Map information updating method and device, equipment and computer readable storage medium

Abstract

The application discloses a map information updating method and device, equipment and a computer readable storage medium. The method comprises the following steps: acquiring a lane element set uploaded by each vehicle; clustering lane elements collected by different vehicles according to lane positions to obtain an element cluster associated with each lane position; determining a distribution relationship between a plurality of element clusters, and sequentially establishing a plurality of element clusters according to the distribution relationship to connect the element clusters, thereby obtaining a lane topology network; identifying an upper-level shunt lane and a lower-level shunt lane having an overlapping structure relationship in the lane topology network, and grouping lane elements of different vehicles according to the upper-level shunt lane and the lower-level shunt lane, thereby obtaining an element grouping result; and updating lane information of the upper-level shunt lane and the lower-level shunt lane in the map according to the element grouping result. In this way, upper and lower lanes of an overlapping structure can be identified, and information of the upper and lower lanes of the overlapping structure in the map can be updated, thereby improving the accuracy of map information.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a map information updating method and device, equipment and computer readable storage medium. BACKGROUND

[0002] Vehicle navigation technology mainly relies on map information to achieve, and lane information in the map plays an important role in navigation function. In order to improve the accuracy of map information, the map information can be updated continuously. According to the related technology, the lane data collected by different vehicles is aligned, and the lane information in the map is updated according to the alignment result of the lane data.

[0003] However, when the related technology aligns the lane data collected by different vehicles, it cannot be applied to the upper and lower multi-layer lanes of the overlapping structure, which easily causes confusion of the lane data of the upper and lower multi-layer lanes, resulting in that the information of the multi-layer lanes of the overlapping structure cannot be updated, and the accuracy of the map information is reduced. SUMMARY

[0004] The embodiments of the present application provide a map information updating method, device, equipment and computer readable storage medium, which can identify the upper and lower lanes of the overlapping structure, and update and construct the information of the upper and lower lanes of the overlapping structure in the map through corresponding lane elements, thereby improving the accuracy of the map information.

[0005] The embodiments of the present application provide a map information updating method, comprising:

[0006] Obtaining a lane element set uploaded by each vehicle, wherein the lane element set comprises lane elements collected by the vehicle at different lane positions;

[0007] Clustering the lane elements collected by different vehicles according to lane positions to obtain element clustering clusters associated with each lane position;

[0008] Determining a distribution relationship between a plurality of element clustering clusters, and sequentially establishing connection between the plurality of element clustering clusters according to the distribution relationship to obtain a lane topology network;

[0009] Identifying an upper split lane and a lower split lane having an overlapping structure relationship in the lane topology network, and grouping lane elements of different vehicles according to the upper split lane and the lower split lane to obtain an element grouping result;

[0010] According to the element grouping result, updating lane information of the upper split lane and the lower split lane in the map respectively.

[0011] Correspondingly, the embodiments of the present application provide a map information updating device, comprising:

[0012] an acquisition unit, configured to acquire a lane element set uploaded by each vehicle, the lane element set containing lane elements collected by the vehicle at different lane positions;

[0013] a clustering unit, configured to cluster lane elements collected by different vehicles according to lane positions, to obtain an element cluster associated with each lane position;

[0014] an establishment unit, configured to determine a distribution relationship between a plurality of element clusters, and sequentially establish the plurality of element clusters according to the distribution relationship to connect, to obtain a lane topology network;

[0015] a grouping unit, configured to identify an upper split lane and a lower split lane having an overlapping structure relationship in the lane topology network, and perform lane grouping on lane element sets of different vehicles according to the upper split lane and the lower split lane, to obtain an element grouping result;

[0016] an updating unit, configured to update lane information of the upper split lane and the lower split lane in the map respectively according to the element grouping result.

[0017] In some embodiments, the clustering unit is further configured to:

[0018] determine a lane position associated with each lane element in each lane element set;

[0019] cluster lane elements belonging to the same lane position to obtain an element cluster associated with each lane position.

[0020] In some embodiments, the establishment unit is further configured to:

[0021] determine a lane position associated with each element cluster;

[0022] determine a distribution relationship between a plurality of element clusters according to the lane position associated with each element cluster.

[0023] In some embodiments, the establishment unit is further configured to:

[0024] construct a cluster sequence of the plurality of element clusters in a lane according to the distribution relationship;

[0025] sequentially perform lane segment region division on each element cluster in the cluster sequence, each lane segment region containing at least one element cluster;

[0026] splice each lane segment region according to an arrangement order of the cluster sequence, to obtain a lane topology network.

[0027] In some embodiments, the establishment unit is further configured to:

[0028] determine a path interval distance between any two adjacent element clusters in the sequence of element clusters;

[0029] determine a path length corresponding to the plurality of element clusters based on the path interval distance between the element clusters;

[0030] perform lane section region division on the plurality of element clusters in the path length according to a preset lane section distance.

[0031] In some embodiments, the establishing unit is further configured to:

[0032] select an element cluster to be connected from each lane section region;

[0033] sequentially connect the element cluster to be connected in each lane section region according to the arrangement order of the sequence of element clusters to obtain a path structure network;

[0034] perform splicing on each lane section region according to the path structure network to obtain a lane topology network.

[0035] In some embodiments, the grouping unit is further configured to:

[0036] determine a first distribution ratio of a lane element in the lane element set of each vehicle in the upper layer of diverging lanes and a second distribution ratio of the lane element in the lane element set in the lower layer of diverging lanes;

[0037] if the first distribution ratio is greater than the second distribution ratio, group the corresponding lane element set to the upper layer of diverging lanes;

[0038] if the first distribution ratio is less than the second distribution ratio, group the corresponding lane element set to the lower layer of diverging lanes.

[0039] In addition, an embodiment of the present application further provides a computer device, including a processor and a memory, the memory stores a computer program, and the processor is used to run the computer program in the memory to realize the steps in the map information updating method provided by the embodiment of the present application.

[0040] In addition, an embodiment of the present application further provides a computer readable storage medium, which stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps in any one of the map information updating methods provided by the embodiment of the present application.

[0041] Further, the embodiment of the present application further provides a computer program product, which comprises computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in any one of the map information updating methods provided by the embodiment of the present application.

[0042] The embodiment of the present application can obtain the lane element set uploaded by each vehicle, the lane element set comprising lane elements collected by the vehicle at different lane positions; cluster the lane elements collected by different vehicles according to lane positions to obtain element cluster clusters associated with each lane position; determine the distribution relationship between the plurality of element cluster clusters, and sequentially connect the plurality of element cluster clusters according to the distribution relationship to obtain a lane topology network; identify the upper and lower split lanes with overlapping structural relationships in the lane topology network, and group the lane element sets of different vehicles according to the upper and lower split lanes to obtain an element grouping result; and update the lane information of the upper and lower split lanes in the map according to the element grouping result. Thus, the present scheme can first obtain the lane element set collected by each vehicle, and cluster the lane elements collected by different vehicles according to lane positions to aggregate the lane elements collected by different vehicles at similar positions according to lane positions, so as to improve the credibility of lane element data. Then, the distribution relationship between the plurality of lane element cluster clusters is determined, and the plurality of lane element cluster clusters are connected, so as to determine the connectivity of the lane by the connection of the cluster clusters to obtain a lane topology network. Finally, the upper and lower split lanes with overlapping structures in the lane topology network are identified, and the lane element set collected by each vehicle is grouped according to lane attribution, so as to update the information of the lane in the map according to the lane element set collected by the vehicle. In this way, the upper and lower lanes with overlapping structures can be identified, and the information of the upper and lower lanes with overlapping structures can be updated in the map by the corresponding lane elements, so as to improve the accuracy of the map information. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0044] Figure 1 is a scene schematic diagram of the map information updating system provided by the embodiment of the present application;

[0045] Figure 2A step flow diagram of a map information updating method provided by an embodiment of the present application is shown in FIG. 1.

[0046] Figure 3 Another step flow diagram of a map information updating method provided by an embodiment of the present application is shown in FIG. 2.

[0047] Figure 4 A clustering scenario of lane elements collected by multiple vehicles provided by an embodiment of the present application is shown in FIG. 3.

[0048] Figure 5 A scenario of dividing a lane section area provided by an embodiment of the present application is shown in FIG. 4.

[0049] Figure 6 A connection scenario of element clustering clusters provided by an embodiment of the present application is shown in FIG. 5.

[0050] Figure 7 A structure diagram of a path structure network provided by an embodiment of the present application is shown in FIG. 6.

[0051] Figure 8 A structure diagram of a map information updating device provided by an embodiment of the present application is shown in FIG. 7.

[0052] Figure 9 A structure diagram of a computer device provided by an embodiment of the present application is shown in FIG. 8. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0054] The present application provides a map information updating method, device, equipment and computer readable storage medium. The embodiments of the present application will be described from the perspective of a map information updating device. The map information updating device can be integrated in a computer device, which can be a terminal device, specifically a terminal device carried on a transportation tool, i.e. a vehicle-mounted terminal. In addition, the terminal device can also be other types of devices, for example, the terminal can be a television, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a smart wearable device, etc. In addition, but not limited to this.

[0055] For example, referring to Figure 1 A scenario diagram of a map information updating system provided by an embodiment of the present application is shown in FIG. 9. The system is not limited to be applied in the map information updating scenarios of expressways, urban lanes, etc. The scenario includes a terminal or a server.

[0056] Specifically, the terminal can be a vehicle terminal, configured to acquire, from a server, a lane element set uploaded by each vehicle, the lane element set comprising lane elements collected by the vehicle at different lane positions; cluster the lane elements collected by different vehicles according to lane positions to obtain an element cluster associated with each lane position; determine a distribution relationship between a plurality of element clusters, and sequentially establish connections between the plurality of element clusters according to the distribution relationship to obtain a lane topology network; identify an upper split lane and a lower split lane having an overlapping structural relationship in the lane topology network, and perform lane grouping on the lane element sets of different vehicles according to the upper split lane and the lower split lane to obtain an element grouping result; and update lane information of the upper split lane and the lower split lane in the map respectively according to the element grouping result.

[0057] It should be noted that when the map information updating system comprises a server, a communication connection can be established between the vehicle terminal and the server. The server can acquire a lane element set uploaded by each vehicle, the lane element set comprising lane elements collected by the vehicle at different lane positions; cluster the lane elements collected by different vehicles according to lane positions to obtain an element cluster associated with each lane position; determine a distribution relationship between a plurality of element clusters, and sequentially establish connections between the plurality of element clusters according to the distribution relationship to obtain a lane topology network; identify an upper split lane and a lower split lane having an overlapping structural relationship in the lane topology network, and perform lane grouping on the lane element sets of different vehicles according to the upper split lane and the lower split lane to obtain an element grouping result; and update lane information of the upper split lane and the lower split lane in the map respectively according to the element grouping result. This is so that the updated map can be fed back to any vehicle driving on the lane subsequently.

[0058] The following will be described in detail. It should be noted that the order of description of the following embodiments is not intended to limit the preferred order of the embodiments.

[0059] In the embodiments of the present application, the description is made from the perspective of a map information updating device, which can be specifically integrated in a computer device such as a terminal device or a server. Referring to Figure 2 , Figure 2 The steps of a map information updating method provided in the embodiments of the present application are shown in a flowchart. Taking a server as an example, when a processor on the server executes program instructions corresponding to the map information updating method, the specific process of the map information updating method is as follows:

[0060] 101、acquire a lane element set uploaded by each vehicle.

[0061] In the embodiments of the present application, in order to construct and update the map information without a base map, lane data collected by any vehicle can be acquired, so as to construct and update the map information by combining the lane data collected by the vehicle with the position information, thereby obtaining the map.

[0062] The lane element set contains lane elements collected by the corresponding vehicle at different lane positions, that is, each lane element set represents all lane elements collected by a vehicle during driving. It should be noted that the lane element can be a lane line, a lane direction arrow, a lane broken line, a number, a character, or the like. It can be understood that each lane element can be associated with corresponding lane position information.

[0063] For example, taking the driving of a vehicle on a highway as an example, the vehicle has a camera assembly, which can collect lane surface information in the driving direction, such as lane lines, lane direction arrows, lane broken lines, numbers, characters, and the like. As the vehicle continuously drives, the vehicle sequentially collects various lane element markers on the lane surface during driving, thereby obtaining a lane element set.

[0064] Specifically, in order to accurately construct or update lane information on a road in the map, lane element sets collected by different vehicles on the same road can be acquired, so as to subsequently align and aggregate lane elements in the plurality of lane element sets, and to construct and update the map information according to the alignment and aggregation result.

[0065] 102. Cluster lane elements collected by different vehicles according to lane positions to obtain element cluster clusters associated with each lane position.

[0066] In the embodiments of the present application, in order to construct the map information according to lane data collected by a plurality of vehicles, after obtaining a plurality of lane element sets uploaded by vehicles, lane elements belonging to the same lane position can be clustered according to the dimension of the lane position, that is, lane elements collected by different vehicles at the same lane position are clustered, so as to subsequently construct the map information according to the clustering result after clustering.

[0067] The element cluster cluster can contain lane elements collected by a plurality of vehicles at the same lane position. For example, it is assumed that vehicle A collects lane elements of an arrow and a lane broken line at a target lane position area, and vehicle B also collects lane elements of an arrow and a lane broken line at the target lane position area. The lane elements collected by vehicle A and vehicle B at the target lane position area are aggregated to obtain an element cluster cluster of the target lane position area.

[0068] In some embodiments, the step 102 of "clustering lane elements collected by different vehicles according to lane positions to obtain element cluster clusters associated with each lane position" can include: determining the lane position associated with each lane element in each lane element set; clustering lane elements belonging to the same lane position to obtain element cluster clusters associated with each lane position.

[0069] Each lane element has a position characteristic. When a vehicle collects lane surface information, each collected lane element is associated with lane position information in real time. The lane position information can be obtained through a global positioning system, which is not limited here.

[0070] Specifically, after obtaining a plurality of lane element sets collected by vehicles, the lane position associated with each lane element in each lane element set can be determined, and then the lane elements collected by vehicles in the same lane position can be clustered according to the lane position dimension to obtain lane element cluster clusters.

[0071] It should be noted that when clustering lane elements according to lane positions, the lane elements collected by different vehicles can be clustered according to precise lane positions. For example, assume that vehicle A collects arrow and lane dash elements in a target lane position area, and vehicle B also collects arrow, number and lane dash elements in the target lane position area. The lane elements collected by vehicles A and B in the target lane position area are aggregated to obtain element cluster clusters of the target lane position area.

[0072] In addition, when clustering lane elements according to lane positions, the lane elements collected by different vehicles can also be clustered according to the range of lane position information. For example, assume that vehicle A collects arrow and lane dash elements in a target lane position area, and vehicle B also collects arrow, number and lane dash elements in the target lane position area. The lane elements collected by vehicles A and B in the target lane position area are aggregated to obtain element cluster clusters of the target lane position area.

[0073] In this way, the lane elements collected by different vehicles can be clustered according to the lane position dimension, so as to aggregate the lane elements collected by different vehicles in the same lane position, align the lane data collected by multiple vehicles, and make the aggregated lane data more reliable relative to the lane data collected by a single vehicle, so as to be used for subsequent map lane information construction / update.

[0074] 103、determining the distribution relationship between a plurality of element cluster clusters, and sequentially establishing connections between the plurality of element cluster clusters according to the distribution relationship to obtain a lane topology network.

[0075] After the lane elements collected by multiple vehicles are clustered, the distribution relationship between the multiple element cluster clusters obtained by clustering can be determined to understand the position arrangement of the multiple element cluster clusters on the lane, and then the connection between adjacent element cluster clusters is sequentially established according to the arrangement, and the connection between the element cluster clusters is collected to obtain the lane topology network.

[0076] In some embodiments, the distribution relationship between the element cluster clusters can be determined in combination with the lane position information. Specifically, the "determining the distribution relationship between the multiple element cluster clusters" in step 103 can include:

[0077] (103.a.1) determining the lane position associated with each element cluster cluster;

[0078] (103.a.2) determining the distribution relationship between the multiple element cluster clusters according to the lane position associated with each element cluster cluster.

[0079] Specifically, since the lane elements collected by different vehicles are clustered according to the lane position, the element cluster clusters obtained by clustering are also associated with the lane position. Then, the lane position associated with each element cluster cluster is determined to determine the distribution of the multiple element cluster clusters on the road plane according to the lane position, to obtain the distribution relationship between the multiple element cluster clusters, so as to subsequently construct the driving route of the vehicle according to the distribution relationship between the multiple element cluster clusters. The driving route can reflect the road route.

[0080] In the embodiments of the present application, the lane topology network includes multiple driving paths or driving route groups, each driving path or driving route is connected by multiple element cluster clusters, reflects the driving trajectory of one or more vehicles, and each driving path or driving route can reflect the road route to a certain extent, and the lane topology network can reflect the lane connectivity relationship.

[0081] In some embodiments, after obtaining the distribution relationship between the multiple element cluster clusters, the element cluster clusters can be connected to reflect the driving trajectories of multiple vehicles, and the lane topology network is constructed according to the connection. Specifically, the "sequentially establishing the connection between the multiple element cluster clusters according to the distribution relationship to obtain the lane topology network" in step 103 can include:

[0082] (103.b.1) constructing the cluster cluster sequence of the multiple element cluster clusters in the lane according to the distribution relationship;

[0083] (103.b.2) sequentially performing road segment area division on each element cluster cluster in the cluster cluster sequence, and each road segment area includes at least one element cluster cluster;

[0084] (103.b.3) according to the arrangement order of the cluster sequence, splicing each lane section area to obtain a lane topology network.

[0085] The cluster sequence can be a sequence containing part or all of the element cluster, which can represent the arrangement order between the element clusters. It should be noted that in the cluster sequence, there can be a column of element clusters arranged in parallel, for example, when the lane appears to be bifurcated and parallel, there are two columns of element clusters arranged in parallel in the cluster sequence. For example, the number of element clusters arranged at the same lane position is taken as an example. "1" indicates that there is only one element cluster arranged at the same parallel lane position in the sequence, and "2" indicates that there are two element clusters arranged in parallel at the same parallel lane position in the sequence, that is, two parallel diverging lanes appear, and the arrangement of the cluster sequence can be represented as "1, 1, 1, 2, 2, 2, 2,...".

[0086] Specifically, first, according to the position distribution of the element clusters in the lane, the arrangement sequence of the element clusters is constructed to reflect the arrangement order and arrangement of the element clusters; then, for each element cluster in the cluster sequence, it can be divided into the corresponding lane section area combined with its associated lane position. It should be noted that a lane section area can contain one or more element clusters; finally, according to the arrangement order and arrangement of the element clusters in the sequence, the lane section area where the element cluster is located is connected in sequence, and when diverging occurs, two lane section areas are spliced in parallel with the previous lane section area. After the splicing of each lane section area is completed, the driving route of each vehicle is represented, reflecting the connected lane route, and the lane topology network is obtained. In this way, the lane topology network is constructed by the lane data collected by multiple vehicles, and the topology of the lane route is represented.

[0087] In some embodiments, the element clusters can be divided into lane section areas according to a specific distance of the section. Specifically, step (103.b.2) can include:

[0088] (103.b.2.1) determining the path interval distance between any two adjacent element clusters in the cluster sequence;

[0089] (103.b.2.2) determining the path length corresponding to the plurality of element clusters based on the path interval distance between the element clusters;

[0090] (103.b.2.3) according to a preset section distance, dividing the plurality of element clusters in the path length into lane section areas.

[0091] The path interval distance can be the path distance length between the two adjacent element cluster groups, which can reflect the interval distance between the two adjacent lane elements in the driving track of the vehicle.

[0092] The preset road section distance can be the planning grouping distance of the element cluster group, which is used to limit the length of each grouping road section when grouping the element cluster group.

[0093] Specifically, the path interval distance between any two adjacent element cluster groups in the element cluster group sequence is determined in combination with the lane position associated with each element cluster group. Specifically, the path interval distance between the two adjacent element cluster groups can be calculated according to the lane positions of the two adjacent element cluster groups. Then, based on the interval distance between any adjacent element cluster groups, all the interval distances are sequentially added according to the arrangement order and arrangement of the plurality of element cluster groups, to determine the distance length of the driving path (driving track) formed by the plurality of element cluster groups, which can also reflect the distance length of the lane where the plurality of element cluster groups are located. It should be noted that for the diverging lanes that exist in parallel, when the path interval distance is added to the diverging point, the path interval distance between the element cluster groups on each diverging lane needs to be added separately, so that each lane obtains the lane path length in the “total-divided” structure. Finally, the plurality of element cluster groups in the path length are divided into road sections according to the preset road section distance, to obtain a plurality of lane section areas, so as to splice the lane topology network formed by the plurality of lane section areas.

[0094] In some embodiments, since each lane section area can contain a plurality of element cluster groups, when connecting the plurality of lane section areas, only one element cluster group can be selected as the connection point of the lane section area, so as to connect the connection points in the plurality of lane section areas. Specifically, step (103.b.3) can include:

[0095] (103.b.3.1) selecting an element cluster group to be connected from each lane section area;

[0096] (103.b.3.2) sequentially connecting the element cluster group to be connected in each lane section area according to the arrangement order of the cluster group sequence, to obtain a path structure network;

[0097] (103.b.3.3) splicing each lane section area according to the path structure network, to obtain a lane topology network.

[0098] Specifically, since each lane section area can contain multiple element cluster clusters, if each element cluster cluster needs to be connected, it is easy to make the connection of the lane line winding and redundant, and when connecting multiple lane section areas, only the splicing order between the lane section areas needs to be determined, therefore, for the lane section area with multiple element cluster clusters, only one element cluster cluster can be selected as the to-be-connected point of the corresponding lane section area. Further, since the cluster cluster sequence contains the arrangement order and arrangement situation between all element cluster clusters, the arrangement order between the to-be-connected points can be determined according to the cluster cluster sequence, and each to-be-connected point is sequentially connected in the arrangement order, to obtain a driving track or a driving route, and multiple inconsistent driving routes converge into a path structure network. Finally, according to the path structure network, the lane section areas are spliced to obtain a lane topology network.

[0099] By the above method, the distribution relationship between the multiple element cluster clusters obtained by clustering can be determined to understand the position arrangement situation of the multiple element cluster clusters on the lane, and then the connection between the adjacent element cluster clusters is sequentially established according to the arrangement situation, and the connection route between the element cluster clusters is collected to obtain a lane topology network. In this way, the lane route topology relationship is constructed according to the lane data collected by multiple vehicles to preliminarily understand the connectivity of the traffic road, so as to further converge subsequently.

[0100] 104、Identify the upper layer and lower layer split lanes with overlapping structure relationship in the lane topology network, and group the lane elements of different vehicles according to the upper layer and lower layer split lanes to obtain an element grouping result.

[0101] In the embodiment of the present application, in order to distinguish the lane element set data of the upper and lower layer split lanes with overlapping parallel structure, the upper layer and lower layer split lanes with overlapping parallel structure relationship need to be identified from the lane topology network, and whether the lane elements collected by each vehicle belong to the upper and lower layer split lanes is determined according to the driving route of each vehicle, so as to group the lane element set collected by each vehicle, so as to update the corresponding lane information according to the grouped lane elements subsequently.

[0102] In some embodiments, the upper-level diverging lane and the lower-level diverging lane having an overlapping structure relationship in the lane topology network are identified mainly according to the length of the distance of the lane lines of the diverging part, the lane direction and the length of the lane coverage after diverging. For example, for the diverging routes or diverging trajectories formed by different vehicles in the diverging lanes, the distance of the diverging route (trajectory) is determined, if the distance of the diverging route is less than a first preset distance threshold (such as 10 meters), the direction of the diverging route is determined, if the directions of the two diverging routes are consistent, the length of the route after converging is determined, if the length of the route after converging is greater than a second preset distance threshold (such as 100 meters), it is determined that the diverging lane belongs to the overlapping upper and lower lanes, that is, it includes the upper-level diverging lane and the lower-level diverging lane.

[0103] In the embodiments of the present application, after the upper-level diverging lane and the lower-level diverging lane of the overlapping diverging structure are identified, the lane element set collected by each vehicle can be grouped to obtain an element grouping result. The element grouping result can be a grouping result of the lane element set, which specifically indicates that the lane element set belongs to the upper-level diverging lane or indicates that the lane element set belongs to the lower-level diverging lane.

[0104] In some embodiments, the "lane grouping of the lane element set of different vehicles according to the upper-level diverging lane and the lower-level diverging lane" in step 104 can include: determining a first distribution ratio of the lane elements in the lane element set of each vehicle in the upper-level diverging lane, and determining a second distribution ratio of the lane elements in each lane element set in the lower-level diverging lane; if the first distribution ratio is greater than the second distribution ratio, the corresponding lane element set is grouped to the upper-level diverging lane; if the first distribution ratio is less than the second distribution ratio, the corresponding lane element set is grouped to the lower-level diverging lane.

[0105] Specifically, the lane lines of the upper and lower diverging lanes are determined by the element cluster connection. When grouping the element cluster collected by each vehicle, for the lane element set uploaded by each vehicle, first, the distribution ratio of the lane elements in the set in the element cluster of the lane line of the upper diverging lane is determined, that is, the first distribution ratio, and the distribution ratio of the lane elements in the set in the element cluster of the lane line of the lower diverging lane is determined, that is, the second distribution ratio. Then, the first distribution ratio and the second distribution ratio are compared in size. If the first distribution ratio is greater than the second distribution ratio, it indicates that the lane element set collected by the vehicle is mainly distributed on the upper diverging lane, that is, the vehicle travels on the upper diverging lane, and therefore, the lane element set collected by the vehicle is assigned to the lane element data group of the upper diverging lane. Conversely, if the first distribution ratio is less than the second distribution ratio, it indicates that the lane element set collected by the vehicle is mainly distributed on the lower diverging lane, that is, the vehicle travels on the lower diverging lane, and therefore, the lane element set collected by the vehicle is assigned to the lane element data group of the lower diverging lane.

[0106] In the above manner, the upper and lower diverging lanes in the overlapping parallel structure relationship can be identified, and whether the lane elements collected by each vehicle belong to the upper and lower diverging lanes is determined according to the driving route of each vehicle, so as to group the lane element set collected by each vehicle, so as to subsequently update the upper and lower lanes in the overlapping parallel structure in the map according to the grouped lane elements.

[0107] 105. According to the element grouping result, the lane information of the upper and lower diverging lanes in the map is updated respectively.

[0108] In the embodiments of the present application, after obtaining the lane element set (i.e., lane data) belonging to the upper and lower diverging lanes respectively, the lane information of the upper diverging lane in the map can be constructed or updated according to the lane data belonging to the upper diverging lane, and the lane information of the lower diverging lane in the map can be constructed or updated according to the lane data belonging to the lower diverging lane.

[0109] By implementing any one of the embodiments or combination of embodiments in the present application, the application scenario of the map information updating process can be realized.

[0110] From the above, the embodiment of the present application can obtain the lane element set uploaded by each vehicle, the lane element set containing lane elements collected by the vehicle at different lane positions; cluster the lane elements collected by different vehicles according to lane positions to obtain element cluster clusters associated with each lane position; determine the distribution relationship between the multiple element cluster clusters, and sequentially connect the multiple element cluster clusters according to the distribution relationship to obtain a lane topology network; identify the upper and lower split lanes with overlapping structural relationships in the lane topology network, and group the lane element sets of different vehicles according to the upper and lower split lanes to obtain an element grouping result; and update the lane information of the upper and lower split lanes in the map according to the element grouping result. Thus, the present scheme can first obtain the lane element set collected by each vehicle, and cluster the lane elements collected by different vehicles according to lane positions to aggregate the lane elements collected by different vehicles at similar positions according to lane positions, so as to improve the credibility of lane element data. Then, the distribution relationship between the multiple lane element cluster clusters is determined, and the multiple lane element cluster clusters are connected to determine the connectivity of the lane through the connection of the cluster clusters to obtain a lane topology network. Finally, the upper and lower split lanes with overlapping structures in the lane topology network are identified, and the lane element sets collected by each vehicle are grouped for lane attribution, so as to update the information of the lanes in the map according to the lane element sets collected by the vehicles. In this way, the upper and lower lanes with overlapping structures can be identified, and the information of the upper and lower lanes with overlapping structures can be updated in the map through the corresponding lane elements, so as to improve the accuracy of the map information.

[0111] According to the method described in the above embodiment, the following will be further described by way of example.

[0112] The embodiment of the present application takes a map information updating device as an example to further describe the map information updating method provided by the embodiment of the present application. Among them, Figure 3 is another step flow diagram of the map information updating method provided by the embodiment of the present application, Figure 4 is a clustering scenario diagram of the lane elements collected by multiple vehicles provided by the embodiment of the present application, Figure 5 is a scenario diagram for dividing lane section areas provided by the embodiment of the present application, Figure 6 is a connection scenario diagram of element cluster clusters provided by the embodiment of the present application, Figure 7 is a structure diagram of a path structure network provided by the embodiment of the present application. For ease of understanding, the embodiment of the present application is described in combination with Figures 3-7 .

[0113] In the embodiments of the present application, the map information updating device can be integrated in a computer device such as a server. When the processor on the server executes the program instructions corresponding to the data transmission method, the specific process of the map information updating method is as follows:

[0114] 201. The server acquires the lane element set uploaded by each vehicle.

[0115] The lane element set contains lane elements collected by the corresponding vehicle at different lane positions, that is, each lane element set represents all lane elements collected by a vehicle during driving. It should be noted that the lane element can be a lane line, a lane direction arrow, a lane broken line, a number, a character, etc. Each lane element can be associated with corresponding lane position information.

[0116] Specifically, in order to realize the construction and updating of the map information without a base map, the lane data collected and uploaded by any vehicle can be acquired, specifically, the lane element sets collected by different vehicles on the same road can be acquired, so as to subsequently align and aggregate the lane elements in the multiple lane element sets, and to construct and update the map information according to the alignment and aggregation result.

[0117] For example, taking the driving of a vehicle on a highway as an example, the vehicle has a camera component, which can collect the road surface information in the driving direction, such as lane lines, lane direction arrows, lane broken lines, numbers, characters, etc. As the vehicle continuously drives, the vehicle will sequentially collect various lane element markers on the road surface during driving, thereby obtaining a lane element set, so as to subsequently construct or update the corresponding lane information in the map through the lane element set.

[0118] 202. The server clusters the lane elements collected by different vehicles according to the lane position, to obtain an element cluster associated with each lane position.

[0119] Specifically, after obtaining the lane element sets uploaded by multiple vehicles, the lane elements belonging to the same lane position can be clustered according to the dimension of the lane position, that is, the lane elements collected by different vehicles at the same lane position are clustered, so as to subsequently construct the map information according to the clustering result after clustering. For example, assuming that vehicle A collects arrow and lane broken line lane elements at a target lane position area, and vehicle B also collects arrow and lane broken line lane elements at the target lane position area, the lane elements collected by vehicle A and vehicle B at the target lane position area are aggregated to obtain an element cluster of the target lane position area.

[0120] Referring to Figure 5As shown, containing different vehicles uploaded lane element set, assuming Case_1 and Case_m, the lane element set can be understood as crowd-sourced lane data, each lane element (marking) in Case_1 set is matched and aligned with the lane element (marking) in Case_m set, and a element cluster (Feature Cluster, FC) is formed, such as Figure 5 As shown, FC1, FC2, FCn respectively represent an element cluster, and the lane element of the center point of the element cluster is taken as an alignment point, which saves the alignment matching relationship of the lane elements collected by different vehicles at the same lane position.

[0121] 203、The server determines the distribution relationship between the plurality of element clusters according to the lane position associated with each element cluster.

[0122] Specifically, since the lane elements collected by different vehicles are clustered according to lane positions during clustering, the element clusters obtained by clustering are also associated with lane positions. Further, the lane position associated with each element cluster is determined to determine the distribution of the plurality of element clusters on the road plane according to the lane position, and the distribution relationship between the plurality of element clusters is obtained.

[0123] 204、The server constructs a cluster sequence of the plurality of element clusters in the lane according to the distribution relationship.

[0124] The cluster sequence can be a sequence containing part or all of the element clusters, which can represent the arrangement order between the plurality of element clusters. It should be noted that in the cluster sequence, there can be a column of element clusters arranged in parallel, or there can be multiple columns of element clusters arranged in parallel. For example, when the lane appears bifurcated and parallel diverging lanes, there are two columns of element clusters arranged in parallel in the cluster sequence. For example, the number of element clusters arranged at the same lane position is taken as an example. "1" indicates that there is only one element cluster arranged at the same parallel lane position in the sequence, and "2" indicates that there are two element clusters arranged in parallel at the same parallel lane position in the sequence, that is, two parallel diverging lanes appear. The arrangement of the cluster sequence can be represented as "1, 1, 1, 2, 2, 2, 2......".

[0125] For example, referring to Figure 5As shown in the figure, a bifurcated road appears starting from section g3, and the diverging lanes "g3-g4-g5" and "g3-g6-g7" are obtained. Among them, sections g3, g4, g5, g6, and g7 each contain 3 element clusters. In terms of parallel lanes, "g3-g4-g5" and "g3-g6-g7" are respectively regarded as a series of element clusters in the sequence. The number of element clusters in the element cluster sequence "g3-g4(g6)-g5(g7)" is arranged as: "1, 1, 1, 2, 2, 2, 2, 2, 2".

[0126] 205. The server sequentially divides each element cluster in the cluster sequence into lane segment areas, and each lane segment area includes at least one element cluster.

[0127] In the embodiment of the present application, after determining the arrangement order and arrangement of the element clusters, each element cluster in the cluster sequence can be divided into a corresponding lane segment area in combination with its associated lane position.

[0128] Specifically, the path separation distance between any two adjacent element clusters in the element cluster sequence is determined based on the lane positions associated with each element cluster. Specifically, the path separation distance between the two adjacent element clusters can be calculated based on their lane positions. Then, based on the separation distances between any two adjacent element clusters, all separation distances are accumulated sequentially according to the arrangement order and arrangement of the multiple element clusters to determine the distance length of the driving path (driving trajectory) formed by the multiple element clusters. This also reflects the distance lengths of the lanes where the multiple element clusters are located. It should be noted that for diverging lanes with bifurcated parallel paths, when accumulating the path length, before accumulating the path separation distances to the bifurcation, the path separation distances between the element clusters on each diverging lane need to be accumulated separately, so that each lane obtains a lane path length based on a "total-divided" structure. Finally, the multiple element clusters within the path length are segmented according to the preset segment distances to obtain multiple lane segment areas.

[0129] For example, the lane position of each lane element (marking) when it is captured by the vehicle camera in the lane driving sequence is determined, and the spacing distance between adjacent lane elements (or clusters) is determined. Thus, from the start of the vehicle driving, the distance traveled by each lane element (or cluster) in the vehicle driving trajectory is determined. The path length of the route associated with all lane elements (clusters) can also be calculated, and the path length can be approximated to the lane length. Then, according to the preset road segment distance, the lane segment area is divided for multiple element clusters within the path length, and combined with Figure 5As shown, it is an architecture diagram containing "main (total) lane-split lane", according to the road section length of 20 meters, a plurality of element cluster clusters are clustered for road section area division, for example, the element cluster cluster 4 element cluster clusters are contained in the road section area g1, the road section area g2 contains 3 element cluster clusters, the road section area g3 contains 3 element cluster clusters, the road section area g4 contains 3 element cluster clusters, the road section area g5 contains 3 element cluster clusters, the road section area g6 contains 3 element cluster clusters, and the road section area g7 contains 3 element cluster clusters.

[0130] 206、The server splices each road section area according to the arrangement order of the cluster cluster sequence to obtain a lane topology network.

[0131] Specifically, since each road section area may contain a plurality of element cluster clusters, if each element cluster cluster needs to be connected, it is easy to make the road line obtained by connection winding and redundant, and when connecting a plurality of road section areas, only the splicing order between the road section areas needs to be determined, therefore, for the road section area with a plurality of element cluster clusters, only one element cluster cluster can be selected as the to-be-connected point of the corresponding road section area. Further, since the cluster cluster sequence contains the arrangement order and arrangement situation between all element cluster clusters, the arrangement order between the to-be-connected points can be determined according to the cluster cluster sequence, and each to-be-connected point is sequentially connected according to the arrangement order, to obtain a driving track or driving route, and a plurality of inconsistent driving routes converge into a path structure network. Finally, according to the path structure network, each road section area is spliced to obtain a lane topology network.

[0132] For example, referring to Figure 6 As shown, according to the track distance of the lane element marking of each lane element set Case, the front and rear connection relationship between the lane elements is obtained, and further, the front and rear connection relationship between a plurality of element cluster clusters in the lane is obtained. For example, taking Case1 as an example, the element cluster clusters corresponding to the marking in Case1 are counted to belong to the road section area, and according to the distance of the lane element marking in the vehicle track, the distance of each element cluster cluster in the whole vehicle driving sequence is determined, the front and rear connection relationship between the road section areas is determined, and the connection relationship of each road section area is "g1-g2-g3-g4-g5"; by analogy, the connection relationship of all Cases is added to each road section area to obtain a path structure network containing a plurality of lane paths, and the path structure network is as shown in Figure 7 Further, according to the path structure network, the road section areas are spliced to obtain a lane topology network.

[0133] It should be noted that the path structure network can contain disordered connection relationship between the road segment areas, such as "g2-g6". In order to remove the disordered connection relationship, taking g1 as the starting point and g5 and g7 as independent terminals respectively, the longest path from g1 to g5 is found out, and the longest path from g1 to g7 is found out, so that two paths are obtained, which are "path1: g1-g2-g3-g4-g5" and "path2: g1-g2-g3-g6-g7" respectively, and thus the connection line of "g2-g6" is deleted.

[0134] 207、The server identifies the upper-layer diverging lane and the lower-layer diverging lane with the overlapping structure relationship in the lane topology network.

[0135] Specifically, when identifying the upper-layer diverging lane and the lower-layer diverging lane with the overlapping structure relationship in the lane topology network, mainly according to the length of the distance of the lane line of the diverging part, the lane direction and the length of the lane coverage after the divergence.

[0136] For example, for the diverging routes or diverging trajectories formed by the diverging lanes of different vehicles, the distance of the diverging path (trajectory) is determined, if the distance of the diverging path is less than a first preset distance threshold (such as 10 meters), the direction of the diverging path is determined, if the directions of the two diverging paths are consistent, the length of the route after the divergence is determined, if the length of the route after the divergence is greater than a second preset distance threshold (such as 100 meters), it is determined that the diverging lane belongs to the overlapping upper and lower lanes, that is, it includes the upper-layer diverging lane and the lower-layer diverging lane.

[0137] 208、The server groups the lane element sets of different vehicles according to the upper-layer diverging lane and the lower-layer diverging lane, to obtain an element grouping result.

[0138] In the embodiment of the present application, after the upper-layer diverging lane and the lower-layer diverging lane of the overlapping diverging structure are identified, the lane element sets collected by each vehicle can be grouped to obtain an element grouping result. The element grouping result can be a grouping result of the lane element set, which specifically indicates that the lane element set belongs to the upper-layer diverging lane, or indicates that the lane element set belongs to the lower-layer diverging lane.

[0139] Specifically, the lane lines of the upper and lower diverging lanes are determined by the element cluster clusters, and when grouping the element cluster clusters collected by each vehicle, for the lane element set uploaded by each vehicle, first, the distribution proportion of the lane elements in the element cluster clusters in the lane line of the upper diverging lane in the set, i.e., the first distribution ratio, is determined, and the distribution proportion of the lane elements in the element cluster clusters in the lane line of the lower diverging lane in the set, i.e., the second distribution ratio, is determined, then, the first distribution ratio and the second distribution ratio are compared in size, if the first distribution ratio is greater than the second distribution ratio, it indicates that the lane element set collected by the vehicle is mainly distributed on the upper diverging lane, i.e., the vehicle travels on the upper diverging lane, therefore, the lane element set collected by the vehicle is assigned to the lane element data group of the upper diverging lane; on the contrary, if the first distribution ratio is less than the second distribution ratio, it indicates that the lane element set collected by the vehicle is mainly distributed on the lower diverging lane, i.e., the vehicle travels on the lower diverging lane, therefore, the lane element set collected by the vehicle is assigned to the lane element data group of the lower diverging lane.

[0140] For example, as shown in FIG. 1, the path "path1: g1-g2-g3-g4-g5" contains the matching relationship between the element cluster FC contained in all lane section areas and the lane element marking point provided by coarse alignment, and when grouping the lane element set collected by each vehicle, taking Case 1 as an example, if most of the marking points in Case 1 match the element cluster (feature cluster) of path1, it indicates that Case 1 belongs to path1, otherwise, it indicates that it is in path2. Further, after grouping, the lane information of the lane where the corresponding path in the map can be constructed according to the element grouping result. Figure 6 Figure 7 For example, as shown in FIG. 1, the path "path1: g1-g2-g3-g4-g5" contains the matching relationship between the element cluster FC contained in all lane section areas and the lane element marking point provided by coarse alignment, and when grouping the lane element set collected by each vehicle, taking Case 1 as an example, if most of the marking points in Case 1 match the element cluster (feature cluster) of path1, it indicates that Case 1 belongs to path1, otherwise, it indicates that it is in path2. Further, after grouping, the lane information of the lane where the corresponding path in the map can be constructed according to the element grouping result.

[0141] 209, the server updates the lane information of the upper and lower diverging lanes in the map according to the element grouping result.

[0142] In the embodiments of the present application, after obtaining the lane element sets (i.e., lane data) belonging to the upper and lower diverging lanes respectively, the lane information of the upper diverging lane in the map can be constructed or updated according to the lane data belonging to the upper diverging lane, and the lane information of the lower diverging lane in the map can be constructed or updated according to the lane data belonging to the lower diverging lane.

[0143] ​From the above, the embodiment of the present application can select a map information updating strategy according to the vehicle state. When the vehicle state is a navigation driving state, a driving planning path of the current state of the vehicle is first constructed, and a path map block on the driving planning path and a path edge map block adjacent to the path map block are selected, and the map information of the path edge map block adjacent to the path map block is sequentially updated. In this way, in the vehicle automatic driving application, only the part of the map blocks associated with the driving planning path are updated, and there is no need to update the map information of all the map blocks in the entire map, thereby reducing the amount of map information to be updated, effectively saving the updating time of the map information, and being able to provide real-time map information for the vehicle automatic driving function, thereby guaranteeing the use demand of the user for the automatic driving function of the vehicle and improving the user experience.

[0144] In order to better implement the above method, the embodiment of the present application further provides a map information updating device, which can be integrated in a computer device, such as a vehicle terminal or the like.

[0145] For example, as shown in Figure 8 The map information updating device can include an acquisition unit 801, a distance unit 802, a construction unit 803, a grouping unit 804, and an updating unit 805.

[0146] The acquisition unit 801 is configured to acquire a lane element set uploaded by each vehicle, the lane element set containing lane elements collected by the vehicle at different lane positions;

[0147] The clustering unit 802 is configured to cluster the lane elements collected by different vehicles according to lane positions, to obtain an element cluster associated with each lane position;

[0148] The construction unit 803 is configured to determine a distribution relationship between a plurality of element clusters, and sequentially connect the plurality of element clusters according to the distribution relationship, to obtain a lane topology network;

[0149] The grouping unit 804 is configured to identify an upper split lane and a lower split lane having an overlapping structure relationship in the lane topology network, and perform lane grouping on the lane element sets of different vehicles according to the upper split lane and the lower split lane, to obtain an element grouping result.

[0150] The updating unit 805 is configured to update lane information of the upper split lane and the lower split lane in the map respectively according to the element grouping result.

[0151] In some embodiments, the clustering unit 802 is further configured to determine a lane position associated with each lane element in each lane element set, and cluster the lane elements belonging to the same lane position, to obtain an element cluster associated with each lane position.

[0152] In some embodiments, the establishing unit 803 is further configured to determine a lane position associated with each element cluster; and determine a distribution relationship between the element clusters according to the lane positions associated with the element clusters.

[0153] In some embodiments, the establishing unit 803 is further configured to construct a cluster sequence of the element clusters in the lane according to the distribution relationship; and sequentially perform lane segment region division on each element cluster in the cluster sequence, each lane segment region containing at least one element cluster; and splice each lane segment region according to the arrangement order of the cluster sequence to obtain the lane topology network.

[0154] In some embodiments, the establishing unit 803 is further configured to determine a path interval distance between any two adjacent element clusters in the cluster sequence; determine a path length corresponding to the element clusters based on the path interval distance between the element clusters; and perform lane segment region division on the element clusters within the path length according to a preset segment distance.

[0155] In some embodiments, the establishing unit 803 is further configured to select an element cluster to be connected from each lane segment region; sequentially connect the element cluster to be connected in each lane segment region according to the arrangement order of the cluster sequence to obtain a path structure network; and splice each lane segment region according to the path structure network to obtain the lane topology network.

[0156] In some embodiments, the grouping unit 804 is further configured to determine a first distribution ratio of the lane elements in each lane element set in the upper layer shunt lane and a second distribution ratio of the lane elements in each lane element set in the lower layer shunt lane; group the corresponding lane element set to the upper layer shunt lane if the first distribution ratio is greater than the second distribution ratio; and group the corresponding lane element set to the lower layer shunt lane if the first distribution ratio is less than the second distribution ratio.

[0157] From the above, the embodiment of the present application can first acquire the lane element set collected by each vehicle, and cluster the lane elements collected by different vehicles according to lane positions, to realize the aggregation of lane elements collected by different vehicles and having similar positions according to lane positions, so as to improve the reliability of lane element data. Then, the distribution relationship between multiple lane element clustering clusters is determined, and the multiple lane element clustering clusters are connected, to determine the connectivity of the lane through the connection of the clustering clusters, to obtain the lane topology network. Finally, the upper and lower split lanes having the upper and lower overlapping structure in the lane topology network are identified, and the lane attribution grouping of the lane element set collected by each vehicle is performed, to update the information of the lane belonging to the map according to the lane element set collected by the vehicle. In this way, the upper and lower lanes of the overlapping structure can be identified, and the information of the upper and lower lanes of the overlapping structure can be updated in the map through the corresponding lane elements, to improve the accuracy of the map information.

[0158] The specific implementation of each operation can refer to the foregoing embodiments, which will not be repeated here.

[0159] The embodiment of the present application also provides a computer device, as shown in the figure, which shows the structure schematic diagram of the computer device related to the embodiment of the present application, in particular: Figure 9

[0160] The computer device can include a processor 901 with one or more processing cores, a memory 902 with one or more computer readable storage media, a power supply 903, an input unit 904, and the like. Those skilled in the art can understand that the structure of the computer device shown in the figure does not constitute a limitation on the computer device, and can include more or fewer components than the figure, or combine certain components, or different component arrangements. Among them: Figure 9

[0161] The processor 901 is the control center of the computer device, which connects all parts of the computer device through various interfaces and lines, executes the software programs and / or modules stored in the memory 902 and the data stored in the memory 902, processes data, and thus monitors the computer device as a whole. Optionally, the processor 901 can include one or more processing cores; preferably, the processor 901 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 901.

[0162] ​​The memory 902 can be used to store software programs and modules, and the processor 901 executes various functional applications and map information updates by running the software programs and modules stored in the memory 902. The memory 902 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to the use of the computer device, etc. In addition, the memory 902 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device. Accordingly, the memory 902 can also include a memory controller to provide the processor 901 with access to the memory 902.

[0163] The computer device also includes a power supply 903 for powering the various components. Preferably, the power supply 903 can be logically connected to the processor 901 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 903 can also include one or more direct current or alternating current power supplies, a recharging system, a power supply fault detection circuit, a power supply converter or inverter, a power supply status indicator, and the like.

[0164] The computer device can also include an input unit 904, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0165] Although not shown, the computer device can also include a display unit and the like, which will not be described here. Specifically, in the present embodiment, the processor 901 in the computer device will load the executable file corresponding to the process of one or more application programs into the memory 902 according to the following instructions, and run the application programs stored in the memory 902 by the processor 901, so as to realize various functions, as follows:

[0166] Obtain a lane element set uploaded by each vehicle, the lane element set containing lane elements collected by the vehicle at different lane positions; cluster the lane elements collected by different vehicles according to lane positions to obtain element cluster clusters associated with each lane position; determine a distribution relationship between the element cluster clusters, and sequentially connect the element cluster clusters according to the distribution relationship to obtain a lane topology network; identify an upper split lane and a lower split lane having an overlapping structure relationship in the lane topology network, and perform lane grouping on the lane element sets of different vehicles according to the upper split lane and the lower split lane to obtain an element grouping result; and update lane information of the upper split lane and the lower split lane in the map respectively according to the element grouping result.

[0167] The specific implementation of each operation above can be found in the previous embodiments, which will not be repeated here.

[0168] As can be seen from the above, the embodiments of the present application can first acquire the lane element set collected by each vehicle, and cluster the lane elements collected by different vehicles according to lane positions, to aggregate the lane elements collected by different vehicles with similar positions according to lane positions, so as to improve the credibility of lane element data. Then, the distribution relationship between multiple lane element clusters is determined, and the multiple lane element clusters are connected, to determine the connectivity of the lane through the connection of the clusters, to obtain the lane topology network. Finally, the upper and lower split lanes with overlapping structure in the lane topology network are identified, and the lane attribution grouping of the lane element set collected by each vehicle is performed, to update the information of the lane in the map according to the lane element set collected by the vehicle. In this way, the upper and lower lanes with overlapping structure can be identified, and the information of the upper and lower lanes with overlapping structure can be updated in the map through the corresponding lane elements, to improve the accuracy of the map information.

[0169] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or controlled by instructions related to hardware, which can be stored in a computer readable storage medium and loaded and executed by a processor.

[0170] To this end, the embodiments of the present application provide a computer readable storage medium, which stores a plurality of instructions capable of being loaded by a processor to execute the steps in any one of the map information updating methods provided by the embodiments of the present application. For example, the instructions can execute the following steps:

[0171] acquire the lane element set uploaded by each vehicle, the lane element set containing lane elements collected by the vehicle at different lane positions; cluster the lane elements collected by different vehicles according to lane positions to obtain element cluster associated with each lane position; determine the distribution relationship between multiple element clusters, and sequentially connect the multiple element clusters according to the distribution relationship to obtain a lane topology network; identify the upper split lane and the lower split lane with overlapping structure relationship in the lane topology network, and perform lane grouping on the lane element set of different vehicles according to the upper split lane and the lower split lane, to obtain an element grouping result; and update the lane information of the upper split lane and the lower split lane in the map according to the element grouping result.

[0172] The specific implementation of each operation above can be found in the previous embodiments, which will not be repeated here.

[0173] The computer readable storage medium can include a read only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0174] The present application also provides a computer program product or computer program, which comprises computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the map information updating method provided in various optional implementation manners in the above embodiments.

[0175] Due to the instructions stored in the computer readable storage medium, the steps in any of the map information updating methods provided in the embodiments of the present application can be executed, thus the beneficial effects of any of the map information updating methods provided in the embodiments of the present application can be achieved, which are described in detail in the above embodiments and will not be repeated here.

[0176] The above describes in detail a map information updating method, device, equipment and computer readable storage medium provided in the embodiments of the present application, and the principles and implementation manners of the present application are described by applying specific examples; the above embodiment descriptions are only used to help understand the method of the present application and its core idea; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manners and application ranges will be changed, and in summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A map information updating method characterized by comprising: The method comprises the following steps: acquiring a lane element set uploaded by each vehicle, the lane element set containing lane elements collected by the vehicle at different lane positions; clustering lane elements collected by different vehicles according to lane positions to obtain element cluster clusters associated with each lane position; determining a distribution relationship between a plurality of element cluster clusters and sequentially connecting the plurality of element cluster clusters according to the distribution relationship to obtain a lane topology network; identifying an upper split lane and a lower split lane having an overlapping structure relationship in the lane topology network and grouping lane element sets of different vehicles according to the upper split lane and the lower split lane to obtain an element grouping result; updating lane information of the upper split lane and the lower split lane in a map respectively according to the element grouping result.

2. The method of claim 1, wherein, The step of clustering lane elements collected by different vehicles according to lane positions to obtain element cluster clusters associated with each lane position comprises the following steps: determining a lane position associated with each lane element in each lane element set; clustering lane elements belonging to the same lane position to obtain element cluster clusters associated with each lane position.

3. The method of claim 1, wherein, The step of determining a distribution relationship between a plurality of element cluster clusters comprises the following steps: determining a lane position associated with each element cluster cluster; determining a distribution relationship between a plurality of element cluster clusters according to the lane position associated with each element cluster cluster.

4. The method of claim 1, wherein, The step of sequentially connecting the plurality of element cluster clusters according to the distribution relationship to obtain a lane topology network comprises the following steps: constructing a cluster sequence of the plurality of element cluster clusters in a lane according to the distribution relationship; sequentially performing lane section area division on each element cluster cluster in the cluster sequence, each lane section area containing at least one element cluster cluster; splicing each lane section area according to an arrangement order of the cluster sequence to obtain a lane topology network.

5. The method of claim 4, wherein, The step of sequentially performing lane section area division on each element cluster cluster in the cluster sequence comprises the following steps: determining a path interval distance between any two adjacent element cluster clusters in the cluster sequence; determining a path length corresponding to the plurality of element cluster clusters based on the path interval distance between the element cluster clusters; performing lane section area division on a plurality of element cluster clusters within the path length according to a preset section distance.

6. The method of claim 4, wherein, The step of splicing each lane section area according to an arrangement order of the cluster sequence to obtain a lane topology network comprises the following steps: selecting an element cluster cluster to be connected from each lane section area; sequentially connecting the element cluster cluster to be connected in each lane section area according to an arrangement order of the cluster sequence to obtain a path structure network; splicing each lane section area according to the path structure network to obtain a lane topology network.

7. The method of claim 1, wherein, The step of grouping lane element sets of different vehicles according to the upper split lane and the lower split lane comprises the following steps: determining a first distribution ratio of lane elements in the lane element set of each vehicle in the upper split lane and determining a second distribution ratio of lane elements in the lane element set of each vehicle in the lower split lane; If the first distribution ratio is greater than the second distribution ratio, the corresponding lane element set is grouped to the upper-level diverging lane; If the first distribution ratio is less than the second distribution ratio, the corresponding lane element set is grouped to the lower-level diverging lane.

8. A map information updating apparatus characterized by comprising: The method comprises the following steps: An acquisition unit is configured to acquire a lane element set uploaded by each vehicle, wherein the lane element set comprises lane elements collected by the vehicle at different lane positions; A clustering unit is configured to cluster the lane elements collected by different vehicles according to lane positions to obtain an element cluster associated with each lane position; An establishment unit is configured to determine a distribution relationship between a plurality of element clusters and sequentially establish the plurality of element clusters to be connected according to the distribution relationship to obtain a lane topology network; A grouping unit is configured to identify an upper-level diverging lane and a lower-level diverging lane having an overlapping structure relationship in the lane topology network, and group lane element sets of different vehicles according to the upper-level diverging lane and the lower-level diverging lane to obtain an element grouping result; An updating unit is configured to update lane information of the upper-level diverging lane and the lower-level diverging lane in a map respectively according to the element grouping result.

9. A computer device, comprising: The computer readable storage medium is computer readable and stores a plurality of instructions, and the instructions are suitable for being loaded by the processor to execute the steps in the map information updating method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium is computer readable and stores a plurality of instructions, and the instructions are suitable for being loaded by the processor to execute the steps in the map information updating method according to any one of claims 1 to 7.

Images