 2, characterized in that, The first type of lane line feature data includes: lane line length difference, lane line center point distance value, lane line point coordinate quantity difference, and lane line point coordinate average distance value; The step of determining whether the lane line feature data of the first type is within a first preset range and obtaining a first determination result includes: Determine whether the difference in lane line lengths is less than or equal to a first preset threshold to obtain a third determination result; If the third judgment result indicates that the difference in lane line length is less than or equal to the first preset threshold, then it is determined whether the distance value of the center point of the lane line is less than or equal to the second preset threshold, and a fourth judgment result is obtained. If the fourth judgment result indicates that the distance value of the center point of the lane line is less than or equal to the second preset threshold, then it is determined whether the difference in the number of coordinates of the lane line points is less than or equal to the third preset threshold, and a fifth judgment result is obtained. If the fifth judgment result indicates that the difference in the number of lane line point coordinates is less than or equal to the third preset threshold, then it is determined whether the average distance value of the lane line point coordinates is less than or equal to the fourth preset threshold, and the first judgment result is obtained; wherein, when the average distance value of the lane line point coordinates is less than or equal to the fourth preset threshold, the first judgment result indicates that the historical lane line data and the target lane line data do not belong to different lanes.

4. The method as described in claim 3, characterized in that, The step of determining whether the second type of lane line feature data is within a second preset range, and obtaining a second determination result reflecting whether the historical lane line data and the target lane line data belong to the same lane, includes: Determine whether the overlapping area of ​​the lane line endpoint buffer zone is less than or equal to a fifth preset threshold to obtain a sixth determination result; If the sixth judgment result indicates that the overlapping area of ​​the lane line endpoint buffer zone is less than or equal to the fifth preset threshold, then it is determined whether the average slope difference of the lane lines is less than or equal to the sixth preset threshold, and a seventh judgment result is obtained. If the seventh judgment result indicates that the average slope difference of the lane lines is less than or equal to the sixth preset threshold, then it is determined whether the average vertical distance between the lane lines is less than or equal to the seventh preset threshold, and the second judgment result is obtained; wherein, when the second judgment result indicates that the average vertical distance between the lane lines is less than or equal to the seventh preset threshold, it reflects that the historical lane line data and the target lane line data belong to the same lane.

5. The method as described in claim 1, characterized in that, The step of updating the historical lane line data in the high-precision map using the target lane line data to obtain the updated high-precision map includes: Obtain the starting coordinates and ending coordinates of the lane line from the target lane line data; In the high-precision map database where the historical lane line data is located, a first coordinate matching the starting coordinate of the lane line and a second coordinate matching the ending coordinate of the lane line are determined. The starting coordinates of the lane line are updated to the first coordinates, and the ending coordinates of the lane line are updated to the second coordinates to obtain the updated target lane line data. Based on the updated target lane line data, the historical lane line data between the first coordinate and the second coordinate in the high-precision map database is updated to obtain the updated high-precision map.

6. The method as described in claim 1, characterized in that, Obtain historical lane line data for the first lane and target lane line data for the second lane, including: Obtain lane line data for any lane line in any historical map sheet stored in the first database to obtain historical lane line data for the first lane; Based on the map sheet number of any historical map sheet, a target map sheet with the map sheet number is determined in the second database; the data collection time used to generate the target map sheet is later than the data collection time used to generate the historical map sheet; Obtain the lane line data at the lane line with the shortest vertical distance to the center point coordinates of any lane line contained in the target map area, and obtain the target lane line data at the second lane.

7. The method as described in claim 4, characterized in that, Both the first preset range and the second preset range are numerical ranges determined based on target thresholds; the target thresholds include the first preset threshold, the second preset threshold, the third preset threshold, the fourth preset threshold, the fifth preset threshold, the sixth preset threshold, and the seventh preset threshold; The method further includes: Obtain the factor values ​​of each influencing factor of the target threshold; the influencing factors include at least: a first type of influencing factor in the road scene dimension, a second type of influencing factor in the lane density dimension, and a third type of influencing factor in the scale information dimension of drawing high-precision maps; Determine the weight values ​​of each of the aforementioned influencing factors; The target threshold is obtained by performing a weighted summation calculation based on the weight values ​​and factor values ​​of each of the influencing factors.

8. A high-precision map updating device, characterized in that, include: The acquisition module is used to acquire historical lane line data of the first lane and target lane line data of the second lane; the historical lane line data is the lane line data to be updated of the first lane in the high-precision map, and the target lane line data is the lane line data generated based on the road perception data of the second lane collected. The judgment module is used to calculate lane line feature data of a first type based on at least one type of data of the same type in the historical lane line data and the target lane line data, and to determine whether the historical lane line data and the target lane line data belong to the same lane based on the first type of lane line feature data, thereby obtaining a first judgment result; if so, it calculates lane line feature data of a second type based on at least one type of data of the same type in the historical lane line data and the target lane line data, and to determine whether the historical lane line data and the target lane line data belong to the same lane based on the second type of lane line feature data, thereby obtaining a second judgment result; wherein, the second type of lane line feature data includes: the overlapping area of ​​lane line endpoint buffer zones, the average slope difference of lane lines, and the average vertical distance between lane lines; The update module is used to update the historical lane line data in the high-precision map using the target lane line data if the second judgment result indicates that the historical lane line data and the target lane line data belong to the same lane, thereby obtaining an updated high-precision map.

9. A high-precision map updating device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 7.

Images