High-precision map verification method and device, electronic equipment and vehicle

Abstract

The invention relates to the technical field of automatic driving, in particular to a high-precision map verification method and device, electronic equipment and a vehicle. Comprising the steps of obtaining road data and road key point data; extracting first road data and second road data in the road data; dividing the first road data and the second road data into single-side first road data and single-side second road data respectively; binding the corresponding two kinds of single-sided road data to obtain target road data; determining the attribute of each road key point data in the target road data; generating each navigation path; matching the navigation path with the high-precision map data; and according to the matching result, determining whether the high-precision map data meets the automatic driving requirement of the navigation path. The method can conveniently, quickly and effectively verify whether the high-precision map matched with each navigation path is complete or not and whether the high-precision map can meet the automatic driving requirement or not, does not need to verify the automatic driving function on each road in real vehicle, and saves manpower, material resources and time cost.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and particularly to a method, device, electronic device and vehicle for verifying a high-precision map. Background Art

[0002] Autonomous driving is a technology that enables a train to achieve real-time and continuous control and two-way data communication between the vehicle and the ground through advanced communication, computer, network and control technologies. This technology can make the train operation more flexible and efficient, and can adapt to various different traffic and operation conditions. Autonomous driving technology is constantly developing and is gradually applied to fields such as urban rail transit and highway transportation. A high-precision map is a high-precision map for autonomous driving, which contains map elements such as road shapes, road markings, traffic signs and obstacles, and the map accuracy can reach the centimeter level. This kind of map can provide comprehensive and high-precision road information to help autonomous driving vehicles for driving planning and navigation. The characteristics of a high-precision map are that it needs to describe lanes, lane boundary lines, various traffic facilities and crosswalks on the road, as well as the connection relationships between roads, etc.

[0003] However, the coverage area of high-precision maps is a big problem. Currently, the navigation-assisted driving function based on high-precision maps can only be used in a few cities / roads covered by high-precision maps. Once driving into a scene without high-precision map coverage or with a difference between the high-precision map information and the actual driving scene, the assisted driving will be downgraded or exited, and only L2 is available. Even if automatic recovery can be achieved, this kind of downgrade will seriously affect the consistency and coherence of the use experience, and the worry about whether there will be route errors caused by function downgrade lingers. The main reason for the small coverage of high-precision maps is the low information collection efficiency and high difficulty of high-precision maps. On the one hand, the surveying and mapping difficulty of high-precision maps is high and the amount of information is large. According to the "White Paper on High-Precision Maps for Intelligent Connected Vehicles", using the traditional surveying vehicle method, the surveying and mapping efficiency of decimeter-level maps is about 500 kilometers per vehicle per day, and the cost is about 10 yuan per kilometer. If it rises to centimeter-level maps, the surveying and mapping efficiency can only be 100 kilometers per vehicle per day, but the surveying and mapping cost will reach 1000 yuan per kilometer. Currently, the urban road network data is huge and the road network structure is complex. If the autonomous driving function of high-precision maps is verified for each road by actual vehicles, it will be a great waste of manpower, material resources and time costs. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention provide a method, device, electronic device and vehicle for verifying a high-precision map, so as to overcome the above problems or at least partially solve the above problems.

[0005] In a first aspect, embodiments of the present invention propose a method for verifying a high-precision map, the method comprising:

[0006] Obtain road data and road key point data in the target map data;

[0007] Extract first road data and second road data from the road data according to the road level;

[0008] Divide each piece of first road data into one-sided first road data according to the traffic direction, and divide each piece of second road data into one-sided second road data;

[0009] Bind the one-sided first road data with the corresponding one-sided second road data according to the road key point data to obtain target road data;

[0010] Determine the attributes of each road key point data in the target road data according to the one-sided second road data in the target road data, where the attributes include diverging points and converging points;

[0011] Generate each navigation path according to the target road data and the attributes of each road key point data in the target road data;

[0012] Match the navigation path with the high-precision map data to obtain a matching result;

[0013] Determine whether the high-precision map data meets the autonomous driving requirements of the navigation path according to the matching result.

[0014] Optionally, the binding the one-sided first road data with the corresponding one-sided second road data according to the road key point data to obtain target road data includes:

[0015] Determine the connectivity relationship between the one-sided first road data and each one-sided second road data according to the road key point data;

[0016] Bind each one-sided second road data connected to the one-sided first road data to obtain the target road data corresponding to the one-sided first road data.

[0017] Optionally, the determining the attributes of each road key point data in the target road data according to the one-sided second road data in the target road data includes:

[0018] Determine the attributes of each road key point data corresponding to each one-sided second road data respectively according to the traffic direction of each one-sided second road data in the target road data;

[0019] When the traffic direction of the one-sided second road data corresponding to the road key point data is towards the bound one-sided first road data, determine the attribute of this road key point data as a converging point;

[0020] When the traffic direction of the second road data on one side corresponding to the road key point data is to leave the first road data on one side bound thereto, determine that the attribute of the road key point data is a split point.

[0021] Optionally, generating each navigation path according to the target road data and the attributes of each road key point data in the target road data includes:

[0022] Determine each navigation direction corresponding to each road key point data according to the attributes of each road key point data in the target road data;

[0023] Determine each navigation end point corresponding to each navigation direction according to each navigation direction and the target road data;

[0024] Generate each navigation path according to each navigation direction and each navigation end point.

[0025] Optionally, matching the navigation path with the high-precision map data to obtain a matching result includes:

[0026] Determine each navigation point in the navigation path according to the navigation path;

[0027] Match each navigation point with the high-precision map data to obtain the high-precision map data corresponding to each navigation point;

[0028] Stitch the high-precision map data corresponding to each navigation point to obtain high-precision stitched map data;

[0029] Determine the matching result of the navigation path and the high-precision map data according to the high-precision stitched map data.

[0030] Optionally, determining whether the high-precision map data meets the autonomous driving requirements of the navigation path according to the matching result includes:

[0031] When the matching result indicates that the high-precision stitched map data corresponding to the navigation path is uninterrupted, determine that the high-precision map data meets the autonomous driving requirements of the navigation path;

[0032] When the matching result indicates that the high-precision stitched map data corresponding to the navigation path has an interruption, determine that the high-precision map data does not meet the autonomous driving requirements of the navigation path.

[0033] Optionally, determining each navigation end point corresponding to each navigation direction according to each navigation direction and the target road data includes:

[0034] When the navigation direction is towards the single-sided first road data in the target road data, the endpoint where the single-sided second road data corresponding to the navigation direction in the target road data is not connected to the single-sided first road data is determined as the navigation starting point;

[0035] Determine the navigation end point according to the navigation starting point and the target road data;

[0036] When the navigation direction is away from the single-sided first road data in the target road data, the endpoint where the single-sided second road data corresponding to the navigation direction in the target road data is not connected to the single-sided first road data is determined as the navigation end point;

[0037] Determine the navigation starting point according to the navigation end point and the target road data.

[0038] In a second aspect, an embodiment of the present invention provides a high-precision map verification device, and the device includes:

[0039] A first acquisition module, configured to acquire road data and road key point data in the target map data;

[0040] A second extraction module, configured to extract first road data and second road data from the road data according to the road grade;

[0041] A third segmentation module, configured to divide each first road data into single-sided first road data and divide each second road data into single-sided second road data according to the traffic direction;

[0042] A fourth binding module, configured to bind the single-sided first road data with the corresponding single-sided second road data according to the road key point data to obtain the target road data;

[0043] A fifth determination module, configured to determine the attributes of each road key point data in the target road data according to the single-sided second road data in the target road data, and the attributes include diversion points and confluence points;

[0044] A sixth generation module, configured to generate each navigation path according to the target road data and the attributes of each road key point data in the target road data;

[0045] A seventh matching module, configured to match the navigation path with the high-precision map data to obtain a matching result;

[0046] An eighth determination module, configured to determine whether the high-precision map data meets the autonomous driving requirements of the navigation path according to the matching result.

[0047] Optionally, the fourth binding module includes:

[0048] A first binding sub-module, configured to determine the connectivity relationship between the single-sided first road data and each single-sided second road data according to the road key point data;

[0049] A second binding sub-module, configured to bind each single-sided second road data connected to the single-sided first road data to obtain the target road data corresponding to the single-sided first road data.

[0050] Optionally, the fifth determination module includes:

[0051] A first determination sub-module, configured to determine the attributes of each road key point data corresponding to each single-sided second road data according to the traffic directions of each single-sided second road data in the target road data;

[0052] A second determination sub-module, configured to determine that the attribute of the road key point data is a confluence point when the traffic direction of the single-sided second road data corresponding to the road key point data is towards the bound single-sided first road data;

[0053] A third determination sub-module, configured to determine that the attribute of the road key point data is a divergence point when the traffic direction of the single-sided second road data corresponding to the road key point data is away from the bound single-sided first road data.

[0054] Optionally, the sixth generation module includes:

[0055] A first generation sub-module, configured to determine each navigation direction corresponding to each road key point data according to the attributes of each road key point data in the target road data;

[0056] A second generation sub-module, configured to determine each navigation end point corresponding to each navigation direction according to each navigation direction and the target road data;

[0057] A third generation sub-module, configured to generate each navigation path according to each navigation direction and each navigation end point.

[0058] Optionally, the seventh matching module includes:

[0059] A first matching sub-module, configured to determine each navigation point in the navigation path according to the navigation path;

[0060] A second matching sub-module, configured to match each navigation point with the high-precision map data to obtain the high-precision map data corresponding to each navigation point;

[0061] A third matching sub-module, configured to splice the high-precision map data corresponding to each of the navigation points to obtain high-precision spliced map data;

[0062] A fourth matching sub-module, configured to determine a matching result between the navigation path and the high-precision map data according to the high-precision spliced map data.

[0063] Optionally, the eighth determination module includes:

[0064] A fourth determination sub-module, configured to determine that the high-precision map data meets the autonomous driving requirements of the navigation path when the matching result indicates that the high-precision spliced map data corresponding to the navigation path is uninterrupted;

[0065] A fifth determination sub-module, configured to determine that the high-precision map data does not meet the autonomous driving requirements of the navigation path when the matching result indicates that the high-precision spliced map data corresponding to the navigation path is interrupted.

[0066] Optionally, the second generation sub-module includes:

[0067] A first endpoint determination sub-module, configured to, when the navigation direction is towards the single-sided first road data in the target road data, determine an endpoint where the single-sided second road data corresponding to the navigation direction in the target road data is not connected to the single-sided first road data as the navigation start point;

[0068] A second endpoint determination sub-module, configured to determine a navigation end point according to the navigation start point and the target road data;

[0069] A third endpoint determination sub-module, configured to, when the navigation direction is away from the single-sided first road data in the target road data, determine an endpoint where the single-sided second road data corresponding to the navigation direction in the target road data is not connected to the single-sided first road data as the navigation end point;

[0070] A fourth endpoint determination sub-module, configured to determine a navigation start point according to the navigation end point and the target road data.

[0071] In a third aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the high-precision map verification method according to any one of the first aspects of the embodiments of the present invention is implemented.

[0072] Fourth aspect, an embodiment of the present invention provides a vehicle, which includes an autonomous driving module configured to achieve autonomous driving based on the high-precision map verified by any one of the high-precision map verification methods according to the first aspect of the embodiments of the present invention.

[0073] Advantages of the present invention:

[0074] The high-precision map verification method provided by the present invention includes: obtaining road data and road key point data in target map data; extracting first road data and second road data from the road data; classifying each first road data into single-sided first road data and each second road data into single-sided second road data; binding the single-sided first road data with the corresponding single-sided second road data to obtain target road data; determining the attributes of each road key point data in the target road data to generate each navigation path; matching the navigation path with high-precision map data to obtain a matching result; and determining whether the high-precision map data meets the autonomous driving requirements of the navigation path according to the matching result. By using the method provided by the present invention, it is convenient, fast, and effective to verify whether the high-precision map matched by each navigation path is complete and can meet the autonomous driving requirements, without the need to verify the autonomous driving function of each road by actual vehicle, which greatly saves labor, material, and time costs. Description of the Drawings

[0075] Figure 1 It is a step diagram of a high-precision map verification method proposed by an embodiment of the present invention;

[0076] Figure 2 It is a target map data diagram proposed by an embodiment of the present invention;

[0077] Figure 3 It is a road grade map data diagram proposed by an embodiment of the present invention;

[0078] Figure 4 It is a road name map data diagram proposed by an embodiment of the present invention;

[0079] Figure 5 It is a road key point data diagram proposed by an embodiment of the present invention;

[0080] Figure 6 It is a navigation path diagram proposed by an embodiment of the present invention;

[0081] Figure 7 It is a module block diagram of a high-precision map verification device proposed by an embodiment of the present invention. Detailed Embodiments

[0082] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand the other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for explaining the present invention and not for limiting the protection scope of the present invention.

[0083] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the components related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and proportion of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0084] In a first aspect, an embodiment of the present invention proposes a high-precision map verification method, as Figure 1 shown, Figure 1 is a step diagram of a high-precision map verification method proposed in an embodiment of the present invention. The method includes the following steps:

[0085] Step S101: Obtain road data and road key point data in the target map data.

[0086] In this embodiment, it is necessary to obtain the map data for verifying the availability of the high-precision map as the target map data. The map data can be OSM map data or some other map data, such as Google Maps data, Mapbox data, Here map data, etc., which are not limited herein. The target map data contains a large amount of road data, road names, road grades, and road key point data associated with the road data. For example, a road bifurcates into two roads, two roads converge into one road, and the connection positions between roads of different grades, etc. In this embodiment, the road data includes information such as road grades and road names; the road key point data includes information such as road bifurcation points and branch roads. Figure 2 is a target map data diagram proposed in an embodiment of the present invention. As Figure 2 shown, a target map data contains all the road data within the scope of this target map.

[0087] Step S102: Extract first road data and second road data from the road data according to the road grade.

[0088] In this embodiment, it is necessary to extract first road data and second road data from the road data of the target map data according to the road grade. As Figure 3 shown,Figure 3 A road grade map data graph proposed in an embodiment of the present invention, in which the road data of the target map data includes road data of various road grades, such as expressways, expressway ramps, first-class highways, expressways, arterial roads, etc. Specifically, in this embodiment, the extracted first road data and second road data may be an expressway and an expressway ramp respectively, or an expressway and an expressway ramp respectively, and there may be multiple first road data and second road data. At the same time, in order to better complete the subsequent steps, in this embodiment, after extracting the first road data and the second road data from the road data, all the extracted road data can be classified according to the road name.

[0089] Step S103: According to the traffic direction, each first road data is divided into one-sided first road data, and each second road data is divided into one-sided second road data.

[0090] In this embodiment, the first road data and the second road data can be two-way lane data or one-way lane data. Specifically, taking the expressway data as an example for the first road data and the expressway ramp data as an example for the second road data, then the two-way expressway data is divided into two one-way expressway data according to the traffic direction of the expressway, and the two-way expressway ramp data is divided into two one-way expressway ramp data according to the traffic direction of the expressway ramp; and in the case where the first road data or the second road data itself is one-way, that is, has a single traffic direction, there is no need to further distinguish it according to the traffic direction; and for the first road data or the second road data that may have three traffic directions or even more traffic directions, they all need to be divided into corresponding one-sided road data according to the traffic direction. At the same time, in order to better complete the subsequent steps, in this embodiment, after splitting the road data according to the traffic direction, all the split road data can be classified according to the road name.

[0091] Step S104: According to the road key point data, the one-sided first road data is bound to the corresponding one-sided second road data to obtain the target road data.

[0092] In this embodiment, the road key point data includes information such as road bifurcation points and branch roads. Still taking the first road data as highway data and the second road data as highway ramp data as an example, the road key point data is the on-ramp point (merge point) and off-ramp point (diverge point) on the highway, and the branch road is the highway ramp. It can be understood that for different first road data and second road data, the road key point data therein may be different, such as expressways and expressway ramps. Taking the first road data as highway data and the second road data as highway ramp data as an example, after dividing each first road data into single-sided first road data and dividing each second road data into single-sided second road data in step S103, the corresponding merged (on-ramp) single-sided highway ramps or diverged (off-ramp) highway ramps can be bound one by one according to the road key point data on the single-sided highway data. Specifically, the same single-sided first road data can bind multiple single-sided second road data, and each road key point data can support the binding of one single-sided second road data.

[0093] Step S105: Determine the attributes of each road key point data in the target road data according to the single-sided second road data in the target road data, where the attributes include diverge points and merge points.

[0094] In this embodiment, according to the single-sided second road data in the target road data, the road traffic direction is determined, and according to the road traffic direction, the attributes of each road key point data in the target road data can be determined. As Figure 4 、 Figure 5 shown, Figure 4 is a road name map data diagram proposed in an embodiment of the present invention, Figure 5 is a road key point data diagram proposed in an embodiment of the present invention, and the single-sided second road data in the diagram is not shown. Taking the first road data as highway data and the second road data as highway ramp data as an example, Figure 4 is a piece of extracted highway data. According to the road key point data, the highway ramps connected to this highway data are bound one by one, and then according to the traffic direction, it is determined whether the road key point data is a diverge point or a merge point in Figure 5 .

[0095] Step S106: Generate each navigation path according to the target road data and the attributes of each road key point data in the target road data.

[0096] In this embodiment, after determining the attributes of each road key point data, the passing direction of the navigation path to be generated for each single-sided second road data and the bound single-sided first road data is determined. Then, after determining the navigation start point and the navigation end point, the navigation path can be generated. The determination of the navigation start point and the navigation end point can be selected according to actual needs, and this embodiment does not make any restrictions. For example, taking each road key point data as a reference, the confluence point extends backward (a fixed distance or until the end of this road), the divergence point extends forward (a fixed distance or until the end of this road), or a fixed point on the single-sided first road can also be selected as the navigation start point or the navigation end point (determined by the passing direction). As Figure 6 shown Figure 6 FIG. Figure 6 is a navigation path map proposed in an embodiment of the present invention. In the case where the road key point data is a divergence point, it extends from the divergence point in the single-sided second road data to determine the navigation path.

[0097] Step S107: Match the navigation path with the high-precision map data to obtain a matching result.

[0098] In this embodiment, it is necessary to match the navigation path with the high-precision map data to verify whether each navigation point in the navigation path can match the high-precision map data, and then splice the high-precision map data matched by each navigation point to verify whether the spliced high-precision map data is continuous and whether it can completely cover this navigation path, and generate a matching result. Specifically, in this embodiment, it is not necessary to actually verify the autonomous driving function for each road. Only an autonomous driving simulation program or other simulation devices are required. The generated navigation path is input into the autonomous driving simulation program, and the simulated vehicle travels from the navigation start point to the navigation end point to verify whether each navigation point in the generated navigation path can match the high-precision map data, perform splicing processing on the high-precision map data matched by each navigation point, verify the continuity of the high-precision map data, whether there are interruptions, and generate a matching result.

[0099] Step S108: Determine whether the high-precision map data meets the autonomous driving requirements of the navigation path according to the matching result.

[0100] In this embodiment, according to the matching result, it can be determined whether the matched (stitched) high-precision map data meets the automatic driving requirements of this navigation path. For example, when high-precision map data can be matched at each navigation point in this navigation path, and the matched high-precision map data is continuous and completely covers this navigation path after stitching, it is determined that the high-precision map data can meet the automatic driving requirements of this navigation path; at the same time, if there is a navigation point where high-precision map data cannot be matched, but the stitched high-precision map data is still complete and continuous and can cover this navigation path, it can also be determined that the high-precision map data can meet the automatic driving requirements of this navigation path. If the high-precision map data does not meet the automatic driving requirements of this navigation path, the unsatisfied situation can be improved, such as manually inputting high-precision map data, real vehicle verification, submitting error reports, applying for high-precision map updates, etc., to improve the passability, safety and stability of the automatic driving function.

[0101] Specifically, by using the method provided in the embodiment of the present application, it is convenient, fast and effective to verify whether the high-precision maps matched by each navigation path are complete and whether they can meet the automatic driving requirements, without having to conduct real vehicle verification of the automatic driving function for each road, which greatly saves manpower, material resources and time costs.

[0102] Optionally, in combination with the above embodiment, in another implementation manner, step S104 includes:

[0103] Step S1041: Determine the connectivity relationship between the single-sided first road data and each single-sided second road data according to the road key point data.

[0104] In this embodiment, the road key point data includes information such as road bifurcation points and branch roads. Still taking the first road data as highway data and the second road data as highway ramp data as an example, the road key point data is the on-ramp point (merging point) and off-ramp point (diverging point) on the highway, and the branch road is the highway ramp. It can be understood that for different first road data and second road data, the road key point data may be different, such as expressways and expressway ramps. Taking the first road data as highway data and the second road data as highway ramp data as an example, according to the merging point and diverging point data on the highway, that is, the road key point data, the connectivity relationship between the single-sided first road data and each single-sided second road data can be determined.

[0105] Step S1042: Bind each single-sided second road data connected to the single-sided first road data to obtain the target road data corresponding to the single-sided first road data.

[0106] In this embodiment, after determining the connectivity relationship between the single-sided first road data and each single-sided second road data, bind the single-sided second roads that are connected to the single-sided first road, and then the target road data corresponding to the single-sided first road data can be obtained.

[0107] Optionally, in combination with the above embodiment, in another implementation manner, step S105 includes:

[0108] Step S1051: Determine the attributes of each road key point data corresponding to each single-sided second road data according to the traffic directions of the single-sided second road data in the target road data.

[0109] Step S1052: When the traffic direction of the single-sided second road data corresponding to the road key point data is towards the bound single-sided first road data, determine the attribute of this road key point data as a confluence point.

[0110] Step S1053: When the traffic direction of the single-sided second road data corresponding to the road key point data is away from the bound single-sided first road data, determine the attribute of this road key point data as a divergence point.

[0111] In this embodiment, the traffic direction of each single-sided second road data is single. Either it starts from the connected position of the bound single-sided first road and drives away from the single-sided first road. In this case, the road key point data at the connection between the single-sided first road and the single-sided second road is a divergence point; or it starts from the other end point of the single-sided second road data and drives towards the single-sided first road. In this case, the road key point data at the connection between the single-sided first road and the single-sided second road is a confluence point.

[0112] Optionally, in combination with the above embodiment, in another implementation manner, step S106 includes:

[0113] Step S1061: Determine each navigation direction corresponding to each road key point data according to the attributes of the road key point data in the target road data.

[0114] In this embodiment, after determining the attributes of each road key point data, the respective navigation directions corresponding to each road key point data can be determined. Specifically, each road key point data has its own attribute (divergence point or confluence point), and each road key point data is also the position data at the connection between the single-sided first road and the single-sided second road. That is to say, the attribute of each road key point data can determine the navigation direction of a navigation path.

[0115] Step S1062: Determine respective navigation endpoints corresponding to the respective navigation directions according to the respective navigation directions and the target road data.

[0116] In this embodiment, the respective navigation endpoints are determined based on the respective navigation directions and the target road data. Exemplarily, taking the respective road key point data as a reference, for a confluence point, extend backward (a fixed distance or until the end of this road), for a divergence point, extend forward (a fixed distance or until the end of this road), or alternatively, a fixed point on the first road on one side can be selected as the navigation start point or the navigation end point (determined according to the traffic direction).

[0117] Step S1063: Generate respective navigation paths according to the respective navigation directions and the respective navigation endpoints.

[0118] In this embodiment, after determining the navigation endpoints, then determine the navigation start point and the navigation end point in the navigation endpoints according to the navigation direction, and the navigation path can be generated. Specifically, for each navigation direction and its corresponding navigation start point and navigation end point, a navigation path needs to be generated. Exemplarily, the navigation path can be an SD navigation path for use by the vehicle after verification in the subsequent process.

[0119] Optionally, in combination with the above embodiment, in another implementation manner, step S107 includes:

[0120] Step S1071: Determine respective navigation points in the navigation path according to the navigation path.

[0121] Step S1072: Match the respective navigation points with the high-precision map data to obtain the high-precision map data corresponding to each of the respective navigation points.

[0122] Step S1073: Piece together the high-precision map data corresponding to each of the respective navigation points to obtain high-precision pieced-together map data.

[0123] Step S1074: Determine the matching result between the navigation path and the high-precision map data according to the high-precision pieced-together map data.

[0124] In this embodiment, the generated navigation path can be input into an autonomous driving simulation program to determine each navigation point in the navigation path. The autonomous driving simulation program simulates the vehicle from the navigation starting point to the navigation ending point, and obtains the high-precision map data corresponding to each navigation point to complete the simulated autonomous driving. Then, the high-precision map data matched for each navigation point is stitched together to obtain high-precision stitched map data. The high-precision stitched map data may be incomplete, interrupted, etc., which depends on whether the navigation point can match the high-precision map data, and also depends on whether the area of the matched high-precision map data is large enough. Finally, based on the stitched high-precision stitched map data, the matching result between the navigation path and the high-precision map data can be determined. Specifically, if high-precision map data can be matched for each navigation point in this navigation path, and the matched high-precision map data is continuous and completely covers this navigation path after stitching, it is determined that the high-precision map data can meet the autonomous driving requirements of this navigation path. At the same time, if there is a navigation point for which high-precision map data cannot be matched, but the stitched high-precision map data is still complete and continuous and can cover this navigation path, it can also be determined that the high-precision map data can meet the autonomous driving requirements of this navigation path. If the high-precision map data cannot meet the autonomous driving requirements of this navigation path, the unsatisfied situation can be improved, such as manually inputting high-precision map data, real vehicle verification, submitting error reports, applying for high-precision map updates, etc., to improve the passability, safety, and stability of the autonomous driving function.

[0125] Optionally, in combination with the above embodiment, in another implementation manner, step S108 includes:

[0126] Step S1081: When the matching result indicates that the high-precision stitched map data corresponding to the navigation path is uninterrupted, it is determined that the high-precision map data meets the autonomous driving requirements of the navigation path.

[0127] In this embodiment, if the matching result indicates that the high-precision stitched map data is uninterrupted, it means that the high-precision map data can meet the autonomous driving requirements of the navigation path.

[0128] Step S1082: When the matching result indicates that the high-precision stitched map data corresponding to the navigation path is interrupted, it is determined that the high-precision map data does not meet the autonomous driving requirements of the navigation path.

[0129] In this embodiment, if the matching result indicates that there is an interruption in the high-precision stitching map data, it means that the high-precision map data cannot meet the autonomous driving requirements of the navigation path. This may be because some navigation points cannot match the high-precision map data, or the high-precision map data matched by some navigation points has too small a range and the data is not detailed enough to meet the autonomous driving conditions.

[0130] Optionally, in combination with the above embodiment, in another implementation manner, the step S1062 includes:

[0131] Step S10621: When the navigation direction is towards the single-sided first road data in the target road data, determine the end point of the single-sided second road data corresponding to the navigation direction in the target road data that is not connected to the single-sided first road data as the navigation start point.

[0132] In this embodiment, when the navigation direction is towards the single-sided first road data in the target road data, since it is necessary to verify whether the single-sided second road data meets the autonomous driving requirements, therefore, the entire section of the single-sided second road needs to be included in the navigation path. At this time, take the other end point of the single-sided second road data (the end point not connected to the single-sided first road) as the navigation start point. This end point may be a highway toll station, or it may not be a toll station but the starting point of this single-sided second road data.

[0133] Step S10622: Determine the navigation end point according to the navigation start point and the target road data.

[0134] In this embodiment, when the navigation start point is determined, it is possible to extend a corresponding distance along the traffic direction of the single-sided second road data to determine the navigation end point, which is located in the single-sided first road data in the target road data. For example, in this embodiment, starting from the determined navigation start point, along the traffic direction of the single-sided second road data, it is possible to extend 3 kilometers as the navigation end point to meet the needs of the autonomous driving simulation program. In actual verification, this distance can be appropriately extended or shortened. For example, when the single-sided second road data exceeds 3 kilometers, if it is only extended by 3 kilometers, then it has not reached the single-sided first road data yet, and at this time, it is necessary to continue to extend until it reaches the single-sided first road data.

[0135] Step S10623: When the navigation direction is away from the single-sided first road data in the target road data, determine the end point of the single-sided second road data corresponding to the navigation direction in the target road data that is not connected to the single-sided first road data as the navigation end point.

[0136] In this embodiment, when the navigation direction is away from the single-sided first road data in the target road data, since it is necessary to verify whether the single-sided second road data meets the requirements of autonomous driving, therefore, the entire section of the single-sided second road needs to be included in the navigation path. At this time, the other endpoint of the single-sided second road data (the endpoint not connected to the single-sided first road) is used as the navigation end point, and this endpoint may be a highway toll station or may not be a toll station but the starting point of the single-sided second road data itself.

[0137] Step S10624: Determine the navigation start point according to the navigation end point and the target road data.

[0138] In this embodiment, when the navigation end point is determined, a corresponding distance can be extended in the reverse direction along the traffic direction of the single-sided second road data to determine the navigation start point, and this navigation start point is located in the single-sided first road data in the target road data. For example, in this embodiment, starting from the determined navigation end point, a distance of 3 kilometers can be extended in the reverse direction along the traffic direction of the single-sided second road data as the navigation start point to meet the needs of the autonomous driving simulation program. In actual verification, this distance can be appropriately extended or shortened. For example, when the single-sided second road data exceeds 3 kilometers, if only 3 kilometers are extended in the reverse direction, then it has not reached the single-sided first road data yet, and at this time, it is necessary to continue to extend until it reaches the single-sided first road data.

[0139] Based on the same inventive concept, another embodiment of the present invention provides a high-precision map verification device, as Figure 7 shown Figure 7 is a module block diagram of a high-precision map verification device proposed in an embodiment of the present invention. The device 400 includes:

[0140] The first acquisition module 401 is used to acquire road data and road key point data in the target map data;

[0141] The second extraction module 402 is used to extract the first road data and the second road data in the road data according to the road grade;

[0142] The third segmentation module 403 is used to divide each first road data into single-sided first road data and divide each second road data into single-sided second road data according to the traffic direction;

[0143] The fourth binding module 404 is used to bind the single-sided first road data with the corresponding single-sided second road data according to the road key point data to obtain the target road data;

[0144] The fifth determination module 405 is configured to determine the attributes of each road key point data in the target road data according to the single-sided second road data in the target road data, where the attributes include divergence points and confluence points;

[0145] The sixth generation module 406 is configured to generate each navigation path according to the target road data and the attributes of each road key point data in the target road data;

[0146] The seventh matching module 407 is configured to match the navigation path with the high-precision map data to obtain a matching result;

[0147] The eighth determination module 408 is configured to determine whether the high-precision map data meets the autonomous driving requirements of the navigation path according to the matching result.

[0148] Optionally, the fourth binding module 404 includes:

[0149] The first binding sub-module 4041 is configured to determine the connectivity relationship between the single-sided first road data and each single-sided second road data according to the road key point data;

[0150] The second binding sub-module 4042 is configured to bind each single-sided second road data connected to the single-sided first road data to obtain the target road data corresponding to the single-sided first road data.

[0151] Optionally, the fifth determination module 405 includes:

[0152] The first determination sub-module 4051 is configured to determine the attributes of each road key point data corresponding to each single-sided second road data according to the traffic direction of each single-sided second road data in the target road data;

[0153] The second determination sub-module 4052 is configured to determine that the attribute of the road key point data is a confluence point when the traffic direction of the single-sided second road data corresponding to the road key point data is towards the bound single-sided first road data;

[0154] The third determination sub-module 4053 is configured to determine that the attribute of the road key point data is a divergence point when the traffic direction of the single-sided second road data corresponding to the road key point data is away from the bound single-sided first road data.

[0155] Optionally, the sixth generation module 406 includes:

[0156] The first generation sub-module 4061 is configured to determine each navigation direction corresponding to each road key point data according to the attributes of each road key point data in the target road data;

[0157] The second generation sub-module 4062 is configured to determine respective navigation endpoints corresponding to the respective navigation directions according to the respective navigation directions and the target road data;

[0158] The third generation sub-module 4063 is configured to generate respective navigation paths according to the respective navigation directions and the respective navigation endpoints.

[0159] Optionally, the seventh matching module 407 includes:

[0160] The first matching sub-module 4071 is configured to determine respective navigation points in the navigation path according to the navigation path;

[0161] The second matching sub-module 4072 is configured to match the respective navigation points with the high-precision map data to obtain the high-precision map data corresponding to each of the respective navigation points;

[0162] The third matching sub-module 4073 is configured to splice the high-precision map data corresponding to each of the respective navigation points to obtain high-precision spliced map data;

[0163] The fourth matching sub-module 4074 is configured to determine a matching result between the navigation path and the high-precision map data according to the high-precision spliced map data.

[0164] Optionally, the eighth determination module 408 includes:

[0165] The fourth determination sub-module 4081 is configured to determine that the high-precision map data meets the autonomous driving requirements of the navigation path when the matching result indicates that the high-precision spliced map data corresponding to the navigation path is uninterrupted;

[0166] The fifth determination sub-module 4082 is configured to determine that the high-precision map data does not meet the autonomous driving requirements of the navigation path when the matching result indicates that the high-precision spliced map data corresponding to the navigation path is interrupted.

[0167] Optionally, the second generation sub-module 4062 includes:

[0168] The first endpoint determination sub-module 40621 is configured to, when the navigation direction is towards the single-sided first road data in the target road data, determine an endpoint of the single-sided second road data corresponding to the navigation direction in the target road data that is not connected to the single-sided first road data as the navigation start point;

[0169] The second endpoint determination sub-module 40622 is configured to determine a navigation end point according to the navigation start point and the target road data;

[0170] The third endpoint determination sub-module 40623 is configured to, when the navigation direction is to drive away from the single-sided first road data in the target road data, determine the endpoint of the single-sided second road data corresponding to the navigation direction in the target road data that is not connected to the single-sided first road data as the navigation end point;

[0171] The fourth endpoint determination sub-module 40624 is configured to determine the navigation start point according to the navigation end point and the target road data.

[0172] Based on the same inventive concept, another embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it implements the high-precision map verification method according to any one of the first aspects of the embodiments of the present invention.

[0173] Based on the same inventive concept, another embodiment of the present invention provides a vehicle, where the vehicle includes an autonomous driving module, and the autonomous driving module is configured to implement autonomous driving according to the high-precision map verified by the high-precision map verification method according to any one of the first aspects of the embodiments of the present invention.

[0174] For the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, refer to the partial description of the method embodiments.

[0175] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other.

[0176] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, devices, electronic devices, storage media, or computer program products. Therefore, the embodiments of the present invention can take the form of completely hardware embodiments, completely software embodiments, or embodiments combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0177] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirits of the present invention. The scope of the present invention is defined by the claims and their equivalents.

[0178] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or terminal device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the element.

[0179] The above has introduced in detail a high-precision map verification method, device, electronic device and vehicle provided by the present invention. Specific examples are used in this text to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application. The above embodiments are only preferred embodiments given to fully illustrate the present invention, and the protection scope of the present invention is not limited thereto. Equivalent substitutions or transformations made by those skilled in the art on the basis of the present invention are within the protection scope of the present invention.

Claims

1. A high-precision map verification method, characterized in that, The method includes: Obtaining road data and road key point data in the target map data; Extracting first road data and second road data from the road data according to the road level; Dividing each piece of first road data into one-sided first road data and each piece of second road data into one-sided second road data according to the traffic direction; Binding the one-sided first road data with the corresponding one-sided second road data according to the road key point data to obtain target road data; Determining the attributes of each road key point data in the target road data according to the one-sided second road data in the target road data, where the attributes include diverging points and converging points; Generating each navigation path according to the target road data and the attributes of each road key point data in the target road data; Matching the navigation path with the high-precision map data to obtain a matching result; Determining whether the high-precision map data meets the autonomous driving requirements of the navigation path according to the matching result.

2. The method according to claim 1, characterized in that, The step of binding the one-sided first road data with the corresponding one-sided second road data according to the road key point data to obtain target road data includes: Determining the connectivity relationship between the one-sided first road data and each piece of one-sided second road data according to the road key point data; Binding each piece of one-sided second road data connected to the one-sided first road data to obtain the target road data corresponding to the one-sided first road data.

3. The method according to claim 1, characterized in that, The step of determining the attributes of each road key point data in the target road data according to the one-sided second road data in the target road data includes: Determining the attributes of each road key point data corresponding to each piece of one-sided second road data respectively according to the traffic direction of each piece of one-sided second road data in the target road data; When the traffic direction of the one-sided second road data corresponding to the road key point data is towards the bound one-sided first road data, determining the attribute of this road key point data as a converging point; When the traffic direction of the one-sided second road data corresponding to the road key point data is away from the bound one-sided first road data, determining the attribute of this road key point data as a diverging point.

4. The method according to claim 1, characterized in that, The step of generating each navigation path according to the target road data and the attributes of each road key point data in the target road data includes: Determining each navigation direction corresponding to each road key point data respectively according to the attributes of each road key point data in the target road data; Determining each navigation endpoint corresponding to each navigation direction respectively according to each navigation direction and the target road data; Generating each navigation path according to each navigation direction and each navigation endpoint.

5. The method according to claim 1, characterized in that, The step of matching the navigation path with the high-precision map data to obtain a matching result includes: Determining each navigation point in the navigation path according to the navigation path; Matching each navigation point with the high-precision map data to obtain the high-precision map data corresponding to each navigation point; Stitching the high-precision map data corresponding to each navigation point to obtain high-precision stitched map data; Determine the matching result between the navigation path and the high-precision map data according to the high-precision spliced map data.

6. The method according to claim 5, characterized in that, The determining whether the high-precision map data meets the automatic driving requirements of the navigation path according to the matching result includes: When the matching result indicates that there is no interruption in the high-precision spliced map data corresponding to the navigation path, determine that the high-precision map data meets the automatic driving requirements of the navigation path; When the matching result indicates that there is an interruption in the high-precision spliced map data corresponding to the navigation path, determine that the high-precision map data does not meet the automatic driving requirements of the navigation path.

7. The method according to claim 4, characterized in that, The determining the respective navigation endpoints corresponding to the respective navigation directions according to the respective navigation directions and the target road data includes: When the navigation direction is to drive towards the single-sided first road data in the target road data, determine the endpoint where the single-sided second road data corresponding to the navigation direction in the target road data is not connected to the single-sided first road data as the navigation starting point; Determine the navigation end point according to the navigation starting point and the target road data; When the navigation direction is to drive away from the single-sided first road data in the target road data, determine the endpoint where the single-sided second road data corresponding to the navigation direction in the target road data is not connected to the single-sided first road data as the navigation end point; Determine the navigation starting point according to the navigation end point and the target road data.

8. A high-precision map verification device, characterized in that, The device includes: A first acquisition module for acquiring road data and road key point data in the target map data; A second extraction module for extracting the first road data and the second road data from the road data according to the road grade; A third segmentation module for dividing each first road data into single-sided first road data and each second road data into single-sided second road data according to the traffic direction; A fourth binding module for binding the single-sided first road data with the corresponding single-sided second road data according to the road key point data to obtain the target road data; A fifth determination module for determining the attributes of each road key point data in the target road data according to the single-sided second road data in the target road data, where the attributes include diversion points and confluence points; A sixth generation module for generating each navigation path according to the target road data and the attributes of each road key point data in the target road data; A seventh matching module for matching the navigation path with the high-precision map data to obtain a matching result; An eighth determination module for determining whether the high-precision map data meets the automatic driving requirements of the navigation path according to the matching result.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the computer program is executed by the processor, it implements the high-precision map verification method according to any one of claims 1 to 7.

10. A vehicle, characterized in that, The vehicle includes an automatic driving module, and the automatic driving module is used to implement automatic driving according to the high-precision map verified by the high-precision map verification method according to any one of claims 1 to 7.

Images