Map update methods and map update devices

Abstract

This invention provides a map updating method and apparatus applied in the cloud. The map updating method includes: acquiring multiple lane line data collected and uploaded by multiple vehicles during their driving; acquiring target map data corresponding to the driving areas of the multiple vehicles; aligning the multiple lane line data with the target map data to obtain heatmap data of the lane lines; determining deviation data of the target map data based on the heatmap data; and updating the target map data according to the deviation data. This invention enables map updating in the cloud based on lane line data uploaded by multiple vehicles, improving map updating speed and avoiding inconsistencies between the current actual lane lines and the lane lines in the map.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to map updating methods and devices. Background Technology

[0002] In vehicles, accurate maps can better assist driving. The maps used by vehicles are usually high-definition maps provided by traditional map providers. However, the lane lines in these high-definition maps are often not updated in a timely manner, which may lead to discrepancies between the actual lane lines and those on the map.

[0003] Moreover, traditional map providers have limited manpower in their data collection fleets, making it difficult to achieve rapid updates and far from meeting the needs of vehicles for map data updates. Summary of the Invention

[0004] In view of the above problems, a map updating method and a map updating apparatus are proposed to overcome or at least partially solve the above problems.

[0005] In one aspect, a map updating method is provided, applied in the cloud, the method comprising:

[0006] Acquire multiple lane line data collected and uploaded by multiple vehicles during their driving process;

[0007] Obtain the target map data corresponding to the driving areas of the multiple vehicles;

[0008] Align the multiple lane line data with the target map data to obtain the lane line heatmap data;

[0009] Based on the heatmap data, the deviation data of the target map data is determined, and the target map data is updated according to the deviation data.

[0010] Optionally, aligning the multiple lane line data with the target map data to obtain lane line heatmap data includes:

[0011] Align each lane line data with the target map data by matching lane lines with the map.

[0012] The lane line data is then matched and aligned to obtain the heatmap data of the lane lines.

[0013] Optionally, the step of matching and aligning each lane line data with the target map data includes:

[0014] Match the target lane line data with the lane lines in the target map data to determine the pose offset data of the matching lane line segments;

[0015] The target lane line data is optimized and aligned based on the pose offset data.

[0016] Optionally, matching the target lane line data with the lane lines in the target map data includes:

[0017] Determine the lane line type in the target lane line data;

[0018] Based on the lane line type, the target lane line data and the lane lines in the target map data are matched.

[0019] Optionally, matching the target lane line data with the lane lines in the target map data includes:

[0020] Determine the positional relationships of lane lines in the target lane line data;

[0021] Based on the lane line position relationship, the target lane line data and the lane lines in the target map data are matched.

[0022] Optionally, it also includes:

[0023] The multiple lane line data are preprocessed to clean the data, remove lane lines that are too short and / or bent, and filter to obtain lane lines that meet the expectations.

[0024] Optionally, the preprocessing of the multiple lane line data includes:

[0025] Determine the coordinate data of the multiple lane lines;

[0026] Based on the coordinate data of the lane lines, the multiple lane lines are filtered.

[0027] In another aspect, a map updating device is provided for use in the cloud, the map updating device comprising:

[0028] The lane line data acquisition module is used to acquire multiple lane line data collected and uploaded by multiple vehicles during their driving process;

[0029] The map data acquisition module is used to acquire target map data corresponding to the driving areas of the multiple vehicles;

[0030] A heatmap generation module is used to align the multiple lane line data with the target map data to obtain heatmap data of the lane lines;

[0031] The map data update module is used to determine the deviation data of the target map data based on the heat map data, and update the target map data according to the deviation data.

[0032] In another aspect, a server is provided, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the map update method as described above.

[0033] In another aspect, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the map updating method as described above.

[0034] The embodiments of the present invention have the following advantages:

[0035] This invention acquires multiple lane line data collected and uploaded by multiple vehicles during their driving process, and can also obtain target map data corresponding to the driving areas of the multiple vehicles. The multiple lane line data are then aligned with the target map data to obtain lane line heatmap data. Based on the heatmap data, the deviation data of the target map data can be determined, and the target map data can be updated according to the deviation data. This enables map updates in the cloud based on lane line data uploaded by multiple vehicles, improving map update speed and avoiding inconsistencies between the actual lane lines and those in the map. Attached Figure Description

[0036] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart of the steps of a map updating method provided in an embodiment of the present invention;

[0038] Figure 2 This is a flowchart of another map updating method provided in an embodiment of the present invention;

[0039] Figure 3 This is a schematic diagram of the structure of a map updating device provided in an embodiment of the present invention. Detailed Implementation

[0040] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0041] Reference Figure 1 The diagram illustrates a flowchart of a map update method according to an embodiment of the present invention, applied in the cloud, and specifically includes the following steps:

[0042] Step 101: Obtain multiple lane line data collected and uploaded by multiple vehicles during their driving process;

[0043] While driving, vehicles can collect environmental data around them using their sensors, such as lane line data, speed bump data, obstacle data (e.g., walls, roadblocks), and intersection data. This environmental data can indicate the actual road conditions and can be used to build maps that reflect the current road conditions.

[0044] To build accurate maps, multiple vehicles can collect data while driving and upload the collected data to the cloud for processing. The data uploaded by the vehicles can include lane line data.

[0045] Lane line data can be generated based on image data captured by multiple cameras on the vehicle during its operation. Specifically, the vehicle can acquire multiple image data from multiple cameras, then stitch these multiple image data together to obtain target image data, from which lane line data can be extracted.

[0046] In one embodiment of the present invention, the method further includes: preprocessing the multiple lane line data to clean the multiple lane line data, removing lane line lines that are too short and / or bent, and filtering to obtain lane line lines that meet the expectations.

[0047] In practical applications, after the cloud obtains multiple lane line data uploaded by the vehicle, it can preprocess the multiple lane line data to clean the data, remove lane line lines that are too short and / or bent, and filter out lane line lines with good shape, thereby ensuring that subsequent lane line matching and alignment can proceed smoothly.

[0048] In one embodiment of the present invention, the preprocessing of the multiple lane line data includes:

[0049] Determine the coordinate data of the multiple lane lines; filter the multiple lane lines based on the coordinate data.

[0050] In practical applications, cloud-based preprocessing methods for multiple lane line data can include: preprocessing based on the coordinate data in the lane line data.

[0051] Specifically, the lane line data acquired by the vehicle can be composed of multiple coordinate points. Based on the distribution of multiple coordinate points, it can be determined whether there are bends in the lane line data, and thus the bends in the lane line data can be removed. In addition, the length of the lane line can be determined based on the coordinate points of the lane line data, and thus the lane line data with a length less than a preset length can be removed.

[0052] In one example, the vehicle can periodically upload lane line data to update the lane line data in the cloud; it can also preset an upload event in the vehicle. When the vehicle detects the preset upload event, it can upload the collected lane line data to the cloud. The upload event can be an event that triggers the vehicle's power-off, that is, the lane line data collected during the current driving process is uploaded to the cloud every time the vehicle is powered off.

[0053] It should be noted that, in the embodiments of the present invention, the triggering of the upload event can be set according to actual needs, and is not limited to the above example.

[0054] Step 102: Obtain the target map data corresponding to the driving areas of the multiple vehicles;

[0055] One or more map data can be pre-stored in the cloud. The map data can be obtained from map providers, or it can be map data synthesized by the cloud based on data uploaded by multiple vehicles, or it can be map data updated by the cloud based on the manufacturer's map.

[0056] Once the cloud receives lane line data uploaded by multiple vehicles, it can determine the target map data corresponding to the driving areas of the multiple vehicles from one or more map datasets, based on the vehicle locations.

[0057] Step 103: Align the multiple lane line data with the target map data to obtain the lane line heat map data;

[0058] After obtaining lane line data and target map data from the cloud, the target map data includes lane line data, which allows multiple lane line data to be aligned with the lane line data in the target map data. After alignment, a heatmap of lane lines can be generated, which can indicate the aggregation of multiple lane lines.

[0059] Step 104: Determine the deviation data of the target map data based on the heat map data, and update the target map data according to the deviation data.

[0060] After obtaining the heatmap, the deviation data between the target map data and the actual multiple lane line data can be determined based on the heatmap. The deviation data can include a first type of deviation data and a second type of deviation data. The first type of deviation data can be lane line data that exists in the multiple lane lines but does not exist in the target map data. The second type of deviation data can be lane line data that exists in both the multiple lane lines and the target map data, but cannot be completely overlapped due to the deviation.

[0061] After determining the deviation data, the target map data can be updated according to the deviation data. For example, errors can be checked for existing lane lines in the target map data, and errors in the target map data can be repaired according to the second type of deviation data. For areas not covered in the target map data, the first type of deviation data can be used to fill in the gaps and generate a high-precision map.

[0062] In this embodiment of the invention, multiple lane line data collected and uploaded by multiple vehicles during their driving process are acquired, and target map data corresponding to the driving areas of the multiple vehicles can be obtained. The multiple lane line data are then aligned with the target map data to obtain heatmap data of the lane lines. Based on the heatmap data, deviation data of the target map data can be determined, and the target map data can be updated according to the deviation data. This enables map updates in the cloud based on lane line data uploaded by multiple vehicles, improving map update speed and avoiding inconsistencies between the current actual lane lines and the lane lines in the map.

[0063] Reference Figure 2 The diagram illustrates a flowchart of another map update method provided by an embodiment of the present invention, applied in the cloud, and specifically includes the following steps:

[0064] Step 201: Obtain multiple lane line data collected and uploaded by multiple vehicles during their driving process;

[0065] While driving, vehicles can collect environmental data around them using their sensors, such as lane line data, speed bump data, obstacle data (e.g., walls, roadblocks), and intersection data. This environmental data can indicate the actual road conditions and can be used to build maps that reflect the current road conditions.

[0066] To build accurate maps, multiple vehicles can collect data while driving and upload the collected data to the cloud for processing. The data uploaded by the vehicles can include lane line data.

[0067] Lane line data can be generated based on image data collected by multiple cameras on the vehicle during its operation. Specifically, the vehicle can acquire multiple image data from multiple cameras, and then stitch these multiple image data together to obtain target image data, from which lane line data can be extracted.

[0068] Step 202: Obtain the target map data corresponding to the driving areas of the multiple vehicles;

[0069] The target map data obtained can be map data synthesized by the cloud based on data previously uploaded by multiple vehicles, or map data updated by the cloud based on the manufacturer's map.

[0070] Once the cloud receives lane line data uploaded by multiple vehicles, it can determine the target map data corresponding to the driving areas of the multiple vehicles from one or more map datasets, based on the vehicle locations.

[0071] Step 203: Align each lane line data with the target map data by matching lane lines with the map.

[0072] After obtaining lane line data and target map data from the cloud, the target lane line data includes lane line data, so that each lane line data can be matched and aligned with the target map data to achieve the greatest possible overlap between each lane line data and the target map data.

[0073] In one embodiment of the present invention, step 203 may include the following sub-steps:

[0074] Sub-step 2031: Match the target lane line data with the lane lines in the target map data to determine the pose offset data of the matched lane line segment;

[0075] In practical applications, target lane line data can be represented as any one of multiple lane lines. The target lane line data can be matched with the lane lines in the target map data. During the matching process, the pose offset between lane lines can be calculated for lane line segments that can be matched, while lane line segments that cannot be matched are left blank.

[0076] Therefore, by matching lane lines with the map, the pose offset data of the matching lane line segments can be determined. When the target lane line data is offset according to this pose offset data, the target lane line data can achieve the maximum overlap with the lane lines in the target map data.

[0077] In practical applications, the cloud can also match target lane line data with target map data by leveraging the characteristics of lane line data (such as lane line type, lane line position relationship, etc.).

[0078] In one embodiment of the present invention, step 2031 may include the following sub-steps:

[0079] Sub-step S21: Determine the lane line type in the target lane line data;

[0080] In practical applications, the cloud can determine the lane line type of each lane line in the target lane line data. Lane line types can be divided into solid line type, dashed line type, etc.

[0081] Sub-step S22: Based on the lane line type, match the target lane line data with the lane lines in the target map data.

[0082] After determining the lane line type, matching can be performed based on the lane line type, such as matching solid line types with solid line types, and dashed line types with dashed line types.

[0083] In another embodiment of the present invention, step 2031 may further include the following sub-steps:

[0084] Sub-step S23: Determine the positional relationship of lane lines in the target lane line data;

[0085] In practical applications, after obtaining the target lane line data in the cloud, it is also possible to determine the positional relationship between multiple lane lines contained in the target lane line data. The positional relationship can refer to the positional relationship between different lane lines in the target lane line data and / or the positional relationship between different coordinate points of the same lane line (whether they are the same lane line).

[0086] For example, the target lane line data includes lane line A, lane line B, and lane line C. The positional relationship can refer to the arrangement of lane line A, lane line B, and lane line C; or it can refer to the positional data between coordinate points on a single lane line.

[0087] Sub-step S24: Based on the lane line position relationship, match the target lane line data and the lane lines in the target map data.

[0088] After determining the positional relationship of the lane lines, matching can be performed based on the positional relationship of the lane lines.

[0089] In one example, the cloud can also combine the lane line type and lane line position relationship of the target lane line data to match the lane lines in the target map data.

[0090] For example, the target lane line data includes lane line A, lane line B, and lane line C, where lane line A is a solid line, lane line B is a dashed line, and lane line C is a solid line. The arrangement of the three lane lines can be represented as: solid line-dashed line-solid line. This arrangement is then matched with the lane line data in the target map data.

[0091] Sub-step 2032: Optimize and align the target lane line data based on the pose offset data.

[0092] After determining the pose offset data of the target lane line data, the target lane line data can be optimized and aligned based on the pose offset data.

[0093] Specifically, a preset optimizer can be used in the cloud to optimize the overall trajectory (target lane line data). While preserving the relative positional relationship of the trajectory (target lane line data), several deltaT (i.e. pose offset data) can be distributed to the entire trajectory, thereby aligning the target lane line data with the target map data.

[0094] Step 204: Match and align the lane lines between the aligned lane line data to obtain the heatmap data of the lane lines.

[0095] After aligning the lane line data with the target map data, the aligned lane line data can be matched and aligned with each other. Specifically, one lane line data is selected from the aligned lane line data, and the remaining lane line data are matched with this lane line data to determine the relative positional relationship between the lane lines (i.e., the lane line offset data). Then, the optimizer is used to align multiple trajectories (multiple lane line data) simultaneously.

[0096] In one example, matching and aligning lane lines between aligned lane line data can include:

[0097] The first lane line data is determined from the aligned lane line data. The first lane line data is then matched with other aligned lane line data to obtain the first pose offset data. All aligned lane line data are then optimized and aligned according to the first pose offset.

[0098] In practical applications, for multiple lane line data after alignment, the first lane line data can be determined, and the other lane line data can be matched with the first lane line data respectively. Specifically, the other lane line data can be matched with the first lane line data according to the lane line type and / or lane line position relationship of the first lane line data.

[0099] After matching, the relative positional relationship between the first lane line data and other lane line data can be determined (i.e., the first pose offset data), so that multiple lane line data can be optimized and aligned simultaneously according to the first pose offset data.

[0100] Step 205: Determine the deviation data of the target map data based on the heat map data, and update the target map data according to the deviation data.

[0101] After obtaining the heatmap, the deviation data between the target map data and the actual multiple lane line data can be determined based on the heatmap. The deviation data can include a first type of deviation data and a second type of deviation data. The first type of deviation data can be lane line data that exists in the multiple lane line data but does not exist in the target map data. The second type of deviation data can be lane line data that exists in both the multiple lane line data and the target map data, but cannot be completely overlapped due to the deviation.

[0102] After determining the deviation data, the target map data can be updated according to the deviation data. For example, errors can be checked for existing lane lines in the target map data, and errors in the target map data can be repaired according to the second type of deviation data. For areas not covered in the target map data, the first type of deviation data can be used to fill in the gaps and generate a high-precision map.

[0103] In this embodiment of the invention, multiple lane line data collected and uploaded by multiple vehicles during their driving process are acquired, and target map data corresponding to the driving areas of the multiple vehicles can be obtained. Each lane line data is then matched and aligned with the target map data. Further matching and alignment of lane lines is performed between the aligned lane line data to obtain lane line heatmap data. Deviation data of the target map data is determined, and the target map data is updated according to the deviation data. This enables map updates in the cloud based on lane line data uploaded by multiple vehicles, improving map update speed and avoiding inconsistencies between the current actual lane lines and the lane lines in the map.

[0104] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0105] Reference Figure 3The diagram illustrates a structural schematic of a map update device according to an embodiment of the present invention, which is applied in the cloud and may specifically include the following modules:

[0106] Lane line data acquisition module 301 is used to acquire multiple lane line data collected and uploaded by multiple vehicles during driving;

[0107] Map data acquisition module 302 is used to acquire target map data corresponding to the driving areas of the multiple vehicles;

[0108] The heatmap generation module 303 is used to align the multiple lane line data with the target map data to obtain the lane line heatmap data;

[0109] The map data update module 304 is used to determine the deviation data of the target map data based on the heat map data, and update the target map data according to the deviation data.

[0110] In one embodiment of the present invention, the heat map generation module 303 may include:

[0111] The first matching and alignment submodule is used to match and align each lane line data with the target map data.

[0112] The second matching and alignment submodule is used to match and align lane lines between the aligned lane line data to obtain lane line heatmap data.

[0113] In one embodiment of the present invention, the first matching alignment submodule may include:

[0114] The matching unit is used to match the target lane line data with the lane lines in the target map data and determine the pose offset data of the matched lane line segment.

[0115] An alignment unit is used to optimize and align the target lane line data based on the pose offset data.

[0116] In one embodiment of the present invention, the matching unit may include:

[0117] The lane line type determination subunit is used to determine the lane line type in the target lane line data;

[0118] The first matching subunit is used to match the target lane line data and the lane lines in the target map data based on the lane line type.

[0119] In one embodiment of the present invention, the matching unit may further include:

[0120] The lane line position relationship determination subunit is used to determine the lane line position relationship in the target lane line data;

[0121] The second matching subunit is used to match the target lane line data and the lane lines in the target map data based on the lane line position relationship.

[0122] In one embodiment of the present invention, the device may include:

[0123] The preprocessing module is used to preprocess the multiple lane line data to clean the data, remove lane lines that are too short and / or bent, and filter out lane lines that meet the expectations.

[0124] In one embodiment of the present invention, the preprocessing module may include:

[0125] The coordinate data determination submodule is used to determine the coordinate data of the multiple lane lines;

[0126] The lane line filtering submodule is used to filter the multiple lane lines based on the coordinate data of the lane lines.

[0127] In this embodiment of the invention, multiple lane line data collected and uploaded by multiple vehicles during their driving process are acquired, and target map data corresponding to the driving areas of the multiple vehicles can be obtained. The multiple lane line data are then aligned with the target map data to obtain heatmap data of the lane lines. Based on the heatmap data, deviation data of the target map data can be determined, and the target map data can be updated according to the deviation data. This achieves map updates in the cloud based on lane line data uploaded by multiple vehicles, improving map update speed and avoiding inconsistencies between the current actual lane lines and the lane lines in the map.

[0128] An embodiment of the present invention also provides a server, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the map update method described above.

[0129] An embodiment of the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the map update method described above.

[0130] As the device embodiment 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.

[0131] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0132] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0134] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0136] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0137] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0138] The map data update method and map update device provided above have been described in detail. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A map updating method, characterized in that, Applied to the cloud, the map update method includes: Multiple lane line data collected and uploaded by multiple vehicles during driving are acquired; the lane line data is extracted based on target image data, which is the data obtained by stitching together multiple image data collected by multiple cameras during vehicle driving. Obtain target map data corresponding to the driving areas of the multiple vehicles; the target map data is map data synthesized based on data uploaded by multiple vehicles; Align the multiple lane line data with the lane line data in the target map data to obtain lane line heatmap data; the heatmap data is used to indicate the aggregation of multiple lane lines; wherein, based on the lane line type and lane line position relationship of the lane line data, the target lane line data and the target map data are matched, the lane line position relationship refers to the position relationship between different lane lines in the target lane line data and / or the position relationship between different coordinate points of the same lane line, and the target lane line data is any one of the multiple lane lines; Based on the heatmap data, the deviation data of the target map data is determined, and the target map data is updated according to the deviation data; wherein, the existing lane lines in the target map data are checked for errors and the errors in the target map data are corrected according to the deviation data, or the areas not covered in the target map data are filled in according to the deviation data.

2. The method according to claim 1, characterized in that, The step of aligning the multiple lane line data with the lane line data in the target map data to obtain lane line heatmap data includes: Align each lane line data with the target map data by matching lane lines with the map. The lane line data is then matched and aligned to obtain the heatmap data of the lane lines.

3. The method according to claim 2, characterized in that, The step of matching and aligning each lane line data with the target map data includes: Match the target lane line data with the lane lines in the target map data to determine the pose offset data of the matching lane line segments; The target lane line data is optimized and aligned based on the pose offset data.

4. The method according to claim 3, characterized in that, The step of matching the target lane line data with the lane lines in the target map data includes: Determine the lane line type in the target lane line data; Based on the lane line type, the target lane line data and the lane lines in the target map data are matched.

5. The method according to claim 3, characterized in that, The step of matching the target lane line data with the lane lines in the target map data includes: Determine the positional relationships of lane lines in the target lane line data; Based on the lane line position relationship, the target lane line data and the lane lines in the target map data are matched.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: The multiple lane line data are preprocessed to clean the data, remove lane lines that are too short and / or bent, and filter to obtain lane lines that meet the expectations.

7. The method according to claim 6, characterized in that, The preprocessing of the multiple lane line data includes: Determine the coordinate data of the multiple lane lines; Based on the coordinate data of the lane lines, the multiple lane lines are filtered.

8. A map updating device, characterized in that, The map update device, applied in the cloud, includes: The lane line data acquisition module is used to acquire multiple lane line data collected and uploaded by multiple vehicles during driving; the lane line data is extracted based on target image data, which is the data obtained by stitching together multiple image data collected by multiple cameras during vehicle driving. The map data acquisition module is used to acquire target map data corresponding to the driving areas of the multiple vehicles; the target map data is map data synthesized based on data uploaded by multiple vehicles. A heatmap generation module is used to align the multiple lane line data with the lane line data in the target map data to obtain heatmap data of the lane lines; the heatmap data is used to indicate the aggregation of multiple lane lines; wherein, based on the lane line type and lane line position relationship of the lane line data, the target lane line data and the target map data are matched, the lane line position relationship refers to the position relationship between different lane lines in the target lane line data and / or the position relationship between different coordinate points of the same lane line, and the target lane line data is any one of the multiple lane lines; The map data update module is used to determine the deviation data of the target map data based on the heat map data, and update the target map data according to the deviation data; wherein, it checks for errors in the existing lane lines in the target map data and repairs the errors in the target map data according to the deviation data, or fills in the areas not covered in the target map data according to the deviation data.

9. A server, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the map update method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the map update method as described in any one of claims 1 to 7.

Images