High-precision Map Update Method, Device, Electronic Device and Medium

Abstract

The present disclosure provides a high-precision map updating method, apparatus, electronic device and medium, which relate to the field of artificial intelligence technology, specifically to the field of high-precision map technology, and can be applied to scenarios such as autonomous driving, intelligent transportation, and smart city. The specific implementation solution is as follows: determining the current map version to be updated, and determining the current map feature data according to the current map version; selecting auxiliary map feature data from the historical map feature data according to the current map feature data, and obtaining the historical tags of the auxiliary map feature data; determining the current tags of the current map feature data according to the historical tags of the auxiliary map feature data; updating the high-precision map according to the current map feature data and the current tags of the current map feature data to obtain the current version map. The present disclosure can improve the updating efficiency of the high-precision map and reduce the updating cost of the high-precision map.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to the field of high-precision map technology, and can be applied to scenarios such as autonomous driving, intelligent transportation, and smart cities. Background Art

[0002] An electronic map refers to a map stored and retrieved digitally using computer technology. Maps are used to describe the names, shapes, sizes, and element attributes of spatial positions of natural and human elements.

[0003] A high-precision map, also known as a high-accuracy map, is used by autonomous vehicles. A high-precision map has accurate vehicle position information and rich road element data information, which can help a vehicle predict complex road surface information, such as slope, curvature, heading, etc., and better avoid potential risks. Compared with ordinary electronic maps, a high-precision map has a larger data scale, so higher processing performance and processing efficiency are required during updating to ensure timeliness, accuracy, and reliability. Summary of the Invention

[0004] The present disclosure provides a high-precision map updating method, apparatus, electronic device, and medium.

[0005] According to one aspect of the present disclosure, a high-precision map updating method is provided. The method includes:

[0006] Determine the current map version to be updated, and determine the current map element data according to the current map version;

[0007] According to the current map element data, select auxiliary map element data from historical map element data, and obtain the historical label of the auxiliary map element data;

[0008] Determine the current label of the current map element data according to the historical label of the auxiliary map element data;

[0009] Update the high-precision map according to the current map element data and the current label of the current map element data to obtain the current version map.

[0010] According to another aspect of the present disclosure, a high-precision map updating apparatus is provided, including:

[0011] A current element determination module, configured to determine the current map version to be updated, and determine the current map element data according to the current map version;

[0012] An auxiliary data determination module, configured to select auxiliary map element data from historical map element data according to the current map element data, and obtain the historical label of the auxiliary map element data;

[0013] A current label determination module, configured to determine a current label of current map feature data according to historical labels of the auxiliary map feature data;

[0014] A high-precision map update module, configured to update a high-precision map according to the current map feature data and the current label of the current map feature data to obtain a current version map.

[0015] According to another aspect of the present disclosure, there is provided an electronic device, which includes:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the high-precision map update method according to any embodiment of the present disclosure.

[0019] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the high-precision map update method according to any embodiment of the present disclosure.

[0020] According to another aspect of the present disclosure, there is provided a computer program product, including a computer program, and the computer program implements the high-precision map update method according to any embodiment of the present disclosure when executed by a processor.

[0021] According to the technology of the present disclosure, the update efficiency of the high-precision map can be improved, and the update cost of the high-precision map can be reduced.

[0022] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0024] Figure 1 is a flowchart of a high-precision map update method provided according to an embodiment of the present disclosure;

[0025] Figure 2 is a flowchart of another high-precision map update method provided according to an embodiment of the present disclosure;

[0026] Figure 3 is a flowchart of another high-precision map update method provided according to an embodiment of the present disclosure;

[0027] Figure 4 is a schematic structural diagram of a high-precision map updating device provided according to an embodiment of the present disclosure;

[0028] Figure 5 is a block diagram of an electronic device for implementing the high-precision map updating method according to an embodiment of the present disclosure. Detailed implementation manners

[0029] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to assist understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following.

[0030] Figure 1 is a flowchart of a high-precision map updating method provided according to an embodiment of the present disclosure. The embodiments of the present disclosure are applicable to updating high-precision maps, especially for the case of full-map updating of high-precision maps. This method can be executed by a high-precision map updating device, which can be implemented in software and / or hardware and can be integrated into an electronic device with the function of high-precision map updating. As Figure 1 shown, the high-precision map updating method of this embodiment may include:

[0031] S101, determine the current map version to be updated, and determine the current map feature data according to the current map version;

[0032] S102, select auxiliary map feature data from historical map feature data according to the current map feature data, and obtain the historical tags of the auxiliary map feature data;

[0033] S103, determine the current tags of the current map feature data according to the historical tags of the auxiliary map feature data;

[0034] S104, update the high-precision map according to the current map feature data and the current tags of the current map feature data to obtain the current version map.

[0035] Map updating of the high-precision map means upgrading the high-precision map from an old map version to a new map version. The current map version to be updated represents the new map version. A high-precision map refers to a map stored and retrieved digitally using computer technology. The map is used to describe the name, shape, size, and spatial location of natural and human elements. As the natural and human elements change, the high-precision map needs to be updated accordingly.

[0036] Among them, the high-precision map is generated based on map feature data. Map feature data refers to the original cartographic data collected by data acquisition devices. Map feature data is used to describe natural and human elements within a certain area. Map feature data can be multimodal, that is, multiple types of data can be used to describe natural and human elements within the same area. Exemplarily, map feature data can be point cloud data or image data used to describe the same intersection.

[0037] It can be understood that the area covered by a complete high-precision map is extremely large, possibly measured in tens of thousands of kilometers. Correspondingly, the data volume of the map feature data used to construct the high-precision map is also quite substantial. In particular, over time, new map feature data needs to be continuously collected to upgrade the map version of the high-precision map. To facilitate the management of map feature data, a map version to which the map feature data belongs is added. According to the map version to which the map feature data belongs, the map feature data can be divided into current map feature data and historical map feature data.

[0038] Among them, current map feature data refers to the map feature data collected for the current map version. Based on the current map feature data, the high-precision map can be updated from an old map version to the current map version. Historical map feature data is relative to the current map feature data, and historical map feature data corresponds to an old map version.

[0039] Historical map feature data has participated in the cartographic process of an old map version, and historical map feature data has corresponding historical tags. The historical tags of historical map feature data refer to the tag data generated during the cartographic process based on the historical map feature data. Among them, the tag data is used to determine the element attributes of natural and human elements within the map area to which the historical map feature data belongs. Exemplarily, the tag data can be the element type of human elements such as lane lines or traffic lights.

[0040] When the current map version is determined, the current map feature data is determined according to the current map version. Optionally, the map feature data belonging to the current map version is determined as the current map feature data. The current map feature data has not participated in the cartographic process, and the current map feature data does not have corresponding tag data.

[0041] It can be understood that the update of the high-precision map is carried out on the basis of an old map version, and there is an association between the current map feature data and the historical map feature data in terms of the map version to which they belong or the map area to which they belong.

[0042] Select auxiliary map feature data from historical map feature data according to the current map feature data. Optionally, determine the historical map feature data associated with the current map feature data as the auxiliary map feature data.

[0043] The auxiliary map feature data is generated from the historical feature data, and there is corresponding tag data for the auxiliary map feature data. Obtain the historical tags of the auxiliary map feature data, and use the historical tags of the auxiliary map feature data to determine the tag data of the current map feature data. In this way, during the mapping process based on the current map feature data, there is no need to re-label the map features described by the current map feature data, which is beneficial to improving the map update efficiency.

[0044] Optionally, if all the current tags of the current map feature data cannot be determined according to the historical tags of the auxiliary map feature data, supplement the labels of the map features described by the current map feature data to improve the current tags of the current map feature data.

[0045] When the current tags of the current map feature data are determined, update the high-precision map according to the current map feature data and the current tags of the current feature data to obtain the current version of the map.

[0046] The technical solution of the present disclosure selects auxiliary map feature data related to the current map feature data from the historical map feature data and obtains the historical tags of the auxiliary map feature data. Then, use the historical tags of the auxiliary map feature data to determine the current tags of the current map feature data, realizing the reuse of the historical tags of the historical map feature data. During the mapping process based on the current map feature data, there is no need to re-label the map features described by the current map feature data, improving the update efficiency of the high-precision map and reducing the update cost of the high-precision map at the same time.

[0047] The high-precision map has accurate vehicle position information and rich road element data information, which can help the vehicle predict complex road surface information, such as slope, curvature, heading, etc., and better avoid potential risks. Compared with ordinary electronic maps, the high-precision map has a larger data scale, so higher processing performance and processing efficiency are required to ensure timeliness, accuracy, and reliability during update. When updating the high-precision map, the map features in the high-precision map correspond to the traffic elements in the real world. The update of the high-precision map can be carried out when the traffic elements in the real world change.

[0048] The road coverage of high-precision maps amounts to hundreds of thousands of kilometers, and updating high-precision maps often involves updating a large area. In related technologies, in the process of updating high-precision maps using the current map element data collected from the area to be updated, it is mostly necessary to re-label the map elements described by the current map element data, which often incurs huge labeling costs, resulting in low map update efficiency and high map update costs. It is difficult to complete a full-map update of high-precision maps in this way.

[0049] The high-precision map update method provided by the embodiments of the present disclosure reuses the historical labels of auxiliary map element data, greatly reducing the map labeling cost and improving the map update efficiency. It provides a practical solution for full-map update of high-precision maps, which can improve the timeliness, accuracy, and reliability of high-precision maps, and is beneficial to improving the perception and decision-making abilities of autonomous driving.

[0050] In an optional embodiment, updating the high-precision map to obtain the current version map according to the current map element data and the current label of the current map element data includes: updating the map base map of the high-precision map according to the current map element data; and updating the label data of the high-precision map based on the current label of the current map element data.

[0051] Among them, the current map element data is used as map update materials to update the map base map of the high-precision map. The label data is used to represent the element attributes of the map elements in the map base map. The current label of the current map element data is used to update the label data of the high-precision map.

[0052] The current map element data not only includes the map elements that need to be reflected in the high-precision map, but may also include other elements. Exemplarily, in the case where the high-precision map is a high-precision map, the traffic elements that need to be reflected in the high-precision map include lane lines, traffic lights, and road signs, etc., while pedestrians and vehicles in the current map element data do not need to be reflected. Update the map base map of the high-precision map according to the current map element data. Optionally, perform screening processing on the current map element data, select the current map element data related to the target element, and update the map base map. It should be noted that the auxiliary map element data does not participate in updating the map base map of the high-precision map. The historical labels of the auxiliary map element data provide a reference for updating the label data of the high-precision map.

[0053] The above technical solution updates the map base map of the high-precision map using the current map element data, and updates the label data of the high-precision map using the current label of the current map element data, simplifying the map update process of the high-precision map and providing a practical high-precision map update method.

[0054] Figure 2 It is a flowchart of another high-precision map update method provided according to an embodiment of the present disclosure; this embodiment is an alternative solution proposed based on the above embodiment. Specifically, the operation of "determining the current label of the current map element data according to the historical label of the auxiliary map element data" in the embodiment of the present disclosure is refined.

[0055] See Figure 2 , the high-precision map update method provided in this embodiment includes:

[0056] S201, determine the current map version to be updated, and determine the current map element data according to the current map version.

[0057] S202, select auxiliary map element data from the historical map element data according to the current map element data, and obtain the historical label of the auxiliary map element data.

[0058] S203, adjust the historical label of the auxiliary map element data according to the current map element data to obtain the current label of the auxiliary map element data.

[0059] The auxiliary map element data is generated from the historical map element data. The map version to which the auxiliary map element data belongs is different from the map version to which the current map element data belongs, and there are differences between the data contents of the auxiliary map element data and the current map element data. The auxiliary map element data cannot adapt to the current map version, and the historical label of the auxiliary map element data cannot be directly used to determine the current label of the current map element data.

[0060] The current map element data corresponds to the current map version. The historical label of the auxiliary map element data is adjusted according to the current map element data to adapt to the current map version, and the current label of the auxiliary map element data is obtained.

[0061] Among them, the historical label of the auxiliary map element is adapted to the old map version, and the current label of the auxiliary map element is adapted to the current map version.

[0062] S204, determine the current label of the current map element data according to the current label of the auxiliary map element data.

[0063] Optionally, use the element set determined by the map element described by the current map element data as the current element set, and use the element set determined by the map element described by the auxiliary map element data as the auxiliary element set.

[0064] Determine the element intersection of the current element set and the auxiliary element set. Based on the element intersection, establish an association relationship between the current label of the auxiliary map element data and the current label of the current map element data.

[0065] If the set of auxiliary elements is a proper subset of the current set of elements, that is, there are map elements in the current set of elements that do not have corresponding current labels, then supplementary labeling is performed on the map elements described by the current map element data to improve the current labels of the current map element data.

[0066] S205, update the high-precision map according to the current map element data and the current labels of the current map element data to obtain the current version map.

[0067] In the technical solution of the present disclosure, by adjusting the historical labels of the auxiliary map element data according to the current map element data to obtain the current labels of the auxiliary map element data, the current labels of the auxiliary map element data can be adapted to the current map version. According to the current labels of the auxiliary map element data, the current labels of the current map element data are determined, ensuring the accuracy of the current labels of the current map element data, and thus ensuring the accuracy of map updates.

[0068] In an alternative embodiment, adjusting the historical labels of the auxiliary map element data according to the current map element data to obtain the current labels of the auxiliary map element data includes: performing pose optimization on the current map element data and the auxiliary map element data to obtain the current pose of the auxiliary map element data; determining the pose deviation between the current pose of the auxiliary map element data and the historical pose of the auxiliary map element data; and adjusting the historical labels of the auxiliary map element data based on the pose deviation to obtain the current labels of the auxiliary map element data.

[0069] It can be understood that due to factors such as data acquisition time, data acquisition equipment, and data acquisition angle, there are often deviations between the poses of the current map element data and the auxiliary map element data.

[0070] The historical labels of the auxiliary map element data are determined based on the historical pose of the auxiliary map element data. To ensure that the historical labels of the auxiliary map element data can be used to determine the current labels of the current map element data, it is necessary to perform pose optimization on the current map element data and the auxiliary map element data together to ensure the consistency of their poses. Then, based on the pose change of the auxiliary map element data, the historical labels of the auxiliary map element data are adjusted accordingly.

[0071] Specifically, the historical labels of the auxiliary map element data are adjusted based on the pose deviation between the current pose and the historical pose of the auxiliary map element data.

[0072] Among them, the pose deviation is used to quantify the pose change of the auxiliary map feature data. The pose deviation can be used as a data reference for adjusting the historical label. Based on the pose deviation, the historical label of the auxiliary map feature data can be adjusted to obtain the current label of the auxiliary map feature data.

[0073] In the above technical solution, the pose of the current map feature data and the auxiliary map feature data is optimized to obtain the current pose of the auxiliary map feature data, ensuring the consistency between the current pose of the auxiliary map feature data and the current pose of the current map feature data. Determine the pose deviation between the current pose of the auxiliary map feature data and the historical pose of the auxiliary map feature data; then, based on the pose deviation, adjust the historical label of the auxiliary map feature data to obtain the current label of the auxiliary map feature data, and use the current label of the auxiliary map feature data to determine the current label of the current map feature data, ensuring the accuracy of the current label of the current map feature data, and thus ensuring the accuracy of map update.

[0074] Figure 3 It is a flowchart of another high-precision map update method provided according to an embodiment of the present disclosure; this embodiment is an alternative solution proposed on the basis of the above embodiment. Specifically, the operation of "selecting auxiliary map feature data from historical map feature data according to the current map feature data" in the embodiment of the present disclosure is refined.

[0075] See Figure 3 , the high-precision map update method provided in this embodiment includes:

[0076] S301, determine the current map version to be updated, and determine the current map feature data according to the current map version.

[0077] S302, determine the overlapping area between the map area to which the current map feature data belongs and the map area to which the historical map feature data belongs.

[0078] It can be known that updating the high-precision map may perform a partial update on the high-precision map or a full-map update on the high-precision map. A partial update will involve splicing processing between the area to be updated and the updated area. In the case of a full-map update of the high-precision map, due to the huge area covered by the high-precision map, it is often impossible to complete all updates at one time, and mostly a method of batch-by-batch update is adopted, and different batches will also involve splicing processing between the area to be updated and the updated area.

[0079] The splicing process between the area to be updated and the updated area is often carried out based on the overlapping area. The overlapping area associates the area to be updated with the updated area, and at the same time, it also associates the current map feature data with the historical map feature data. Determining the overlapping area between the map area to which the current map feature data belongs and the map area to which the historical map feature data belongs is actually determining the regional correlation between the historical map feature data and the current map feature data.

[0080] S303. Select the auxiliary map feature data from the historical map feature data based on the overlapping area, and obtain the historical label of the auxiliary map feature data.

[0081] The regional correlation between the historical map feature data corresponding to the overlapping area and the current map feature data is the strongest. Optionally, the historical map feature data corresponding to the overlapping area is used as the auxiliary map feature data.

[0082] S304. Determine the current label of the current map feature data according to the historical label of the auxiliary map feature data.

[0083] The map area to which the current map feature data belongs includes the map area to which the auxiliary map feature data belongs. Optionally, determine the current label of the current map feature data corresponding to the overlapping area according to the historical label of the auxiliary map feature data.

[0084] S305. Update the high-precision map according to the current map feature data and the current label of the current map feature data to obtain the current version map.

[0085] In the embodiment of the present disclosure, by determining the overlapping area between the map area to which the current map feature data belongs and the map area to which the historical map feature data belongs, determining the regional correlation between the historical map feature data and the current map feature data, based on the regional correlation between the two, determining the auxiliary map feature data from the historical map feature data, and using the historical label data of the auxiliary map feature data for the current label of the current map feature data, it is beneficial to ensure the accuracy of map update.

[0086] In an optional embodiment, selecting the auxiliary map feature data from the historical map feature data according to the current map feature data includes: determining the map version to which the historical map feature data belongs; based on the current map version and the map version to which the historical map feature data belongs, selecting the auxiliary map feature data from the historical map feature data.

[0087] It is understandable that over time, the high-precision map may undergo multiple version updates. That is to say, the historical map feature data may correspond to multiple old map versions. There are differences in the degree of change of map features between different map versions. Generally speaking, the closer the historical map version is to the current map version, the smaller the change in map features, and the higher the feature correlation between the historical map feature data and the current map feature data.

[0088] Based on the current map version and the map version to which the historical map feature data belongs, select auxiliary map feature data from the historical map feature data. Optionally, select historical map feature data with a higher feature correlation as the auxiliary map feature data. Exemplarily, taking the current map version as the starting point in time, historical map feature data belonging to the previous map version can be selected forward along the time axis as the auxiliary map feature data.

[0089] In the above technical solution, based on the current map version and the map version to which the historical map feature data belongs, auxiliary map feature data is selected from the historical map feature data. The feature correlation between different versions of the map is considered, and based on the feature correlation between the two, the auxiliary map feature data is determined from the historical map feature data. Using the historical label data of the auxiliary map feature data for the current label of the current map feature data is beneficial to ensuring the accuracy of map updates.

[0090] Embodiments of the present disclosure provide a process for updating the entire high-precision map. The road coverage of the high-precision map is measured in tens of thousands of kilometers, and updating the high-precision map often involves updating a relatively large area. Updating the high-precision map, especially updating the entire high-precision map, often cannot be completed in one go, and mostly a batch-by-batch update method is adopted.

[0091] Taking the map version corresponding to the intermediate update batch as the current map version, taking the map feature data belonging to the intermediate update batch as the current map feature data, and determining the map feature data belonging to the previous update batch as the historical map feature data. Determine the overlapping area between the map area to which the historical map feature data belongs and the area to which the current map feature data belongs, and determine the historical map feature data corresponding to the overlapping area as the auxiliary map feature data, obtain the historical label of the auxiliary map feature data, and the historical pose of the auxiliary map feature data.

[0092] Perform pose optimization on the auxiliary map feature data and the current map feature data to obtain the current pose of the auxiliary map feature data. Determine the pose deviation between the current pose of the auxiliary map feature data and the historical pose of the auxiliary map feature data, and based on the pose deviation, adjust the historical label of the auxiliary map feature data to obtain the current label of the auxiliary map feature data. If all the current labels of the current map feature data cannot be determined according to the historical label of the auxiliary map feature data, supplement the annotation of the map features described by the current map feature data to improve the current label of the current map feature data.

[0093] Use the current map feature data as the update material for the high-precision map, update the map base map of the high-precision map with the current map feature data, and update the label data of the high-precision map with the current label of the current map feature data.

[0094] It should be noted that if the current map feature data corresponds to the first update batch, select the one closest to the current map version from the old map versions to determine the auxiliary map feature data.

[0095] Figure 4 It is a schematic structural diagram of a high-precision map update device provided by an embodiment of the present disclosure. The embodiments of the present disclosure are applicable to updating high-precision maps, especially for the case of full-map updating of high-precision maps. The device can be implemented by software and / or hardware, and the device can implement the high-precision map update method described in any embodiment of the present disclosure. As Figure 4 shown, the high-precision map update device 400 includes:

[0096] A current feature determination module 401, configured to determine the current map version to be updated, and determine the current map feature data according to the current map version;

[0097] An auxiliary data determination module 402, configured to select auxiliary map feature data from the historical map feature data according to the current map feature data, and obtain the historical label of the auxiliary map feature data;

[0098] A current label determination module 403, configured to determine the current label of the current map feature data according to the historical label of the auxiliary map feature data;

[0099] A high-precision map update module 404, configured to update the high-precision map according to the current map feature data and the current label of the current map feature data to obtain the current version map.

[0100] In the technical solution of the present disclosure, by selecting auxiliary map feature data related to the current map feature data from the historical map feature data and obtaining the historical tags of the auxiliary map feature data. Then, using the historical tags of the auxiliary map feature data to determine the current tags of the current map feature data realizes the reuse of historical tags, and there is no need to re-label the map features described by the current map feature data during the cartography process based on the current map feature data, improving the update efficiency of the high-precision map and reducing the update cost of the high-precision map.

[0101] Optionally, the current tag determination module 403 includes: a historical tag adjustment sub-module for adjusting the historical tags of the auxiliary map feature data according to the current map feature data to obtain the current tags of the auxiliary map feature data; a current tag determination sub-module for determining the current tags of the current map feature data according to the current tags of the auxiliary map feature data.

[0102] Optionally, the historical tag adjustment sub-module includes: a current pose determination unit for optimizing the pose of the current map feature data and the auxiliary map feature data to obtain the current pose of the auxiliary map feature data; a pose deviation determination unit for determining the pose deviation between the current pose and the historical pose of the auxiliary map feature data; a historical tag adjustment unit for adjusting the historical tags of the auxiliary map feature data based on the pose deviation to obtain the current tags of the auxiliary map feature data.

[0103] Optionally, the auxiliary data determination module 402 includes: an overlapping area determination sub-module for determining the overlapping area between the map area to which the current map feature data belongs and the map area to which the historical map feature data belongs; a first auxiliary data determination sub-module for selecting the auxiliary map feature data from the historical map feature data based on the overlapping area.

[0104] Optionally, the auxiliary data determination module 402 includes: a map version determination sub-module for determining the map version to which the historical map feature data belongs; a second auxiliary data determination sub-module for selecting the auxiliary map feature data from the historical map feature data based on the current map version and the map version to which the historical map feature data belongs.

[0105] Optionally, the high-precision map update module 404 includes: a base map update sub-module for updating the map base map of the high-precision map according to the current map feature data; a tag update sub-module for updating the tag data of the high-precision map based on the current tags of the current map feature data.

[0106] The high-precision map update device provided by the embodiments of the present disclosure can execute the high-precision map update method provided by any embodiment of the present disclosure, and has corresponding functional modules and beneficial effects for executing the high-precision map update method.

[0107] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of user information involved all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0108] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0109] Figure 5 FIG. shows a schematic block diagram of an exemplary electronic device 500 that can be used to implement the embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, for example, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, for example, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0110] As Figure 5 shown, the electronic device 500 includes a computing unit 501, which can execute various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0111] A plurality of components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0112] The computing unit 501 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 executes the various methods and processes described above, such as the high-precision map update method. For example, in some embodiments, the high-precision map update method can be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the high-precision map update method described above can be executed. Alternatively, in other embodiments, the computing unit 501 can be configured to execute the high-precision map update method in any other suitable way (e.g., by means of firmware).

[0113] Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0114] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to the processor or controller of a general-purpose computer, a special-purpose computer, or other programmable high-precision map update devices, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program codes can be executed entirely on the machine, partially on the machine, executed partially on the machine and partially on a remote machine as an independent software package, or executed entirely on a remote machine or server.

[0115] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0116] To provide for interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic, speech, or tactile input).

[0117] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0118] A computer system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0119] Artificial intelligence is a discipline that studies the use of computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and it has technologies at both the hardware and software levels. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include several major directions such as computer vision technology, speech recognition technology, natural language processing technology, machine learning / deep learning technology, big data processing technology, and knowledge graph technology.

[0120] Cloud computing refers to a technical system that accesses an elastic and scalable shared physical or virtual resource pool through a network. The resources can include servers, operating systems, networks, software, applications, and storage devices, etc., and the resources can be deployed and managed in a on-demand and self-service manner. Through cloud computing technology, it can provide efficient and powerful data processing capabilities for the application and model training of technologies such as artificial intelligence and blockchain.

[0121] It should be understood that various forms of processes shown above can be used, steps can be reordered, added, or deleted. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitations are imposed herein.

[0122] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A high-precision map update method, the method comprises: determine the current map version to be updated, and determine the current map feature data according to the current map version; select auxiliary map feature data from the historical map feature data according to the current map feature data, and obtain the historical tags of the auxiliary map feature data; determine the current tags of the current map feature data according to the historical tags of the auxiliary map feature data; update the high-precision map according to the current map feature data and the current tags of the current map feature data to obtain the current version map.

2. The method according to claim 1, wherein, determine the current tags of the current map feature data according to the historical tags of the auxiliary map feature data, including: adjust the historical tags of the auxiliary map feature data according to the current map feature data to obtain the current tags of the auxiliary map feature data; determine the current tags of the current map feature data according to the current tags of the auxiliary map feature data.

3. The method according to claim 2, wherein, adjust the historical tags of the auxiliary map feature data according to the current map feature data to obtain the current tags of the auxiliary map feature data, including: perform pose optimization on the current map feature data and the auxiliary map feature data to obtain the current pose of the auxiliary map feature data; determine the pose deviation between the current pose and the historical pose of the auxiliary map feature data; adjust the historical tags of the auxiliary map feature data based on the pose deviation to obtain the current tags of the auxiliary map feature data.

4. The method according to claim 1, wherein, select auxiliary map feature data from the historical map feature data according to the current map feature data, including: determine the overlapping area between the map area to which the current map feature data belongs and the map area to which the historical map feature data belongs; select the auxiliary map feature data from the historical map feature data based on the overlapping area.

5. The method according to claim 1, wherein, select auxiliary map feature data from the historical map feature data according to the current map feature data, including: determine the map version to which the historical map feature data belongs; select the auxiliary map feature data from the historical map feature data based on the current map version and the map version to which the historical map feature data belongs.

6. The method according to claim 1, wherein, update the high-precision map according to the current map feature data and the current tags of the current map feature data to obtain the current version map, including: update the map base map of the high-precision map according to the current map feature data; update the tag data of the high-precision map based on the current tags of the current map feature data.

7. A high-precision map update device, the device comprises: a current feature determination module, configured to determine the current map version to be updated, and determine the current map feature data according to the current map version; An auxiliary data determination module, configured to select auxiliary map feature data from historical map feature data according to the current map feature data, and obtain historical tags of the auxiliary map feature data; A current tag determination module, configured to determine current tags of the current map feature data according to the historical tags of the auxiliary map feature data; A high-precision map update module, configured to update the high-precision map according to the current map feature data and the current tags of the current map feature data to obtain the current version map.

8. The apparatus according to claim 7, wherein, the current tag determination module includes: A historical tag adjustment sub-module, configured to adjust the historical tags of the auxiliary map feature data according to the current map feature data to obtain current tags of the auxiliary map feature data; A current tag determination sub-module, configured to determine current tags of the current map feature data according to the current tags of the auxiliary map feature data.

9. The apparatus according to claim 8, wherein, the historical tag adjustment sub-module includes: A current pose determination unit, configured to perform pose optimization on the current map feature data and the auxiliary map feature data to obtain the current pose of the auxiliary map feature data; A pose deviation determination unit, configured to determine a pose deviation between the current pose and the historical pose of the auxiliary map feature data; A historical tag adjustment unit, configured to adjust the historical tags of the auxiliary map feature data based on the pose deviation to obtain current tags of the auxiliary map feature data.

10. The apparatus according to claim 7, wherein, the auxiliary data determination module includes: An overlapping area determination sub-module, configured to determine an overlapping area between the map area to which the current map feature data belongs and the map area to which the historical map feature data belongs; A first auxiliary data determination sub-module, configured to select the auxiliary map feature data from the historical map feature data based on the overlapping area.

11. The apparatus according to claim 7, wherein, the auxiliary data determination module includes: A map version determination sub-module, configured to determine the map version to which the historical map feature data belongs; A second auxiliary data determination sub-module, configured to select the auxiliary map feature data from the historical map feature data based on the current map version and the map version to which the historical map feature data belongs.

12. The apparatus according to claim 7, wherein, the high-precision map update module includes: A base map update sub-module, configured to update the map base map of the high-precision map according to the current map feature data; A tag update sub-module, configured to update the tag data of the high-precision map based on the current tags of the current map feature data.

13. An electronic device, including: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the high-precision map updating method according to any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, the computer instructions are used to cause a computer to execute the high-precision map updating method according to any one of claims 1-6.

15. A computer program product, comprising a computer program which, when executed by a processor, implements the high-precision map updating method according to any one of claims 1-6.

Images