Road data fusion method and vehicle automatic driving method

Abstract

The disclosed embodiment discloses a road data fusion method and a vehicle automatic driving method, the road data fusion method comprising: acquiring road physical layer data; the road physical layer data comprises a first mapping relationship between actual road data and high-precision road network data and a second mapping relationship between actual road data and standard-precision road network data; determining a matching relationship between high-precision road network data and standard-precision road network data based on the first mapping relationship and the second mapping relationship; the matching relationship comprises an interval correspondence relationship and a path correspondence relationship between roads in an intersection; based on the matching relationship, the high-precision road network data and the standard-precision road network data are fused. This technical solution can update only the road physical layer data and the mapping relationship between the road physical layer data and the high-precision road network data and the standard-precision road network data respectively when the actual road is updated, with high stability and low maintenance cost.

Description

Technical Field

[0001] The present disclosure relates to the technical field of electronic maps, and in particular to a road data fusion method and a vehicle automatic driving method. Background Art

[0002] With the development of location-based services (LBS), more and more application software has integrated service capabilities related to electronic maps. In addition, some artificial intelligence devices also rely on electronic maps, for example, autonomous driving equipment relies on high-precision maps to achieve the driving process. Compared with the electronic navigation map used by drivers in manual driving, high-precision maps describe the road with more accurate and rich information, so that autonomous driving equipment can understand the road conditions, plan actions based on the road conditions, and complete the driving process by executing actions.

[0003] At present, due to the late start of high-precision maps, high-precision maps have only been produced for some areas, and most areas still only have standard-precision maps. Therefore, autonomous driving equipment needs to use both high-precision maps and standard-precision maps at the same time, and use them by integrating high-precision maps and standard-precision maps.

[0004] A common fusion solution between HD maps and standard maps is the ID (identification) mapping solution of roads or intersections. For example, when planning a route, the standard map is used to calculate the route, and the corresponding HD road ID is obtained through the standard road ID on the route, and then converted into a HD route. However, since the road IDs on standard maps and HD maps are frequently updated, as long as any road ID changes, the ID mapping relationship needs to be re-created, which has poor stability and high maintenance costs.

[0005] Therefore, it is necessary to propose a fusion solution of high-precision maps and standard-precision maps to solve the problems of poor stability and high maintenance costs mentioned above. Summary of the invention

[0006] The embodiments of the present disclosure provide a road data fusion method and a vehicle automatic driving method.

[0007] In a first aspect, an embodiment of the present disclosure provides a road data fusion method, comprising:

[0008] Acquire road physical layer data; the road physical layer data includes a first mapping relationship between actual road data and high-precision road network data and a second mapping relationship between actual road data and standard-precision road network data;

[0009] Determine a matching relationship between the high-precision road network data and the standard-precision road network data based on the first mapping relationship and the second mapping relationship; the matching relationship includes an interval correspondence relationship and a path correspondence relationship between roads in an intersection;

[0010] The high-precision road network data and the standard-precision road network data are fused based on the matching relationship.

[0011] Furthermore, the first mapping relationship includes a mapping relationship between an actual intersection and a high-precision intersection, and a mapping relationship between roads within an actual intersection and roads within a high-precision intersection; and / or, the second mapping relationship includes a mapping relationship between an actual intersection and a standard-precision intersection, and a mapping relationship between roads within an actual intersection and roads within a standard-precision intersection.

[0012] Further, determining a matching relationship between the high-precision road network data and the standard-precision road network data based on the first mapping relationship and the second mapping relationship includes:

[0013] Determine the target high-precision data and target standard-precision data corresponding to the target intersection in the high-precision road network data based on the first mapping relationship and the second mapping relationship;

[0014] Determine a target high-precision path corresponding to the target intersection based on the target high-precision data;

[0015] Determine a target marked precise path corresponding to the target intersection based on the target marked precise data;

[0016] A matching relationship between the target high-precision path and the target standard-precision path is determined.

[0017] Further, determining target high-precision data and target standard-precision data corresponding to the target intersection in the high-precision road network data based on the first mapping relationship and the second mapping relationship includes:

[0018] The high-precision road network data is grouped according to intersections based on the first mapping relationship, each group including target high-precision data corresponding to a target intersection;

[0019] Determine, based on the second mapping relationship, a marked precise intersection corresponding to the target intersection in the marked precise road network data;

[0020] The target precise data corresponding to the precise intersection is extracted from the precise road network data.

[0021] Further, determining a target high-precision path corresponding to the target intersection based on the target high-precision data further includes:

[0022] A high-precision road topology directed graph corresponding to the target intersection is established based on the target high-precision data; the vertices in the high-precision road topology directed graph include the intersection of the high-precision road associated with the target intersection and the high-precision intersection road surface corresponding to the target intersection, and other path endpoints in the high-precision path passing through the intersection, the connection lines between the vertices in the high-precision road topology directed graph include the high-precision roads in the high-precision path passing through the vertices, and the direction of the connection lines is the driving direction of the high-precision road;

[0023] Determine isolated vertices in the high-precision road topology directed graph; the isolated vertices are vertices that only correspond to entering or exiting the high-precision road;

[0024] A target high-precision path corresponding to the target intersection in the target high-precision data is determined based on the high-precision path between the isolated vertices.

[0025] Further, determining a target marked precise path corresponding to the target intersection based on the target marked precise data includes:

[0026] A directed graph of a topological precision road corresponding to the target intersection is established based on the target precision data; vertices in the directed graph of the topological precision road include intersections between precision roads associated with the target intersection, and other path endpoints in a precision path passing through the intersections; lines between vertices in the directed graph of the topological precision road include precision paths in the precision path passing through the vertices; and directions of the lines are driving directions of the precision roads;

[0027] Determine an isolated vertex in the topological directed graph of the marked refined road; the isolated vertex is a vertex that only corresponds to the marked refined road with entry or exit;

[0028] The target precise path corresponding to the target intersection in the target precise data is determined based on the precise path between the isolated vertices.

[0029] Further, determining a matching relationship between the target high-precision path and the target standard-precision path includes:

[0030] Determine, in the target high-precision path, a first actual road corresponding to the last high-precision road entering the target intersection and a second actual road corresponding to the first high-precision road exiting the target intersection;

[0031] Determine, in the target precise path, a third actual road corresponding to the last precise road entering the target intersection and a fourth actual road corresponding to the first precise road exiting the target intersection;

[0032] When the first actual road includes the third actual road and the second actual road includes the fourth actual road, it is determined that the target high-precision path matches the target standard-precision path.

[0033] Further, based on the matching relationship, the high-precision road network data and the standard-precision road network data are merged, including:

[0034] For the matched target high-precision path and target standard precision path, if the standard precision road in the target standard precision path is a standard precision road in an intersection, all the high-precision roads in the intersection in the matched target high-precision path are attached to the standard precision road in the intersection;

[0035] If the precision road in the target precision path is a precision road not in an intersection, the precision road not in an intersection is divided into a divided road section using the high-precision intersection road surface of the target intersection, and all the high-precision roads in intersections in the target high-precision path are attached to the divided road section obtained by the division.

[0036] In a second aspect, a method for autonomous driving of a vehicle is provided in an embodiment of the present disclosure, wherein the method utilizes the fusion data of high-precision road network data and standard-precision road network data obtained by the method described in the first aspect to control the autonomous driving process of the vehicle.

[0037] In a third aspect, a location-based service provision method is provided in an embodiment of the present disclosure, wherein the method utilizes the fusion data of high-precision road network data and standard-precision road network data obtained by the method described in the first aspect to provide location-based services to the service object, wherein the location-based services include one or more of navigation, map rendering, and route planning.

[0038] In a fourth aspect, an embodiment of the present disclosure provides a road data fusion device, which includes:

[0039] An acquisition module is configured to acquire road physical layer data; the road physical layer data includes a first mapping relationship between actual road data and high-precision road network data and a second mapping relationship between actual road data and standard-precision road network data;

[0040] A determination module is configured to determine a matching relationship between the high-precision road network data and the standard-precision road network data based on the first mapping relationship and the second mapping relationship; the matching relationship includes an interval correspondence relationship and a path correspondence relationship between roads in an intersection;

[0041] The fusion module is configured to fuse the high-precision road network data and the standard-precision road network data based on the matching relationship.

[0042] In a fifth aspect, a vehicle automatic driving device is provided in an embodiment of the present disclosure, which controls the automatic driving process of the vehicle by utilizing the fusion data of the high-precision road network data and the standard-precision road network data obtained by the device described in the fourth aspect.

[0043] In the sixth aspect, a location-based service providing device is provided in an embodiment of the present disclosure, which utilizes the fusion data of high-precision road network data and standard-precision road network data obtained by the device described in the fourth aspect to provide location-based services to the service object, and the location-based services include: navigation, map rendering, route planning or one or more thereof.

[0044] The functions can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions.

[0045] In one possible design, the structure of the above-mentioned device includes a memory and a processor, the memory is used to store one or more computer instructions that support the above-mentioned device to execute the above-mentioned corresponding method, and the processor is configured to execute the computer instructions stored in the memory. The above-mentioned device may also include a communication interface for the above-mentioned device to communicate with other devices or communication networks.

[0046] In a seventh aspect, an embodiment of the present disclosure provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method described in any one of the above aspects.

[0047] In an eighth aspect, an embodiment of the present disclosure provides a computer-readable storage medium for storing computer instructions used by any of the above-mentioned devices, and when the computer instructions are executed by a processor, they are used to implement the method described in any of the above-mentioned aspects.

[0048] In a ninth aspect, an embodiment of the present disclosure provides a computer program product, which includes computer instructions, and when the computer instructions are executed by a processor, they are used to implement the method described in any of the above aspects.

[0049] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0050] When the high-precision road network data and the standard-precision road network data are merged, the disclosed embodiment pre-abstracts a road physical layer that describes the actual road data, the first mapping relationship between the actual road data and the high-precision road network data, and the second mapping relationship between the actual road data and the standard-precision road network data. When the fusion is performed, the matching relationship between the high-precision road network data and the standard-precision road network data is determined based on the first mapping relationship and the second mapping relationship, and then the fusion is performed based on the matching relationship. The above technical solution, because the mapping relationship between the high-precision road network data and the standard-precision road network data is maintained respectively through the road physical layer data, when the actual road is updated, only the road physical layer data and the mapping relationship between the road physical layer data and the high-precision road network data and the standard-precision road network data can be updated, and the high-precision road network data and the standard-precision road network data can be merged based on the updated mapping relationship before actual use, without the need to re-produce the high-precision road network data and the standard-precision road network data, and has high stability and low maintenance cost.

[0051] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Other features, objectives and advantages of the present disclosure will become more apparent through the following detailed description of non-limiting embodiments in conjunction with the accompanying drawings. In the accompanying drawings:

[0053] Figure 1 A flow chart showing a road data fusion method according to an embodiment of the present disclosure;

[0054] Figure 2 A schematic diagram showing the corresponding relationship between high-precision road network data, standard-precision road network data and road physical layer data corresponding to the same intersection according to an embodiment of the present disclosure;

[0055] Figure 3 A schematic diagram showing a high-precision path corresponding to a target intersection in high-precision road network data and isolated vertices in a high-precision road topology directed graph according to an embodiment of the present disclosure;

[0056] Figure 4 A schematic diagram showing a precise path corresponding to a target intersection in precise road network data and isolated vertices in a precise road topology directed graph according to an embodiment of the present disclosure;

[0057] Figure 5 A schematic diagram showing the application of fused data of high-precision road network data and standard-precision road network data on an autonomous driving vehicle according to one embodiment of the present disclosure;

[0058] Figure 6 A structural block diagram of a road data fusion device according to an embodiment of the present disclosure is shown;

[0059] Figure 7 It is a structural diagram of an electronic device suitable for implementing the road data fusion method, vehicle automatic driving method and / or location-based service provision method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0060] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts not related to the description of the exemplary embodiments are omitted in the accompanying drawings.

[0061] In the present disclosure, it should be understood that terms such as "include" or "have" are intended to indicate the presence of features, numbers, steps, behaviors, components, parts, or a combination thereof disclosed in the specification, and do not exclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or a combination thereof exist or are added.

[0062] It should also be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0063] The details of the embodiments of the present disclosure are described in detail below through specific examples.

[0064] Figure 1 A flow chart of a road data fusion method according to an embodiment of the present disclosure is shown. Figure 1 As shown, the road data fusion method includes the following steps:

[0065] In step S101, the physical layer data of the road is obtained; the physical layer data of the road includes a first mapping relationship between the actual road data and the high-precision road network data and a second mapping relationship between the actual road data and the standard-precision road network data;

[0066] In step S102, a matching relationship between the high-precision road network data and the standard-precision road network data is determined based on the first mapping relationship and the second mapping relationship; the matching relationship includes a path correspondence relationship between the high-precision road network data and the standard-precision road network data;

[0067] In step S103, the high-precision road network data and the standard-precision road network data are fused based on the matching relationship.

[0068] In this embodiment, the road data fusion method can be executed on a server. The server determines the matching relationship between the high-precision road network data in the high-precision map and the standard-precision road network data in the standard-precision map, and fuses the high-precision road network data and the standard-precision road network data based on the matching relationship.

[0069] High-Definition Map (HD Map) can have accurate vehicle location information and rich road element data information. It can assist autonomous driving equipment in predicting complex road information, slope, curvature, heading, etc., and can better avoid potential risks. It is the key to realizing autonomous driving.

[0070] Street Directory Map (SD Map) is the abbreviation of traditional navigation electronic map. It is a map that is stored and viewed digitally using computer technology. It indirectly serves users for retrieval, positioning, route planning and navigation through mobile terminals such as cars and mobile phones.

[0071] High-precision maps include high-precision road network data, and standard-precision maps include standard-precision road network data. Standard-precision road network data can be the road network data with lower precision that is usually used by the navigation system during the navigation process. That is, in the traditional navigation guidance process, the road information displayed on the navigation page is basically based on standard-precision road network data. Compared with standard-precision road network data, high-precision road network data has higher precision and more detailed expression of land features. High-precision road network data not only has high-precision coordinates, but also includes accurate lane shapes, and also includes more detailed data such as the slope, curvature, heading, elevation, roll, etc. of each lane.

[0072] Since high-precision road network data contains a lot of information, data collection is difficult, and it occupies a lot of storage space and bandwidth resources during transmission. Therefore, in general, the navigation system uses standard precision road network data to establish a map model, and provides navigation guidance based on the map model established with the standard precision road network data.

[0073] In the autonomous driving system or other systems with high requirements for map accuracy, it is necessary to rely on high-precision road network data for the control and guidance of autonomous driving. Therefore, the traditional map-precision road network data and high-precision road network data can be fused and used.

[0074] In the disclosed embodiment, in order to increase the stability of the fusion of the standard precise road network data and the high-precision road network data and reduce the maintenance cost, the road physical layer data is abstracted between the standard precise road network data and the high-precision road network data. The road physical layer data includes a first mapping relationship between the actual road in reality and the high-precision road network data, and a second mapping relationship between the actual road and the standard precise road network data. For example, the first mapping relationship may include a mapping relationship between the intersection mark in the actual road and the intersection mark in the high-precision road network data, a mapping relationship between the road mark in the actual road and the road mark in the high-precision road network data, etc.; the second mapping relationship may include a mapping relationship between the intersection mark in the actual road and the intersection mark in the standard precise road network data, and a mapping relationship between the road mark in the actual road and the road mark in the standard precise road network data.

[0075] Figure 2 A schematic diagram showing the corresponding relationship between high-precision road network data, standard-precision road network data, and road physical layer data corresponding to the same intersection according to an embodiment of the present disclosure. Figure 2 As shown, SD data represents the display effect diagram of the intersection in the standard precision road network data, the physical layer represents the display effect diagram of the intersection in the road physical layer data, and HD data represents the display effect diagram of the intersection in the high precision road network data. The first mapping relationship between the high precision road network data and the actual road data is shown in the HD LaneGroup and physical association table, and the second mapping relationship between the standard precision road network data and the actual road data is shown in the SD Road and physical association table. EL1-EL10 represent the various physical roads involved in the physical intersection EI1, S1-S8 represent the standard precision roads corresponding to the physical roads EL1-EL10, SC1 represents the standard precision intersection corresponding to the physical intersection EI1, H1-H7 represent the high precision roads corresponding to the physical roads EL1-EL10, and H12, H18, H34, H36, H38, H52, H54, H56, H72, H74, and H78 represent the roads within the high precision intersection corresponding to the physical intersection EI1.

[0076] In the disclosed embodiment, the physical layer data of the road is always consistent with the actual road. When the number of intersections in reality increases or decreases, the number of road sections increases or decreases, or the road geometry changes significantly (such as diversion), the physical layer data of the road will be updated. The physical layer data of the road is globally unique, stable, and can be inherited across versions.

[0077] When integrating high-precision road network data and standard-precision road network data, the road physical layer data can be used as an intermediary. In the data maintenance stage, the road physical layer data can be maintained based only on the actual intersection data, and the first mapping relationship between the high-precision road network data and the actual road data and the second mapping relationship between the standard-precision road network data and the actual road data can be maintained. Since the road physical layer data only gives the corresponding relationship between intersections and roads, the maintenance cost is lower and the stability is higher.

[0078] In the data fusion stage, the matching relationship between the high-precision road network data and the standard-precision road network data corresponding to the same intersection can be calculated based on the first mapping relationship and the second mapping relationship maintained in the road physical layer data. The matching relationship may include but is not limited to the interval correspondence and path correspondence between the roads in the intersection. It should be noted that the interval correspondence represents the correspondence between the interval high-precision roads and the standard-precision roads within the range of the intersection, and the path correspondence represents the correspondence between all or part of the paths involving the intersection in the high-precision road network data and all or part of the paths involving the intersection in the standard-precision road network data.

[0079] After determining the matching relationship between the high-precision road network data and the standard-precision road network data, the high-precision road network data and the standard-precision road network data can be merged based on the matching relationship. For example, for the same intersection, the path in the high-precision road network data can be mounted to the path in the standard-precision road network data. In actual use, the path can be calculated based on the standard-precision road network data, and then the mounted high-precision road network data can be used based on the path.

[0080] When the high-precision road network data and the standard-precision road network data are merged, the disclosed embodiment pre-abstracts a road physical layer that describes the actual road data, the first mapping relationship between the actual road data and the high-precision road network data, and the second mapping relationship between the actual road data and the standard-precision road network data. When the fusion is performed, the matching relationship between the high-precision road network data and the standard-precision road network data is determined based on the first mapping relationship and the second mapping relationship, and then the fusion is performed based on the matching relationship. The above technical solution, because the mapping relationship between the high-precision road network data and the standard-precision road network data is maintained respectively through the road physical layer data, when the actual road is updated, only the road physical layer data and the mapping relationship between the road physical layer data and the high-precision road network data and the standard-precision road network data can be updated, and the high-precision road network data and the standard-precision road network data can be merged based on the updated mapping relationship before actual use, without the need to re-produce the high-precision road network data and the standard-precision road network data, and has high stability and low maintenance cost.

[0081] In an optional implementation of this embodiment, the first mapping relationship includes a mapping relationship between actual roads and high-precision roads, and a mapping relationship between actual intersections and roads within high-precision intersections; and / or, the second mapping relationship includes a mapping relationship between actual roads and standard-precision roads, and a mapping relationship between actual intersections and standard-precision intersections.

[0082] In this optional implementation, if Figure 2 As shown in the figure, the physical layer data of roads divides the actual roads into actual intersections and actual roads connected to the actual intersections; while the roads in the high-precision road network data are described as high-precision roads (such as Figure 2 H1-H7 in ), the intersection is described as a high-precision intersection road (such as Figure 2 H12, H18, H34, H36, H38, H52, H54, H56, H72, H74, H78 in the standard road network data, and roads in the standard road network data are described as standard roads (such as Figure 2 S1-S8 shown), the intersection is described as a marked intersection (such as Figure 2 S1) and the roads within the marked intersection (such as Figure 2Therefore, when maintaining the physical layer data of the road, the first mapping relationship established includes the mapping relationship between the actual road and the high-precision road, and the mapping relationship between the actual intersection and the road in the high-precision intersection, and the second mapping relationship includes the mapping relationship between the actual road and the standard-precision road, and the mapping relationship between the actual intersection and the standard-precision intersection.

[0083] In an optional implementation of this embodiment, step S102, i.e., the step of determining the matching relationship between the high-precision road network data and the standard-precision road network data based on the first mapping relationship and the second mapping relationship, further includes the following steps:

[0084] Determine the target high-precision data and target standard-precision data corresponding to the target intersection in the high-precision road network data based on the first mapping relationship and the second mapping relationship;

[0085] Determine a target high-precision path corresponding to the target intersection based on the target high-precision data;

[0086] Determine a target marked precise path corresponding to the target intersection based on the target marked precise data;

[0087] A matching relationship between the target high-precision path and the target standard-precision path is determined.

[0088] In this optional implementation, considering that path calculation and the like are all performed on the basis of the standard precision road network data, the high-precision road network data can be fused by mounting it on the standard precision road network data. During the fusion process, the high-precision road network data can be grouped according to the actual intersections, and each group only includes high-precision data corresponding to an actual intersection. In this embodiment, for the convenience of description, the actual intersection currently targeted can be referred to as the target intersection, and the group in the high-precision road network data corresponding to the target intersection can be referred to as the target high-precision data, and the target standard precision data is the standard precision road network data corresponding to the target intersection.

[0089] Based on the target high-precision data corresponding to the target intersection, all or part of the target high-precision path passing through the target intersection can be determined, and based on the target standard-precision data corresponding to the target intersection, all or part of the standard-precision path passing through the target intersection can be determined, and then the matching relationship between the target high-precision path and the target standard-precision path can be determined.

[0090] In an optional implementation of this embodiment, the step of determining the target high-precision data and the target standard-precision data corresponding to the target intersection in the high-precision road network data based on the first mapping relationship and the second mapping relationship further includes the following steps:

[0091] The high-precision road network data is grouped according to intersections based on the first mapping relationship, each group including target high-precision data corresponding to a target intersection;

[0092] Determine, based on the second mapping relationship, a marked precise intersection corresponding to the target intersection in the marked precise road network data;

[0093] The target precise data corresponding to the precise intersection is extracted from the precise road network data.

[0094] In this optional implementation, as described above, the high-precision road network data that needs to be fused includes multiple intersections. In order to facilitate fusion, the disclosed embodiment can perform data fusion for each actual intersection separately. Therefore, the high-precision road network data can be grouped according to the actual intersections, and each group includes the target high-precision data corresponding to the target intersection, and the target intersection can be an actual intersection. Based on the first mapping relationship, the road in the high-precision intersection corresponding to the target intersection and the high-precision road involved in the target intersection can be determined, and then the high-precision data involved in the road in the high-precision intersection and the high-precision road are extracted from the high-precision road network data. Therefore, the target high-precision data corresponding to a target intersection may include but are not limited to the high-precision data involved in the road in the high-precision intersection corresponding to the target intersection and the high-precision road involved in the target intersection.

[0095] Based on the grouping data of the high-precision road network data, the identifier of the actual intersection having a mapping relationship with the target intersection corresponding to each group of data can be determined based on the first mapping relationship, and then the standard precise intersection in the standard precise road network data corresponding to the actual intersection can be determined based on the second mapping relationship, and the target standard precise data corresponding to the standard precise intersection can be extracted from the standard precise road network data based on the identifier of the standard precise intersection. The target standard precise data may include but is not limited to the standard precise data involved in the standard precise intersection and the standard precise road associated with the standard precise intersection.

[0096] Based on the above method, the target high-precision data and target standard-precision data corresponding to the same target intersection can be obtained.

[0097] The high-precision road network data can be grouped in the following ways:

[0098] Based on the first mapping relationship, a high-precision intersection mark corresponding to the actual intersection is determined, and based on the high-precision intersection mark, corresponding target high-precision data is extracted. The target high-precision data may include but is not limited to the following data:

[0099] Data related to high-precision intersections include geometric features of the intersection surface (size, shape, etc.) and high-precision road signs within the intersection. Figure 2 The polygon in the black dashed box in the HD data is the intersection surface geometry data, and the polygon is the high-precision road in the intersection;

[0100] Data related to high-precision roads (roads within high-precision intersections and high-precision roads connected to them), including basic attributes of high-precision roads (such as length, direction of travel, road grade, etc.), geometric features, road surface, front and rear connection relationships, etc. Figure 2 Gray lines marked with white driving arrows in the HD data are high-precision roads.

[0101] After the high-precision road network data is grouped based on the second mapping relationship, the identifier of the target intersection corresponding to each group of target high-precision data is determined, and the target standard precision data is extracted from the standard precision road network data based on the identifier of the standard precision intersection. The target standard precision data may include but is not limited to the following data:

[0102] Data related to the precise intersection, including the geometric features of the intersection, the signs of the precise roads within the intersection, etc. Figure 2 In the SD data, SC1 is the marked intersection, and S12, S34, S56, and S78 are SD roads within the intersection;

[0103] Data related to the marked roads (marked roads within the intersection and the marked roads connected to them), including basic attributes of the marked roads (length, direction of travel, road grade, etc.), geometry, etc. Figure 2 The gray lines marked with white driving arrows in the SD data are marked roads.

[0104] In an optional implementation of this embodiment, the step of determining the target high-precision path corresponding to the target intersection based on the target high-precision data further includes the following steps:

[0105] A high-precision road topology directed graph corresponding to the target intersection is established based on the target high-precision data; the vertices in the high-precision road topology directed graph include the intersection of the high-precision road associated with the target intersection and the high-precision intersection road surface corresponding to the target intersection, and other path endpoints in the high-precision path passing through the intersection, the connection lines between the vertices in the high-precision road topology directed graph include the high-precision roads in the high-precision path passing through the vertices, and the direction of the connection lines is the driving direction of the high-precision road;

[0106] Determine isolated vertices in the high-precision road topology directed graph; the isolated vertices are vertices that only correspond to entering or exiting the high-precision road;

[0107] A target high-precision path corresponding to the target intersection in the target high-precision data is determined based on the high-precision path between the isolated vertices.

[0108] In this optional implementation, for a target high-precision data corresponding to a target intersection, a target high-precision path corresponding to the target intersection can be extracted from it. The target high-precision path can be a path in the high-precision road network data prepared for the target intersection, and the target high-precision path includes the high-precision road inside the target intersection corresponding to the target intersection, the high-precision road entering the target intersection, and the high-precision road exiting the target intersection.

[0109] In order to determine all or part of the target high-precision path involved in the target intersection, in this embodiment, a high-precision road topology directed graph is established for the target high-precision data corresponding to the target intersection, wherein the vertices in the high-precision road topology directed graph include the intersection of the high-precision road associated with the target intersection and the high-precision road surface corresponding to the target intersection, as well as other endpoints of all high-precision paths passing through the intersection. It should be noted that in the high-precision road network data, a road surface is established for each road, that is, a road surface with the two road edges corresponding to the road as the left and right boundaries. Therefore, the high-precision road surface corresponding to the target intersection can be the sum of the road surfaces corresponding to the roads in the high-precision intersection corresponding to the target intersection. In other embodiments, the geometric data of the high-precision intersection road surface corresponding to the target intersection will also be directly recorded in the high-precision road network data, including location information, boundary information, shape, size and other information. See. Figure 2 The black dotted box in the high-precision intersection schematic diagram is the high-precision intersection road surface corresponding to the target intersection, and the origin above represents the point where the high-precision road associated with the target intersection intersects with the high-precision intersection road surface, that is, the vertex in the high-precision road topology directed graph to be established, and the high-precision roads connecting these vertices and the roads within the high-precision intersection are all lines in the high-precision road topology directed graph, and the driving direction is the direction of the line in the high-precision road topology directed graph.

[0110] After establishing the high-precision road topology directed graph, isolated vertices can be found from it. Isolated vertices are vertices that only correspond to entering or exiting the high-precision road.

[0111] Figure 3 A schematic diagram showing a high-precision path corresponding to a target intersection in high-precision road network data and isolated vertices in a high-precision road topology directed graph according to an embodiment of the present disclosure. Figure 3 As shown, in the path starting from any hollow circle shown in the upper, lower, left and right directions, passing through the intersection of the high-precision road at the intersection and the high-precision intersection road surface, and then to the hollow circle in the other direction as the end point, any hollow circle shown in the upper, lower, left and right directions is an isolated vertex in the established high-precision road topological directed graph, while the black solid circle on the high-precision intersection road surface is not an isolated vertex.

[0112] For all isolated vertices in the high-precision road topology directed graph, all navigable simple paths between all isolated vertices are calculated. A simple path can be understood as a path in which the same vertex does not appear repeatedly.

[0113] After determining the navigable simple paths between all isolated vertices, invalid paths (such as prohibited paths, etc.) can be removed. For paths with the same starting point and the same end point, if there are multiple paths, the shortest path is retained, that is, the path with the least number of roads. If the path with the least number of roads includes multiple paths, they can all be retained.

[0114] The path finally retained is the target high-precision path corresponding to the determined target intersection.

[0115] In an optional implementation of this embodiment, the step of determining the target high-precision path corresponding to the target intersection based on the target high-precision data further includes the following steps:

[0116] A directed graph of a topological precision road corresponding to the target intersection is established based on the target precision data; vertices in the directed graph of the topological precision road include intersections between precision roads associated with the target intersection, and other path endpoints in a precision path passing through the intersections; lines between vertices in the directed graph of the topological precision road include precision paths in the precision path passing through the vertices; and directions of the lines are driving directions of the precision roads;

[0117] Determine an isolated vertex in the topological directed graph of the marked refined road; the isolated vertex is a vertex that only corresponds to the marked refined road with entry or exit;

[0118] The target precise path corresponding to the target intersection in the target precise data is determined based on the precise path between the isolated vertices.

[0119] In this optional implementation, for a target precise data corresponding to a target intersection, a target precise path corresponding to the target intersection can be extracted therefrom. The target precise path can be a path in the precise road network data prepared for the target intersection, and the target precise path includes the precise intersection corresponding to the target intersection, the precise road entering the precise intersection, and the precise road exiting the precise intersection.

[0120] In order to determine all or part of the target precise path involved in the target intersection, in this embodiment, a precise road topology directed graph is established for the target precise data corresponding to the target intersection, wherein the vertices in the precise road topology directed graph include the intersection between the precise roads associated with the target intersection, and other path endpoints on the precise path passing through the intersection. Figure 2The points in the standard precise road intersection diagram are the intersection points between the standard precise roads, that is, the vertices in the standard precise road topological directed graph to be established, and the other path endpoints on the standard precise path where the vertex is located are also vertices in the standard precise road topological directed graph. The standard precise roads connecting these vertices and the roads in the standard precise intersection are all connecting lines in the standard precise road topological directed graph, and the driving direction is the direction of the connecting line in the standard precise road topological directed graph.

[0121] After establishing the topological directed graph of the standard refined road, isolated vertices can be found from it. Isolated vertices are vertices that only correspond to entering or exiting the standard refined road.

[0122] Figure 4 A schematic diagram showing a precise path corresponding to a target intersection in the precise road network data and isolated vertices in a precise road topology directed graph according to an embodiment of the present disclosure is shown. Figure 4 As shown, in the path starting from any hollow circle shown in the upper, lower, left and right directions, passing through the intersection of the marked road at the intersection and the marked intersection road surface (shown by the square black solid dot), and then to the hollow circle in the other direction as the end point, any hollow circle shown in the upper, lower, left and right directions is an isolated vertex in the established marked road topological directed graph, while the black solid circle on the marked intersection road surface is not an isolated vertex.

[0123] For all isolated vertices in the directed graph with the marked road topology, all navigable simple paths between all isolated vertices are calculated. A simple path can be understood as a path in which the same vertex does not appear repeatedly.

[0124] In addition, since the marked roads in the marked road network data are represented by a road line, there is also a special case, that is, the road that can only make a U-turn at the end of the road is represented as a two-way road. Therefore, if an isolated vertex is only connected to two-way roads, the U-turn path can be calculated separately for the isolated vertex.

[0125] The simple path and the U-turn path finally obtained are the target precise paths corresponding to the determined target intersection.

[0126] In an optional implementation of this embodiment, the step of determining the matching relationship between the target high-precision path and the target standard-precision path further includes the following steps:

[0127] Determine, in the target high-precision path, a first actual road corresponding to the last high-precision road entering the target intersection and a second actual road corresponding to the first high-precision road exiting the target intersection;

[0128] Determine, in the target precise path, a third actual road corresponding to the last precise road entering the target intersection and a fourth actual road corresponding to the first precise road exiting the target intersection;

[0129] When the first actual road includes the third actual road and the second actual road includes the fourth actual road, it is determined that the target high-precision path matches the target standard-precision path.

[0130] In this optional implementation, after the high-precision road network data is grouped according to intersections, a target high-precision path is extracted for the target intersection included in each group, and a target standard precision path corresponding to the same target intersection is extracted from the standard precision road network data.

[0131] When matching the target high-precision path with the target standard-precision path, the matching can be performed based on whether it is a U-turn path. For non-U-turn paths, all non-U-turn paths in the target high-precision path corresponding to the target intersection can be matched with all non-U-turn paths in the target standard-precision path corresponding to the target intersection, and for U-turn paths, the U-turn paths in the target high-precision path corresponding to the target intersection can be matched with the U-turn paths in the target standard-precision path.

[0132] In some embodiments, when determining whether the target high-precision path matches the target standard precision path, the first actual road corresponding to the last high-precision road entering the target intersection in the target high-precision path and the second actual road corresponding to the first high-precision road exiting the target intersection can be determined. The third actual road corresponding to the last standard precision road entering the target intersection in the target standard precision path and the fourth actual road corresponding to the first standard precision road exiting the target intersection can also be determined.

[0133] Considering that the first actual road and the second actual road may include multiple high-precision roads in the high-precision road network data, it is possible to determine whether the target high-precision path to be matched and the target standard-precision path match by determining whether the first actual road contains the third actual road and whether the second actual road contains the fourth actual road. If the first actual road contains the third actual road and the second actual road contains the fourth actual road, the target high-precision path to be matched and the target standard-precision path match; otherwise, if the first actual road does not contain the third actual road or the second actual road does not contain the fourth actual road, the target high-precision road to be matched and the target standard-precision road do not match.

[0134] See also Figure 2, the target standard precision path "S7-S78-S12-S2" in the SD data (also known as standard precision data), the last road entering the target intersection in this path is S7, and the first road exiting the target intersection is S2, while the target high precision path "H7-H72-H2" in the HD data (also known as high precision data), the last road entering the target intersection in this path is H7, and the first road exiting the target intersection is H2, the actual road associated with H7 is EL10, which is the same as the actual road associated with S7, and the actual road associated with H2 is EL1, which is the same as the actual road associated with S2. Therefore, it can be considered that the target standard precision path "S7-S78-S12-S2" and the target high precision path "H7-H72-H2" match successfully.

[0135] In an optional implementation of this embodiment, step S103, i.e., the step of fusing the high-precision road network data and the standard-precision road network data based on the matching relationship, further includes the following steps:

[0136] For the matched target high-precision path and target standard precision path, if the standard precision road in the target standard precision path is a standard precision road in an intersection, all the high-precision roads in the intersection in the matched target high-precision path are attached to the standard precision road in the intersection;

[0137] If the precision road in the target precision path is a precision road not in an intersection, the precision road not in an intersection is divided into a divided road section using the high-precision intersection road surface of the target intersection, and all the high-precision roads in intersections in the target high-precision path are attached to the divided road section obtained by the division.

[0138] In this optional implementation method, after finding the matching target high-precision path and target standard precision path based on the target high-precision data and target standard precision data corresponding to the target intersection, the target high-precision data and target standard precision data can be fused by mounting the target high-precision path to the matching target standard precision path.

[0139] In some embodiments, the non-intersection marked precise roads and the intersection marked precise roads in the target marked precise path can be processed separately. For the intersection marked precise roads, the intersection marked precise roads in the matching target high-precision path can be directly mounted on the intersection marked precise roads, and for the non-intersection marked precise roads, the high-precision intersection road surface of the target intersection in the high-precision data is used to segment the non-intersection marked precise roads, and after obtaining the segmented road interval, all the intersection marked precise roads in the target high-precision path are mounted to the segmented road interval obtained by the segmentation.

[0140] As described above, the high-precision intersection road surface can be pre-defined in the high-precision road network data, and can also be obtained based on the road surface combination of the roads in each intersection corresponding to the target intersection.

[0141] Refer to the following Figure 2 Detailed description:

[0142] If the marked precision road is a road within an intersection, all the roads within the intersection in the high-precision path are attached to the marked precision road. Figure 2 As shown, S78 and S12 both correspond to H72, and H72 is mounted on S78 and S12.

[0143] If the standard precision road is not a standard precision road in the intersection, the geometric relationship between the high-precision intersection road surface and the standard precision road is calculated, and the high-precision intersection road surface geometry is used to segment the high-precision road, and all high-precision roads in the intersection in the high-precision path are attached to the segmented standard precision road interval. Figure 2 As shown, the high-precision intersection road surface is used to divide S7 and S2, and H72 is attached to the parts of S7 and S2 in the high-precision intersection road surface.

[0144] If it is a U-turn intersection, only the U-turn path is matched. The high-precision path includes the U-turn road (the road includes the U-turn lane), and the standard-precision path includes the U-turn dedicated road. The path matching is the same as above. After the match is successful, the path matching relationship is output, and the U-turn road in the high-precision path is attached to the U-turn road in the standard-precision path.

[0145] According to an automatic driving method for a vehicle in one embodiment of the present disclosure, the automatic driving method for the vehicle controls the automatic driving process of the vehicle by utilizing the fusion data of the high-precision road network data and the standard-precision road network data obtained by the above-mentioned road data fusion method.

[0146] In this embodiment, the vehicle automatic driving method can be executed on the on-board device of the automatic driving vehicle. The on-board device can receive the fusion data of the high-precision road network data and the standard-precision road network data from the server, and control the automatic driving process of the automatic driving vehicle on the road based on the fusion data. For example, the driving action in the current driving process can be generated based on the fusion data, and then the automatic driving vehicle can be controlled to perform the driving action. The specific details of the fusion of high-precision road network data and standard-precision road network data can be found in the above description of the road data fusion method, which will not be repeated here.

[0147] According to a location-based service providing method in one embodiment of the present disclosure, the location-based service providing method utilizes the fusion data of high-precision road network data and standard-precision road network data obtained by the above-mentioned road data fusion method to provide location-based services to the service object, and the location-based services include: navigation, map rendering, route planning or one or more thereof.

[0148] In this embodiment, the location-based service providing method can be executed on a location service terminal, which can be a mobile phone, iPad, computer, smart watch, vehicle-mounted device, etc. In the disclosed embodiment, the precise road network data can be used for path planning, and then based on the fusion data of the high-precision road network data and the precise road network data, location-based services can be provided to the service object.

[0149] The service object may be a mobile phone, iPad, computer, smart watch, vehicle, robot, etc. The server may obtain the fusion data of high-precision road network data and standard-precision road network data based on the above method, and plan the navigation path based on the request of the location service terminal, and then provide the navigation path and fusion data to the location service terminal. The location service terminal may navigate, plan the path or render the map for the service object based on the navigation path and fusion data. For details, please refer to the above description of the road data fusion method, which will not be repeated here.

[0150] Figure 5 FIG. 1 is a schematic diagram showing the application of the fusion data of high-precision road network data and standard-precision road network data on an autonomous driving vehicle according to an embodiment of the present disclosure. Figure 5 As shown, the server can maintain high-precision road network data, standard-precision road network data, and road physical layer data. As described above, after the high-precision road network data and standard-precision road network data are produced, the mapping relationship between each intersection and the associated roads in reality and the high-precision road network data and standard-precision road network data can be recorded in the road physical layer data. After the actual intersection and the associated road change, only the road physical layer data can be updated without updating the high-precision road network data and standard-precision road network data.

[0151] Before use, the data fusion server can match the high-precision road network data with the standard-precision road network data based on the mapping relationship recorded in the road physical layer data, and mount the successfully matched high-precision path on the standard-precision path to obtain the fusion data of the high-precision road network data and the standard-precision road network data. The data fusion server can provide the fusion data to the navigation server.

[0152] During the autonomous driving process of the autonomous driving vehicle, the navigation server can provide the fused data to the on-board equipment of the autonomous driving vehicle. The on-board equipment generates autonomous driving instructions for the vehicle based on the fused data to control the autonomous driving vehicle to perform corresponding driving actions during driving.

[0153] The following are embodiments of the apparatus of the present disclosure, which can be used to execute embodiments of the method of the present disclosure.

[0154] Figure 6FIG. 1 is a block diagram showing a road data fusion device according to an embodiment of the present disclosure. The device can be implemented as part or all of an electronic device through software, hardware, or a combination of both. Figure 6 As shown, the road data fusion device includes:

[0155] The acquisition module 601 is configured to acquire road physical layer data; the road physical layer data includes a first mapping relationship between actual road data and high-precision road network data and a second mapping relationship between actual road data and standard-precision road network data;

[0156] The determination module 602 is configured to determine a matching relationship between the high-precision road network data and the standard-precision road network data based on the first mapping relationship and the second mapping relationship; the matching relationship includes an interval correspondence relationship and a path correspondence relationship between roads in the intersection;

[0157] The fusion module 603 is configured to fuse the high-precision road network data and the standard-precision road network data based on the matching relationship.

[0158] In an optional implementation of this embodiment, the first mapping relationship includes a mapping relationship between an actual intersection and a high-precision intersection, and a mapping relationship between roads within an actual intersection and roads within a high-precision intersection; and / or, the second mapping relationship includes a mapping relationship between an actual intersection and a standard-precision intersection, and a mapping relationship between roads within an actual intersection and roads within a standard-precision intersection.

[0159] In an optional implementation of this embodiment, the determining module includes:

[0160] A first determining submodule is configured to determine target high-precision data and target standard-precision data corresponding to a target intersection in the high-precision road network data based on the first mapping relationship and the second mapping relationship;

[0161] A second determination submodule is configured to determine a target high-precision path corresponding to the target intersection based on the target high-precision data;

[0162] A third determination submodule is configured to determine a target mark precise path corresponding to the target intersection based on the target mark precise data;

[0163] The fourth determination submodule is configured to determine a matching relationship between the target high-precision path and the target standard-precision path.

[0164] In an optional implementation of this embodiment, the first determining submodule includes:

[0165] A grouping submodule is configured to group the high-precision road network data according to intersections based on the first mapping relationship, each group including target high-precision data corresponding to a target intersection;

[0166] A fifth determining submodule is configured to determine, based on the second mapping relationship, a marked precise intersection corresponding to the target intersection in the marked precise road network data;

[0167] The extraction submodule is configured to extract the target precise data corresponding to the precise intersection from the precise road network data.

[0168] In an optional implementation of this embodiment, the second determining submodule further includes:

[0169] The first establishment submodule is configured to establish a high-precision road topology directed graph corresponding to the target intersection based on the target high-precision data; the vertices in the high-precision road topology directed graph include the intersection of the high-precision road associated with the target intersection and the high-precision intersection road surface corresponding to the target intersection, and other path endpoints in the high-precision path passing through the intersection, the connection lines between the vertices in the high-precision road topology directed graph include the high-precision roads in the high-precision path passing through the vertices, and the direction of the connection lines is the driving direction of the high-precision road;

[0170] A sixth determination submodule is configured to determine isolated vertices in the high-precision road topology directed graph; the isolated vertices are vertices that only correspond to entering or exiting the high-precision road;

[0171] The seventh determination submodule is configured to determine a target high-precision path corresponding to the target intersection in the target high-precision data based on the high-precision path between the isolated vertices.

[0172] In an optional implementation of this embodiment, the third determining submodule includes:

[0173] The second establishment submodule is configured to establish a directed graph of a topology of a precision road corresponding to the target intersection based on the target precision data; the vertices in the directed graph of the precision road topology include intersections between precision roads associated with the target intersection, and other path endpoints in a precision path passing through the intersections; the lines between the vertices in the directed graph of the precision road topology include precision paths in the precision path passing through the vertices; and the direction of the lines is the driving direction of the precision road;

[0174] An eighth determination submodule is configured to determine isolated vertices in the marked refined road topology directed graph; the isolated vertices are vertices corresponding only to marked refined roads with entry or exit;

[0175] The ninth determination submodule is configured to determine a target precise path corresponding to the target intersection in the target precise data based on the precise path between the isolated vertices.

[0176] In an optional implementation of this embodiment, the fourth determining submodule includes:

[0177] a tenth determination submodule, configured to determine, in the target high-precision path, a first actual road corresponding to the last high-precision road entering the target intersection and a second actual road corresponding to the first high-precision road exiting the target intersection;

[0178] An eleventh determination submodule is configured to determine, in the target precise path, a third actual road corresponding to the last precise road entering the target intersection and a fourth actual road corresponding to the first precise road exiting the target intersection;

[0179] The twelfth determination submodule is configured to determine that the target high-precision path matches the target standard-precision path when the first actual road includes the third actual road and the second actual road includes the fourth actual road.

[0180] In an optional implementation of this embodiment, the fusion module includes:

[0181] The first mounting submodule is configured to mount all the high-precision roads in the matched target high-precision path to the marked precision road in the intersection if the marked precision road in the target marked precision path is a marked precision road in the intersection;

[0182] The second mounting submodule is configured to, if the precision road in the target precision path is a precision road outside the intersection, use the high-precision intersection road surface of the target intersection to divide the precision road outside the intersection to obtain a divided road section, and mount all the high-precision roads inside the intersection in the target high-precision path to the divided road section obtained by dividing.

[0183] The road data fusion device in this embodiment corresponds to the road data fusion method described above. For specific details, please refer to the description of the road data fusion method described above, which will not be repeated here.

[0184] According to an embodiment of the vehicle automatic driving device of the present disclosure, the device can be implemented as part or all of an electronic device through software, hardware or a combination of both. The vehicle automatic driving device uses the fusion data of the high-precision road network data and the standard-precision road network data obtained by the above-mentioned road data fusion device to control the automatic driving process of the vehicle.

[0185] The vehicle automatic driving device in this embodiment corresponds to the vehicle automatic driving fusion method mentioned above. For specific details, please refer to the description of the vehicle automatic driving method above, which will not be repeated here.

[0186] According to a location-based service providing device in one embodiment of the present disclosure, the device utilizes the fusion data of high-precision road network data and standard-precision road network data obtained by the above-mentioned location-based service providing device to provide location-based services to the service objects, and the location-based services include: navigation, map rendering, route planning or one or more thereof.

[0187] The location-based service providing device in this embodiment corresponds to the location-based service providing method described above. For specific details, please refer to the description of the location-based service providing method described above, which will not be repeated here.

[0188] Figure 7 It is a structural diagram of an electronic device suitable for implementing the road data fusion method, vehicle automatic driving method and / or location-based service provision method according to an embodiment of the present disclosure.

[0189] like Figure 7 As shown, the electronic device 700 includes a processing unit 701, which can be implemented as a processing unit such as a CPU, a GPU, an FPGA, and an NPU. The processing unit 701 can perform various processes in the embodiments of any of the above methods of the present disclosure according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 are also stored. The processing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0190] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0191] In particular, according to an embodiment of the present disclosure, any method in the above referenced embodiment of the present disclosure may be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes a program code for executing any method in the embodiment of the present disclosure. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 709, and / or installed from a removable medium 711.

[0192] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the road map or block diagram can represent a part of a module, program segment or code, and the part of the module, program segment or code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a different order from the order marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0193] The units or modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The units or modules described may also be set in a processor, and the names of these units or modules do not constitute limitations on the units or modules themselves in some cases.

[0194] As another aspect, the present disclosure further provides a computer-readable storage medium, which may be a computer-readable storage medium included in the device described in the above embodiment; or a computer-readable storage medium that exists independently and is not assembled into the device. The computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the method described in the present disclosure.

[0195] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present disclosure is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other.

Claims

1. A road data fusion method, in, include: Obtain road physical layer data; The road physical layer data includes a first mapping relationship between actual road data and high-precision road network data and a second mapping relationship between actual road data and standard-precision road network data; Determine a matching relationship between the high-precision road network data and the standard-precision road network data based on the first mapping relationship and the second mapping relationship; the matching relationship includes a path correspondence relationship between the high-precision road network data and the standard-precision road network data; Based on the matching relationship, the high-precision road network data and the standard-precision road network data are merged; Among them, the first mapping relationship includes the mapping relationship between the actual road and the high-precision road, and the mapping relationship between the actual intersection and the road within the high-precision intersection; and / or, the second mapping relationship includes the mapping relationship between the actual road and the standard-precision road, and the mapping relationship between the actual intersection and the standard-precision intersection.

2. The method according to claim 1, in, Determining a matching relationship between high-precision road network data and standard-precision road network data based on the first mapping relationship and the second mapping relationship includes: Determine the target high-precision data and target standard-precision data corresponding to the target intersection in the high-precision road network data based on the first mapping relationship and the second mapping relationship; Determine a target high-precision path corresponding to the target intersection based on the target high-precision data; Determine a target marked precise path corresponding to the target intersection based on the target marked precise data; A matching relationship between the target high-precision path and the target standard-precision path is determined.

3. The method according to claim 2, in, Determining target high-precision data and target standard-precision data corresponding to a target intersection in the high-precision road network data based on the first mapping relationship and the second mapping relationship includes: The high-precision road network data is grouped according to intersections based on the first mapping relationship, each group including target high-precision data corresponding to a target intersection; Determine, based on the second mapping relationship, a marked precise intersection corresponding to the target intersection in the marked precise road network data; The target precise data corresponding to the precise intersection is extracted from the precise road network data.

4. The method according to claim 2 or 3, in, Determining a target high-precision path corresponding to the target intersection based on the target high-precision data also includes: A high-precision road topology directed graph corresponding to the target intersection is established based on the target high-precision data; the vertices in the high-precision road topology directed graph include the intersection of the high-precision road associated with the target intersection and the high-precision intersection road surface corresponding to the target intersection, and other path endpoints in the high-precision path passing through the intersection, the connection lines between the vertices in the high-precision road topology directed graph include the high-precision roads in the high-precision path passing through the vertices, and the direction of the connection lines is the driving direction of the high-precision road; Determine isolated vertices in the high-precision road topology directed graph; the isolated vertices are vertices that only correspond to entering or exiting the high-precision road; A target high-precision path corresponding to the target intersection in the target high-precision data is determined based on the high-precision path between the isolated vertices.

5. The method according to claim 2 or 3, in, Determining a target marked precise path corresponding to the target intersection based on the target marked precise data includes: A directed graph of a topological precision road corresponding to the target intersection is established based on the target precision data; vertices in the directed graph of the topological precision road include intersections between precision roads associated with the target intersection, and other path endpoints in a precision path passing through the intersections; lines between vertices in the directed graph of the topological precision road include precision paths in the precision path passing through the vertices; and directions of the lines are driving directions of the precision roads; Determine an isolated vertex in the topological directed graph of the marked refined road; the isolated vertex is a vertex that only corresponds to the marked refined road with entry or exit; The target precise path corresponding to the target intersection in the target precise data is determined based on the precise path between the isolated vertices.

6. The method according to claim 2 or 3, in, Determining a matching relationship between the target high-precision path and the target standard-precision path includes: Determine, in the target high-precision path, a first actual road corresponding to the last high-precision road entering the target intersection and a second actual road corresponding to the first high-precision road exiting the target intersection; Determine, in the target precise path, a third actual road corresponding to the last precise road entering the target intersection and a fourth actual road corresponding to the first precise road exiting the target intersection; When the first actual road includes the third actual road and the second actual road includes the fourth actual road, it is determined that the target high-precision path matches the target standard-precision path.

7. The method according to claim 2 or 3, in, Based on the matching relationship, the high-precision road network data and the standard-precision road network data are merged, including: For the matched target high-precision path and target standard precision path, if the standard precision road in the target standard precision path is a standard precision road in an intersection, all the high-precision roads in the intersection in the matched target high-precision path are attached to the standard precision road in the intersection; If the precision road in the target precision path is a precision road not in an intersection, the precision road not in an intersection is divided into a divided road section using the high-precision intersection road surface of the target intersection, and all the high-precision roads in intersections in the target high-precision path are attached to the divided road section obtained by the division.

8. A method for automatic driving of a vehicle, the method utilizing the fusion data of high-precision road network data and standard-precision road network data obtained by the method described in any one of claims 1 to 7 to control the automatic driving process of the vehicle.

9. A method for providing location-based services, the method using the fusion data of high-precision road network data and standard-precision road network data obtained by the method according to any one of claims 1 to 7 to provide location-based services for service objects. include: One or more of navigation, map rendering, and route planning.

Images