Road network structure base map generation method, device, computer equipment and storage medium

Abstract

The present application relates to a method, device, computer equipment and storage medium for generating a road network structure base map. The method relates to the field of intelligent driving, and comprises: obtaining first data collected by a target vehicle, the first data comprising perception information and trajectory information; generating multiple sets of temporary road network data according to the first data; generating a road network structure base map according to the multiple sets of temporary road network data and a historical road network base map. The method can simplify the complexity of map construction and improve the efficiency of map construction.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a method, device, computer equipment and storage medium for generating a road network structure base map. Background Art

[0002] With the development of mapping technology in the field of autonomous driving, crowdsourcing mapping uses mass-produced vehicles to transmit vehicle-side data in real time, process the vehicle-side data in the cloud, and build maps. In the process of building maps in the cloud, in order to obtain a relatively complete map, it is necessary to use massive vehicle-side data for mapping at one time, and the processing process is highly complex. Summary of the invention

[0003] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for generating a road network structure base map in response to the above-mentioned technical problems.

[0004] In a first aspect, the present application provides a method for generating a road network structure base map, the method comprising:

[0005] Acquire first data collected by the target vehicle, the first data including perception information and trajectory information;

[0006] generating multiple sets of temporary road network data according to the first data;

[0007] A road network structure base map is generated based on the multiple sets of temporary road network data and the historical road network base map.

[0008] In one of the embodiments, the temporary road network data includes: intersection data and road data;

[0009] The generating of a road network structure base map according to the multiple sets of temporary road network data and the historical road network base map comprises:

[0010] Clustering the multiple groups of temporary road network data and the intersection data in the historical road network base map to obtain clustered intersection data;

[0011] Clustering the multiple groups of temporary road network data and the road data in the historical road network base map to obtain clustered road data;

[0012] Based on the clustered intersection data and the clustered road data, the road network structure base map is determined.

[0013] In one embodiment, the intersection data includes intersection location information, and clustering the multiple groups of temporary road network data and the intersection data in the historical road network base map to obtain clustered intersection data includes:

[0014] Clustering the multiple groups of temporary road network data and the intersection data whose intersection location information meets a first preset condition in the historical road network base map to obtain clustered intersection data;

[0015] The intersection location information satisfies a first preset condition including: a distance difference is less than or equal to a first distance threshold, and / or a height difference is less than or equal to a first height threshold.

[0016] In one embodiment, the road data includes road location information, and clustering the multiple sets of temporary road network data and the road data in the historical road network base map to obtain clustered road data includes:

[0017] Clustering the multiple groups of temporary road network data and the road data in the historical road network base map whose road location information meets a second preset condition to obtain clustered road data;

[0018] The road position information satisfies the second preset condition including: the distance difference is less than or equal to a second distance threshold, and / or the height difference is less than or equal to a second height threshold.

[0019] In one embodiment, the road data includes: a road number, an entry intersection number, and an exit intersection number;

[0020] The clustering of the multiple groups of temporary road network data and the road data in the historical road network base map to obtain clustered road data includes:

[0021] Clustering the multiple groups of temporary road network data and the road data in the historical road network base map according to the association relationship to obtain clustered road data;

[0022] Among them, the association relationship is the relationship between the clustered intersection data and the multiple intersection data before clustering, the clustered intersection data includes the intersection number, entry road number and exit road number after clustering; the multiple intersection data includes the intersection number, entry road number and exit road number before clustering.

[0023] In one embodiment, clustering the multiple groups of temporary road network data and the road data in the historical road network base map according to the association relationship to obtain clustered road data includes:

[0024] According to the association relationship, clustering the multiple groups of temporary road network data and the road data in the historical road network base map whose road location information meets the second preset condition to obtain clustered road data;

[0025] The road position information satisfies the second preset condition including: the distance difference is less than or equal to a second distance threshold, and / or the height difference is less than or equal to a second height threshold.

[0026] In one of the embodiments, the historical road network base map is determined based on multiple sets of temporary road network data generated based on second data, and the second data is perception information and trajectory information collected by the target vehicle.

[0027] In one embodiment, after generating the road network structure base map according to the multiple sets of temporary road network data and the historical road network base map, the method further includes:

[0028] Acquire third data collected by the target vehicle, wherein the third data includes perception information and trajectory information;

[0029] Segmenting the collected third data according to the road network structure in the road network structure base map to obtain segmented data;

[0030] Associating the segmented data with the road network structure in the road network structure base map for storage;

[0031] When the number of segmented data associated with the same road network structure is greater than or equal to a preset number, fusion composition is performed based on the segmented data associated with the same road network structure to construct a map.

[0032] In a second aspect, the present application also provides a road network structure base map generating device, the device comprising:

[0033] An acquisition module, used to acquire first data collected by the vehicle for multiple times, wherein the first data includes perception information and trajectory information;

[0034] A generation module is used to generate multiple sets of temporary road network data based on the first data; and to generate a road network structure base map based on the multiple sets of temporary road network data and the historical road network base map.

[0035] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0036] Acquire first data collected by the target vehicle, the first data including perception information and trajectory information;

[0037] generating multiple sets of temporary road network data according to the first data;

[0038] A road network structure base map is generated based on the multiple sets of temporary road network data and the historical road network base map.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0040] Acquire first data collected by the target vehicle, the first data including perception information and trajectory information;

[0041] generating multiple sets of temporary road network data according to the first data;

[0042] A road network structure base map is generated based on the multiple sets of temporary road network data and the historical road network base map.

[0043] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0044] Acquire first data collected by the target vehicle, the first data including perception information and trajectory information;

[0045] generating multiple sets of temporary road network data according to the first data;

[0046] A road network structure base map is generated based on the multiple sets of temporary road network data and the historical road network base map.

[0047] The above-mentioned road network structure base map generation method can obtain the first data including perception information and trajectory information collected by the target vehicle, and generate multiple sets of temporary road network data according to the first data; and generate the road network structure base map according to the multiple sets of temporary road network data and the historical road network base map. Through this scheme, on the one hand, since when generating road network data, the road network structure base map can be further generated based on the multiple sets of temporary road network data generated by the collected first data and the historical road network base map that has been generated, the road network structure base map can be generated incrementally. Such an incremental generation method does not require the acquisition of a large amount of data, which can simplify the complexity of the mapping process and improve the mapping efficiency; on the other hand, multiple sets of temporary road network data are generated based on the trajectory information and the perception information together, and the temporary road network data obtained in this way are more accurate than the temporary road network data generated only based on the trajectory information. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A diagram showing an application environment of a method for generating a road network structure base map in an embodiment;

[0050] Figure 2 A schematic diagram of a method for generating a road network structure base map in an embodiment Figure 1 ;

[0051] Figure 3A A schematic diagram of generating temporary road network data in one embodiment;

[0052] Figure 3B A schematic diagram of a method for generating a road network structure base map in an embodiment Figure 2 ;

[0053] Figure 4 A schematic diagram of a process of clustering based on a geographical location nearest neighbor clustering algorithm in one embodiment;

[0054] Figure 5 A schematic diagram of a road network construction in one embodiment;

[0055] Figure 6 Schematic diagram 3 of a process for generating a road network structure base map in one embodiment;

[0056] Figure 7 It is a structural block diagram of a road network structure base map generating device in one embodiment;

[0057] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] In the scenario of autonomous driving in urban areas where smart cars are deployed, high-precision maps are important information elements, but their application is limited due to the high cost of acquisition equipment and production and the long update cycle. With the advancement of autonomous driving technology, mass-produced vehicles are equipped with more and more sensors, and the trend of single-vehicle intelligence is obvious. Various lightweight maps have become important elements to replace high-precision maps, and crowdsourcing mapping is one of them. Crowdsourcing mapping uses information collected by mass-produced vehicles to produce lightweight maps through big data processing. It has the advantages of low cost, deployment on mass production solutions, high data freshness, rapid detection of road changes, and closed-loop map services.

[0060] However, crowdsourcing mapping also has its shortcomings, such as insufficient data quality in a single collection and lack of human correction, which can lead to problems such as insufficient composition coverage, which can be fatal to map users. Crowdsourcing mapping solutions usually require multiple collections to generate complete coverage maps using the advantages of massive data. In this process, data management, production, and updating face higher challenges.

[0061] In order to solve the above problems, an embodiment of the present application provides a method for generating a road network structure base map, which can automatically and incrementally map crowdsourced data without a map backbone base map.

[0062] The road network structure base map generation method provided in the embodiment of the present application can be applied to the vehicle side or to the cloud side, where the cloud side can refer to a server.

[0063] The road network structure base map generation method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be but not limited to various intelligent vehicle-mounted devices, and the above-mentioned terminal 102 can be a vehicle-mounted terminal of the target vehicle. The server 104 can be implemented with an independent server or a server cluster composed of multiple servers. In some embodiments, the terminal 102 can obtain the first data collected by the target vehicle, and generate multiple groups of temporary road network data according to the first data, and generate a road network structure base map according to the multiple groups of temporary road network data and the historical road network base map, and then the road network structure base map can be saved in the vehicle-mounted terminal. Optionally, the generated road network structure base map can also be sent to the server 104. In some embodiments, the server 104 can receive the first data collected by the target vehicle obtained by the terminal 102, and generate multiple sets of temporary road network data based on the first data, and generate a road network structure base map based on the multiple sets of temporary road network data and the historical road network base map, and then the road network structure base map can be sent to the terminal 102.

[0064] In an exemplary embodiment, Figure 2 As shown, a schematic diagram of the process of generating a road network structure base map is provided. Figure 1 , including but not limited to the following steps 201 to 203:

[0065] 201. Acquire first data collected by a target vehicle.

[0066] The first data includes perception information and trajectory information.

[0067] In some embodiments, the target vehicle may be any one or more vehicles.

[0068] In some embodiments, the above-mentioned trajectory information may be GPS trajectory information, inertial navigation trajectory information, etc.

[0069] In some embodiments, the above-mentioned trajectory information may be high-precision trajectory information including longitude and latitude coordinates.

[0070] The above-mentioned perception information may include visual perception information and laser perception information.

[0071] The above-mentioned perception information may include: zebra crossings, stop lines, indicator lights and other information, which can be used to distinguish intersection data from road data.

[0072] In order to improve the accuracy of the generated road network structure, in the process of generating and matching the road network, the zebra crossings, stop lines, indicator lights and other information in the perception information can be used to pre-generate intersections and road structures, so that the part of the trajectory belonging to the intersection is accurately matched to the intersection data, and the part of the trajectory belonging to the road is accurately matched to the road data, thereby greatly reducing the dependence on the accuracy of the trajectory or road network position, and the generated road network structure is more accurate.

[0073] 202. Generate multiple groups of temporary road network data according to the first data.

[0074] In an exemplary embodiment, the first data collected by the target vehicle multiple times may be acquired, and temporary road network data may be generated based on the first data collected each time, so as to obtain multiple groups of temporary road network data.

[0075] The first data collected multiple times may be data collected by the target vehicle at different time periods, and may include, for example, sensing information and trajectory information collected on the commuting route yesterday, and sensing information and trajectory information collected on the commuting route today.

[0076] In the embodiment of the present application, the road network data (such as the temporary road network data mentioned above) includes: intersection data and road data.

[0077] The above-mentioned intersection data includes but is not limited to one or more of the following: geographic coordinates, intersection type, intersection radius, intersection number, entry road number, and exit road number.

[0078] The above road data includes but is not limited to one or more of the following: geographic coordinates, road number, entry intersection number, and exit intersection number.

[0079] For example, Figure 3A As shown in FIG. 1 , a schematic diagram for generating temporary road network data is provided. Figure 3A The vehicle shown in FIG. 1 can collect data during driving to obtain the above-mentioned first data, and then pre-generate a road network based on the collected data, so as to obtain the following: Figure 3AThe temporary road network data shown in the figure includes: intersection data corresponding to temporary intersection 1, temporary intersection 2 and temporary intersection 3, and road data corresponding to temporary road 1 and temporary road 2. It should be noted that the above temporary road network data is only an exemplary description, and in actual applications, more or less intersection data and / or road network data may be included.

[0080] 203. Generate a road network structure base map based on multiple sets of temporary road network data and historical road network base maps.

[0081] In some embodiments, the historical road network base map may be a road network structure base map that has been generated. Exemplarily, the historical road network base map may be a road network structure base map generated last time, or the historical road network base map may be a road network structure base map generated multiple times in history.

[0082] The above-mentioned historical road network base map is determined based on multiple groups of temporary road network data generated based on second data, and the second data is the perception information and trajectory information collected by the target vehicle.

[0083] In some embodiments, when the above-mentioned historical road network base map is a road network structure base map generated for the first time, its generation process may include: obtaining second data collected by the vehicle multiple times, and generating temporary road network data based on the second data collected each time to obtain multiple sets of temporary road network data, and then generating the historical road network base map based on the multiple sets of temporary road network data.

[0084] Among them, the above-mentioned first data and second data are both perception information and trajectory information collected by the target vehicle, and the first data and the second data can be perception information and trajectory information collected at different times.

[0085] In some embodiments, a road network structure base map is generated based on multiple sets of temporary road network data and historical road network base maps, and the road network structure base map may be generated by clustering the multiple sets of temporary road network data and historical road network base maps.

[0086] In the embodiment of the present application, some clustering algorithms can be used to cluster multiple sets of temporary road network data and historical road network base maps to obtain a road network structure base map. Exemplarily, algorithms such as geographic location nearest neighbor clustering algorithms can be used to cluster multiple sets of temporary road network data.

[0087] The above-mentioned road network structure base map generation method can obtain the first data including perception information and trajectory information collected by the target vehicle, and generate multiple sets of temporary road network data according to the first data; and generate the road network structure base map according to the multiple sets of temporary road network data and the historical road network base map. Through this scheme, on the one hand, since when generating road network data, the road network structure base map can be further generated based on the multiple sets of temporary road network data generated by the collected first data and the historical road network base map that has been generated, the road network structure base map can be generated incrementally. Such an incremental generation method does not require the acquisition of a large amount of data, which can simplify the complexity of the mapping process and improve the mapping efficiency; on the other hand, multiple sets of temporary road network data are generated based on the trajectory information and the perception information together, and the temporary road network data obtained in this way are more accurate than the temporary road network data generated only based on the trajectory information.

[0088] It should be noted that based on the above Figure 2 After the road network structure base map generation method shown generates the road network structure base map, in the subsequent process of incrementally generating the road network structure base map, it can be used as a historical road network base map, combined with the subsequently generated temporary road network data, to continue to incrementally generate the road network structure base map.

[0089] In an exemplary embodiment, Figure 3B As shown, a schematic diagram of the process of generating a road network structure base map is provided. Figure 2 , including but not limited to the following steps 301 to 305:

[0090] 301. Acquire first data collected by a target vehicle.

[0091] 302. Generate multiple groups of temporary road network data according to the first data.

[0092] For the description of the above steps 301 and 302, reference may be made to the relevant description of the above steps 201 and 202, which will not be repeated here.

[0093] 303. Cluster multiple groups of temporary road network data and intersection data in the historical road network base map to obtain clustered intersection data.

[0094] In some embodiments, the intersection data includes intersection location information, and the clustering of the multiple sets of temporary road network data and intersection data in the historical road network base map to obtain clustered intersection data may include but is not limited to: clustering the multiple sets of temporary road network data and intersection data in the historical road network base map whose intersection location information meets a first preset condition to obtain clustered intersection data.

[0095] The intersection location information satisfies a first preset condition including: a distance difference is less than or equal to a first distance threshold, and / or a height difference is less than or equal to a first height threshold.

[0096] It should be noted that the first distance threshold and the first height threshold can be set according to actual needs and are not limited in this application. For example, the first distance threshold can be set to 1 meter, 2 meters, 3 meters, etc., and the first height threshold can be set to 1.5 meters, 2 meters, 3 meters, etc.

[0097] The above distance difference may include: the distance difference between the intersection position information in every two sets of temporary road network data in the multiple sets of temporary road network data and the historical road network base map (ie, the road network data in the historical road network base map).

[0098] The above-mentioned height difference may include: the height difference between the intersection position information in every two sets of temporary road network data in the multiple sets of temporary road network data and the historical road network base map (ie, the road network data in the historical road network base map).

[0099] In some embodiments, the above-mentioned clustering of the multiple groups of temporary road network data and the intersection data whose intersection location information in the historical road network base map meets the first preset condition to obtain clustered intersection data can be performed by clustering the multiple groups of temporary road network data according to a geographical location nearest neighbor clustering algorithm.

[0100] In some embodiments, when the road network structure base map is generated for the first time, the intersection data in the multiple groups of temporary road network data can be directly clustered to obtain clustered intersection data.

[0101] For example, Figure 4 A schematic diagram of a clustering process based on a geographical location nearest neighbor clustering algorithm is provided. The clustering process may include but is not limited to the following steps:

[0102] 401. Establish a spatial binary tree based on the Euclidean distance of the geographical locations of all intersections.

[0103] Among them, a spatial binary tree is established according to the Euclidean distance of the geographical locations of all intersections, and the intersections can be constructed into a binary tree structure according to the distance relationship between them to facilitate subsequent search operations.

[0104] When establishing the spatial binary tree based on the Euclidean distances of the geographical locations of all intersections, the Euclidean distances of the geographical locations of all intersections can be determined based on the geographical locations in the intersection data of all intersections, and the spatial binary tree can be further established.

[0105] The above-mentioned spatial binary tree is a data structure used to organize and manage spatial data. It forms a structure similar to a binary tree by dividing the space according to certain rules, so as to facilitate fast search operations on elements in the space. In the spatial binary tree, each node represents a spatial region, and the left subtree and right subtree of the node correspond to different subregions respectively. By continuously recursively dividing the space, the efficiency of spatial search can be effectively improved.

[0106] 402. Use the intersection radius as the search radius and perform a breadth-first search for all intersections within the range of the spatial binary tree.

[0107] Among them, the intersection radius is used as the search radius, and all intersections within the range of the spatial binary tree are searched in a breadth-first manner, starting from the current intersection data and expanding the search outward layer by layer until the specified search radius is reached.

[0108] 403. When it is determined that there are no other intersections within the search radius, the search ends.

[0109] 404. Aggregate the intersection data of all searched intersections into one intersection data.

[0110] Since the geographical locations collected multiple times for the same intersection usually do not differ too much, clustering based on the geographical location neighbor clustering algorithm can aggregate the data of intersections with adjacent geographical locations collected multiple times into the data of the same intersection, thereby obtaining accurate road network data.

[0111] In some embodiments, after clustering the intersection data, the above method may further save the association relationship between the clustered intersection data and the plurality of intersection data before clustering.

[0112] The clustered intersection data includes the intersection number, the incoming road number and the outgoing road number after clustering; and the multiple intersection data includes the intersection number, the incoming road number and the outgoing road number before clustering.

[0113] Exemplarily, the association relationship between the clustered intersection data and the plurality of intersection data before clustering may be saved as shown in Table 1 below.

[0114] Table 1

[0115]

[0116] 304. Cluster multiple groups of temporary road network data and road data in the historical road network base map to obtain clustered road data.

[0117] In some embodiments, the road data includes road location information, and the clustering of the multiple groups of temporary road network data and the road data in the historical road network base map to obtain clustered road data may include but is not limited to: clustering the road data whose road location information satisfies a second preset condition in the multiple groups of temporary road network data and the historical road network base map to obtain clustered road data; wherein the road location information satisfies the second preset condition including: the distance difference is less than or equal to a second distance threshold, and / or the height difference is less than or equal to a second height threshold.

[0118] It should be noted that the second distance threshold and the second height threshold can be set according to actual needs and are not limited in this application. For example, the second distance threshold can be set to 1 meter, 2 meters, 3 meters, etc., and the second height threshold can be set to 1.5 meters, 2 meters, 3 meters, etc.

[0119] The second distance threshold and the first distance threshold may be the same or different, and the second height threshold and the first height threshold may be the same or different.

[0120] The above distance difference may include: the distance difference between the road position information in every two sets of temporary road network data in the multiple sets of temporary road network data and the historical road network base map (ie, the road network data in the historical road network base map).

[0121] The above-mentioned height difference may include: the height difference between the road position information in every two sets of temporary road network data in the multiple sets of temporary road network data and the historical road network base map (ie, the road network data in the historical road network base map).

[0122] In some embodiments, the road data includes: road number, entry intersection number and exit intersection number; clustering the road data in multiple sets of temporary road network data to obtain clustered road data may include but is not limited to: clustering the road data in multiple sets of temporary road network data according to association relationships to obtain clustered road data. Among them, the road number, entry intersection number and exit intersection number in the road data can correspond to the intersection number, entry road number and exit road number of the intersection data before clustering, and then the road data in multiple sets of temporary road network data can be clustered with the above association relationships to obtain clustered road data.

[0123] For example, based on the association relationship shown in Table 1, it can be known that the entry road 1, the entry road 2 and the entry road 3 can be clustered into one road, and the exit road 1, the exit road 2 and the exit road 3 can also be clustered into one road. According to the road number, the entry intersection number and the exit intersection number in the road data, the intersection number, the entry road number and the exit road number of the intersection data before clustering can be corresponded, so it can be known which road data can be clustered.

[0124] In some embodiments, clustering road data in multiple groups of temporary road network data according to association relationships to obtain clustered road data may include but is not limited to: clustering road data in multiple groups of temporary road network data whose road location information meets a second preset condition according to association relationships to obtain clustered road data; wherein the road location information meets the second preset condition including: the distance difference is less than or equal to a second distance threshold, and / or the height difference is less than or equal to a second height threshold.

[0125] In the above embodiment, the clustering algorithm based on geographical proximity and the above clustering algorithm based on association relationship may be combined to perform clustering, so as to obtain a more accurate clustering result.

[0126] In some embodiments, when the road network structure base map is generated for the first time, the road data in the multiple groups of temporary road network data can be directly clustered to obtain clustered road data.

[0127] It should be noted that if there is a historical road network base map during the aggregation process, the intersection number and road number in the road base map can be used after aggregation, and the road number can be added to the entrance road number or exit road number of the intersection.

[0128] For example, Figure 5 As shown, Figure 5 Construct a schematic diagram for a road network, from Figure 5 It can be seen that the road base map before construction includes data on intersection 1, intersection 2, intersection 3, intersection 4 and intersection 5, as well as data on road 1, road 2, road 3 and road 4. After the road network is constructed using the data of temporary road 1, temporary road 2, temporary intersection 1 and temporary intersection 2 in the historical road network base map and temporary road network data, the data of intersection 5 in the historical road network base map is aggregated with the data of temporary intersection 2. After aggregation, the number of intersection 5 can still be used. The numbers of other newly added intersections and roads are also set according to the numbering rules in the historical road network base map. It can be seen that Figure 5 After the road network is constructed, the newly added content includes: data of new road 5, new road 6, new intersection 6 and new intersection 7.

[0129] 305. Determine a road network structure base map based on the clustered intersection data and the clustered road data.

[0130] Among them, the integrated clustered intersection data and clustered road data can be used to obtain the road network structure base map.

[0131] The road network structure base map generation method provided in the above embodiment can determine the clustered intersection data and clustered road data by clustering during the process of incrementally generating the road network structure base map. Finally, the clustered intersection data and clustered road data obtained by integrating them can obtain the road network structure base map. Such an incremental generation method does not require the acquisition of a large amount of data, which can simplify the complexity of the mapping process and improve the mapping efficiency.

[0132] In an exemplary embodiment, Figure 6 As shown, a flowchart diagram 3 of a method for generating a road network structure base map is provided, including but not limited to the following steps 601 to 607:

[0133] 601. Acquire first data collected by a target vehicle.

[0134] 602. Generate multiple groups of temporary road network data according to the first data.

[0135] 603. Generate a road network structure base map based on multiple sets of temporary road network data and historical road network base maps.

[0136] For the description of the above steps 601 to 603 , reference may be made to the relevant description of steps 201 to 203 , which will not be repeated here.

[0137] 604. Obtain third data collected by the target vehicle.

[0138] 605. Segment the collected third data according to the road network structure in the road network structure base map to obtain segmented data.

[0139] The third data may also include perception information and trajectory information, and the trajectory information may be high-precision trajectory information including longitude and latitude coordinates.

[0140] The third data may be the same as or different from the first data.

[0141] In some embodiments, the third data may include the first data, and the third data may further include data other than the first data.

[0142] In some embodiments, the third data may include perception information and trajectory information recorded before executing step 604.

[0143] The second data collected is segmented according to the road network structure in the road network structure base map, which may be segmented according to the road network structure in the road network structure base map. Figure 5 The data of intersection 1, intersection 2, and road 1 between intersection 1 and intersection 2 are divided into one segment data.

[0144] In some embodiments, the above-mentioned segmentation of the collected second data according to the road network structure in the road network structure base map may include but is not limited to: obtaining the collected data recorded by the vehicle side, that is, the above-mentioned collected third data; obtaining perception information and high-precision trajectory information containing longitude and latitude coordinates corresponding to the perception information from the collected data, and then segmenting these perception information and high-precision trajectory information according to the road network structure in the road network structure base map.

[0145] 606. Associate the segmented data with the road network structure in the road network structure base map for storage.

[0146] The segmented data may be associated with a road network structure and uploaded to a storage medium for storage.

[0147] In some embodiments, multiple segment data within the same road or intersection are associated with the same road number or intersection number.

[0148] 607. When the number of segmented data associated with the same road network structure is greater than or equal to a preset number, fusion composition is performed based on the segmented data associated with the same road network structure to construct a map.

[0149] Before performing the above data fusion to construct a map, it can be determined whether the current data volume is sufficient to ensure the accuracy after fusion.

[0150] Among them, the above preset number can be set according to the actual demand for accuracy and is not limited in the application embodiment.

[0151] In some embodiments, for segmented data associated with the same road number or intersection number, when the amount of segmented data reaches a certain level, all segmented data under the same road number or intersection number are downloaded and these segmented data are fused and mapped.

[0152] In some embodiments, the above-mentioned segmented data associated with the same road network structure are fused and composed to construct a map, which may include but is not limited to:

[0153] 1. In the fusion composition stage, all perception information is converted into a unified coordinate system, and the position / angle deviation between the segmented data is calculated, that is, vector loop calculation is performed.

[0154] In this stage, all sensory information from different sources is converted into a unified coordinate system. At the same time, the deviation between the segmented data in position and angle is calculated to perform vector loop calculation, which helps to determine the difference between different segmented data.

[0155] 2. Align the segmented data, and use the iterative optimization algorithm to calculate the aligned position / posture according to the original position and posture, as well as the calculated position / angle deviation.

[0156] In the present application, for each segmented data, the aligned position and posture can be calculated using an iterative optimization algorithm based on its original position and posture and the previously calculated position or angle deviation, so that each segmented data can be aligned more accurately.

[0157] 3. The perception data in the segmented data is converted to a unified coordinate system according to the aligned position / posture, and the weighted average value is calculated for the same perception information with a position distance difference less than a certain threshold, so as to obtain the vector result of the perception information;

[0158] In this application, the perception data in all segmented data can be converted into a unified coordinate system according to the aligned position and posture. For the same perception information with a position distance difference less than a certain threshold, the vector result of the perception information is obtained by calculating the weighted average. In this way, multiple similar perception information can be integrated to improve the accuracy of the results.

[0159] 4. Upload the vector result of the fused perception information as the vector result of the lightweight map to the storage medium.

[0160] In the present application, the vector result of the fused perception information can be uploaded to a storage medium as a vector result of a lightweight map for subsequent use or further processing.

[0161] In the above embodiment, after obtaining the road network structure base map, the perception information and trajectory information can be further fused on the existing road network structure base map by segmented fusion to add vector information to the existing road network structure base map, thereby obtaining a more detailed map.

[0162] Traditional methods of generating road network structures usually use trajectory information in collected data to match road networks and trajectory information based on geographic spatial locations. Such methods are more dependent on the accuracy of trajectory information. When the accuracy of trajectory information is poor or the road network information used is poor, more mismatches will occur, which may cause the trajectory data to match the wrong road network structure. In this application, in the process of generating a road network structure base map, information such as zebra crossings, stop lines, and indicator lights in the perception information can be used to pre-generate intersections and road structures, so that the part of the trajectory that belongs to the intersection is accurately matched to the intersection data, and the part of the trajectory that belongs to the road is accurately matched to the road data, thereby greatly reducing the dependence on the accuracy of the trajectory or road network location, and the generated road network structure is more accurate.

[0163] Traditional road network structure generation methods cannot achieve incremental generation. In this application, incremental generation of road network data can be achieved when generating road network structures. For crowdsourcing mapping services that require real-time performance, incremental generation means that there is no need to process the data in full again, greatly improving the efficiency of crowdsourcing mapping.

[0164] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0165] Based on the same inventive concept, the embodiment of the present application also provides a road network structure base map generation device for implementing the road network structure base map generation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more mapping device embodiments provided below can refer to the limitations of the road network structure base map generation method above, and will not be repeated here.

[0166] In an exemplary embodiment, Figure 7 As shown, a road network structure base map generating device is provided, comprising:

[0167] An acquisition module 701 is used to acquire first data collected by the vehicle for multiple times, where the first data includes perception information and trajectory information;

[0168] The generation module 702 is used to generate multiple sets of temporary road network data according to the first data; and generate a road network structure base map according to the multiple sets of temporary road network data and the historical road network base map.

[0169] In one of the embodiments, the temporary road network data includes: intersection data and road data;

[0170] The generating module 702 is specifically used to: cluster the multiple groups of temporary road network data and the intersection data in the historical road network base map to obtain clustered intersection data;

[0171] Clustering the multiple groups of temporary road network data and the road data in the historical road network base map to obtain clustered road data;

[0172] Based on the clustered intersection data and the clustered road data, the road network structure base map is determined.

[0173] In one embodiment, the intersection data includes intersection location information, and the generating module 702 is specifically used for:

[0174] Clustering the multiple groups of temporary road network data and the intersection data whose intersection location information meets a first preset condition in the historical road network base map to obtain clustered intersection data;

[0175] The intersection location information satisfies a first preset condition including: a distance difference is less than or equal to a first distance threshold, and / or a height difference is less than or equal to a first height threshold.

[0176] In one embodiment, the road data includes road location information, and the generating module 702 is specifically used to: cluster the road data whose road location information in the multiple groups of temporary road network data and the historical road network base map meets the second preset condition to obtain clustered road data;

[0177] The road position information satisfies the second preset condition including: the distance difference is less than or equal to a second distance threshold, and / or the height difference is less than or equal to a second height threshold.

[0178] In one embodiment, the road data includes: a road number, an entry intersection number, and an exit intersection number;

[0179] The generating module 702 is specifically used to: cluster the multiple groups of temporary road network data and the road data in the historical road network base map according to the association relationship to obtain clustered road data;

[0180] Among them, the association relationship is the relationship between the clustered intersection data and the multiple intersection data before clustering, the clustered intersection data includes the intersection number, entry road number and exit road number after clustering; the multiple intersection data includes the intersection number, entry road number and exit road number before clustering.

[0181] In one embodiment, the generating module 702 is specifically used to: cluster the multiple groups of temporary road network data and the road data whose road location information in the historical road network base map meets the second preset condition according to the association relationship to obtain clustered road data;

[0182] The road position information satisfies the second preset condition including: the distance difference is less than or equal to a second distance threshold, and / or the height difference is less than or equal to a second height threshold.

[0183] In one of the embodiments, the historical road network base map is determined based on multiple sets of temporary road network data generated based on second data, and the second data is perception information and trajectory information collected by the target vehicle.

[0184] In one embodiment, after the generating module 702 generates the road network structure base map according to the multiple sets of temporary road network data and the historical road network base map, the acquiring module 701 is further used to: acquire third data collected by the target vehicle, the third data including perception information and trajectory information;

[0185] The fusion composition module 703 is used to segment the collected third data according to the road network structure in the road network structure base map to obtain segmented data; associate the segmented data with the road network structure in the road network structure base map for storage; when the number of segmented data associated with the same road network structure is greater than or equal to a preset number, perform fusion composition based on the segmented data associated with the same road network structure to construct a map.

[0186] Each module in the above-mentioned road network structure base map generation method can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0187] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a vehicle-mounted terminal. The internal structure diagram thereof may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for storage. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external device through a network connection. When the computer program is executed by the processor, a method for generating a road network structure base map is implemented.

[0188] Those skilled in the art will understand that Figure 8The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0189] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0190] Acquire first data collected by the target vehicle, the first data including perception information and trajectory information;

[0191] generating multiple sets of temporary road network data according to the first data;

[0192] A road network structure base map is generated based on the multiple sets of temporary road network data and the historical road network base map.

[0193] In one embodiment, the temporary road network data includes: intersection data and road data;

[0194] When the processor executes the computer program, it also performs the following steps:

[0195] The generating of a road network structure base map according to the multiple sets of temporary road network data and the historical road network base map comprises:

[0196] Clustering the multiple groups of temporary road network data and the intersection data in the historical road network base map to obtain clustered intersection data;

[0197] Clustering the multiple groups of temporary road network data and the road data in the historical road network base map to obtain clustered road data;

[0198] Based on the clustered intersection data and the clustered road data, the road network structure base map is determined.

[0199] In one embodiment, the intersection data includes intersection location information, and the processor further implements the following steps when executing the computer program:

[0200] Clustering the multiple groups of temporary road network data and the intersection data whose intersection location information meets a first preset condition in the historical road network base map to obtain clustered intersection data;

[0201] The intersection location information satisfies a first preset condition including: a distance difference is less than or equal to a first distance threshold, and / or a height difference is less than or equal to a first height threshold.

[0202] In one embodiment, the road data includes road location information, and the processor further implements the following steps when executing the computer program:

[0203] The clustering of the road data in the plurality of groups of temporary road network data to obtain clustered road data includes:

[0204] Clustering the multiple groups of temporary road network data and the road data in the historical road network base map whose road location information meets a second preset condition to obtain clustered road data;

[0205] The road position information satisfies the second preset condition including: the distance difference is less than or equal to a second distance threshold, and / or the height difference is less than or equal to a second height threshold.

[0206] In one embodiment, the road data includes: a road number, an entry intersection number, and an exit intersection number;

[0207] When the processor executes the computer program, it also performs the following steps:

[0208] Clustering the multiple groups of temporary road network data and the road data in the historical road network base map according to the association relationship to obtain clustered road data;

[0209] Among them, the association relationship is the relationship between the clustered intersection data and the multiple intersection data before clustering, the clustered intersection data includes the intersection number, entry road number and exit road number after clustering; the multiple intersection data includes the intersection number, entry road number and exit road number before clustering.

[0210] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0211] According to the association relationship, clustering the multiple groups of temporary road network data and the road data in the historical road network base map whose road location information meets the second preset condition to obtain clustered road data;

[0212] The road position information satisfies the second preset condition including: the distance difference is less than or equal to a second distance threshold, and / or the height difference is less than or equal to a second height threshold.

[0213] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0214] The historical road network base map is determined based on multiple groups of temporary road network data generated based on second data, and the second data is the perception information and trajectory information collected by the target vehicle.

[0215] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0216] After generating a road network structure base map based on the multiple sets of temporary road network data and the historical road network base map,

[0217] Acquire third data collected by the target vehicle, wherein the third data includes perception information and trajectory information;

[0218] Segmenting the collected third data according to the road network structure in the road network structure base map to obtain segmented data;

[0219] Associating the segmented data with the road network structure in the road network structure base map for storage;

[0220] When the number of segmented data associated with the same road network structure is greater than or equal to a preset number, fusion composition is performed based on the segmented data associated with the same road network structure to construct a map.

[0221] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, each process of the method for generating a road network structure base map shown in the above method embodiment is implemented.

[0222] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the various processes of the road network structure base map generation method shown in the above method embodiment.

[0223] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0224] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0225] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0226] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for generating a road network structure base map, characterized in that: The method comprises: Acquire first data collected by the target vehicle, the first data including perception information and trajectory information; Generate multiple sets of temporary road network data according to the first data; the temporary road network data includes: intersection data and road data; Clustering the multiple groups of temporary road network data and the intersection data in the historical road network base map to obtain clustered intersection data; Clustering the multiple groups of temporary road network data and the road data in the historical road network base map according to the association relationship to obtain clustered road data; determining the road network structure base map based on the clustered intersection data and the clustered road data; The association relationship is the relationship between the clustered intersection data and a plurality of intersection data before clustering.

2. The method according to claim 1, characterized in that: The intersection data includes intersection location information, and the clustering of the plurality of groups of temporary road network data and the intersection data in the historical road network base map to obtain clustered intersection data includes: Clustering the multiple groups of temporary road network data and the intersection data whose intersection location information meets a first preset condition in the historical road network base map to obtain clustered intersection data; The intersection location information satisfies a first preset condition including: a distance difference is less than or equal to a first distance threshold, and / or a height difference is less than or equal to a first height threshold.

3. The method according to claim 1, characterized in that The road data also includes road location information. The clustering of the multiple groups of temporary road network data and the road data in the historical road network base map to obtain clustered road data includes: Clustering the multiple groups of temporary road network data and the road data in the historical road network base map whose road location information meets a second preset condition to obtain clustered road data; The road position information satisfies the second preset condition including: the distance difference is less than or equal to a second distance threshold, and / or the height difference is less than or equal to a second height threshold.

4. The method according to claim 1, characterized in that The road data includes: road number, entry intersection number and exit intersection number; The clustered intersection data includes the intersection number, the incoming road number and the outgoing road number after clustering; and the multiple intersection data includes the intersection number, the incoming road number and the outgoing road number before clustering.

5. The method according to claim 4, characterized in that The step of clustering the plurality of groups of temporary road network data and the road data in the historical road network base map according to the association relationship to obtain clustered road data includes: According to the association relationship, clustering the multiple groups of temporary road network data and the road data in the historical road network base map whose road location information meets the second preset condition to obtain clustered road data; The road position information satisfies the second preset condition including: the distance difference is less than or equal to a second distance threshold, and / or the height difference is less than or equal to a second height threshold.

6. The method according to any one of claims 1 to 5, characterized in that: The historical road network base map is determined based on multiple groups of temporary road network data generated based on second data, and the second data is the perception information and trajectory information collected by the target vehicle.

7. The method according to any one of claims 1 to 5, characterized in that: After determining the road network structure base map based on the clustered intersection data and the clustered road data, the method further includes: Acquire third data collected by the target vehicle, wherein the third data includes perception information and trajectory information; Segmenting the collected third data according to the road network structure in the road network structure base map to obtain segmented data; Associating the segmented data with the road network structure in the road network structure base map for storage; When the number of segmented data associated with the same road network structure is greater than or equal to a preset number, fusion composition is performed based on the segmented data associated with the same road network structure to construct a map.

8. A road network structure base map generating device, characterized in that: The device comprises: An acquisition module, used to acquire first data collected by the target vehicle, wherein the first data includes perception information and trajectory information; A generating module, configured to generate a plurality of sets of temporary road network data according to the first data; the temporary road network data includes: intersection data and road data; clustering the plurality of sets of temporary road network data and the intersection data in the historical road network base map to obtain clustered intersection data; clustering the plurality of sets of temporary road network data and the road data in the historical road network base map according to the association relationship to obtain clustered road data; determining the road network structure base map based on the clustered intersection data and the clustered road data; The association relationship is the relationship between the clustered intersection data and a plurality of intersection data before clustering.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

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

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images