High-precision map generation method, related method, device and equipment

Abstract

The invention discloses a high-precision map generation method, a related method, a related device and related equipment, and the method comprises the steps: respectively generating initial lane geometric data, element map and road-level map data and real-time lane geometric data, element map and road-level map data according to the time according to the obtained multiple groups of crowdsourcing map element data; fusing the generated multiple groups of real-time lane geometric data, the real-time matching map element data and the real-time road-level map data, and obtaining the real-time lane geometric data based on the mean value and the variance of each key point in the initial lane geometric data and the determined mean value and the variance corresponding to each fusion key point in the fused lane geometric data. And updating the fused matched map element data and the fused road-level map data, repeating the step of iterative updating until an iteration stop condition is met, obtaining optimal lane geometric data, optimal matched map element data and optimal road-level map data, and generating a high-precision map.

Description

Technical Field

[0001] The present invention relates to the field of map processing technology, and in particular to a method for generating a high-precision map, related methods, devices and equipment. Background Art

[0002] With the rapid development of intelligent transportation and autonomous driving, the requirements for maps have surpassed the content, accuracy and completeness that traditional navigation electronic maps can provide. In order to meet such advanced application requirements, high-precision maps for roads have gradually emerged and are widely recognized. In autonomous driving systems, high-precision maps have three key functions: map matching, auxiliary environmental perception and path planning. These functions are rigid requirements and cannot be replaced by other alternatives. The introduction of high-precision maps provides important support for the safety and feasibility of autonomous driving.

[0003] Crowdsourcing map generation is a method of collecting, organizing and updating geographic information data based on crowdsourcing. With the help of a large number of Internet users, the creation and update of map data can be participated in in a crowdsourcing manner. Through the crowdsourcing model, real-time road conditions, traffic signs and other geographic feature data can be quickly obtained. By utilizing the collaborative and sharing spirit of the crowdsourcing model, the power of the public can be used to build newer, faster, more comprehensive and more accurate maps to meet the needs of intelligent transportation and autonomous driving systems for high-precision maps. Summary of the invention

[0004] In order to generate a stable high-precision map, the inventors proposed a method for generating a high-precision map, related methods, devices and equipment.

[0005] In a first aspect, an embodiment of the present application provides a method for generating a high-precision map, the method comprising:

[0006] generating initial lane geometry data and initial feature maps, and determining initial road-level map data based on the acquired multiple sets of initial crowdsourced map feature data;

[0007] According to each set of real-time crowdsourced map element data obtained, corresponding real-time lane geometry data, real-time matching map element data and real-time road-level map data are generated respectively;

[0008] The generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data are fused to obtain fused lane geometry data, fused matching map element data and fused road-level map data;

[0009] Based on the fused matching map element data and the fused road-level map data, according to the determined mean and variance of each initial key point in the initial lane geometry data, and the determined mean and variance of each corresponding fused key point in the fused lane geometry data, obtaining updated lane geometry data, updated matching map element data, and updated road-level map data;

[0010] Repeat the steps of iteratively updating the updated lane geometry data, the updated matching map element data, and the updated road-level map data until an iteration stop condition is reached, thereby obtaining optimal lane geometry data, optimal matching map element data, and optimal road-level map data;

[0011] A high-precision map is generated based on the optimal lane geometry data, the optimal matching map element data and the optimal road-level map data.

[0012] In one or some optional implementations of the embodiment of the present application, based on the fused matching map element data and the fused road-level map data, according to the determined mean and variance of each initial key point in the initial lane geometry data, and the determined mean and variance of each fused key point in the fused lane geometry data, the updated lane geometry data, the updated matching map element data and the updated road-level map data are obtained, including:

[0013] Determining the mean and variance of each initial key point in the initial lane geometry data;

[0014] Determine the mean and variance of each fused key point corresponding to the fused lane geometry data;

[0015] Based on the fused matching map element data and the fused road-level map data, determining whether a difference in mean and a difference in variance between each initial key point in the initial lane geometry data and a corresponding fused key point in the fused lane geometry data are both within a corresponding threshold range;

[0016] If yes, based on the mean and variance of each initial key point in the initial lane geometry data and the corresponding fused key point in the fused lane geometry data, the mean and variance of the updated key points are updated to obtain the updated lane geometry data, the updated matching map element data and the updated road-level map data.

[0017] In one or some optional implementations of the embodiment of the present application, determining the mean and variance of each initial key point of each divided road segment in the initial lane geometry data includes:

[0018] Determining the center position and edge position of each cluster according to the semantic information in the initial lane geometry data;

[0019] According to the center positions and edge positions of each cluster, the center line position point of the head or tail of the road segment is determined to obtain the initial key point position;

[0020] Fine-tuning the position of the initial key point to obtain an adjusted position of the initial key point;

[0021] Determine the mean, lateral variance and longitudinal variance of the initial key points according to the positions of the cluster centers of the road segments and the adjusted positions of the initial key points;

[0022] and / or,

[0023] Determining the mean and variance of each fused key point corresponding to the fused lane geometry data includes:

[0024] Determining the center position and edge position of each cluster according to the semantic information in the fused lane geometry data;

[0025] According to the center position and edge position of each cluster, determine the center line position point of the head or tail of the road segment to obtain the initial position of the fusion key point;

[0026] Fine-tuning the initial position of the fusion key point to obtain an adjusted position of the fusion key point;

[0027] According to the positions of the cluster centers of the road segments and the adjusted positions of the fused key points, the mean, lateral variance and longitudinal variance of the fused key points are determined.

[0028] In one or some optional implementations of the embodiment of the present application, the determining, based on the fused matching map element data and the fused road-level map data, whether the difference between the mean and the difference between the variance of each initial key point in the initial lane geometry data and the corresponding fused key point in the fused lane geometry data are both within a corresponding threshold range includes:

[0029] Based on the fused matching map element data and the fused road-level map data, determine whether the differences between the means of each initial key point in the initial lane geometry data and the corresponding fused key points in the fused lane geometry data are all within a first threshold range, whether the differences in lateral variances are within a second threshold range, and whether the differences in longitudinal variances are all within a third threshold range.

[0030] In one or some optional implementations of the embodiment of the present application, the updating of the mean and variance of the updated key points according to the means and variances of the initial key points in the initial lane geometry data and the corresponding fused key points in the fused lane geometry data, and obtaining the updated lane geometry data, the updated matching map element data and the updated road-level map data, includes:

[0031] According to the mean, lateral variance and longitudinal variance of each initial key point in the initial lane geometry data and the corresponding fused key points of the fused lane geometry data, the Kalman filter algorithm is used to update the mean and variance of the updated key points, generate the updated lane geometry data, and obtain the updated matching map element data and the updated road-level map data.

[0032] In one or some optional implementations of the embodiment of the present application, the determining, based on the fused matching map element data and the fused road-level map data, whether the difference between the mean and the difference between the variance of each initial key point in the initial lane geometry data and the corresponding fused key point in the fused lane geometry data are both within a corresponding threshold range, further includes:

[0033] If the difference between the means of each initial key point in the initial lane geometry data and the corresponding fused key point in the fused lane geometry data is not within the first threshold range, the difference in lateral variance is not within the second threshold range, or the difference in longitudinal variance is not within the third threshold range, the fused lane geometry data, the fused matching map element data, and the fused road-level map data are discarded.

[0034] In one or some optional implementations of the embodiment of the present application, the generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data are fused to obtain fused lane geometry data, fused matching map element data and fused road-level map data, including:

[0035] For each set of real-time crowdsourced map element data, the road is transversely segmented according to the corresponding real-time road-level map data obtained to obtain a road segment with two marking points at the beginning and the end;

[0036] Aligning the real-time crowdsourced map element data with the initial element map to obtain aligned map element data;

[0037] According to the aligned map element data, identifying the left and right lane lines in the road segment and the edge position of the drivable area to obtain the current lane position;

[0038] Generate lane geometry information of each lane marking point using the current lane position and the real-time road-level map data;

[0039] Generate corresponding real-time matching map element data according to the lane geometry information of each lane marking point and the aligned map element data;

[0040] The generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data are fused to obtain fused lane geometry data, fused matching map element data and fused road-level map data.

[0041] In one or some optional implementations of the embodiment of the present application, the lane geometry information includes a lane ID, a lane number, and a lane number confidence;

[0042] The generating corresponding real-time matching map element data according to the lane geometry information of each lane marking point and the aligned map element data includes:

[0043] Determining a lane number and a lane number confidence level corresponding to the current lane position according to the current lane position, the lane geometry information, and the aligned map element data;

[0044] According to the lane number corresponding to the lane ID, identify the lane lines on the left and right sides of the current lane position;

[0045] Identifying lane line types of the lane lines on the left and right sides of the current lane position according to the lane lines on the left and right sides of the current lane position and the aligned map element data;

[0046] Generate a solid line area according to the lane line types of the lane lines on the left and right sides of the current lane position;

[0047] The solid line data in the aligned map element data are matched with the solid line area to obtain corresponding real-time matching map element data.

[0048] In one or some optional implementations of the embodiment of the present application, the generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data are fused to obtain fused lane geometry data, fused matching map element data and fused road-level map data, including:

[0049] fusing the plurality of sets of the real-time road-level map data to obtain the fused road-level map data;

[0050] Using the fused road-level map data, the data at the same position in the multiple sets of real-time lane geometry data are fused to obtain fused lane geometry data;

[0051] According to the principle of time sequence, the optimal preset number of groups of real-time matching map element data are selected from the multiple groups of real-time matching map element data to obtain fused matching map element data.

[0052] In one or some optional implementations of the embodiments of the present application, after aligning the real-time crowdsourced map element data with the initial element map to obtain the aligned map element data, it also includes: filtering abnormal data on the aligned map element data.

[0053] In a second aspect, an embodiment of the present application provides a method for using a high-precision map, the method comprising:

[0054] Receive high-precision map data;

[0055] Generate lane geometry data based on currently collected map feature data;

[0056] Matching the lane geometry data to the high-precision map data to obtain map data to be displayed;

[0057] The map data to be displayed is displayed.

[0058] In a third aspect, an embodiment of the present application provides a device for generating a high-precision map, the method comprising:

[0059] A first generation module, configured to generate initial lane geometry data and an initial feature map according to the acquired multiple sets of initial crowdsourced map feature data, and determine initial road-level map data;

[0060] A second generation module is used to generate corresponding real-time lane geometry data, real-time matching map element data and real-time road-level map data according to each set of real-time crowd-sourced map element data obtained;

[0061] A fusion module is used to fuse the generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data to obtain fused lane geometry data, fused matching map element data and fused road-level map data;

[0062] an updating module, for obtaining updated lane geometry data, updated matching map element data and updated road-level map data based on the fused matching map element data and the fused road-level map data, according to the determined mean and variance of each key point in the initial lane geometry data, and the determined mean and variance of each key point corresponding to the fused lane geometry data; and repeating the steps of iteratively updating the updated lane geometry data, the updated matching map element data and the updated road-level map data until an iteration stop condition is reached, thereby obtaining optimal lane geometry data, optimal matching map element data and optimal road-level map data;

[0063] The third generation module is used to generate a high-precision map based on the optimal lane geometry data, the optimal matching map element data and the optimal road-level map data.

[0064] In a fourth aspect, an embodiment of the present application provides a device for using a high-precision map, the method comprising:

[0065] A receiving module, used for receiving high-precision map data;

[0066] A data generation module, used to generate lane geometry data based on currently collected map element data;

[0067] A matching module, used for matching the lane geometry data to the high-precision map data to obtain map data to be displayed;

[0068] The display module is used to display the map data to be displayed.

[0069] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for generating a high-precision map as described above, and / or the method for using the high-precision map as described above.

[0070] In a sixth aspect, an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for generating a high-precision map as described above is implemented, and / or the method for using the high-precision map as described above is implemented.

[0071] In the seventh aspect, an embodiment of the present application provides a computer program product comprising instructions. When the computer program product is run on a computer device, the computer device executes the method for generating a high-precision map as described above, and / or the method for using the high-precision map as described above.

[0072] In an eighth aspect, an embodiment of the present application provides a chip, the chip comprising a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run a computer program or instructions to implement the method for generating a high-precision map as described above, and / or the method for using the high-precision map as described above.

[0073] The beneficial effects of the above technical solution provided by the embodiment of the present application include at least:

[0074] The method for generating a high-precision map provided in the embodiment of the present application fuses the real-time lane geometry data, real-time matching map element data and real-time road-level map data generated by multiple sets of real-time crowd-sourced map element data, thereby eliminating the impact of the discreteness and instability of the complex crowd-sourced map data on the generation of high-precision maps, and obtaining more accurate lane geometry information through data fusion, providing a more reliable data basis for map generation and improving the accuracy of map data; updating the initial lane geometry data based on the fused real-time lane geometry data can provide a stable and consistent map experience and improve the map update speed. Moreover, generating a high-precision map based on the optimal lane geometry data, optimal matching map element data and optimal road-level map data obtained through repeated iterative updates can effectively improve lane recognition errors and improve map navigation accuracy.

[0075] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0076] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0078] Figure 1 A schematic diagram of the steps of the method for generating a high-precision map provided in an embodiment of the present application;

[0079] Figure 2 A schematic diagram of the steps of the method for using the high-precision map provided in the embodiment of the present application;

[0080] Figure 3 A schematic diagram of the structure of a device for generating a high-precision map provided in an embodiment of the present application;

[0081] Figure 4 A schematic diagram of the structure of a device for using a high-precision map provided in an embodiment of the present application. DETAILED DESCRIPTION

[0082] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0083] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0084] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0085] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0086] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0087] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0088] It should be understood that the size of the serial numbers of the steps in the following embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0089] In order to illustrate the technical solution of the present application, a specific embodiment is provided below for illustration.

[0090] The inventors have found that the current means of generating high-precision maps based on crowdsourced map data is to collect video data from the vehicle and then process it. The data obtained is naturally highly random and contains a lot of abnormal data. In order to obtain a more complete and accurate high-precision map and eliminate the impact of the discreteness and instability of map data on high-precision map generation, the embodiments of this application provide a method for generating a high-precision map, related methods, devices and equipment.

[0091] Embodiment 1

[0092] This application embodiment provides a method for generating a high-precision map. Figure 1 As shown, the method includes:

[0093] S101: Generate initial lane geometry data and initial feature map according to the acquired multiple sets of initial crowd-sourced map feature data, and determine initial road-level map data.

[0094] In the embodiment of the present application, the initial crowdsourced map element data refers to data collected by crowdsourcing, mainly including data collected and uploaded by the vehicle side, wherein the data uploaded by the vehicle side includes semantic information of the road and target detection information, and may also include GPS track point data, vehicle posture and positioning information and other data. For the accuracy and credibility of data processing, after obtaining the initial crowdsourced map element data, it can be preprocessed first, including cleaning and integrating it to remove redundant or erroneous data. Based on the preprocessed crowdsourced map element data, the initial lane geometry data and the initial element map are generated.

[0095] In the embodiment of the present application, the initial lane geometry data includes lane line geometry data, lane ID, geometry information ID, position information, lateral offset error, longitudinal offset error and element polyline information, wherein the lane line geometry data includes lane line ID, lane line geometry information ID, lane line equation information and constituent line segment definitions (whether it is a starting point or an end point, whether there is a key point, key point category, key point information and line shape category). The initial element map includes map elements such as roads, traffic facilities, and traffic signs. The initial road-level map data can be historical road-level map data obtained, or it can be road-level map data generated using GPS track point data in the initial crowdsourced map element data.

[0096] S102: Generate corresponding real-time lane geometry data, real-time matching map element data and real-time road-level map data according to each set of real-time crowd-sourced map element data obtained.

[0097] In an embodiment of the present application, a set of real-time crowdsourced map element data may include multiple trips of map element data collected and uploaded by different vehicles within a preset time period, such as one day. For the accuracy and credibility of data processing, after obtaining the real-time crowdsourced map element data, it may be preprocessed, including cleaning and integrating it to remove redundant or erroneous data. Based on the preprocessed real-time crowdsourced map element data, real-time lane geometry data, real-time matching map element data, and real-time road-level map data are generated.

[0098] In the embodiment of the present application, the real-time lane geometry data includes lane line geometry data, lane ID, geometry information ID, position information, lateral offset error, longitudinal offset error and element polyline information, wherein the lane line geometry data includes lane line ID, lane line geometry information ID, lane line equation information and constituent line segment definitions (whether it is a starting point or an end point, whether there is a key point, key point category, key point information and line shape category). The real-time matching map element data includes map elements such as roads, traffic facilities, and traffic signs. The generated real-time lane geometry data and element map are corrected and verified, and the real-time road-level map data is determined based on the corrected and verified data.

[0099] S103: Fusing the generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data to obtain fused lane geometry data, fused matching map element data and fused road-level map data.

[0100] In the above step S103, the generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data are fused to obtain fused lane geometry data, fused matching map element data and fused road-level map data, which specifically include:

[0101] For each set of real-time crowdsourced map element data, the road is transversely segmented according to the corresponding real-time road-level map data obtained to obtain a road segment with two marking points at the beginning and the end;

[0102] Aligning the real-time crowdsourced map element data with the initial element map to obtain aligned map element data;

[0103] According to the aligned map element data, identifying the left and right lane lines in the road segment and the edge position of the drivable area to obtain the current lane position;

[0104] Generate lane geometry information of each lane marking point using the current lane position and the real-time road-level map data; wherein the lane geometry information includes a lane ID, a lane number, and a lane number confidence;

[0105] Generate corresponding real-time matching map element data according to the lane geometry information of each lane marking point and the aligned map element data;

[0106] The generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data are fused to obtain fused lane geometry data, fused matching map element data and fused road-level map data.

[0107] In an embodiment of the present application, for each set of real-time crowdsourced map element data, the road is transversely divided into road segments according to the corresponding real-time road-level map data. Since the lengths of solid lines and dashed lines in actual roads are made according to pre-specified standards, the length of the road segment obtained by the segmentation can also be set in advance. For example, if the length of the dashed line is 6 meters and the length of the solid line is 9 meters, the length of the road segment can be set to 15 meters or 24 meters. When dividing the road segment, it can be divided according to lane marking points, such as the starting point or end point of the dashed line, traffic signs, etc., to divide the road transversely into road segments of set lengths.

[0108] In the embodiment of the present application, the alignment of the real-time crowdsourced map element data with the initial element map can be achieved by using the alignment method of the prior art. The specific implementation process can refer to the detailed description of the prior art and is not specifically limited here.

[0109] In a specific embodiment, after aligning the real-time crowdsourced map element data with the initial element map to obtain aligned map element data, the method may further include: filtering abnormal data on the aligned map element data.

[0110] In an embodiment of the present application, after obtaining the aligned map element data, semantic information in the aligned map element data can be obtained, and the left and right lane lines in the road segment and the edge position of the drivable area are identified based on the voice information. If the right lane line of the current lane is identified as the edge of the drivable area, the current lane position is identified as the first lane. At this time, the lane number can be set to 1, and the confidence of the lane number can be set to the highest. If the right lane line of the right lane of the current lane is identified as the edge of the drivable area, the current lane position is identified as the second lane. At this time, the lane number can be set to 2, and the confidence of the lane number can be set to a higher level. If the edge of the drivable area of ​​the current lane cannot be identified, the current lane position is identified as not the first lane or the second lane. At this time, the lane number can be set to an estimated value according to the number of lanes in the road segment, such as 3 or 4, and the confidence of the lane number can be set to a very low level. Similarly, if the left lane line of the current lane is recognized as the edge of the drivable area, the current lane position is recognized as the leftmost lane. Assuming the number of lanes is 6, the lane number can be set to 6, and the confidence of the lane number can be set to the highest. If the left lane line of the left lane of the current lane is recognized as the edge of the drivable area, the current lane position is recognized as the 5th lane. The lane number can be set to 5, and the confidence of the lane number can be set to a higher level. If the edge of the drivable area of ​​the current lane cannot be recognized, the current lane position is recognized as not the 6th lane or the 5th lane. At this time, the lane number can be set to an estimated value according to the number of lanes in the road segment, such as 3 or 4, and the confidence of the lane number can be set to a very low level.

[0111] In an embodiment of the present application, the current lane position and the real-time road-level map data are used to generate lane geometry information for each lane marking point, wherein the lane marking point represents the current road segment division point, and the lane geometry information includes a lane ID, a lane number, and a lane number confidence level.

[0112] In a specific embodiment, the above-mentioned generating corresponding real-time matching map element data according to the lane geometry information of each lane marking point and the aligned map element data specifically includes:

[0113] Determining a lane number and a lane number confidence level corresponding to the current lane position according to the current lane position, the lane geometry information, and the aligned map element data;

[0114] According to the lane number corresponding to the lane ID, identify the lane lines on the left and right sides of the current lane position;

[0115] Identifying lane line types of the lane lines on the left and right sides of the current lane position according to the lane lines on the left and right sides of the current lane position and the aligned map element data;

[0116] Generate a solid line area according to the lane line types of the lane lines on the left and right sides of the current lane position;

[0117] The solid line data in the aligned map element data are matched with the solid line area to obtain corresponding real-time matching map element data.

[0118] In an embodiment of the present application, the matching algorithm used when matching the solid line data in the aligned map element data with the solid line area can be the EM algorithm. The specific implementation process can refer to the detailed description in the prior art and no specific limitation can be made here.

[0119] In a specific embodiment, the above-mentioned multiple sets of generated real-time lane geometry data, real-time matching map element data and real-time road-level map data are fused to obtain fused lane geometry data, fused matching map element data and fused road-level map data, specifically including:

[0120] fusing the plurality of sets of the real-time road-level map data to obtain the fused road-level map data;

[0121] Using the fused road-level map data, the data at the same position in the multiple sets of real-time lane geometry data are fused to obtain fused lane geometry data;

[0122] According to the principle of time sequence, the optimal preset number of groups of real-time matching map element data are selected from the multiple groups of real-time matching map element data to obtain fused matching map element data.

[0123] S104: Based on the fused matching map element data and the fused road-level map data, updated lane geometry data, updated matching map element data and updated road-level map data are obtained according to the determined mean and variance of each initial key point in the initial lane geometry data and the determined mean and variance of each corresponding fused key point in the fused lane geometry data.

[0124] In the above step S104, based on the fused matching map element data and the fused road-level map data, according to the determined mean and variance of each initial key point in the initial lane geometry data, and the determined mean and variance of each fused key point in the fused lane geometry data, the updated lane geometry data, the updated matching map element data and the updated road-level map data are obtained, which specifically includes:

[0125] Determining the mean and variance of each initial key point in the initial lane geometry data;

[0126] Determine the mean and variance of each fused key point corresponding to the fused lane geometry data;

[0127] Based on the fused matching map element data and the fused road-level map data, determining whether a difference in mean and a difference in variance between each initial key point in the initial lane geometry data and a corresponding fused key point in the fused lane geometry data are both within a corresponding threshold range;

[0128] If yes, based on the mean and variance of each initial key point in the initial lane geometry data and the corresponding fused key point in the fused lane geometry data, the mean and variance of the updated key points are updated to obtain the updated lane geometry data, the updated matching map element data and the updated road-level map data.

[0129] In a specific embodiment, the above-mentioned determination of the mean and variance of each initial key point of each divided road segment in the initial lane geometry data specifically includes:

[0130] Determining the center position and edge position of each cluster according to the semantic information in the initial lane geometry data;

[0131] According to the center positions and edge positions of each cluster, the center line position point of the head or tail of the road segment is determined to obtain the initial key point position;

[0132] Fine-tuning the position of the initial key point to obtain an adjusted position of the initial key point;

[0133] According to the positions of the cluster centers of the road segments and the adjusted positions of the initial key points, the mean, lateral variance and longitudinal variance of the initial key points are determined.

[0134] In a specific embodiment, the above-mentioned determination of the mean and variance of each fused key point corresponding to the fused lane geometry data specifically includes:

[0135] Determining the center position and edge position of each cluster according to the semantic information in the fused lane geometry data;

[0136] According to the center position and edge position of each cluster, determine the center line position point of the head or tail of the road segment to obtain the initial position of the fusion key point;

[0137] Fine-tuning the initial position of the fusion key point to obtain an adjusted position of the fusion key point;

[0138] According to the positions of the cluster centers of the road segments and the adjusted positions of the fused key points, the mean, lateral variance and longitudinal variance of the fused key points are determined.

[0139] In the embodiment of the present application, each key point in the above-mentioned initial lane geometry data and each key point in the fused lane geometry data are pre-defined key points, wherein the key point refers to the cluster center position of the semantic information uploaded by the vehicle. According to the implementation principle, the edge confidence of the semantic information is higher, so the initial position of the key point is generally the center line position of the head or tail of the solid line segment, arrow, etc. The method of fine-tuning the initial key point position and the initial position of the fused key point can be implemented using the GM algorithm. The specific implementation method of the GM algorithm can refer to the detailed description of the prior art and will not be repeated here.

[0140] In a specific embodiment, the above-mentioned determining, based on the fused matching map element data and the fused road-level map data, whether the difference between the mean and the difference between the variance of each initial key point in the initial lane geometry data and the corresponding fused key point in the fused lane geometry data are both within the corresponding threshold range, specifically includes:

[0141] Based on the fused matching map element data and the fused road-level map data, determine whether the differences between the means of each initial key point in the initial lane geometry data and the corresponding fused key points in the fused lane geometry data are all within a first threshold range, whether the differences in lateral variances are within a second threshold range, and whether the differences in longitudinal variances are all within a third threshold range.

[0142] In the embodiment of the present application, the fused map data is compared with the initial map data to determine whether the differences between the means of the key points of the initial map data and the key points of the fused map data are all within the first threshold range, whether the differences in the lateral variances are within the second threshold range, and whether the differences in the longitudinal variances are all within the third threshold range, thereby achieving validity detection of the fused map data.

[0143] In a specific embodiment, the above-mentioned updating of the mean and variance of the updated key points based on the mean and variance of each initial key point in the initial lane geometry data and the corresponding fused key points of the fused lane geometry data, and obtaining the updated lane geometry data, the updated matching map element data and the updated road-level map data specifically includes:

[0144] According to the mean, lateral variance and longitudinal variance of each initial key point in the initial lane geometry data and the corresponding fused key points of the fused lane geometry data, the Kalman filter algorithm is used to update the mean and variance of the updated key points, generate the updated lane geometry data, and obtain the updated matching map element data and the updated road-level map data.

[0145] In a specific embodiment, after determining, based on the fused matching map element data and the fused road-level map data, whether the difference in mean and variance between each initial key point in the initial lane geometry data and the corresponding fused key point in the fused lane geometry data are both within a corresponding threshold range, the method may further include:

[0146] If the difference between the means of each initial key point in the initial lane geometry data and the corresponding fused key point in the fused lane geometry data is not within the first threshold range, the difference in lateral variance is not within the second threshold range, or the difference in longitudinal variance is not within the third threshold range, the fused lane geometry data, the fused matching map element data, and the fused road-level map data are discarded.

[0147] In an embodiment of the present application, if the difference between the mean of each key point of the initial map data and each key point of the fused map data is within the first threshold range, the difference of the lateral variance is within the second threshold range, and the difference of the longitudinal variance is within the third threshold range, then according to the mean, lateral variance and longitudinal variance of each initial key point in the initial lane geometry data and the corresponding fused key point of the fused lane geometry data, the Kalman filter algorithm is used to update the mean and variance of the updated key point, generate the updated lane geometry data, and obtain the updated matching map element data and the updated road-level map data. Specifically, the Kalman filter algorithm is used to update the mean and variance of the initial key point and generate the updated lane geometry data. The Kalman filter continuously updates the position estimate of the key point through prediction and update steps. The prediction step is based on the system model, taking into account the motion model of the key point, and predicting the position of the next key point. The update step uses the observation model to compare the actual observed key point position with the predicted value, calculate the Kalman gain, and then use the gain to update the position estimate of the key point. Repeating this process can obtain the updated position estimate of the key point. Finally, based on the updated key point position estimation, updated lane geometry data can be generated, and updated matching map feature data and updated road-level map data can be obtained.

[0148] In an embodiment of the present application, if the difference between the means of each initial key point in the initial lane geometry data and the corresponding fused key point of the fused lane geometry data is not within the first threshold range, the difference in lateral variance is not within the second threshold range, or the difference in longitudinal variance is not within the third threshold range, the fused lane geometry data, the fused matching map element data, and the fused road-level map data are discarded.

[0149] S105: Repeat the steps of iteratively updating the updated lane geometry data, the updated matching map element data and the updated road-level map data until the iteration stop condition is reached, thereby obtaining the optimal lane geometry data, the optimal matching map element data and the optimal road-level map data.

[0150] In the embodiment of the present application, the specific implementation process of the above step S105 can be that, according to each group of new real-time crowdsourced map element data obtained, corresponding new real-time lane geometry data, new real-time matching map element data and new real-time road-level map data are respectively generated. The generated multiple groups of new real-time lane geometry data, new real-time matching map element data and new real-time road-level map data are fused to obtain new fused lane geometry data, new fused matching map element data and new fused road-level map data. Based on the new fused matching map element data and the new fused road-level map data, according to the determined mean and variance of each key point in the updated lane geometry data, and the determined mean and variance of each key point corresponding to the new fused lane geometry data, new updated lane geometry data, new updated matching map element data and new updated road-level map data are obtained. Repeat the above steps of obtaining new updated lane geometry data, new updated matching map element data and new updated road-level map data until the iteration stop condition is reached, and the optimal lane geometry data, optimal matching map element data and optimal road-level map data are obtained. The iteration stopping condition is that the difference between two adjacent iterations is less than a fourth preset threshold.

[0151] S106: Generate a high-precision map based on the optimal lane geometry data, the optimal matching map element data and the optimal road-level map data.

[0152] In an embodiment of the present application, when generating a high-precision map, the optimal lane geometry data, matching map element data and road-level map data can be fused, and a map generation tool or algorithm can be used to generate a high-precision map based on the fused data. The specific implementation method is not specifically limited here.

[0153] The method for generating a high-precision map provided in the embodiment of the present application fuses the real-time lane geometry data, real-time matching map element data and real-time road-level map data generated by multiple sets of real-time crowd-sourced map element data, thereby eliminating the impact of the discreteness and instability of the complex crowd-sourced map data on the generation of high-precision maps, and obtaining more accurate lane geometry information through data fusion, providing a more reliable data basis for map generation and improving the accuracy of map data; updating the initial lane geometry data based on the fused real-time lane geometry data can provide a stable and consistent map experience and improve the map update speed. Moreover, generating a high-precision map based on the optimal lane geometry data, optimal matching map element data and optimal road-level map data obtained through repeated iterative updates can effectively improve lane recognition errors and improve map navigation accuracy.

[0154] Embodiment 2

[0155] Based on the same inventive concept, the present application also provides a method for using a high-precision map. Figure 2 As shown, the method includes:

[0156] S201: receiving high-precision map data;

[0157] S202: Generate lane geometry data based on currently collected map element data;

[0158] S203: Matching the lane geometry data to the high-precision map data to obtain map data to be displayed;

[0159] S204: Displaying the map data to be displayed.

[0160] The method for using the high-precision map provided in the embodiment of the present application can be applied to the vehicle side, and the high-precision map data in the above step S201 is the high-precision map data obtained through the above steps S101 to S106. During the process of using the map for navigation, the vehicle side can continuously request the cloud server to obtain the high-precision map data, thereby receiving the high-precision map data returned by the cloud server.

[0161] In the above step S202, the currently collected map element data may include semantic information and target detection information of the road, and may also include GPS trajectory point data, vehicle posture and positioning information and other data to generate lane geometry data. The method of generating lane geometry data based on the map element data can refer to the description of the above step S101, which will not be repeated here.

[0162] In the above step S203, the matching algorithm used to match the lane geometry data to the high-precision map data may be the EM algorithm. The specific implementation process may refer to the detailed description in the prior art and no specific limitation may be made here.

[0163] In the above step S204, the manner of displaying the obtained map data to be displayed may refer to the detailed description in the prior art, and no specific limitation is made here.

[0164] Embodiment 3

[0165] Based on the same inventive concept, the present application embodiment also provides a device for generating a high-precision map, referring to Figure 3 As shown, the device comprises:

[0166] A first generating module 101 is used to generate initial lane geometry data and initial element map according to the acquired multiple sets of initial crowdsourced map element data, and determine initial road-level map data;

[0167] The second generation module 102 is used to generate corresponding real-time lane geometry data, real-time matching map element data and real-time road-level map data according to each set of real-time crowd-sourced map element data obtained;

[0168] A fusion module 103 is used to fuse the generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data to obtain fused lane geometry data, fused matching map element data and fused road-level map data;

[0169] The updating module 104 is used to obtain updated lane geometry data, updated matching map element data and updated road-level map data based on the fused matching map element data and the fused road-level map data according to the determined mean and variance of each key point in the initial lane geometry data and the determined mean and variance of each key point corresponding to the fused lane geometry data; and repeat the steps of iteratively updating the updated lane geometry data, the updated matching map element data and the updated road-level map data until an iteration stop condition is reached, thereby obtaining optimal lane geometry data, optimal matching map element data and optimal road-level map data;

[0170] The third generation module 105 is used to generate a high-precision map according to the optimal lane geometry data, the optimal matching map element data and the optimal road-level map data.

[0171] Embodiment 4

[0172] Based on the same inventive concept, the present application also provides a device for using a high-precision map. Figure 4As shown, the device comprises:

[0173] Receiving module 201, used for receiving high-precision map data;

[0174] The data generation module 202 is used to generate lane geometry data according to the currently collected map element data;

[0175] A matching module 203, used for matching the lane geometry data to the high-precision map data to obtain map data to be displayed;

[0176] The display module 204 is used to display the map data to be displayed.

[0177] Embodiment 5

[0178] Based on the same inventive concept, an embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, it implements the method for generating a high-precision map as described in the above embodiment one, and / or the method for using a high-precision map as described in the above embodiment two.

[0179] Embodiment 6

[0180] Based on the same inventive concept, an embodiment of the present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method for generating a high-precision map as described in the above embodiment 1, and / or the method for using a high-precision map as described in the above embodiment 2.

[0181] Embodiment 7

[0182] Based on the same inventive concept, an embodiment of the present application also provides a computer program product comprising instructions. When the computer program product is run on a computer device, the computer device executes the method for generating a high-precision map as described in the above embodiment one, and / or the method for using a high-precision map as described in the above embodiment two.

[0183] Embodiment 8

[0184] Based on the same inventive concept, an embodiment of the present application also provides a chip, the chip includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run a computer program or instructions to implement the method for generating a high-precision map as described in the above embodiment one, and / or the method for using a high-precision map as described in the above embodiment two.

[0185] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0186] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0187] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0188] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0189] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for generating a high-precision map, characterized in that: include: generating initial lane geometry data and initial feature maps, and determining initial road-level map data based on the acquired multiple sets of initial crowdsourced map feature data; According to each set of real-time crowdsourced map element data obtained, corresponding real-time lane geometry data, real-time matching map element data and real-time road-level map data are generated respectively; The generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data are fused to obtain fused lane geometry data, fused matching map element data and fused road-level map data; Based on the fused matching map element data and the fused road-level map data, according to the determined mean and variance of each initial key point in the initial lane geometry data, and the determined mean and variance of each corresponding fused key point in the fused lane geometry data, obtaining updated lane geometry data, updated matching map element data, and updated road-level map data; Repeat the steps of iteratively updating the updated lane geometry data, the updated matching map element data, and the updated road-level map data until an iteration stop condition is reached, thereby obtaining optimal lane geometry data, optimal matching map element data, and optimal road-level map data; A high-precision map is generated based on the optimal lane geometry data, the optimal matching map element data and the optimal road-level map data.

2. The method according to claim 1, characterized in that The method of obtaining updated lane geometry data, updated matching map element data and updated road-level map data based on the fused matching map element data and the fused road-level map data according to the determined mean and variance of each initial key point in the initial lane geometry data and the determined mean and variance of each fused key point in the fused lane geometry data comprises: Determining the mean and variance of each initial key point in the initial lane geometry data; Determine the mean and variance of each fused key point corresponding to the fused lane geometry data; Based on the fused matching map element data and the fused road-level map data, determining whether a difference in mean and a difference in variance between each initial key point in the initial lane geometry data and a corresponding fused key point in the fused lane geometry data are both within a corresponding threshold range; If yes, based on the mean and variance of each initial key point in the initial lane geometry data and the corresponding fused key point in the fused lane geometry data, the mean and variance of the updated key points are updated to obtain the updated lane geometry data, the updated matching map element data and the updated road-level map data.

3. The method according to claim 2, characterized in that The determining of the mean and variance of each initial key point of each divided road segment in the initial lane geometry data includes: Determining the center position and edge position of each cluster according to the semantic information in the initial lane geometry data; According to the center positions and edge positions of each cluster, the center line position point of the head or tail of the road segment is determined to obtain the initial key point position; Fine-tuning the position of the initial key point to obtain an adjusted position of the initial key point; Determine the mean, lateral variance and longitudinal variance of the initial key points according to the positions of the cluster centers of the road segments and the adjusted positions of the initial key points; and / or, Determining the mean and variance of each fused key point corresponding to the fused lane geometry data includes: Determining the center position and edge position of each cluster according to the semantic information in the fused lane geometry data; According to the center position and edge position of each cluster, determine the center line position point of the head or tail of the road segment to obtain the initial position of the fusion key point; Fine-tuning the initial position of the fusion key point to obtain an adjusted position of the fusion key point; According to the positions of the cluster centers of the road segments and the adjusted positions of the fused key points, the mean, lateral variance and longitudinal variance of the fused key points are determined.

4. The method according to claim 3, characterized in that The determining, based on the fused matching map element data and the fused road-level map data, whether the difference between the mean and the difference between the variance of each initial key point in the initial lane geometry data and the corresponding fused key point in the fused lane geometry data are both within a corresponding threshold range includes: Based on the fused matching map element data and the fused road-level map data, determine whether the differences between the means of each initial key point in the initial lane geometry data and the corresponding fused key points in the fused lane geometry data are all within a first threshold range, whether the differences in lateral variances are within a second threshold range, and whether the differences in longitudinal variances are all within a third threshold range.

5. The method according to claim 4, characterized in that The updating of the mean and variance of the updated key points according to the means and variances of the initial key points in the initial lane geometry data and the corresponding fused key points in the fused lane geometry data, and obtaining the updated lane geometry data, the updated matching map element data and the updated road-level map data, includes: According to the mean, lateral variance and longitudinal variance of each initial key point in the initial lane geometry data and the corresponding fused key points of the fused lane geometry data, the Kalman filter algorithm is used to update the mean and variance of the updated key points, generate the updated lane geometry data, and obtain the updated matching map element data and the updated road-level map data.

6. The method according to claim 4, characterized in that Also includes: If the difference between the means of each initial key point in the initial lane geometry data and the corresponding fused key point in the fused lane geometry data is not within the first threshold range, the difference in lateral variance is not within the second threshold range, or the difference in longitudinal variance is not within the third threshold range, the fused lane geometry data, the fused matching map element data, and the fused road-level map data are discarded.

7. The method according to claim 1, characterized in that The generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data are fused to obtain fused lane geometry data, fused matching map element data and fused road-level map data, including: For each set of real-time crowdsourced map element data, the road is transversely segmented according to the corresponding real-time road-level map data obtained to obtain a road segment with two marking points at the beginning and the end; Aligning the real-time crowdsourced map element data with the initial element map to obtain aligned map element data; According to the aligned map element data, identifying the left and right lane lines in the road segment and the edge position of the drivable area to obtain the current lane position; Generate lane geometry information of each lane marking point using the current lane position and the real-time road-level map data; Generate corresponding real-time matching map element data according to the lane geometry information of each lane marking point and the aligned map element data; The generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data are fused to obtain fused lane geometry data, fused matching map element data and fused road-level map data.

8. The method according to claim 7, characterized in that The lane geometry information includes a lane ID, a lane number, and a lane number confidence; The generating corresponding real-time matching map element data according to the lane geometry information of each lane marking point and the aligned map element data includes: Determining a lane number and a lane number confidence level corresponding to the current lane position according to the current lane position, the lane geometry information, and the aligned map element data; According to the lane number corresponding to the lane ID, identify the lane lines on the left and right sides of the current lane position; Identifying lane line types of the lane lines on the left and right sides of the current lane position according to the lane lines on the left and right sides of the current lane position and the aligned map element data; Generate a solid line area according to the lane line types of the lane lines on the left and right sides of the current lane position; The solid line data in the aligned map element data are matched with the solid line area to obtain corresponding real-time matching map element data.

9. The method according to claim 7, characterized in that The generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data are fused to obtain fused lane geometry data, fused matching map element data and fused road-level map data, including: fusing the plurality of sets of the real-time road-level map data to obtain the fused road-level map data; Using the fused road-level map data, the data at the same position in the multiple sets of real-time lane geometry data are fused to obtain fused lane geometry data; According to the principle of time sequence, the optimal preset number of groups of real-time matching map element data are selected from the multiple groups of real-time matching map element data to obtain fused matching map element data.

10. The method according to claim 7, characterized in that After aligning the real-time crowd-sourced map element data with the initial element map to obtain the aligned map element data, the method further includes: filtering abnormal data on the aligned map element data.

11. A method for using a high-precision map, characterized in that: include: Receive high-precision map data; Generate lane geometry data based on currently collected map feature data; Matching the lane geometry data to the high-precision map data to obtain map data to be displayed; The map data to be displayed is displayed.

12. A high-precision map generation device, applied to a server, characterized in that: include: A first generation module, configured to generate initial lane geometry data and an initial feature map according to the acquired multiple sets of initial crowdsourced map feature data, and determine initial road-level map data; A second generation module is used to generate corresponding real-time lane geometry data, real-time matching map element data and real-time road-level map data according to each set of real-time crowd-sourced map element data obtained; A fusion module is used to fuse the generated multiple sets of real-time lane geometry data, real-time matching map element data and real-time road-level map data to obtain fused lane geometry data, fused matching map element data and fused road-level map data; an updating module, for obtaining updated lane geometry data, updated matching map element data and updated road-level map data based on the fused matching map element data and the fused road-level map data, according to the determined mean and variance of each key point in the initial lane geometry data, and the determined mean and variance of each key point corresponding to the fused lane geometry data; and repeating the steps of iteratively updating the updated lane geometry data, the updated matching map element data and the updated road-level map data until an iteration stop condition is reached, thereby obtaining optimal lane geometry data, optimal matching map element data and optimal road-level map data; The third generation module is used to generate a high-precision map based on the optimal lane geometry data, the optimal matching map element data and the optimal road-level map data.

13. A device for using a high-precision map, applied to a client, characterized in that: include: A receiving module, used for receiving high-precision map data; A data generation module, used to generate lane geometry data based on currently collected map element data; A matching module, used for matching the lane geometry data to the high-precision map data to obtain map data to be displayed; The display module is used to display the map data to be displayed.

14. A computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal, the terminal executes the method for generating a high-precision map as described in any one of claims 1 to 10 or the method for using a high-precision map as described in claim 11.

15. A computer device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the method for generating a high-precision map as described in any one of claims 1 to 10 or the method for using a high-precision map as described in claim 11.

16. A computer program product comprising instructions, which, when executed on a computer device, enables the computer device to execute the method for generating a high-precision map as described in any one of claims 1 to 10 or the method for using a high-precision map as described in claim 11.

17. A chip, comprising a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is used to run a computer program or instruction to implement the method for generating a high-precision map as described in any one of claims 1 to 10 or the method for using a high-precision map as described in claim 11.

Images