High-precision map accuracy verification method, device, equipment and readable storage medium

By partitioning the real geographical area and selecting true value points for comparison, the problem of inaccurate error evaluation of high-precision maps is solved, and a comprehensive and accurate evaluation of high-precision map data is achieved, and the safety and stability of autonomous vehicles are improved. .

CN118640936BActive Publication Date: 2024-11-08HANGZHOU HIGH-TECH INTELLECTUAL PROPERTY OPERATION CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411096678.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-12
Publication Date
2024-11-08
Estimated Expiration
2044-08-12

AI Technical Summary

Technical Problem

The error evaluation of existing high-precision maps is inaccurate, which affects the safety and stability of autonomous vehicles.

Method used

By partitioning the real geographical area into regional units and configuring sampling areas in each regional unit, selecting true value points to obtain real coordinates, which are used to compare coordinates in high-precision maps to determine the accuracy of high-precision maps.

Benefits of technology

It realizes a comprehensive and accurate evaluation of the accuracy of high-precision map data, and improves the reliability of map production quality monitoring and use.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118640936B_ABST
    Figure CN118640936B_ABST
Patent Text Reader

Abstract

The present application provides a method, device, equipment and readable storage medium for verifying the accuracy of a high-precision map, which relates to the field of autonomous driving technology. The method includes: partitioning a real geographical area into at least one area unit; configuring at least one sampling area for each area unit based on the environmental information of the area unit; selecting at least one set of true value points in the sampling area; obtaining the real coordinates of the true value points; and determining the accuracy of the high-precision map based on the real coordinates and the map coordinates corresponding to the true value points in the high-precision map. This solution can ensure that the selection of true value points is more representative, so that a comprehensive and accurate assessment of the accuracy of high-precision map data can be achieved during subsequent data comparison.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, device, equipment and readable storage medium for verifying the accuracy of a high-precision map. Background Art

[0002] With the development of autonomous driving technology, high-precision maps are an important tool for autonomous vehicles to perceive the environment, and their data accuracy is directly related to the safety and stability of vehicle driving. However, due to the influence of factors such as lidar measurement error, inertial navigation system error, time synchronization error, calibration error, motion distortion error, and inertial navigation attitude positioning error, high-precision maps will inevitably produce errors during the production process.

[0003] In the existing technology, the traditional global navigation satellite system, real-time dynamic carrier phase difference and total station and other measurement tools are mainly relied on to collect the spatial coordinates of specific location points, and then compare them with the corresponding coordinates in the high-precision map to determine the accuracy of the high-precision map.

[0004] However, this existing method is not accurate in error assessment of high-precision maps. Summary of the invention

[0005] The present application provides a high-precision map accuracy verification method, device, equipment and readable storage medium, which are used to solve the problem of inaccurate error assessment of existing high-precision maps.

[0006] In a first aspect, an embodiment of the present application provides a method for verifying the accuracy of a high-precision map, comprising:

[0007] partitioning the real geographical area into at least one area unit;

[0008] Based on the environmental information of the area unit, configuring at least one sampling area for each area unit;

[0009] Selecting at least one set of true value points in the sampling area;

[0010] Obtaining the real coordinates of the true value point;

[0011] The accuracy of the high-precision map is determined based on the real coordinates and the map coordinates corresponding to the true value points in the high-precision map.

[0012] In a possible design of the first aspect, configuring at least one sampling area for each area unit based on the environmental information of the area unit includes:

[0013] Based on the environmental information of the area unit, determining whether there is a target environment that meets a set condition in the area unit;

[0014] If the target environment exists, at least one sampling area is configured for each target environment.

[0015] In another possible design of the first aspect, the target environment includes: one or any combination of mountainous areas, tunnels, highways, and urban areas.

[0016] In another possible design of the first aspect, configuring at least one sampling area for each target environment includes:

[0017] The exit or entrance of the road section of the target environment is selected as the sampling area.

[0018] In yet another possible design of the first aspect, the set of true value points includes at least one of: a horizontal verification point, an elevation verification point, and a relative accuracy verification point.

[0019] In another possible design of the first aspect, determining the accuracy of the high-precision map based on the real coordinates and the map coordinates corresponding to the true value points in the high-precision map includes:

[0020] If the set of true value points includes the horizontal verification point, determining the absolute accuracy of the high-precision map based on the real coordinates of the horizontal verification point and the map coordinates corresponding to the horizontal verification point in the high-precision map;

[0021] If the set of true value points includes the elevation verification point, determining the absolute accuracy of the high-precision map based on the real coordinates of the elevation verification point and the map coordinates corresponding to the elevation verification point in the high-precision map;

[0022] If the relative accuracy verification point is included in the set of true value points, the relative accuracy of the high-precision map is determined based on the real coordinates of at least two relative accuracy verification points and the corresponding map coordinates of each relative accuracy verification point in the high-precision map.

[0023] In another possible design of the first aspect, selecting at least one set of true value points in the sampling area includes:

[0024] If the set of true value points includes the horizontal verification point, at least one horizontal verification point is selected based on at least one of the sharp angle of the guide strip at the outlet or inlet of the sampling area, the merging and separation point of the outlet or inlet of the sampling area, and a specific position point in the sampling area.

[0025] If the set of true value points includes the elevation verification point, then the road signs around the horizontal verification point are obtained, and at least one elevation verification point is selected based on the road signs.

[0026] If the group of true value points includes the relative accuracy verification point, a road sign in the target environment is acquired, and at least two position points are determined in the boundary line of the road sign as at least two relative accuracy verification points.

[0027] In another possible design of the first aspect, determining the relative accuracy of the high-precision map based on the real coordinates of at least two relative accuracy verification points and the map coordinates corresponding to each relative accuracy verification point in the high-precision map includes:

[0028] Obtaining the accuracy error between each relative accuracy verification point and the map coordinates corresponding to the relative accuracy verification point in the high-precision map;

[0029] Based on at least two of the precision errors, the relative accuracy of the high-precision map is determined.

[0030] In another possible design of the first aspect, the method further includes:

[0031] Determining the total number of true value point groups required for the real geographic area according to the sampling interval distance;

[0032] The number of groups of true value points of each area unit is determined according to the total number of groups of true value points and the number of sampling areas of each area unit.

[0033] In a second aspect, the embodiment of the present application provides a high-precision map accuracy verification device, including:

[0034] A region division module, used for dividing a real geographical region into at least one region unit;

[0035] A sampling configuration module, configured to configure at least one sampling area for each area unit based on the environmental information of the area unit;

[0036] A point value selection module, used to select at least one set of true value points in the sampling area;

[0037] A coordinate acquisition module, used to acquire the real coordinates of the true value point;

[0038] The accuracy verification module is used to determine the accuracy of the high-precision map based on the real coordinates and the map coordinates corresponding to the true value points in the high-precision map.

[0039] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method as described above.

[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to implement the above-mentioned method when executed by a processor.

[0041] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0042] The high-precision map accuracy verification method, device, equipment and readable storage medium provided in the embodiments of the present application can ensure that the selection of true value points is more representative by partitioning the real geographical area and selecting different types of sampling areas according to the different surrounding environments of the trajectories in the partitioned area units. When the data is compared subsequently, a comprehensive and accurate assessment of the accuracy of the high-precision map data can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application;

[0044] Figure 1 A schematic diagram of a scenario for high-precision map accuracy verification provided in an embodiment of the present application;

[0045] Figure 2 A flowchart of a high-precision map accuracy verification method provided in an embodiment of the present application;

[0046] Figure 3 A schematic diagram of a flow chart of a method for determining a sampling area provided in an embodiment of the present application;

[0047] Figure 4 The overall framework flow chart of the high-precision map accuracy verification method provided in the embodiment of the present application;

[0048] Figure 5 A schematic diagram of the structure of a high-precision map accuracy verification device provided in an embodiment of the present application;

[0049] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0050] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] With the development of autonomous driving technology, high-precision maps (abbreviated as HD maps) are an important tool for autonomous vehicles to perceive the environment. The accuracy of their data is directly related to the safety and stability of vehicle driving. However, due to the influence of factors such as radar measurement error, inertial navigation system error, time synchronization error, calibration error, motion distortion error, and inertial navigation attitude positioning error, HD maps will inevitably produce errors during the production process. Therefore, how to accurately evaluate the error distribution of map data and ensure the accuracy of map data has become a key issue in the quality monitoring of HD map production.

[0053] In related technologies, the methods for evaluating the accuracy of high-precision maps mainly rely on traditional measurement tools such as the Global Navigation Satellite System (GNSS), Real-time kinematic and total stations. The spatial coordinates of specific feature points on the map are measured and compared with the corresponding coordinates in the map data to evaluate the accuracy of the map data. However, these methods often have problems such as unscientific and comprehensive sampling point selection and inaccurate error assessment, which make it difficult to meet the needs of high-precision map production.

[0054] In response to the above problems, the present application provides a high-precision map accuracy verification solution, which divides the real geographic area into regional units, then selects sampling areas in each regional unit, and selects different types of verification points for data comparison according to the different surrounding environments of the trajectory, so as to achieve a comprehensive and accurate evaluation of the absolute accuracy of high-precision map data, and provide reliable technical support for map production quality monitoring and the use of map products.

[0055] For example, Figure 1 A schematic diagram of a scenario for high-precision map accuracy verification provided in an embodiment of the present application, such as Figure 1 As shown, when verifying the high-precision map, the real coordinates of some verification points can be collected on site (for example Figure 1 The real coordinates are then compared with the corresponding map coordinates in the HD map. By comparing the difference between the two coordinates, it is possible to determine whether the HD map is reliable and evaluate its accuracy.

[0056] The technical solution of the present application is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0057] Figure 2 A flowchart of a method for verifying the accuracy of a high-precision map provided in an embodiment of the present application, which can be applied to electronic devices (such as Figure 1 The method may specifically include the following steps:

[0058] Step S210: partition the real geographical area into at least one area unit.

[0059] In this embodiment, the real geographical area represents the actual spatial environment. Correspondingly, there are corresponding geographical areas in the high-precision map, but the geographical areas in the high-precision map are usually formed by scaling the real geographical areas based on the corresponding scale.

[0060] For example, taking the real geographical area as area Q, a high-precision map corresponding to the area Q is formed after mapping the area Q. The high-precision map will inevitably produce errors during the production process. If the error is too large, it may affect the safety of the autonomous driving vehicle. That is, if the autonomous driving vehicle uses the high-precision map as a navigation basis and drives in area Q, if the error of the high-precision map is large, it may cause the autonomous driving vehicle to collide with obstacles and other dangerous situations.

[0061] In this embodiment, each area unit can be directly divided into its occupied range to achieve partitioning of the real geographical area. For example, each area unit is configured with a reasonable size to achieve differentiation of the real geographical area. Specifically, a point in the real geographical area is taken as the origin, and the vehicle travels n kilometers (n is a positive integer) in different directions to obtain boundary points in multiple directions, and then these boundary points are connected to obtain a regional unit.

[0062] In other embodiments, the real geographical area can also be partitioned by environmental information. For example, when partitioning, it is necessary to ensure that each area unit has some specific landform environments (such as mountainous areas, tunnels, highways, urban areas, etc.). Among them, these specific landform environments are usually influencing factors, causing errors in the production process of high-precision maps (for example, some landform environments will affect the signal reception of the collection vehicle, resulting in inaccurate data from the collection vehicle, thereby causing errors in the production process of high-precision maps).

[0063] Among them, by configuring some specific geomorphic environments in each regional unit, it is more representative and can subsequently verify whether there are errors in the high-precision maps in these geomorphic environments.

[0064] Step S220: Based on the environmental information of the area unit, configure at least one sampling area for each area unit.

[0065] In this embodiment, the sampling area refers to an area in the area unit that needs to be sampled on site later. The sampling area is smaller than the entire area unit, which is convenient for subsequent on-site sampling to select true value points.

[0066] Among them, environmental information may refer to the road trajectory environmental information in the regional unit. When in these environments, it is easier to affect the accuracy of surveying and mapping, resulting in errors in the production process of high-precision maps.

[0067] Exemplarily, the environmental information may include mountainous areas, highways, tunnels, urban areas, etc.

[0068] In this embodiment, each area unit may include multiple pieces of such environmental information, for example, area unit A includes both tunnels and mountainous areas. Each piece of such environmental information can be configured with a sampling area to ensure the integrity of subsequent data (i.e., true value points) selection and further improve the accuracy of subsequent verification.

[0069] Step S230: Select at least one set of true value points in the sampling area.

[0070] Step S240: Obtain the real coordinates of the true value point.

[0071] In this embodiment, the real coordinates of the true value point can be obtained by measuring the coordinates of the true value point on site by surveyors, and the accuracy of the real coordinates is higher. The coordinates in the high-precision map are usually measured by corresponding equipment (such as a collection vehicle) using corresponding instruments, and their accuracy is poor, which can easily lead to errors in the production of high-precision maps.

[0072] In this embodiment, some representative position points can be selected in the sampling area as true value points, for example, specific position points at the entrance or exit of a tunnel, or specific position points at the entrance or exit of a highway can be selected as true value points.

[0073] Among them, in order to ensure that the data is more comprehensive, the number of groups of true value points can be as large as possible, so that when the accuracy of the high-precision map is verified later, the accuracy of the verification results can also be guaranteed.

[0074] In addition, when the total number of groups of truth points is fixed, it is necessary to reasonably allocate a corresponding number of groups of truth points to each regional unit. Specifically, in some embodiments, the total number of groups of truth points required to verify the high-precision map corresponding to the real geographic area can be determined in combination with the actual spatial area occupied by the real geographic area and the set sampling interval distance (for example, 150-200 kilometers), and then the number of sampling areas of each regional unit is further determined in combination with whether each regional unit contains a target environment that meets the conditions. Finally, based on the number of sampling areas of each regional unit and the total number of groups of truth points, a number of groups of truth points are evenly configured for each regional unit.

[0075] Specifically, taking the sampling interval of 150 kilometers as an example, assuming that in the real geographic area, a set of true value points needs to be selected at an interval of 150 kilometers, a total of 1250 sets of true value points need to be selected. Then, it is necessary to combine the number of target environments contained in each area unit and evenly distribute these 1250 sets of true value points to each area unit (this will facilitate the subsequent verification of the accuracy of each area unit in the high-precision map).

[0076] For example, if the real geographical area is divided into area unit A, area unit B and area unit C, if area unit A includes mountainous areas, tunnels and highways, area unit B includes tunnels and highways, and area unit C only includes highways, then more groups of truth points need to be allocated to area unit A. For example, the ratio of the number of truth point groups of area unit A, area unit B and area unit C is 3:2:1.

[0077] This implementation method partitions the real geographical area, so that it is convenient to evenly distribute the required number of truth point groups to each area unit according to the total number of truth point groups, so as to better verify the accuracy of the high-precision map corresponding to each area unit.

[0078] Step S250: Determine the accuracy of the high-precision map based on the real coordinates and the map coordinates corresponding to the true value points in the high-precision map.

[0079] In this embodiment, both the real coordinates and the map coordinates may include values ​​in three directions (x, y, z) (i.e., horizontal axis coordinate values, horizontal axis coordinate values, and vertical axis coordinate values). By comparing the differences between the three values ​​(x, y, z) of the real coordinates and the map coordinates, the accuracy of the high-precision map can be determined.

[0080] For example, taking the real coordinates as (x1, y1, z1) and the map coordinates as (x2, y2, z2), if the position distance difference between the two coordinate points is greater than 1 meter, it means that the accuracy of the high-precision map is poor.

[0081] The embodiment of the present application partitions the real geographical area and selects different types of sampling areas according to the different surrounding environments of the trajectories in the partitioned area units, so as to ensure that the subsequent selection of true value points is more representative. When the data is compared subsequently, a comprehensive and accurate assessment of the accuracy of the high-precision map data can be achieved.

[0082] The following describes in detail how to select a sampling area through some embodiments.

[0083] Figure 3 A flow chart of a method for determining a sampling area provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the method comprises the following steps:

[0084] Step S310: Based on the environmental information of the area unit, determine whether there is a target environment that meets the set conditions in the area unit.

[0085] In this embodiment, the area unit may include various environments. The environment that does not affect the accuracy of the high-precision map is called a normal environment (such as an open road), and the environment that affects the accuracy of the high-precision map is called an abnormal environment (such as a mountainous area, a tunnel, etc.). The target environment can refer to these abnormal environments. That is, the set condition can refer to: an environment that affects the accuracy of the high-precision map.

[0086] As mentioned above, when dividing the area units, the real geographical area can be partitioned directly by configuring the range occupied by each area unit. The area units obtained by such partitioning may include the above-mentioned normal environment and abnormal environment, or may only include the normal environment. Among them, when only the normal environment is included, the sampling area can only be determined in the normal environment for the subsequent selection of true value points. In this embodiment, when there is an abnormal environment (ie, the target environment) in the area unit, the sampling area can be determined in the abnormal environment, so that the true value points selected subsequently are more representative, further improving the accuracy of high-precision map verification.

[0087] Exemplarily, in some embodiments, the target environment may include: a mountainous area, a tunnel, a highway, an urban area, or any combination thereof.

[0088] In practical applications, the production of high-precision maps requires the use of data collection vehicles. When collecting data in these target environments, the signals may be weak or unreceivable due to the influence of these environmental factors, which may result in errors in the final high-precision maps. In addition, if high-precision maps are mainly used for autonomous driving, the above target environment should at least include lanes, and the selection of true value points can be realized based on the corresponding feature positions in the area around the lanes.

[0089] Specifically, taking mountainous areas as an example, due to the large terrain undulations, satellite signals may be blocked by objects such as buildings, trees or rocks, resulting in weak signals or failure to receive them. Another example is that there may be large areas of water near highways: reflections on the surface of water bodies can cause multipath effects, and because water bodies have a high reflectivity, the intensity of reflected signals may exceed the direct signal, making it difficult for the receiver to distinguish. Another example is that urban highways are next to high-rise buildings or dense high-rise buildings, in valleys, canyons, etc., and GPS signals may be obstructed, forming positioning blind spots. At the same time, these target environments may also contain large areas of signal towers, power stations, substations, high-voltage cables, radars, etc., which may generate electromagnetic interference and interfere with the transmission and reception of GPS signals.

[0090] Further, based on the above situation, in some implementations, when determining the sampling area, the exit or entrance of the road section of the target environment can be selected as the sampling area.

[0091] For example, if there is a mountainous area in the area unit, the exit or entrance of the road section in the mountainous area can be selected as the sampling area of ​​the mountainous area, and if there is a tunnel in the area unit, the exit or entrance of the road section in the tunnel can be selected as the sampling area of ​​the tunnel; finally, if there is a highway in the area unit, the exit or entrance of the road section in the highway can be selected as the sampling area of ​​the highway.

[0092] In this embodiment, the accuracy of the exit or entrance of a road section or tunnel has a significant impact on the accuracy of the high-precision map. When the exit or entrance is inaccurate, it may cause great safety risks for the autonomous driving vehicle. Therefore, by using the exit or entrance of a road section or tunnel as a sampling area, the representativeness of the truth point can be further improved during the subsequent truth single selection, thereby further improving the accuracy of the high-precision map verification.

[0093] This embodiment sets the target environment to one or any combination of mountainous areas, tunnels, and highways, and uses the entrance or exit of mountainous sections, the entrance or exit of tunnels, and the exit or entrance of highway sections as sampling areas. In this way, a variety of different types of sampling areas can be determined, ensuring the adequacy and rationality of the data when selecting true value points later.

[0094] Step S320: If there are target environments, configure at least one sampling area for each target environment.

[0095] In this embodiment, multiple sampling areas can be configured in the target environment. For example, taking the target area as a tunnel, a sampling area can be configured at the entrance of the tunnel, and a sampling area can be configured at the exit of the tunnel. In this way, the number of true value points selected can be increased in the future, thereby further improving the accuracy of subsequent high-precision map verification.

[0096] The embodiment of the present application configures the sampling area for the target environment preferentially, so that more representative true value points can be selected from the sampling area later to more accurately verify whether there are errors in the high-precision map.

[0097] The truth point and the selection of the truth point are described in detail below through some embodiments.

[0098] In some embodiments, a set of truth points may include at least one of a horizontal verification point, an elevation verification point, and a relative accuracy verification point. The horizontal verification point and the elevation verification point are used to determine the absolute accuracy of the high-precision map, and the relative accuracy verification point is used to determine the relative accuracy of the high-precision map.

[0099] Among them, the horizontal verification point can be a feature point on the road surface, such as a feature point at a certain position on the road sign, and the elevation verification point can be a feature point at a certain position on the road sign. Among them, the elevation of the road sign can be 5 meters. The elevation of the road sign specifically refers to the height of the road sign relative to the ground, which is set according to actual needs and road design. The elevation verification point can be a tunnel sign in the tunnel. The tunnel sign is usually set in front of the tunnel entrance and in the tunnel to provide information such as tunnel length, speed limit, and no overtaking.

[0100] In some implementations, the true value point can be selected in the following two ways to improve the subsequent accuracy verification effect:

[0101] Method (1) Select at least one horizontal verification point and at least one elevation verification point in the sampling area as a set of true value points;

[0102] Method (2) selects at least one horizontal verification point, at least one elevation verification point and at least two relative accuracy verification points in the sampling area as a set of true value points.

[0103] In some embodiments, in order to improve the accuracy of post-precision verification, each set of true value points should at least include horizontal verification points and elevation verification points. In addition, relative precision verification points can be selected or not to be omitted according to actual conditions.

[0104] In this embodiment, the distribution of the truth points in the regional unit should be as uniform as possible to ensure the accuracy of the subsequent verification of the high-precision map. For example, a set of truth points can be collected in the regional unit at intervals of 250-300 kilometers.

[0105] Furthermore, when selecting true value points, different types of verification points (i.e., horizontal verification points, elevation verification points, and relative accuracy verification points) have different corresponding selection methods, including the following methods:

[0106] Method 1: If a set of true value points includes horizontal verification points, at least one horizontal verification point is selected based on at least one of the sharp corners of the guide strip at the outlet or inlet of the sampling area, the merging and separation points at the outlet or inlet of the sampling area, and specific position points of the sampling area.

[0107] Method 2: If a set of true value points includes elevation verification points, obtain the road signs around the horizontal verification points, and select at least one elevation verification point based on the road signs.

[0108] Method three: If a set of true value points includes relative accuracy verification points, a road sign in the target environment is obtained, and at least two position points are determined in the boundary line of the road sign as at least two relative accuracy verification points.

[0109] When selecting the above verification points, clear and high-density exits or entrances (including exits or entrances of road sections and tunnels) should be selected. Furthermore, when selecting elevation verification points, exits or entrances should be selected with guide strips and road signs less than 5 meters high as much as possible to ensure the rationality and accuracy of the selection of true value points.

[0110] For method one:

[0111] In this embodiment, the entrance and exit guide strip sharp corner refers to the triangular area of ​​the exit or entrance of the highway where the guide strip is often provided, wherein the sharp corner portion is used to guide vehicles to travel along the designated route. The guide strip sharp corner is usually presented as a V-shaped or diagonal line area, and its size is set according to the specific intersection terrain. Among them, the position of the guide strip sharp corner can be selected as a horizontal verification point, and other adjacent or close positions near the guide strip sharp corner can also be selected as horizontal verification points.

[0112] In this embodiment, the merging and separation points of the exit or entrance may refer to the points at the exit or entrance of the highway where vehicles need to merge or separate, and these points are the merging and separation points. Among them, these merging and separation points can be selected as a horizontal verification point, and other adjacent or similar positions near the merging and separation points can also be selected as horizontal verification points.

[0113] In this embodiment, if the sampling area is a tunnel, the characteristic position point of the sampling area may be a front characteristic point or a rear characteristic point of the tunnel, wherein the front characteristic point or the rear characteristic point of the tunnel refers to a specific position before the tunnel entrance and after the tunnel exit, which is usually used to set a warning sign or a speed limit sign.

[0114] For method 2:

[0115] In this embodiment, the road sign may refer to a signboard erected vertically on a road section, which is used to indicate the current road section, the road section available ahead, etc. The road sign elevation refers to the height of the road sign relative to the ground, which is set according to actual needs and road design. If the sampling area is a tunnel, then the road sign may refer to a tunnel sign, which is usually set in front of the tunnel entrance and inside the tunnel to provide information such as tunnel length, speed limit, and no overtaking.

[0116] For method three:

[0117] Since the relative accuracy verification points are used to verify the relative accuracy of the HD map (i.e., whether there is an error in the distance between two points), at least two relative accuracy verification points need to be selected. Among them, since there are usually road signs such as ground lines, road signs, longitudinal length indicator lines, guide arrows, and features in tunnels during vehicle driving, relative accuracy verification points can be selected from these road signs.

[0118] For example, the ground line has length and width dimensions. Therefore, if a relative accuracy verification point is selected before, after, or to the left or right of the ground line, the actual distance between the two relative accuracy verification points can be determined, which can be used to verify whether the distance between the two relative accuracy verification points in the high-precision map is different from the actual distance.

[0119] Among them, the ground lines of the highway include lane dividing lines, vehicle distance confirmation lines, etc. Their length and width play an important role in ensuring driving safety and providing visual guidance. For example, each white dotted line of the lane dividing line is 6 meters long, the distance between the two lines is 9 meters, and the total distance between the two white lines plus the middle is 21 meters.

[0120] Similarly, road signs also have length and width. Road signs on highways are used to provide direction instructions, distance prompts and other information. Their length and width are set according to actual needs. The design of road signs should ensure that drivers can clearly identify them when driving at high speeds and respond in advance. In addition, in some cases, longitudinal 100-meter length signs will be set on highways to remind drivers to keep a safe distance from the vehicle in front. Guide arrows also have length and width. Guide arrows are used to indicate the direction of vehicle travel. Their length is set according to actual needs and road width. Features that may exist in tunnels include emergency parking areas, fire-fighting equipment, surveillance cameras, etc., and their length and width are set according to actual needs.

[0121] Among them, when selecting true value points through the above-mentioned methods 1 to 3, environmental factors need to be considered. For example, the environmental factors in some sampling areas are relatively harsh, which may affect the accuracy of the coordinate collection of the true value points. For this reason, it is necessary to specially mark the coordinates of the true value points collected in these harsh environments. When verifying the high-precision map later, the coordinates of the true value points collected in these harsh environments can be considered as extreme points, which are distinguished from the coordinates of the true value points collected in normal environments.

[0122] Among them, if the error between the coordinates of the true value points collected in some normal environments and the corresponding coordinates in the high-precision map is large, it may indicate that there may be problems such as a collection vehicle failure during the production of the high-precision map, resulting in problems with the original data used to make the high-precision map. In addition, the error range between the coordinates of the true value points collected in some harsh environments and the corresponding coordinates in the high-precision map can be appropriately relaxed to eliminate the influence of environmental factors.

[0123] Among them, after the true value point is determined, the selected true value point can be accurately measured using measurement tools such as GNSS, RTK and total station to obtain its true spatial coordinates as the above-mentioned true coordinates.

[0124] For example, the following three examples of verification point selection are listed below:

[0125] Example 1: Taking area unit A and the selected sampling area as the mountain highway in area unit A as an example, the horizontal verification point can be selected from a clear and densely populated section entrance of the mountain highway, where the road surface is flat and there are no obstructions, which is suitable for horizontal accuracy verification. The elevation verification point can be selected from a road sign less than 5 meters away from the entrance. The road sign is located in an open area, which is convenient for measuring its elevation accuracy. In addition, due to the complex terrain of the mountainous area, the relative accuracy verification point (which can be omitted) can be selected from an obvious feature point in front of the tunnel, such as a warning sign in front of the tunnel entrance.

[0126] Among them, mountain highways pass through mountainous areas with undulating terrain and dense trees around them, which has a certain impact on satellite signal reception. Therefore, mountain highways are selected as the sampling area to be more representative.

[0127] Example 2: Taking regional unit B as an example, the suburban expressway between city C1 and city C2 is selected as the sampling area. This section is located in the suburbs of the city and is surrounded by some buildings and trees, but overall it has little impact on satellite signal reception. The horizontal verification point can be selected from a straight road section exit of a suburban expressway, where the road section has a wide field of view, moderate traffic volume, and clear point cloud data. The elevation verification point can be selected near the exit to select a road sign with a guide strip less than 5 meters high. The road sign is located in an open area, which is convenient for elevation accuracy verification. The relative accuracy verification point (can be omitted) can be selected from a curve near the exit. The lane lines on the curve are clear and can be used as a relative accuracy verification point.

[0128] Example 3: Taking regional unit C as an example, the urban ordinary road of city C3 in regional unit C is selected as the sampling area. This road section is located in the central area of ​​the city, surrounded by high-rise buildings, and there are many vehicles and pedestrians, which have a certain impact on satellite signal reception. There may be electromagnetic interference and signal blocking problems. Among them, the horizontal verification point can be selected from an intersection entrance of an ordinary urban road. The traffic there is busy, but the point cloud data is still relatively clear and can be used for horizontal accuracy verification. The elevation verification point can be selected near the intersection. A road sign with traffic information can be selected. The road sign is located in an open area with a moderate height, which is convenient for elevation accuracy verification. Since there is a lack of obvious relative accuracy verification points on ordinary urban roads, it can be omitted here.

[0129] In addition, in some implementations, for example, to ensure the accuracy of the data source during high-precision map verification, the data accuracy of the true value points can be verified by itself to exclude inaccurate true value point data, thereby ensuring the objectivity and fairness of subsequent high-precision map evaluations.

[0130] The embodiment of the present application ensures the comprehensiveness and representativeness of the truth points by dividing the area units and evenly extracting the truth points in units of area. At the same time, different types of sampling areas are selected according to the surrounding environment of the trajectory and the road characteristics to ensure the adequacy and rationality of the sampling. In addition, through detailed truth point selection criteria, including clear and dense road section exits or entrances, guide strips and road signs at road section entrances and exits, and various road feature points, such as tunnel front / rear feature points, ground line length and width, road sign length and width, etc., the accuracy and effectiveness of the truth points are ensured. Finally, when selecting the truth points, the influence of environmental factors on the GPS signal is fully considered, such as mountainous areas, waters, electromagnetic interference, etc., thereby improving the reliability of the truth points.

[0131] The following describes in detail how to verify the accuracy of a high-precision map through some examples.

[0132] As mentioned above, a set of true value points may include at least one of a horizontal verification point, an elevation verification point, and a relative accuracy verification point. Among them, the horizontal verification point and the elevation verification point can be used to verify the absolute accuracy of the high-precision map, and the relative accuracy verification point can be used to verify the relative accuracy of the high-precision map. The following three examples are provided:

[0133] Case ①: If a set of true value points includes horizontal verification points, the absolute accuracy of the HD map is determined based on the real coordinates of the horizontal verification points and the corresponding map coordinates of the horizontal verification points in the HD map;

[0134] Case ②: If a set of true value points includes elevation verification points, the absolute accuracy of the high-precision map is determined based on the real coordinates of the elevation verification points and the corresponding map coordinates of the elevation verification points in the high-precision map;

[0135] Case ③: If a set of true value points includes relative accuracy verification points, the relative accuracy of the high-precision map is determined based on the real coordinates of at least two relative accuracy verification points and the corresponding map coordinates of each relative accuracy verification point in the high-precision map.

[0136] For situations ① and ②, the following formula can be set:

[0137]

[0138] Pass rate = (number of points less than the threshold / sample size) * 100%

[0139] In the above formula, , , are the real coordinates of the true value point p1 on the X-axis, Y-axis, and Z-axis on the point cloud, respectively. , , are the map coordinates of the corresponding point of the true value point p1 on the high-precision map on the X-axis, Y-axis, and Z-axis respectively. The threshold is a set value (for example, 1 meter). The number of points less than the threshold refers to the number of true value points whose absolute accuracy D is less than the threshold. The sample size is the total number of true value points selected.

[0140] For situation ③, when determining the relative accuracy of the high-precision map, it is necessary to obtain the precision error between each relative accuracy verification point and the map coordinates corresponding to the relative accuracy verification point in the high-precision map, and then determine the relative accuracy of the high-precision map based on at least two precision errors.

[0141] Exemplarily, taking the first relative accuracy verification point and the second relative accuracy verification point as examples, the absolute accuracy of the first relative accuracy verification point and the absolute accuracy of the second relative accuracy verification point can be calculated using the above-mentioned absolute accuracy calculation formula, and then based on these two absolute accuracies, the relative accuracy of the high-precision map can be further determined.

[0142] For example, the relative accuracy of a high-precision map can be calculated using the following formula:

[0143]

[0144] Pass rate = (number of points less than the threshold / sample size) * 100%

[0145] In the above formula, , are the real coordinates of the first relative accuracy verification point on the X-axis and Y-axis on the point cloud respectively; , They are the real coordinates of the second relative accuracy verification point on the X-axis and Y-axis on the point cloud respectively; , are the map coordinates of the first relative accuracy verification point on the high-precision map on the X-axis and Y-axis respectively; , They are the map coordinates of the second relative accuracy verification point on the high-precision map on the X-axis and Y-axis respectively. The threshold is a set value (for example, 10 meters). The number of points less than the threshold refers to the number of true value points whose relative accuracy is less than the threshold. The sample size is the total number of true value points selected.

[0146] Among them, since the relative accuracy verification points are usually selected as position points on the horizontal plane in the real scene, the real coordinates of the relative accuracy verification points on the z-axis on the point cloud are omitted in the above relative accuracy calculation formula. It should be noted that in some special cases, if the relative accuracy verification points have real coordinates on the z-axis on the point cloud, the relative accuracy calculation formula can also be reconstructed with reference to the above relative accuracy calculation formula to calculate the relative accuracy.

[0147] Among them, the result set is calculated according to the above formula, and it can be judged as qualified if it meets certain quality requirements. For example, the quality requirement of absolute accuracy is defined as 98%≤1m.

[0148] The embodiment of the present application can verify the absolute accuracy and relative accuracy of the high-precision map by utilizing the real coordinates of the horizontal verification points, elevation verification points and relative accuracy verification points, thereby making the verification more sufficient and accurate.

[0149] Figure 4 The overall framework flow chart of the high-precision map accuracy verification method provided in the embodiment of the present application is as follows: Figure 4 As shown, it is generally divided into 4 major steps:

[0150] Step 1: Select a location.

[0151] Step (2): Get the true value.

[0152] Step (3): Data comparison.

[0153] Step 4: Accuracy assessment.

[0154] In this embodiment, step (1) uniformly selects true value points in each area unit, and ensures that the true value points can contain feature points under various environments. Then, step (2) uses measurement tools such as GNSS, RTK and total station to accurately measure the selected true value points, and obtains their spatial coordinates as true coordinates. Then, step (3) compares the measured true coordinates with the map coordinates of the corresponding points in the high-precision map data to calculate the error value between the two. Finally, step (4) evaluates the accuracy of the high-precision map data according to the size and distribution of the error value, and generates a corresponding evaluation report. Through the above steps, this solution can achieve a comprehensive and accurate evaluation of the absolute accuracy and relative accuracy of high-precision map data, and provide reliable support for map production quality monitoring and map product use.

[0155] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0156] Figure 5 A schematic diagram of the structure of a high-precision map accuracy verification device provided in an embodiment of the present application, such as Figure 5 As shown, the high-precision map accuracy verification device 500 includes a region division module 510, a sampling configuration module 520, a point value selection module 530, a coordinate acquisition module 540, and an accuracy verification module 550.

[0157] Among them, the area division module 510 is used to partition the real geographical area into at least one area unit. The sampling configuration module 520 is used to configure at least one sampling area for each area unit based on the environmental information of the area unit. The point value selection module 530 is used to select at least one group of true value points in the sampling area. The coordinate acquisition module 540 is used to obtain the real coordinates of the true value points. The accuracy verification module 550 is used to determine the accuracy of the high-precision map based on the real coordinates and the map coordinates corresponding to the true value points in the high-precision map.

[0158] Optionally, the sampling configuration module may be specifically used to: determine whether there is a target environment that meets set conditions in the area unit based on the environmental information of the area unit; if there is a target environment, configure at least one sampling area for each target environment.

[0159] Optionally, the target environment includes: mountainous area, tunnel, highway, urban area or any combination thereof.

[0160] Optionally, the sampling configuration module may be specifically used to select an exit or entrance of a road section of a target environment as a sampling area.

[0161] Optionally, a set of true value points includes: at least one of: horizontal verification points, elevation verification points, and relative accuracy verification points.

[0162] Optionally, the accuracy verification module can be specifically used for: if a group of true value points include horizontal verification points, then the absolute accuracy of the high-precision map is determined based on the real coordinates of the horizontal verification points and the corresponding map coordinates of the horizontal verification points in the high-precision map; if a group of true value points include elevation verification points, then the absolute accuracy of the high-precision map is determined based on the real coordinates of the elevation verification points and the corresponding map coordinates of the elevation verification points in the high-precision map; if a group of true value points include relative accuracy verification points, then the relative accuracy of the high-precision map is determined based on the real coordinates of at least two relative accuracy verification points and the corresponding map coordinates of each relative accuracy verification point in the high-precision map.

[0163] Optionally, the point value selection module can be specifically used for: if a group of true value points includes horizontal verification points, then at least one horizontal verification point is selected based on at least one of the sharp corners of the guide strip at the exit or entrance of the sampling area, the merged separation point at the exit or entrance of the sampling area, and the specific position points in the sampling area. If a group of true value points includes elevation verification points, then the road signs around the horizontal verification points are obtained, and at least one elevation verification point is selected based on the road signs. If a group of true value points includes relative accuracy verification points, then the road signs in the target environment are obtained, and at least two position points are determined on the boundary line of the road signs as at least two relative accuracy verification points.

[0164] Optionally, the accuracy verification module can be specifically used to: obtain the accuracy error between each relative accuracy verification point and the map coordinates corresponding to the relative accuracy verification point in the high-precision map; and determine the relative accuracy of the high-precision map based on at least two accuracy errors.

[0165] Optionally, it also includes a group number determination module, which is used to determine the total number of groups of true value points required for the real geographical area based on the sampling interval distance; and determine the number of groups of true value points for each area unit based on the total number of groups of true value points and the number of sampling areas for each area unit.

[0166] The device provided in the embodiment of the present application can be used to execute the method in the above-mentioned embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0167] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the area division module can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the above area division module. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0168] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more microprocessors (digital signal processors, DSP), or one or more field programmable gate arrays (FPGA), etc. For another example, when a module above is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0169] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 600 includes: at least one processor 601, a memory 602, a bus 603 and a communication interface 604. In the embodiment, the processor, the communication interface and the memory communicate with each other through the bus. The communication interface is used to communicate with other devices. The communication interface includes a communication interface for data transmission and a display interface or an operation interface for human-computer interaction. The processor is used to execute computer execution instructions, and specifically can execute the relevant steps in the method described in the above embodiment.

[0170] The processor may be a central processing unit, or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the electronic device may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs. The memory is used to store computer execution instructions. The memory may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0171] This embodiment also provides a computer-readable storage medium, in which computer instructions are stored. When at least one processor of an electronic device executes the computer instructions, the electronic device executes the methods provided in the above-mentioned various implementation modes.

[0172] This embodiment also provides a computer program product, which includes computer instructions. The computer instructions are stored in a readable storage electronic device. At least one processor can read the computer instructions from the readable storage medium. At least one processor executes the computer instructions so that the electronic device implements the methods provided by the above-mentioned various embodiments.

[0173] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0174] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0175] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0176] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0177] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0178] In this application, "at least one" means one or more, and "more" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship; in the formula, the character " / " indicates that the previous and next associated objects are in a "division" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0179] It is to be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and are not intended to limit the scope of the embodiments of the present application. In the embodiments of the present application, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0180] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for verifying the accuracy of a high-precision map, characterized in that: include: partitioning the real geographical area into at least one area unit; Based on the environmental information of the area unit, configuring at least one sampling area for each area unit; Selecting at least one set of true value points in the sampling area; Obtaining the real coordinates of the true value point; Determining the accuracy of the high-precision map based on the real coordinates and the map coordinates corresponding to the true value points in the high-precision map; The configuring at least one sampling area for each area unit based on the environmental information of the area unit includes: Based on the environmental information of the area unit, determining whether there is a target environment that meets a set condition in the area unit; If the target environment exists, at least one sampling area is configured for each target environment.

2. The method according to claim 1, characterized in that: The target environment includes: one or any combination of mountainous areas, tunnels, highways, and urban areas.

3. The method according to claim 1, characterized in that The configuring at least one sampling area for each target environment comprises: The exit or entrance of the road section of the target environment is selected as the sampling area.

4. The method according to any one of claims 1 to 3, characterized in that: The group of true value points includes: at least one of: horizontal verification points, elevation verification points, and relative accuracy verification points.

5. The method according to claim 4, characterized in that The determining the accuracy of the high-precision map based on the real coordinates and the map coordinates corresponding to the true value points in the high-precision map includes: If the set of true value points includes the horizontal verification point, determining the absolute accuracy of the high-precision map based on the real coordinates of the horizontal verification point and the map coordinates corresponding to the horizontal verification point in the high-precision map; If the set of true value points includes the elevation verification point, determining the absolute accuracy of the high-precision map based on the real coordinates of the elevation verification point and the map coordinates corresponding to the elevation verification point in the high-precision map; If the relative accuracy verification point is included in the set of true value points, the relative accuracy of the high-precision map is determined based on the real coordinates of at least two relative accuracy verification points and the corresponding map coordinates of each relative accuracy verification point in the high-precision map.

6. The method according to claim 4, characterized in that The selecting at least one set of true value points in the sampling area comprises: If the set of true value points includes the horizontal verification point, at least one horizontal verification point is selected based on at least one of the guide strip tip angle at the outlet or inlet of the sampling area, the merging and separation point at the outlet or inlet of the sampling area, and a specific position point in the sampling area; If the set of true value points includes the elevation verification point, then obtaining road signs existing around the horizontal verification point, and selecting at least one elevation verification point based on the road signs; If the group of true value points includes the relative accuracy verification point, a road sign in the target environment is acquired, and at least two position points are determined in the boundary line of the road sign as at least two relative accuracy verification points.

7. The method according to claim 5, characterized in that The determining the relative accuracy of the high-precision map based on the real coordinates of at least two relative accuracy verification points and the map coordinates corresponding to each relative accuracy verification point in the high-precision map includes: Obtaining the accuracy error between each relative accuracy verification point and the map coordinates corresponding to the relative accuracy verification point in the high-precision map; Based on at least two of the precision errors, the relative accuracy of the high-precision map is determined.

8. The method according to claim 1, characterized in that The method further comprises: Determining the total number of true value point groups required for the real geographic area according to the sampling interval distance; The number of groups of true value points of each area unit is determined according to the total number of groups of true value points and the number of sampling areas of each area unit.

9. A high-precision map accuracy verification device, characterized in that: include: A region division module, used for dividing a real geographical region into at least one region unit; A sampling configuration module, configured to configure at least one sampling area for each area unit based on the environmental information of the area unit; A point value selection module, used to select at least one set of true value points in the sampling area; A coordinate acquisition module, used to acquire the real coordinates of the true value point; An accuracy verification module, used to determine the accuracy of the high-precision map based on the real coordinates and the map coordinates corresponding to the true value points in the high-precision map; The sampling configuration module is specifically used to determine whether there is a target environment that meets the set conditions in the area unit based on the environmental information of the area unit; if the target environment exists, at least one sampling area is configured for each target environment.

10. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.