A map creation method and apparatus

Abstract

The application discloses a map creation method and device. In the method, first, environment data collected by a mobile device for a target area is acquired; then, the environment data is classified to acquire at least one data set containing environment data corresponding to the same type of road surface element; then, based on the three-dimensional space coordinates corresponding to each environment data contained in each data set, the confidence degrees corresponding to each data set are determined; and based on the confidence degrees corresponding to each data set, a high-precision map is created. Compared with the prior art, the scheme provided in the embodiment of the application can create a high-precision map, thereby solving the problem of low accuracy of the map created by the prior art, and the scheme provided in the embodiment of the application does not need to use a high-performance mobile device, so that a high-precision map can be acquired at a reduced cost, and the scheme has a wide application range.

Description

Technical Field

[0001] This application relates to the field of map creation technology, and in particular to a map creation method and apparatus. Background Technology

[0002] In applications such as assisted driving or autonomous driving, vehicles typically need to determine the type and location of road elements (such as lane lines, road edges, and road signs) in the surrounding environment in order to adjust their driving behavior accordingly.

[0003] To meet this need of vehicles, maps that display the surrounding environment are typically built for them. When building a map, environmental data is first acquired by data acquisition devices (such as depth cameras or LiDAR), and then a map is created based on this environmental data.

[0004] However, the environmental data may contain data with low accuracy, resulting in low map accuracy. Therefore, there is an urgent need for a solution that can build maps with higher accuracy. Summary of the Invention

[0005] To address the aforementioned technical problems, this disclosure is proposed. Embodiments of this disclosure provide a map creation method and apparatus.

[0006] According to one aspect of this disclosure, a map creation method is provided, comprising:

[0007] Acquire environmental data collected by mobile devices for a target area;

[0008] By classifying the environmental data, at least one data set is determined, wherein the environmental data contained in each data set corresponds to the same type of road surface element;

[0009] Based on the three-dimensional spatial coordinates corresponding to each environmental data contained in each of the data sets, the confidence level corresponding to each of the data sets is determined.

[0010] High-precision maps are created based on the confidence levels corresponding to each of the aforementioned data sets.

[0011] According to another aspect of the present disclosure, a map creation apparatus is provided, comprising:

[0012] The data acquisition module is used to acquire environmental data collected by mobile devices for the target area;

[0013] The set determination module is used to classify the environmental data acquired by the data acquisition module to determine at least one data set, wherein the environmental data contained in each data set corresponds to the same type of road surface element;

[0014] The confidence level determination module is used to determine the confidence level of each data set based on the three-dimensional spatial coordinates of each data set contained in each data set determined by the set determination module.

[0015] The map creation module is used to create a high-precision map based on the confidence scores corresponding to each of the data sets determined by the confidence score determination module.

[0016] According to another aspect of the present disclosure, a computer-readable storage medium is provided, the storage medium storing a computer program for performing the map creation method described in any of the above embodiments of the present disclosure.

[0017] According to another aspect of the present disclosure, an electronic device is provided, the electronic device comprising:

[0018] processor;

[0019] Memory used to store the processor's executable instructions;

[0020] The processor is configured to read the executable instructions from the memory and execute the instructions to implement the map creation method described in any of the above embodiments of this disclosure.

[0021] Based on the solution provided in this disclosure, after acquiring environmental data of a target area, the environmental data can be divided into at least one data set. Each data set contains environmental data corresponding to the same type of road surface element. Then, the three-dimensional spatial coordinates corresponding to the environmental data in each data set are determined, and the confidence level for each data set is determined. Finally, a high-precision map is created based on the confidence level. Compared with existing solutions, the solution provided in this disclosure can create higher-precision maps, solving the problem of low accuracy in maps created by existing technologies.

[0022] Furthermore, the solution provided in this disclosure has low performance requirements for the mobile devices used to collect environmental data, eliminating the need for high-performance mobile devices. This allows for the acquisition of high-precision maps at a reduced cost, thus having a wider range of applications. Attached Figure Description

[0023] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0024] Figure 1 This is a scenario diagram to which this disclosure applies.

[0025] Figure 2 This is a schematic flowchart of a map creation method provided in an exemplary embodiment of this disclosure.

[0026] Figure 3 This is a flowchart illustrating a map creation method provided in another exemplary embodiment of this disclosure.

[0027] Figure 4 This is an example diagram of the distribution of environmental data provided in an exemplary embodiment of this disclosure.

[0028] Figure 5(a) is an example diagram of the distribution of environmental data provided by another exemplary embodiment of this disclosure.

[0029] Figure 5(b) is an example diagram of the distribution of environmental data provided by another exemplary embodiment of this disclosure.

[0030] Figure 6 This is a flowchart illustrating a map creation method provided in another exemplary embodiment of this disclosure.

[0031] Figure 7 This is a flowchart illustrating a map creation method provided in another exemplary embodiment of this disclosure.

[0032] Figure 8 This is a flowchart illustrating a map creation method provided in another exemplary embodiment of this disclosure.

[0033] Figure 9 This is a flowchart illustrating a map creation method provided in another exemplary embodiment of this disclosure.

[0034] Figure 10 This is a schematic diagram of the structure of a map creation apparatus provided in an exemplary embodiment of the present disclosure.

[0035] Figure 11 This is a schematic diagram of the structure of a map creation apparatus provided in another exemplary embodiment of the present disclosure.

[0036] Figure 12 This is a structural diagram of an electronic device provided in an exemplary embodiment of this disclosure. Detailed Implementation

[0037] Hereinafter, exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present disclosure, and not all embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described herein.

[0038] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0039] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of this disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0040] It should also be understood that in the embodiments of this disclosure, "multiple" can refer to two or more, and "at least one" can refer to one, two or more.

[0041] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.

[0042] Furthermore, the term "and / or" in this disclosure is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.

[0043] It should also be understood that the description of the various embodiments in this disclosure emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0044] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0045] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0046] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0047] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0048] The embodiments disclosed herein can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate together with a wide range of other general-purpose or special-purpose computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, and servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems, etc.

[0049] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are executed by remote processing devices linked through communication networks. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0050] Application Overview

[0051] In applications such as assisted driving or autonomous driving, vehicles often need to determine the type and location of road elements (such as lane lines, road edges, and road signs) in their surroundings in order to adjust their driving behavior accordingly. For example, if a road sign is located ahead of the vehicle, the vehicle's direction can be adjusted appropriately based on the sign's indication. To meet this need, a map including the surrounding environment is typically built for the vehicle.

[0052] When building a map, environmental data of various road elements in the surrounding environment is usually collected by a data acquisition device. This environmental data includes data that indicates the type and location of the road elements. For example, the environmental data may include point cloud datasets and / or depth images corresponding to the road elements. Then, by clustering the environmental data, the type and location of each road element are determined, and a map indicating the surrounding environment is further constructed accordingly.

[0053] The point cloud dataset consists of multiple points, each referring to a corresponding point cloud data. In one example, the point cloud dataset can be determined by LiDAR measurement (i.e., the acquisition device includes LiDAR). The laser emitted by the LiDAR is reflected after encountering a certain location of the road element, and the reflected light is received by the LiDAR. Therefore, each point in the point cloud dataset (i.e., point cloud data) typically includes the three-dimensional coordinates of a certain location of the road element and the laser reflection intensity.

[0054] However, the accuracy of environmental data collected by the acquisition equipment is sometimes low. For example, if the environmental data includes depth images of road surface elements, the depth images captured by the acquisition equipment may be blurry in rainy weather, resulting in low clarity of road surface elements in the depth images and a corresponding decrease in the accuracy of the environmental data. In addition, if there are obstructions such as trees or buildings in the surrounding environment, the laser light reflected from the road surface elements may be affected by the obstructions and cannot be received by the lidar, resulting in sparse distribution of point cloud data and a corresponding decrease in the accuracy of the point cloud dataset determined by the lidar.

[0055] When the collected road surface element data is inaccurate, the map created based on that data will typically be less accurate. Therefore, maps created using existing methods are generally less accurate.

[0056] In addition, to improve map accuracy, one approach is to use high-performance data acquisition equipment to obtain more accurate environmental data. However, high-performance acquisition equipment is typically expensive, increasing the cost of map creation and thus limiting its widespread adoption.

[0057] In view of this, embodiments of this disclosure provide a map creation method and apparatus. During the map creation process using the scheme of this disclosure, after acquiring environmental data, the confidence level of the environmental data is determined, and a map is created based on environmental data with a higher confidence level.

[0058] When constructing a map using the scheme of this disclosure embodiment, a high-precision map can be obtained by using environmental data with high confidence, thus meeting the needs of vehicles. Furthermore, this scheme does not require high-performance data acquisition equipment, resulting in lower costs for creating high-precision maps, and therefore has a wide range of applications.

[0059] Exemplary System

[0060] The embodiments disclosed herein can be applied to application scenarios that require map creation, such as assisted driving or autonomous driving.

[0061] For example, in assisted driving or autonomous driving applications, environmental data corresponding to the vehicle's surrounding environment can be collected by depth cameras and LiDAR installed in the vehicle. The solution provided in this disclosure can be used to create a high-precision map of the vehicle using the environmental data, so that the map can provide a reference for assisted driving or autonomous driving.

[0062] The device used to implement the map creation method of the embodiments of this disclosure can be an electronic device such as a computer, an intelligent driving control device, or a server (e.g., an in-vehicle server), and... Figure 1 An example diagram of the device is disclosed in the document.

[0063] See Figure 1 The map creation device 100, which creates a map based on the solution provided in the embodiments of this disclosure, is connected to a device for collecting environmental data. This device is usually installed on a vehicle and moves with the vehicle. In this disclosure, the device for collecting environmental data is referred to as a mobile device.

[0064] exist Figure 1 In this context, the mobile device includes a first device 200 and a second device 300 connected to the map creation device 100. In practical applications, more mobile devices connected to the map creation device 100 and used for collecting environmental data may also be included, but this disclosure does not limit this.

[0065] The first device 200 and the second device 300 can collect the same type of environmental data or different types of environmental data. In one example, one mobile device may include a depth camera, and the environmental data collected by this mobile device may include depth images corresponding to road surface elements; the other mobile device may include a LiDAR, and the environmental data collected by this mobile device may include point cloud datasets corresponding to road surface elements. Alternatively, in another example, the environmental data collected by both the first device 200 and the second device 300 may include point cloud datasets corresponding to road surface elements, or may both include depth images corresponding to road surface elements.

[0066] Furthermore, the connection methods between the first device 200 and the second device 300 and the map creation device 100 can include various methods. In one feasible method, the map creation device 100 can be electrically connected to the first device 200 and the second device 300. For example, if the map creation device 100 is an in-vehicle infotainment device, then the map creation device 100 is electrically connected to the first device 200 and the second device 300.

[0067] In another feasible approach, the connection between the map creation device 100 and the first device 200 and the second device 300 can also be a network connection.

[0068] Of course, the connection between the map creation device 100 and the first device 200, and between the map creation device 100 and the second device 300, can be the same or different; this disclosure does not limit this.

[0069] The first device 200 and the second device 300 can collect environmental data for a target area. In one example, the solution provided in this embodiment is applied to the field of assisted driving or autonomous driving. The target area may include the area of ​​the vehicle's surrounding environment. The environmental data may include data indicating the type and location of road surface elements included in the target area. For example, the environmental data may include a point cloud dataset corresponding to the road surface elements, or a depth image corresponding to the road surface elements, or both a point cloud dataset and a depth image corresponding to the road surface elements. Of course, the environmental data may also include other data that can indicate the type and location of road surface elements, which is not limited in this disclosure.

[0070] The first device 200 and the second device 300 can transmit the collected environmental data to the map creation device 100. After acquiring the environmental data, the map creation device 100 executes the map creation method provided in this embodiment of the disclosure to create a high-precision map.

[0071] In assisted driving or autonomous driving applications, the map creation device 100 can be an in-vehicle device (such as an in-vehicle smart terminal). In this case, the map creation device 100 can create a high-precision map for the vehicle based on the received environmental data to meet the vehicle's needs.

[0072] Exemplary methods

[0073] Figure 2 This is a schematic flowchart of a map creation method provided in an exemplary embodiment of this application. This embodiment can be applied to electronic devices, such as... Figure 2 As shown, it includes the following steps:

[0074] Step S201: Obtain environmental data collected by the mobile device for the target area.

[0075] The target area typically includes the area where a map needs to be created. For example, in assisted driving or autonomous driving applications, the target area usually includes the area surrounding the road where the vehicle is located.

[0076] The environmental data includes data indicating the type and location of road surface elements. For example, the environmental data may include depth images corresponding to the road surface elements; in this case, the mobile device may include a depth camera capable of capturing depth images. Alternatively, the environmental data may include a point cloud dataset corresponding to the road surface elements; in this case, the mobile device may include a LiDAR capable of generating the point cloud dataset. Or, in another example, the environmental data may include both depth images and point cloud datasets corresponding to the road surface elements, or it may also include other data indicating the type and location of the road surface elements.

[0077] Step S202: By classifying the environmental data, at least one data set is determined. Each data set contains environmental data corresponding to the same type of road surface element.

[0078] In this step, the semantics of the environmental data can be determined by analyzing and processing the environmental data, and the environmental data can be classified accordingly, with environmental data corresponding to the same type of road surface element grouped into the same data set.

[0079] In one example, the environmental data collected by the mobile device includes a point cloud dataset corresponding to the road edge. Through step S202, a dataset can be determined, in which the environmental data corresponds to the road surface element of the road edge.

[0080] In another example, the environmental data collected by the mobile device includes a point cloud dataset corresponding to the road edge, a point cloud dataset corresponding to the lane line, a depth image corresponding to the road edge, and a depth image corresponding to the lane line. Then, through the operation of step S202, the data set corresponding to the road edge can be obtained, which includes the point cloud dataset and depth image corresponding to the road edge, and the data set corresponding to the lane line can be obtained, which includes the point cloud dataset and depth image corresponding to the lane line.

[0081] Step S203: Based on the three-dimensional spatial coordinates corresponding to each environmental data contained in each dataset, determine the confidence level corresponding to each dataset.

[0082] The confidence level of a dataset can be used to characterize its accuracy. In the embodiments of this disclosure, generally, the higher the confidence level of a dataset, the higher its accuracy.

[0083] Step S204: Create a high-precision map based on the confidence level corresponding to each data set.

[0084] Since the confidence level of each dataset reflects its accuracy, the dataset with higher accuracy can be identified based on the confidence level of each dataset, thus enabling the creation of high-precision maps.

[0085] Based on the solution provided in this disclosure, after acquiring the environmental data of the target area, the environmental data can be divided into at least one data set, and the environmental data contained in each data set corresponds to the same type of road surface element. Then, the three-dimensional spatial coordinates corresponding to the environmental data contained in each data set are determined, the confidence level corresponding to each data set is determined, and a high-precision map is created based on the confidence level.

[0086] Therefore, compared with the solutions of the prior art, the solution provided by the embodiments of this disclosure can create higher accuracy maps and solve the problem of low accuracy of maps created by the prior art.

[0087] Furthermore, the solution provided in this disclosure has low performance requirements for the mobile devices used to collect environmental data, eliminating the need for high-performance mobile devices. This allows for the acquisition of high-precision maps at a reduced cost, thus having a wider range of applications.

[0088] In step S203 of this disclosure, the confidence level corresponding to each data set is determined based on the three-dimensional spatial coordinates corresponding to each environmental data contained in each data set. In one feasible implementation, such as... Figure 3 As shown above, in the above Figure 2 Based on the illustrated embodiment, step S203 may include the following steps:

[0089] Step S2031: Based on the three-dimensional spatial coordinates of each environmental data contained in each dataset, determine the three relationship curves between the first parameter of the road surface element and the three second parameters.

[0090] In step S2031, by performing data fitting on the environmental data contained in the same dataset, three relationship curves are determined for the road surface elements corresponding to that dataset. These three relationship curves respectively characterize the relationship between the first parameter and one of the second parameters.

[0091] The first parameter is the arc length of the observation point of the road element from the starting point of the relationship curve, and the second parameters are the distances in three dimensions between the observation point and the projection point of the observation point on the relationship curve.

[0092] In the solutions provided in this disclosure, the observation point refers to a point on the surface of a road element. If the environmental data includes a point cloud dataset corresponding to the road element, the laser emitted by the mobile device will be reflected after reaching the observation point of the road element. The mobile device receives the emitted laser and generates a point cloud dataset accordingly. Furthermore, if the environmental data includes depth images corresponding to the road element, the mobile device can acquire depth images of the observation points of the road element at different angles when capturing images of the target environment from different angles.

[0093] Based on the operation in step S2031, three relationship curves for the road surface elements corresponding to each data set can be obtained in parts. Each relationship curve can be represented by a cubic polynomial. For example, the three relationship curves can be represented by the following formula:

[0094] rx =a0 t t t + b0 t t + c0 Formula (1) is given by t + d0 - x_obs.

[0095] ry =a1 t t t + b1 t t + c1 t + d1 - y_obs formula (2);

[0096] rz =a2 t t t + b2 t t + c2 Formula (3) is t + d2 - z_obs.

[0097] The three formulas above correspond to three relationship curves, where t is the first parameter, which is the arc length of the observation point of the road element from the starting point of the relationship curve; rx, ry, and rz are all second parameters, where rx represents the distance in the x-direction between the observation point and its projection point on the relationship curve, ry represents the distance in the y-direction between the observation point and its projection point on the relationship curve, and rz represents the distance in the z-direction between the observation point and its projection point on the relationship curve; a0, b0, c0, d0, a1, b1, c1, d1, a2, b2, c2, and d2 are the coefficients of the cubic polynomial, and x_obs, y_obs, and z_obs represent the constant terms of the relationship curve.

[0098] By fitting and calculating the environmental data contained in each dataset, the specific values ​​of a0, b0, c0, d0, a1, b1, c1, d1, a2, b2, c2, d2, x_obs, y_obs, and z_obs can be determined, thereby obtaining the corresponding relationship curves.

[0099] Step S2032: Based on the relationship curve, determine the degree of aggregation of the distribution of environmental data contained in each dataset.

[0100] In the solution provided in the embodiments of this disclosure, the environmental data contained in each data set corresponds to the same type of road surface element. That is, based on the environmental data contained in a certain data set, the type and location of a certain type of road surface element corresponding to that data set can be determined.

[0101] In this case, if the environmental data contained in a certain dataset is relatively concentrated, it indicates that the degree of aggregation of the environmental data contained in the dataset is high, the accuracy of the environmental data contained in the dataset is high, and the category and location of the road surface elements determined based on the dataset are close to the actual environment.

[0102] Correspondingly, if the environmental data contained in a certain dataset is scattered, that is, the degree of aggregation of the environmental data contained in the dataset is low, then the accuracy of the environmental data contained in the dataset is low, and the category and location of the road surface elements determined based on the dataset have a large deviation from the actual environment.

[0103] In other words, the accuracy of determining road surface elements based on environmental data contained in a dataset is usually related to the degree of aggregation of the environmental data contained in the dataset. The higher the degree of aggregation, the higher the accuracy of determining road surface elements based on the environmental data contained in the dataset.

[0104] See Figure 4 The diagram illustrates a scenario where road surface elements include lane lines and road edges. After classifying the environmental data, a first data set corresponding to the lane lines and a second data set corresponding to the road edges can be determined. The distribution of lane lines determined based on the environmental data contained in the first data set is shown below. Figure 4 As shown by the solid line in the image, the distribution of road edges, determined based on environmental data contained in the second dataset, is as follows: Figure 4 As shown by the dashed lines, the lines containing arrows represent the vehicle's travel route in this example.

[0105] exist Figure 4 In this context, the solid lines corresponding to lane markings are more concentrated than the dashed lines corresponding to road edges, indicating a higher degree of aggregation in the environmental data distribution within the first dataset. In this case, lane markings determined based on the environmental data within the first dataset are often closer to the actual environment than road edges determined based on the environmental data within the second dataset.

[0106] In another example, the distribution of environmental data within one dataset is shown in Figure 5(a), and the distribution of environmental data within another dataset is shown in Figure 5(b). Comparing the two, it can be determined that the environmental data distribution within the dataset corresponding to Figure 5(b) has a higher degree of aggregation. Consequently, the accuracy of the road surface elements determined based on the environmental data within the dataset corresponding to Figure 5(b) is higher.

[0107] Step S2033: Based on the degree of aggregation of the distribution of environmental data, determine the confidence level corresponding to each data set.

[0108] The accuracy of a dataset is generally related to the degree of aggregation of the environmental data contained within it. Typically, the higher the degree of aggregation of the environmental data distributions within a dataset, the higher the confidence level of that dataset, and consequently, the higher the accuracy of the road surface elements determined by that dataset. Therefore, in this embodiment of the disclosure, the confidence level corresponding to each dataset can be determined based on the degree of aggregation of the environmental data distributions within the dataset.

[0109] In the solution provided by the embodiments of this disclosure, the degree of aggregation of the environmental data distribution contained in the dataset is determined, and then the confidence level corresponding to each dataset is determined based on the degree of aggregation. The accuracy of a dataset is generally related to the degree of aggregation of the environmental data contained within it, and the confidence level of each dataset is determined based on the degree of aggregation of the environmental data distribution within the dataset. Therefore, the confidence level determined by the solution of the embodiments of this disclosure can be used to evaluate the accuracy of the environmental data within each dataset.

[0110] See Figure 6 In another exemplary embodiment of this disclosure, the above-described Figure 3 Based on the illustrated embodiment, the degree of aggregation of the distribution of environmental data contained in each dataset is determined through the following steps:

[0111] Step S20321: Based on the relationship curve and the three-dimensional spatial coordinates of each environmental data in each data set, determine the residual matrix corresponding to each data set.

[0112] In one example, the residual matrix corresponding to a certain dataset can be represented by the following formula:

[0113] Formula (4).

[0114] Where R represents the residual matrix corresponding to one of the datasets, which includes n environmental data points, where n is a positive integer, (rx0,ry0,rz0), (rx1,ry1,rz1), and (rxn,ryn,rzn) are the three-dimensional spatial coordinates of the environmental data contained in the dataset, and r is a constant.

[0115] Step S20322: Based on the residual matrix corresponding to each data set, determine the covariance matrix corresponding to each data set.

[0116] In this disclosure, the distribution of the residuals of environmental data typically approximates a normal distribution, which generally follows the formula:

[0117] Formula (5).

[0118] In the above formula, Let rx, ry, and rz be the parameters; rx, ry, and rz are all second parameters. rx represents the distance in the x-direction between the observation point and the projection point of the observation point on the relationship curve, ry represents the distance in the y-direction between the observation point and the projection point of the observation point on the relationship curve, and rz represents the distance in the z-direction between the observation point and the projection point of the observation point on the relationship curve. Represent the covariance matrix; The dimension representing environmental data is determined by using the three-dimensional spatial coordinates of the environmental data to determine the residual matrix corresponding to each data set in this application. It is 3; This represents the average of rx, ry, and rz; This is the transpose symbol for a matrix.

[0119] Therefore, based on formula (4), the covariance matrix of the dataset can be expressed by the following formula:

[0120] Formula (6).

[0121] In formula (6), Let R be the covariance matrix of one of the datasets, and let R be the residual matrix of that dataset. This represents the transpose of the residual matrix R.

[0122] Step S20323: Based on the trace of the covariance matrix corresponding to each data set, determine the unbiased estimator corresponding to each data set. The unbiased estimator is used to characterize the degree of aggregation of the distribution of environmental data contained in the data set.

[0123] In this embodiment of the disclosure, the variance of the residual matrix corresponding to a certain data set can be represented by the trace of the covariance matrix corresponding to that data set. The smaller the variance, the better the aggregation of the environmental data within that data set.

[0124] In one example, the unbiased estimator for one of the datasets can be expressed by the following formula:

[0125] Formula (7).

[0126] in, Let n represent the unbiased estimator corresponding to the dataset, and n represent the number of environmental data points contained in the dataset. This represents the trace of the covariance matrix corresponding to the dataset.

[0127] Based on formula (7), the trace of the covariance matrix corresponding to the data set can be used to determine the unbiased estimator corresponding to the data set. The unbiased estimator can characterize the degree of aggregation of the distribution of environmental data contained in the data set.

[0128] Furthermore, the confidence level of a dataset is generally positively correlated with the number of times environmental data is collected by the mobile device. Typically, the higher the number of times environmental data is collected, the richer the amount of environmental data contained in the dataset, and the higher the accuracy of determining road surface elements using this dataset. In other words, the higher the number of times environmental data is collected, the greater the confidence level of the dataset. Therefore, after determining the degree of aggregation of the various environmental data distributions within the dataset, the step of determining the confidence level of each dataset based on the degree of aggregation of each environmental data distribution can be achieved through the following operations:

[0129] Based on the unbiased estimator corresponding to the dataset and the number of times the mobile device collects environmental data, the confidence level corresponding to each dataset is determined.

[0130] In one example, the confidence level of a dataset can be determined using the following formula:

[0131] Formula (8).

[0132] In the above formula, This represents the confidence level of a data set, and the unbiased estimator of that data set is... , This represents the trace of the covariance matrix corresponding to the dataset.

[0133] in, Let n represent the unbiased estimator corresponding to the dataset, which contains n environmental data points. Furthermore, since the dataset contains n data points, and mobile devices typically acquire one environmental data point per data collection, the number of times the mobile device collects environmental data from this dataset is also n.

[0134] The solution provided by the above embodiments of this disclosure can determine the unbiased estimator corresponding to each data set based on the relationship curves of each data set. This unbiased estimator can characterize the degree of aggregation of the distributions of environmental data contained in each data set. Furthermore, based on the unbiased estimator and the number of times the mobile device collects environmental data, the confidence level corresponding to each data set can be determined, so as to create a high-precision map using the confidence levels of each data set.

[0135] In various embodiments of this disclosure, at least one data set is determined by classifying environmental data. In the actual map creation process, this data set can be determined in a variety of ways.

[0136] In one feasible implementation, environmental data is classified based on the semantics of each data set. In this case, the environmental data contained in the same data set may include environmental data collected by different mobile devices and corresponding to the same type of road surface elements.

[0137] Correspondingly, if the data set is determined through the above implementation method, the confidence level of each data set represents the confidence level of the environmental data corresponding to each type of road surface element.

[0138] For example, if the mobile device used to collect environmental data includes a depth camera and a lidar, and the collected environmental data includes environmental data corresponding to road edges and environmental data corresponding to lane lines, based on the above implementation, two data sets can be determined. One data set includes environmental data of road edges collected by the depth camera and lidar, and the other data set includes environmental data of lane lines collected by the depth camera and lidar.

[0139] In another feasible implementation, see [link to relevant documentation] Figure 7 , can be found in the above Figure 3 Based on the illustrated embodiment, environmental data is classified through the following steps to determine at least one dataset:

[0140] Step S2021: Based on the type of mobile device corresponding to each environmental data, classify the environmental data and determine at least one intermediate data set;

[0141] Step S2022: Based on the type of road surface element corresponding to each environmental data, classify the environmental data contained in each intermediate data set and determine at least one data set.

[0142] In other words, in this implementation, the environmental data is first classified based on the mobile devices that collect the environmental data to obtain an intermediate data set. In this case, the environmental data contained in the same intermediate data set are collected by the same type of mobile devices. Then, based on the type of road surface element corresponding to the environmental data, the environmental data contained in the intermediate data set are classified to determine at least one data set.

[0143] Alternatively, in this implementation, the environmental data can first be classified based on the type of road surface element corresponding to each environmental data to determine at least one intermediate data set. In this case, the environmental data contained in the same intermediate data set correspond to the same type of road surface element. Then, based on the type of mobile device corresponding to each environmental data, the environmental data contained in the intermediate data set can be classified to determine at least one data set.

[0144] The solution provided by the above implementation method ensures that the environmental data contained in each data set are collected by the same type of mobile device and correspond to the same type of road surface element.

[0145] For example, if the mobile device used to collect environmental data includes a depth camera and a LiDAR, and the collected environmental data includes environmental data corresponding to road edges and environmental data corresponding to lane lines, four data sets can be determined based on the above implementation method. These four data sets include: a data set consisting of environmental data of road edges collected by the depth camera, a data set consisting of environmental data of road edges collected by the LiDAR, a data set consisting of environmental data of lane lines collected by the depth camera, and a data set consisting of environmental data of lane lines collected by the LiDAR.

[0146] Furthermore, since the scheme for determining the data set provided by the embodiments of this disclosure contains environmental data collected by the same type of mobile device and corresponding to the same type of road surface element, the accuracy of each mobile data collection environmental data can be determined based on the confidence level of each data set.

[0147] For example, if the data set determined based on the scheme provided in the embodiments of this disclosure includes: a third data set consisting of environmental data of the roadside collected by a depth camera, and a fourth data set consisting of environmental data of the roadside collected by a lidar, if the confidence level of the third data set is higher than the confidence level of the fourth data set, it indicates that the accuracy of the environmental data collected by the depth camera is higher than the accuracy of the environmental data collected by the lidar.

[0148] Accordingly, see Figure 8 In the above Figure 7 Based on the illustrated embodiment, the following steps may also be included:

[0149] Step S2023: Determine the first target data set in each data set, where the confidence level of the first target data set is lower than the confidence level of the other data sets in each data set.

[0150] In this embodiment of the disclosure, the number of the first target data set can be N, where N is a preset positive integer.

[0151] Step S2024: Generate a prompt message based on the mobile device corresponding to the first target data set. This prompt message indicates that the mobile device corresponding to the first target data set has a low accuracy problem when collecting environmental data.

[0152] Through the operations in steps S2021 to S2022, the environmental data contained in each dataset is collected by the same type of mobile device and corresponds to the same type of road surface element. Accordingly, the confidence level of each dataset can reflect the accuracy of the environmental data collected by each mobile data collection device.

[0153] Because the confidence level of the first target dataset is lower than that of other datasets, the accuracy of the mobile device collecting environmental data within the first target dataset is low. This prompt message can alert technicians to inspect and repair the mobile device to improve its accuracy in collecting environmental data and further enhance the accuracy of map creation.

[0154] In the above embodiments of this disclosure, an operation is provided to create a high-precision map based on the confidence level corresponding to each data set. This operation can be implemented in a variety of ways.

[0155] In one feasible implementation, the operation of creating a high-precision map based on the confidence level corresponding to each dataset may include the following steps:

[0156] First, based on the confidence levels of each data set, a second target data set is determined, with the confidence level of the second target data set being greater than that of the other data sets.

[0157] The number of second target data sets can be preset, and the second target data sets are determined based on the confidence level of each data set and the preset number of second target data sets. Alternatively, a confidence threshold can be preset, and if the confidence level of a data set is greater than the confidence threshold, then that data set is determined to be the second target data set.

[0158] Because the confidence level of the second target dataset is higher than that of other datasets, the accuracy of the road surface elements determined by the second target dataset is higher.

[0159] Then, create high-precision maps corresponding to each data set, and mark and display the road surface elements determined by the second target data set in the high-precision maps.

[0160] The road surface elements determined by the second target data set are defined as high-accuracy road surface elements. These high-accuracy road surface elements are marked and displayed in the high-precision map, which can distinguish them from other road surface elements in the high-precision map.

[0161] There are several ways to mark and display this high-accuracy road surface element. In one example, the high-accuracy road surface element can be displayed in the high-precision map by highlighting it. Alternatively, in another example, the high-accuracy road surface element can be displayed in the high-precision map by using a different color than other road surface elements.

[0162] When creating a high-precision map using this implementation method, the map can be created based on the type and location of road elements determined by each data set. In this map, the road elements determined by the second target data set are marked. Since the road elements determined by the second target data set have higher accuracy, the high-precision map marks and displays the road elements with higher accuracy. This enables the distinction between high-accuracy road elements and other road elements in the high-precision map, making it easier to identify high-accuracy road elements in the high-precision map.

[0163] In another feasible implementation, the process of creating a high-precision map based on the confidence level corresponding to each dataset may include the following steps:

[0164] First, based on the confidence levels of each data set, a third target data set is determined, with the confidence level of the third target data set being greater than that of the other data sets.

[0165] Then, a high-precision map is created based on the third target dataset.

[0166] In this implementation, the map is created only using a third target dataset with high confidence, thus resulting in a map with high accuracy.

[0167] In practical applications, to ensure navigation accuracy, vehicles can navigate using both maps and other methods simultaneously. For example, vehicles can also navigate using the Global Positioning System (GPS) and an Inertial Navigation System (INS).

[0168] Based on the solution provided in the above embodiments of this disclosure, the confidence level of each data set can be determined. In this case, the weights of different navigation methods can be adjusted according to the confidence level of the data set. For this situation, if the mobile device includes at least two navigation methods, and one of these at least two navigation methods is a first map navigation method based on a high-precision map, see [link to relevant documentation]. Figure 9 In the above Figure 2 Based on the illustrated embodiments, the solution provided in this disclosure further includes the following steps:

[0169] Step S205: Determine the weight of applying the first map navigation method based on the confidence level and the preset threshold corresponding to each data set.

[0170] If the confidence level of each data set is greater than the preset threshold for each data set, it indicates that the accuracy of the environmental data contained in each data set is high, and the accuracy of the high-precision map created based on the data set is also high. In this case, the weight of using the first map navigation method for navigation can be increased accordingly.

[0171] Furthermore, if the confidence level of each data set is not greater than the preset threshold for each data set, it indicates that the accuracy of the environmental data contained in each data set is low. In this case, the weight of applying the first map navigation method for navigation can be reduced accordingly. In this operation, "the confidence level of each data set is not greater than the preset threshold for each data set" means that the confidence level of any one data set is not greater than the preset threshold for that data set.

[0172] In one feasible example, a pre-defined correspondence can be established between a first difference and the weight of applying a first map navigation method. This first difference is the difference between the confidence level of each data set and a preset threshold. In this correspondence, a larger first difference generally corresponds to a higher weight for applying the first map navigation method. Based on this correspondence, the weight of applying the first map navigation method can be determined.

[0173] Step S206: Navigate the mobile device based on the determined weight of the first map navigation method of the application.

[0174] The solution provided by this disclosure can adjust the weight of navigation using the first map navigation method based on the confidence level corresponding to each data set, thereby enabling the navigation method to be adjusted based on the confidence level corresponding to each data set, ensuring the accuracy of the navigation method and improving vehicle safety.

[0175] To clarify the beneficial effects of the embodiments of this disclosure, two examples are disclosed below. In one example, the navigation methods of the mobile device include a first map navigation method and an INS navigation method using INS. In this case, if the confidence level corresponding to each data set is greater than a preset threshold corresponding to that data set, the weight of the first map navigation method is increased, and the INS navigation method and the first map navigation method with increased weight are used together for navigation.

[0176] In this example, based on the comparison between the confidence level corresponding to each data set and the preset threshold, the weight of the first map navigation method among various navigation methods is adjusted, which can improve the accuracy of navigation accordingly.

[0177] In another example, the mobile device's navigation methods include: a first map navigation method, an INS navigation method using INS, and a GPS navigation method using GPS. In this case, if the confidence level corresponding to each data set is greater than a preset threshold corresponding to that data set, the weight of the first map navigation method is increased. Additionally, since the strength of the GPS signal easily affects the accuracy of GPS navigation, the current GPS signal strength can be determined; if the current GPS signal is weak, the weight of the GPS navigation method is decreased. Then, navigation is performed based on the adjusted weighted navigation methods.

[0178] In this example, the weight of the first map navigation method among various navigation methods is adjusted based on the comparison between the confidence level corresponding to each data set and the preset threshold, and the weight of the GPS navigation method among various navigation methods is adjusted based on the strength of the GPS signal, which can improve the accuracy of navigation accordingly.

[0179] In the above embodiments of this disclosure, the weight of applying the first map navigation method is determined based on the comparison between the confidence level corresponding to each data set and a preset threshold. The preset threshold can be determined in a variety of ways.

[0180] In one feasible implementation, the preset thresholds corresponding to each dataset are determined as follows:

[0181] Based on the correspondence between road surface elements and preset thresholds, the preset thresholds corresponding to each data set are determined.

[0182] In this implementation, the correspondence between each road surface element and a preset threshold is pre-defined. Then, based on this correspondence and the road surface elements corresponding to each data set, the preset threshold corresponding to each data set can be determined.

[0183] For example, when determining this correspondence, a preset threshold corresponding to the road surface element can be determined based on the size of the road surface element. In this case, since larger road surface elements are easier to identify, generally, the larger the size of the road surface element, the larger the preset threshold corresponding to this correspondence.

[0184] Alternatively, a preset threshold can be determined based on the importance attached to a road surface element. In this case, the more importance attached to a particular road surface element, the larger the preset threshold in that relationship. For example, if the road surface elements corresponding to each data set include road signs, and during navigation, vehicles often need to determine whether to adjust their direction based on the instructions of road signs, thus placing greater emphasis on road signs, then a larger preset threshold can be set for the road sign as a road surface element.

[0185] Alternatively, in another feasible implementation, the preset thresholds corresponding to each data set are determined in the following way:

[0186] The first step is to determine the environmental data impact parameters, which include at least one of the following parameters: environmental data collection time, illumination, and weather.

[0187] In practical applications, the accuracy of environmental data collected by the same mobile device is often affected by the current environment. For example, if the current light intensity is low and there are obstructions in the surrounding area, this will lead to a decrease in the accuracy of the LiDAR in determining the point cloud dataset, and low light intensity will often reduce the clarity of the depth image captured by the depth camera. If it is cloudy or rainy, the clarity of the depth image captured by the depth camera will usually decrease, and the accuracy of the LiDAR in acquiring the point cloud dataset will also decrease. In addition, different collection times correspond to different light conditions. For example, the light intensity in the morning is often lower than that at noon, and under conditions of strong light intensity, the accuracy of the depth image captured by the depth camera is usually higher.

[0188] The second step is to determine the preset thresholds for each data set based on the influencing parameters.

[0189] In this step, when the environmental data's influencing parameters cause the mobile device to reduce the accuracy of collecting environmental data, the preset thresholds corresponding to each data set are reduced accordingly; when the environmental data's influencing parameters cause the mobile device to improve the accuracy of collecting environmental data, the preset thresholds corresponding to each data set are increased accordingly.

[0190] The weight of the first map navigation method in each navigation method is related to the preset threshold corresponding to each data set. The solution provided by the present disclosure embodiment can adjust the preset threshold corresponding to each data set based on the current influence parameters. Therefore, the present disclosure embodiment can adjust the weight of the first map navigation method based on the current influence parameters, thereby further improving the accuracy of navigation for mobile devices.

[0191] Exemplary device

[0192] Figure 10 This is a structural diagram of a map creation apparatus provided in an exemplary embodiment of this disclosure. The map creation apparatus can be installed in electronic devices such as terminal devices and servers, or on objects such as vehicles, to execute the map creation method of any of the embodiments described above. Figure 10 As shown, the map creation device of this embodiment includes: a data acquisition module 201, a set determination module 202, a confidence determination module 203, and a map creation module 204.

[0193] Among them, the data acquisition module 201 is used to acquire environmental data collected by the mobile device for the target area;

[0194] The set determination module 202 is used to classify the environmental data obtained by the data acquisition module 21 to determine at least one data set, wherein the environmental data contained in each data set corresponds to the same type of road surface element;

[0195] The confidence level determination module 203 is used to determine the confidence level of each data set based on the three-dimensional spatial coordinates of each data set contained in each data set determined by the set determination module 22.

[0196] The map creation module 204 is used to create a high-precision map based on the confidence levels corresponding to each of the data sets determined by the confidence determination module 23.

[0197] Further, see Figure 11 The structural diagram shown illustrates that, in one feasible example, the confidence determination module 203 includes:

[0198] The curve determination unit 2031 is used to determine three relationship curves between the first parameter of the road surface element and the three second parameters based on the three-dimensional spatial coordinates of the environmental data contained in each data set. The first parameter is the arc length of the observation point of the road surface element from the starting point of the relationship curve, and each second parameter is the distance in three dimensions between the observation point and the projection point of the observation point on the relationship curve.

[0199] Aggregation Degree Determination Unit 2032 is used to determine the aggregation degree of the distribution of each environmental data contained in each data set based on the relationship curve determined by Curve Determination Unit 2031.

[0200] The confidence level determination unit 2033 is used to determine the confidence level corresponding to each data set based on the aggregation degree of each environmental data distribution determined by the aggregation degree determination unit 2032.

[0201] Furthermore, the aggregation degree determination unit 2032 includes:

[0202] The residual matrix determines the sub-unit, which is used to determine the residual matrix corresponding to each data set based on the relationship curve and the three-dimensional spatial coordinates of each environmental data in each data set;

[0203] The covariance matrix determines the sub-unit, which is used to determine the residual matrix corresponding to each data set determined by the residual matrix, and to determine the covariance matrix corresponding to each data set.

[0204] The unbiased estimator determination subunit is used to determine the trace of the covariance matrix corresponding to each data set determined by the covariance matrix determination subunit, and to determine the unbiased estimator corresponding to each data set. The unbiased estimator is used to characterize the degree of aggregation of the distribution of each environmental data contained in the data set.

[0205] Accordingly, in this case, the confidence determination unit 203 includes a confidence determination subunit, which is used to determine the confidence level corresponding to each data set based on the unbiased estimator corresponding to each data set and the number of times the mobile device collects environmental data.

[0206] In one feasible example, the set-determining module 202 includes:

[0207] The first classification unit 2021 is used to classify environmental data based on the type of mobile device corresponding to each environmental data, and determine at least one intermediate data set;

[0208] The second classification unit 2022 classifies the environmental data contained in each intermediate data set determined by the first classification unit based on the type of road surface elements corresponding to each environmental data, and determines at least one data set.

[0209] Furthermore, the solution provided in this embodiment of the present disclosure also includes a prompting module 205. The prompting module 205 is used to determine a first target data set among the data sets after determining at least one data set, wherein the confidence level of the first target data set is lower than the confidence level of other data sets among the data sets; and the prompting module 205 is also used to generate prompt information based on the mobile device corresponding to the first target data set.

[0210] Additionally, in one feasible example, the map creation module 204 includes:

[0211] The target set determination unit 2041 is used to determine a second target data set based on the confidence level corresponding to each data set, wherein the confidence level of the second target data set is greater than the confidence level of the other data sets;

[0212] The map creation unit 2042 is used to create high-precision maps corresponding to each data set, and to mark and display the road surface elements determined by the second target data set determined by the target set determination unit 2041 in the high-precision map.

[0213] Furthermore, if the mobile device includes at least two navigation methods, including a first map navigation method based on a high-precision map, the map creation device provided in this embodiment of the present disclosure further includes a navigation module 206.

[0214] The navigation module 206 is used to determine the weight of applying the first map navigation method based on the confidence level corresponding to each data set after creating a high-precision map based on the confidence level corresponding to each data set and the preset threshold corresponding to each data set; and the navigation module 206 is also used to navigate the mobile device based on the weight.

[0215] In one feasible implementation, the navigation module 206 may include:

[0216] The first threshold determination unit 2061 is used to determine the preset threshold corresponding to each data set based on the correspondence between road surface elements and preset thresholds.

[0217] Alternatively, in another feasible implementation, the navigation module 206 includes:

[0218] The parameter determination unit 2062 is used to determine the influence parameters of the environmental data, the influence parameters including at least one of the following parameters: the collection time of the environmental data, illumination and weather;

[0219] The second threshold determination unit 2063 is used to determine the preset threshold corresponding to each data set based on the influence parameters determined by the parameter determination unit 2062.

[0220] Exemplary electronic devices

[0221] Below, for reference Figure 12 This document describes an electronic device according to embodiments of this application. In an exemplary embodiment of this disclosure, the electronic device may include... Figure 1The electronic device of the map creation device 100 shown, or, in another exemplary embodiment of this disclosure, the electronic device may include... Figure 1 The electronic devices of the map creation device 100, the first device 200, and the second device 300 shown are, of course, also possible in other forms, and this disclosure does not limit them.

[0222] Figure 12 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0223] like Figure 12 As shown, the electronic device 11 includes one or more processors 111 and memory 112.

[0224] The processor 111 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 11 to perform desired functions.

[0225] The memory 112 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 111 may execute the program instructions to implement the map creation methods of the various embodiments of this application described above and / or other desired functions. Various content such as environmental data and created high-precision maps may also be stored in the computer-readable storage medium.

[0226] In one example, the electronic device 11 may also include an input device 113 and an output device 114, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0227] In addition, the input device 113 may also include, for example, a keyboard, a mouse, etc.

[0228] The output device 114 can output various information to the outside, including created high-precision maps. The output device 114 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0229] Of course, for the sake of simplicity, Figure 12Only some of the components of the electronic device 11 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 11 may include any other suitable components depending on the specific application.

[0230] Exemplary computer program products and computer-readable storage media

[0231] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the map creation methods according to various embodiments of this application as described in the "Exemplary Methods" section of this specification.

[0232] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0233] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the map creation methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0234] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fiber, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0235] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0236] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0237] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0238] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0239] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A map creation method, comprising: Acquire environmental data collected by mobile devices for a target area; By classifying the environmental data, at least one data set is determined, wherein the environmental data contained in each data set corresponds to the same type of road surface element; Based on the three-dimensional spatial coordinates corresponding to each environmental data contained in each of the data sets, the confidence level corresponding to each of the data sets is determined. High-precision maps are created based on the confidence levels corresponding to each of the aforementioned data sets. The step of determining the confidence level corresponding to each of the data sets based on the three-dimensional spatial coordinates corresponding to each environmental data contained in each data set includes: Based on the three-dimensional spatial coordinates of each environmental data contained in each of the aforementioned datasets, three relationship curves are determined between the first parameter of the road surface element and three second parameters, respectively. The first parameter is the arc length of the observation point of the road surface element from the starting point of the relationship curve, and each of the second parameters is the three-dimensional distance between the observation point and the projection point of the observation point on the relationship curve. Based on the relationship curve, the degree of aggregation of the distribution of each environmental data contained in each of the data sets is determined; Based on the degree of aggregation of the environmental data distributions, the confidence level corresponding to each data set is determined.

2. The method according to claim 1, wherein, The determination of the degree of aggregation of the distributions of environmental data contained in each of the data sets based on the relationship curve includes: Based on the relationship curve and the three-dimensional spatial coordinates of each environmental data in each data set, the residual matrix corresponding to each data set is determined. Based on the residual matrix corresponding to each of the data sets, determine the covariance matrix corresponding to each of the data sets. Based on the trace of the covariance matrix corresponding to each of the data sets, an unbiased estimator corresponding to each of the data sets is determined. The unbiased estimator is used to characterize the degree of aggregation of the distributions of the environmental data contained in the data set. The determination of the confidence level corresponding to each data set based on the aggregation degree of each environmental data distribution includes: Based on the unbiased estimator corresponding to each of the data sets and the number of times the mobile device collects the environmental data, the confidence level corresponding to each of the data sets is determined.

3. The method according to claim 1, wherein, The step of classifying the environmental data to determine at least one data set includes: Based on the type of mobile device corresponding to each of the environmental data, the environmental data is classified to determine at least one intermediate data set; Based on the type of road surface element corresponding to each of the environmental data, the environmental data contained in each of the intermediate data sets are classified to determine at least one data set.

4. The method according to claim 3, wherein, After determining at least one data set, the method further includes: A first target data set is determined from each of the data sets, wherein the confidence level of the first target data set is lower than the confidence level of the other data sets in each of the data sets; Based on the mobile device corresponding to the first target data set, a prompt message is generated.

5. The method according to any one of claims 1 to 4, wherein, The step of creating a high-precision map based on the confidence levels corresponding to each of the aforementioned data sets includes: Based on the confidence levels corresponding to each of the aforementioned data sets, a second target data set is determined, wherein the confidence level of the second target data set is greater than that of the other data sets; Create high-precision maps corresponding to each of the aforementioned data sets, and mark and display the road surface elements determined by the second target data set in the high-precision maps.

6. The method according to any one of claims 1 to 4, wherein, The mobile device includes at least two navigation methods, one of which is a first map navigation method based on the high-precision map. After creating the high-precision map based on the confidence levels corresponding to each of the data sets, the method further includes: Based on the confidence level corresponding to each of the data sets and the preset threshold corresponding to each of the data sets, the weight for applying the first map navigation method is determined; Navigation is performed for the mobile device based on the weights.

7. The method according to claim 6, wherein, The preset thresholds corresponding to each of the aforementioned data sets are determined in the following ways: Based on the correspondence between the road surface elements and preset thresholds, determine the preset threshold corresponding to each of the data sets; or... Determine the influencing parameters of the environmental data, wherein the influencing parameters include at least one of the following parameters: the collection time of the environmental data, illumination, and weather; Based on the aforementioned influence parameters, preset thresholds are determined for each of the aforementioned data sets.

8. A map creation apparatus, comprising: The data acquisition module is used to acquire environmental data collected by mobile devices for the target area; The set determination module is used to classify the environmental data acquired by the data acquisition module to determine at least one data set, wherein the environmental data contained in each data set corresponds to the same type of road surface element; The confidence level determination module is used to determine the confidence level of each data set based on the three-dimensional spatial coordinates corresponding to each environmental data contained in each data set determined by the set determination module. The map creation module is used to create a high-precision map based on the confidence scores corresponding to each of the data sets determined by the confidence score determination module. The confidence level determination module is used to perform the following operations: Based on the three-dimensional spatial coordinates of each environmental data contained in each of the aforementioned datasets, three relationship curves are determined between the first parameter of the road surface element and three second parameters, respectively. The first parameter is the arc length of the observation point of the road surface element from the starting point of the relationship curve, and each of the second parameters is the three-dimensional distance between the observation point and the projection point of the observation point on the relationship curve. Based on the relationship curve, the degree of aggregation of the distribution of each environmental data contained in each of the data sets is determined; Based on the degree of aggregation of the environmental data distributions, the confidence level corresponding to each data set is determined.

9. A computer-readable storage medium storing a computer program for performing the map creation method according to any one of claims 1-7.

10. An electronic device, the electronic device comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the map creation method according to any one of claims 1-7.

Images