High-precision map information prediction method, device, readable storage medium and electronic device

Abstract

The disclosed embodiments disclose a method, apparatus, computer-readable storage medium, and electronic device for predicting high-precision map information. The method comprises: determining a vehicle's current location information; obtaining, based on the current location information, digital map information corresponding to a target road section on which the vehicle is about to travel from a digital map; determining historical high-precision map information corresponding to the current location information; and predicting high-precision map information corresponding to the target road section based on the digital map information and the historical high-precision map information. The disclosed embodiments can combine digital map information of the road the vehicle is about to travel with historical high-precision map information. This allows for the inclusion of more known information when predicting high-precision map information, significantly improving the accuracy of the predicted high-precision map information and providing prior information for the subsequent real-time generation of high-precision maps. This helps improve the accuracy of the real-time generated high-precision maps and reduces the subsequent time, labor costs, and computing resource investment.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method and device for predicting high-precision map information, a computer-readable storage medium, and an electronic device. Background Art

[0002] High-precision maps are essential for vehicles to perform computer-assisted driving functions. Compared to common digital maps used for navigation, HD maps represent a wider variety of road elements and provide more comprehensive geometric information.

[0003] Take some road element information as an example: (1) For each road, the digital map only records the approximate central axis position of the road, the number of lanes, the driving direction (distinguishing between two directions), and the turning information (marking which side you can turn to at the end of each lane); the high-precision map will record the world coordinate system coordinates of the two vertices of each lane segment (including dotted and solid lines) on both sides of each lane, the coordinates of the lane merging and bifurcation points, and the world coordinate system coordinates of each vertex of the arrow pattern marking the turning information on the ground. (2) For traffic lights, the digital map does not record whether there is a traffic light at the intersection; while the high-precision map not only records whether there is a traffic light at the intersection, but also records the location, size, shape, and direction of the traffic light. (3) For street light poles, the digital map does not record the location of the street light poles on the road; while the high-precision map records the location, height, and other information of the street light poles. (4) For traffic signs, the digital map only records the traffic sign information; while the high-precision map includes the center point, height, size, and other information of the traffic sign.

[0004] High-precision maps can now be generated in real time as vehicles move on the road through various technologies. However, their accuracy often varies significantly depending on the method used to generate them. Therefore, real-time HD maps require extensive post-processing. Summary of the Invention

[0005] Embodiments of the present disclosure provide a method, device, computer-readable storage medium, and electronic device for predicting high-precision map information.

[0006] An embodiment of the present disclosure provides a method for predicting high-precision map information, the method comprising: determining the current position information of a vehicle; obtaining, from a digital map, digital map information corresponding to a target road section on which the vehicle is about to travel, based on the current position information; determining historical high-precision map information corresponding to the current position information; and predicting high-precision map information corresponding to the target road section based on the digital map information and the historical high-precision map information.

[0007] According to another aspect of an embodiment of the present disclosure, a high-precision map information prediction device is provided, which includes: a first determination module for determining the current position information of a vehicle; an acquisition module for acquiring, from a digital map, digital map information corresponding to a target road section on which the vehicle is about to travel, based on the current position information; a second determination module for determining historical high-precision map information corresponding to the current position information; and a prediction module for predicting the high-precision map information corresponding to the target road section based on the digital map information and the historical high-precision map information.

[0008] According to another aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and the computer program is used to execute the above-mentioned high-precision map information prediction method.

[0009] According to another aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; and the processor for reading the executable instructions from the memory and executing the instructions to implement the above-mentioned high-precision map information prediction method.

[0010] The high-precision map information prediction method, device, computer-readable storage medium, and electronic device provided in the above-mentioned embodiments of the present disclosure obtain digital map information corresponding to the target road section that the vehicle is about to travel on from a digital map based on the current position information of the vehicle, then determine the historical high-precision map information corresponding to the current position information, and finally predict the high-precision map information corresponding to the target road section based on the digital map information and the historical high-precision map information, thereby combining the digital map information of the road that the vehicle is about to pass with the historical high-precision map information. When predicting the high-precision map information, more known information can be introduced, which greatly improves the accuracy of the predicted high-precision map information, provides prior information for the subsequent real-time generation of high-precision maps, and is conducive to improving the accuracy of the real-time generated high-precision maps, reducing the subsequent time, labor costs, and computing resource investment.

[0011] The technical solution of the present disclosure is further described in detail below through the accompanying drawings and examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other purposes, features, and advantages of the present disclosure will become more apparent through a more detailed description of the embodiments of the present disclosure in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and are not intended to limit the present disclosure. In the drawings, the same reference numerals generally represent the same components or steps.

[0013] Figure 1 is a system diagram to which the present disclosure is applicable.

[0014] Figure 2 It is a flowchart of a high-precision map information prediction method provided by an exemplary embodiment of the present disclosure.

[0015] Figure 3 It is a flow chart of a high-precision map information prediction method provided by another exemplary embodiment of the present disclosure.

[0016] Figure 4 It is a flow chart of a high-precision map information prediction method provided by another exemplary embodiment of the present disclosure.

[0017] Figure 5A This is a schematic diagram of determining a set of sampling points from a high-precision map provided by an exemplary embodiment of the present disclosure.

[0018] Figure 5B It is a schematic diagram of determining historical high-precision map information and future high-precision map information from a high-precision map provided by an exemplary embodiment of the present disclosure.

[0019] Figure 6 It is a flow chart of a high-precision map information prediction method provided by another exemplary embodiment of the present disclosure.

[0020] Figure 7 It is a structural diagram of a high-precision map information prediction device provided by an exemplary embodiment of the present disclosure.

[0021] Figure 8 It is a structural diagram of a high-precision map information prediction device provided by another exemplary embodiment of the present disclosure.

[0022] Figure 9 is a structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] Below, the exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described herein.

[0024] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.

[0025] Those skilled in the art will understand that the terms "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, and do not represent any specific technical meanings, nor do they indicate a necessary logical order between them.

[0026] It should also be understood that in the embodiments of the present disclosure, “a plurality of” may refer to two or more than two, and “at least one” may refer to one, two, or more than two.

[0027] It should also be understood that any component, data or structure mentioned in the embodiments of the present disclosure can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0028] In addition, the term "and / or" in this disclosure is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this disclosure generally indicates that the related objects are in an "or" relationship.

[0029] It should also be understood that the description of the various embodiments in this disclosure focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced with each other. For the sake of brevity, they will not be described one by one.

[0030] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0031] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0032] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0033] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0034] The embodiments of the present disclosure can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate in conjunction with numerous 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 personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the above systems, among others.

[0035] 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. Generally, 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 a distributed cloud computing environment, where tasks are performed by remote processing devices linked via a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media, including storage devices.

[0036] Application Overview

[0037] Typically, real-time HD maps require extensive post-processing. This process is both time-consuming and labor-intensive. Current methods for generating HD maps in real time lack predictive processes and fail to integrate digital map information into the HD map generation process. Real-time HD maps can easily deviate from real-world road scene information.

[0038] Exemplary Systems

[0039] Figure 1 An exemplary system architecture 100 is shown to which the high-precision map information prediction method or high-precision map information prediction device according to an embodiment of the present disclosure can be applied.

[0040] like Figure 1 As shown, system architecture 100 may include a terminal device 101, a network 102, a server 103, and a vehicle 104. The terminal device may be located in the vehicle 104. Network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. Network 102 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0041] The user can use the terminal device 101 to interact with the server 103 via the network 102 to receive or send messages, etc. Various communication client applications, such as map applications, navigation applications, etc., can be installed on the terminal device 101.

[0042] The terminal device 101 may be any electronic device, including but not limited to a mobile phone, a laptop computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a vehicle navigation terminal), etc. The terminal device 101 is usually installed in a vehicle 104.

[0043] The server 103 may be a server that provides various services, such as a backend server that supports the digital maps and high-precision maps used on the terminal device 101. The backend server may receive the current location information of the vehicle and perform high-precision map information prediction based on the digital map information and historical high-precision map information to obtain predicted high-precision map information.

[0044] It should be noted that the high-precision map information prediction method provided in the embodiments of the present disclosure can be executed by the server 103 or by the terminal device 101. Accordingly, the high-precision map information prediction device can be set in the server 103 or in the terminal device 101.

[0045] It should be understood that Figure 1 The number of vehicles 104, terminal devices 101, networks 102, and servers 103 in the above description is merely illustrative. Any number of vehicles 104, terminal devices 101, networks 102, and servers 103 may be provided as needed. If digital maps and high-precision maps do not need to be acquired remotely, the above system architecture may include only vehicles 104 and terminal devices 101, excluding the network and servers.

[0046] Exemplary Methods

[0047] Figure 2 This is a flow chart of a method for predicting high-precision map information provided by an exemplary embodiment of the present disclosure. This embodiment can be applied to electronic devices (such as Figure 1 On the terminal device 101 or server 103 shown in FIG. Figure 2 As shown, the method includes the following steps:

[0048] Step 201: Determine the current location information of the vehicle.

[0049] In this embodiment, the electronic device can determine the current location information of the vehicle. The current location information can be location information determined in real time by the vehicle's navigation system. The current location information is used to indicate the current location of the vehicle. Typically, the current location information can be represented by information such as longitude, latitude, and altitude.

[0050] Step 202: According to the current position information, obtain digital map information corresponding to the target road section where the vehicle is about to travel from the digital map.

[0051] In this embodiment, the electronic device can obtain digital map information corresponding to the target road section that the vehicle is about to travel from a digital map based on the current location information. The digital map can be stored locally on the electronic device or on another device that is communicatively connected to the electronic device. The target road section can be determined in various ways. For example, the target road section can be a road section of a predetermined length that the vehicle is about to pass, starting from the vehicle's current location. In another example, the target road section can be the road section between the vehicle's current location and the next landmark that the vehicle is about to pass.

[0052] The digital map information corresponding to the target road segment is used to characterize the characteristics of the target road segment. For example, the digital map information may include, but is not limited to, at least one of the following: the number of lanes on the target road segment, the position of the centerline of the target road segment in the world coordinate system, whether there are lanes merging into or out of the target road segment, the distance from the vehicle to the next intersection, and lane direction information indicated by ground arrows and signs on the target road segment.

[0053] Step 203: Determine the historical high-precision map information corresponding to the current location information.

[0054] In this embodiment, the electronic device can determine historical high-precision map information corresponding to the current location information. The high-precision map information can be determined based on a pre-established high-precision map. The high-precision map can be set locally on the electronic device or on another device that is communicatively connected to the electronic device.

[0055] Compared to the aforementioned digital maps, HD maps contain richer information. For example, HD maps can include the following: the world coordinate system coordinates of the two vertices of each lane segment (including dashed and solid lines) on both sides of each lane, the coordinates of lane merging and bifurcation points, the world coordinate system coordinates of each vertex of the arrow pattern on the ground marking turn information, etc.; the location, size, shape, and orientation of traffic lights; the location and height of streetlight poles; and the center point, height, and size of traffic signs.

[0056] The electronic device can determine historical high-precision map information from the high-precision map. Historical high-precision map information can be information indicating the characteristics of a section of road that the vehicle has traveled (e.g., a road traveled over a fixed period of time in the past, a fixed length of road in the past, or the road between the vehicle's current location and the last landmark, intersection, etc.). For information on the content of historical high-precision maps, please refer to the examples of high-precision map information included in the high-precision map described above.

[0057] Step 204: Based on the digital map information and historical high-precision map information, predict the high-precision map information corresponding to the target road section.

[0058] In this embodiment, the electronic device can predict the high-precision map information corresponding to the target road section based on the digital map information and historical high-precision map information.

[0059] As an example, the electronic device can search a pre-established correspondence table for the predicted high-precision map information corresponding to the digital map information and historical high-precision map information as the high-precision map information corresponding to the target road segment. The correspondence table can be a table obtained by pre-collecting digital map information and historical high-precision map information corresponding to a large amount of location information, as well as high-precision map information corresponding to a future section of the road.

[0060] The method provided by the above-mentioned embodiments of the present disclosure obtains digital map information corresponding to the target road section that the vehicle is about to travel on from a digital map based on the current position information of the vehicle, then determines the historical high-precision map information corresponding to the current position information, and finally predicts the high-precision map information corresponding to the target road section based on the digital map information and the historical high-precision map information, thereby combining the digital map information of the road that the vehicle is about to pass with the historical high-precision map information. When predicting the high-precision map information, more known information can be introduced, which greatly improves the accuracy of the predicted high-precision map information, provides prior information for the subsequent real-time generation of high-precision maps, and is conducive to improving the accuracy of the real-time generated high-precision maps, reducing the subsequent time, labor costs, and computing resource investment.

[0061] Optionally, after step 204, the electronic device may further perform the following steps:

[0062] Based on the high-precision map information corresponding to the target road section, determine the real-time high-precision map information corresponding to the current location information.

[0063] Specifically, the predicted HD map information can serve as the initial value for the algorithm used to generate real-time HD map information, thereby providing prior information for the real-time HD map generation algorithm. By incorporating the predicted HD map information into the real-time HD map generation algorithm, a more accurate real-time HD map can be obtained. Based on the real-time HD map information, an HD map corresponding to the target road segment can be further generated. It should be noted that the real-time HD map generation algorithm is well known in the art and will not be further described here.

[0064] This step uses the predicted high-precision map information as prior information for the real-time high-precision map generation algorithm, greatly improving the accuracy of real-time high-precision map generation.

[0065] Further references Figure 3 , shows a flow chart of another embodiment of a high-precision map information prediction method. Figure 3 As shown in the above Figure 2 Based on the illustrated embodiment, step 204 may include the following steps:

[0066] Step 2041 : Vectorize the digital map information and the historical high-precision map information respectively to obtain a digital map vector and a high-precision map vector.

[0067] Vectorization involves quantizing the various information contained in historical HD map information and digital map information, and then combining the quantized values ​​into vectors. For example, a HD map vector might take the form of (number of lanes, lane type, lane dividing line length, distance 1, curvature 1, distance 2, curvature 2, distance 3, curvature 3, ..., sign style, sign length, sign width, sign height, ...). A digital map vector might take the form of (vehicle position coordinates, road centerline position coordinates, number of lanes, direction of travel, ...).

[0068] Step 2042: Input the digital map vector and the high-precision map vector into a pre-trained high-precision map prediction model to obtain a predicted high-precision map vector.

[0069] The HD map prediction model is used to characterize the correspondence between digital map vectors, HD map vectors, and predicted HD map vectors. For example, the HD map prediction model can take the form of a mathematical formula, a correspondence table, or other similar form. It inputs a digital map vector and an HD map vector, and after calculation or lookup, it outputs a predicted HD map vector. The HD map prediction model can also be a model pre-trained using machine learning methods.

[0070] Step 2043: Based on the predicted high-precision map vector, obtain the high-precision map information corresponding to the target road section.

[0071] After obtaining the high-precision map vector, the electronic device can restore each element in the vector to the high-precision map information corresponding to the target road section based on the correspondence between the elements in the vector and the actual meaning represented.

[0072] above Figure 3 The method provided in the corresponding embodiment obtains high-precision map information corresponding to the target road section by vectorizing the digital map information and the historical high-precision map information respectively, and using the high-precision map prediction model, thereby combining the digital map information and the historical high-precision map information, and using mathematical methods to accurately predict the high-precision map information corresponding to the target road section to be traveled, thereby effectively improving the accuracy of the generated predicted high-precision map information.

[0073] In some optional implementations, such as Figure 4 As shown in the figure, the high-precision map prediction model is pre-trained according to the following steps:

[0074] Step 401: Determine a set of sampling points on a road in a digital map or a high-precision map.

[0075] The digital map and high-precision map of this embodiment can be respectively Figure 2 The digital map and high-precision map described in the corresponding embodiments may be the same or different.

[0076] Specifically, the electronic device can traverse the roads in the high-precision map or digital map to obtain the possible position and direction of the vehicle. Figure 5A As shown in the figure, it shows a schematic diagram of determining the sampling point set from the high-precision map. The high-precision map or digital map records road information, and each road is divided into multiple lanes. The high-precision map or digital map records the centerline position, tangent direction and lane width of each lane. Based on the above information, the coordinates of the vehicle's position are obtained at equal intervals along the extension direction of the centerline of each lane. During the vehicle's movement, since the center of the vehicle may not coincide with the center of the lane line, it can be used as follows Figure 5A The vertical direction of the tangent line of the lane centerline shown extends to both sides to simulate the position of the vehicle and record the sampling points.

[0077] Step 402: For each sampling point in the sampling point set, determine the future digital map information corresponding to the sampling point from the digital map, and perform vectorization processing on the future digital map information to obtain a future digital map vector; determine the historical high-precision map information and future high-precision map information corresponding to the sampling point from the high-precision map, and perform vectorization processing on the historical high-precision map information and the future high-precision map information, respectively, to obtain a historical high-precision map vector and a future high-precision map vector.

[0078] The future digital map information corresponding to a sampling point may be the digital map information corresponding to the road extending a predetermined distance in the direction of vehicle travel, starting from the sampling point. After this step is completed, the future digital map vector, historical high-precision map vector, and future high-precision map vector corresponding to each sampling point or portion of the sampling points are obtained.

[0079] The future high-precision map information corresponding to a sampling point can be the high-precision map information corresponding to the road that is extended from the sampling point to the vehicle's travel direction for a set distance. The historical high-precision map information corresponding to the sampling point can be the high-precision map information corresponding to the road that is extended from the sampling point to the vehicle's travel direction for a set distance. Figure 5BAs shown, it shows a schematic diagram of determining historical high-precision map information and future high-precision map information from a high-precision map. The arrow represents the extension direction of the road (i.e., the driving direction of the vehicle), the sampling point 501 represents the current position of the vehicle, and the straight line 502 passing through the sampling point and perpendicular to the tangent of the center line of the road is used as the dividing line. The high-precision map information corresponding to the range covered by the set distance extended in the direction of the road extension is the future high-precision map information, and the high-precision map information corresponding to the range covered by the set distance extended in the opposite direction of the road extension is the historical high-precision map. Future high-precision map information and historical high-precision map information include the following: Figure 5B The displayed information includes the location of the street light pole, the location of the center line of the road, the extension direction of the center line, the information of the no-parking sign, the information of the road sign, etc.

[0080] Optionally, since the high-precision map information prediction is based on the map information corresponding to a distance that the vehicle has just traveled, the map information of a future distance is predicted, and the distance traveled may not include intersections, therefore, usually when extending in the above-mentioned direction of road extension or in the opposite direction of road extension, the road section that does not include intersections is selected to extract future digital map information, historical high-precision map information and future high-precision map information.

[0081] In step 403, the future digital map vectors and historical high-precision map vectors corresponding to the sampling points in the sampling point set are used as input, and the future high-precision map vectors corresponding to the input sampling points are used as expected outputs to train a high-precision map prediction model.

[0082] The electronic device can utilize a machine learning method, taking the future digital map vector and the historical high-precision map vector obtained in step 402 as input, and the future high-precision map vector corresponding to the input vector as the expected output, to train an initial model (e.g., a convolutional neural network, a recurrent neural network, etc.). For each training run of the future digital map vector and the historical high-precision map vector input, an actual output can be obtained. The actual output is the predicted future high-precision map vector actually output by the initial model. The electronic device can then utilize a gradient descent method and a backpropagation method to adjust the parameters of the initial model based on the actual output and the expected output, using the model obtained after each parameter adjustment as the initial model for the next training run. The training can be terminated when a preset training termination condition is met, thereby training a high-precision map prediction model. The preset training termination condition may include, but is not limited to, at least one of the following: the training time exceeds a preset duration; the number of training runs exceeds a preset number; or the loss value calculated using a preset loss function is less than a preset loss value threshold.

[0083] This implementation method extracts a set of sampling points from a digital map or a high-precision map, uses the map vectors corresponding to the sampling points as training samples, and uses machine learning methods to train a high-precision map prediction model. This effectively utilizes existing digital maps and high-precision maps, fully simulates actual road conditions, and trains a high-precision map prediction model with high accuracy.

[0084] Further references Figure 6 , shows a flow chart of another embodiment of a high-precision map information prediction method. Figure 6 As shown in the above Figure 2 Based on the embodiment shown, step 203 may include the following steps:

[0085] Step 2031: Obtain the first historical high-precision map information generated at the target historical moment.

[0086] The target historical moment can be any set moment before the current time. For example, if high-precision map information is generated at a predetermined interval according to a preset period, the first historical high-precision map information generated at the target historical moment can be the high-precision map information generated last time, or a combination of the high-precision map information generated two times previously (or at a predetermined number of times).

[0087] Step 2032: Search a preset high-precision map database for second historical high-precision map information corresponding to the road segment represented by the first historical high-precision map information.

[0088] The high-precision map database can be stored locally on the electronic device or on another device connected to the electronic device. The electronic device can determine the coordinate range of the road segment represented by the first historical high-precision map information and search the high-precision map information corresponding to the range from the high-precision map database as the second historical high-precision map information.

[0089] Step 2033: Based on the search results, determine the historical high-precision map information corresponding to the current location information.

[0090] The search result indicates two states: found or not found. If not found, the first historical high-precision map information can be determined as the historical high-precision map information corresponding to the current location information. If found, the second historical high-precision map information can be determined as the historical high-precision map information corresponding to the current location information.

[0091] Figure 6The method provided in the corresponding embodiment, by obtaining the first historical high-precision map information and searching the second historical high-precision map information from the high-precision map database, determines the historical high-precision map information corresponding to the current location information based on the search results, which can enrich the way of obtaining historical high-precision map information, provide more prior information for subsequent high-precision map information prediction, and improve the prediction accuracy.

[0092] In some optional implementations, step 2033 may include the following sub-steps:

[0093] If the search result indicates that the second historical high-precision map information can be found, the corresponding data in the first historical high-precision map information and the second historical high-precision map information are fused to obtain the historical high-precision map information corresponding to the current location information.

[0094] As an example, the fusion method can be to average the data representing the same meaning in the first and second historical HD map information and replace the original data. For example, the lane curvature at a certain location is averaged, and the resulting value is used as the data included in the historical HD map information corresponding to the current location information.

[0095] This implementation method obtains the historical high-precision map information corresponding to the current location information by fusing the first historical high-precision map information and the second historical high-precision map information, thereby utilizing the data in the existing database to provide prior information for subsequent high-precision map information prediction. Since the data in the database is highly accurate, the prediction accuracy can be improved.

[0096] In some optional implementations, the above-mentioned fusion of corresponding data in the first historical high-precision map information and the second historical high-precision map information to obtain the historical high-precision map information corresponding to the current location information includes:

[0097] First, extract at least one corresponding data pair from the first historical high-precision map information and the second historical high-precision map information.

[0098] The data pair consisting of corresponding data refers to data representing the same meaning in the first historical high-precision map information and the second historical high-precision map information, such as the number of lanes on the current road, the width of the current lane, the height of the same road sign, etc.

[0099] Then, fused data corresponding to each data pair in the at least one data pair is determined.

[0100] As an example, the data included in each data pair may be averaged or weighted averaged to obtain fused data.

[0101] Finally, based on the at least one fused data obtained, the target historical high-precision map information corresponding to the current location information is generated.

[0102] Specifically, the fused data can be determined as the data included in the newly generated historical high-precision map information.

[0103] This implementation method obtains fused data by fusing a data pair consisting of corresponding data in the first historical high-precision map information and the second historical high-precision map information. This can effectively reduce the error between the high-precision map information generated historically and the high-precision map in the database, thereby improving the accuracy of the historical high-precision map information corresponding to the current location information, which is beneficial to the accuracy of subsequent high-precision map information prediction.

[0104] In some optional implementations, determining the fused data corresponding to each data pair in the at least one data pair includes:

[0105] For each data pair in at least one data pair, if the gap between the data pairs meets the preset conditions, the weighted average of the data pairs is determined to obtain fused data; if the data pairs do not meet the preset conditions, the data from the second historical high-precision map information in the data pair is determined as fused data.

[0106] As an example, the preset condition may include: the difference between the data pairs is less than or equal to a corresponding threshold. For example, if a data pair represents the number of lanes on the current road, and the difference between the two is less than or equal to the corresponding threshold, a weighted average of the data pair is determined to obtain the fused data; if the difference is greater than the threshold, the number of lanes in the second historical HD map information is determined as the fused data. For another example, if a data pair represents the width of the current road, and the difference between the two is less than or equal to the corresponding threshold, a weighted average of the data pair is determined to obtain the fused data; if the difference is greater than the threshold, the lane width in the second historical HD map information is determined as the fused data.

[0107] The weights used in the above-mentioned weighted average calculation can be pre-set. For example, a larger weight (such as 0.6) can be given to the data from the high-precision map database, and a smaller weight (such as 0.4) can be given to the data from the high-precision map generated in real time in history. This allows the use of the prior information provided by the existing high-precision map database to be emphasized when predicting high-precision map information.

[0108] By setting preset conditions for each data pair, this implementation method can remove the impact of errors in historically generated real-time high-precision map information on high-precision map information predictions, further improving the accuracy of high-precision map information predictions.

[0109] Exemplary devices

[0110] Figure 7 This is a schematic diagram of the structure of a high-precision map information prediction device provided by an exemplary embodiment of the present disclosure. This embodiment can be applied to electronic devices such as Figure 7 As shown, the high-precision map information prediction device includes: a first determination module 701, which is used to determine the current position information of the vehicle; an acquisition module 702, which is used to obtain digital map information corresponding to the target road section that the vehicle is about to travel from the digital map based on the current position information; a second determination module 703, which is used to determine the historical high-precision map information corresponding to the current position information; and a prediction module 704, which is used to predict the high-precision map information corresponding to the target road section based on the digital map information and the historical high-precision map information.

[0111] In this embodiment, the first determination module 701 can determine the current location information of the vehicle. The current location information can be location information determined in real time by the vehicle's navigation system. The current location information is used to indicate the current location of the vehicle. Typically, the current location information can be represented by information such as longitude, latitude, and altitude.

[0112] In this embodiment, the acquisition module 702 can obtain digital map information corresponding to the target road section that the vehicle is about to travel from a digital map based on the current location information. The digital map can be stored locally on the electronic device or on another device that is communicatively connected to the electronic device. The target road section can be determined in various ways. For example, the target road section can be a road section of a predetermined length that the vehicle is about to pass, starting from the vehicle's current location. For another example, the target road section can be the road section between the vehicle's current location and the next landmark that the vehicle is about to pass.

[0113] The digital map information corresponding to the target road segment is used to characterize the characteristics of the target road segment. For example, the digital map information may include, but is not limited to, at least one of the following: the number of lanes on the target road segment, the position of the centerline of the target road segment in the world coordinate system, whether there are lanes merging into or out of the target road segment, the distance from the vehicle to the next intersection, and lane direction information indicated by ground arrows and signs on the target road segment.

[0114] In this embodiment, the second determination module 703 may determine historical high-precision map information corresponding to the current location information. The high-precision map information may be determined based on a pre-established high-precision map. The high-precision map may be located locally on the electronic device or in another device that is communicatively connected to the electronic device.

[0115] Compared to the aforementioned digital maps, HD maps contain richer information. For example, HD maps can include the following: the world coordinate system coordinates of the two vertices of each lane segment (including dashed and solid lines) on both sides of each lane, the coordinates of lane merging and bifurcation points, the world coordinate system coordinates of each vertex of the arrow pattern on the ground marking turn information, etc.; the location, size, shape, and orientation of traffic lights; the location and height of streetlight poles; and the center point, height, and size of traffic signs.

[0116] The second determination module 703 can determine historical high-precision map information from the high-precision map. Historical high-precision map information can be information indicating the characteristics of a section of road that the vehicle has traveled (e.g., a road that the vehicle has traveled over a fixed period of time in the past, a road of a fixed length in the past, or a road between the vehicle's current location and a previous landmark, intersection, etc.). For information on the content of historical high-precision maps, please refer to the examples of high-precision map information included in the high-precision map described above.

[0117] In this embodiment, the prediction module 704 can predict the high-precision map information corresponding to the target road section based on the digital map information and the historical high-precision map information.

[0118] As an example, the prediction module 704 may search a pre-established correspondence table for the predicted high-precision map information corresponding to the digital map information and the historical high-precision map information as the high-precision map information corresponding to the target road segment. The correspondence table may be a table obtained by pre-collecting digital map information and historical high-precision map information corresponding to a large amount of location information, as well as high-precision map information corresponding to a future section of the road.

[0119] Reference Figure 8 , Figure 8 It is a structural diagram of a high-precision map information prediction device provided by another exemplary embodiment of the present disclosure.

[0120] In some optional implementations, the device may further include: a third determination module 705, configured to determine real-time high-precision map information corresponding to the current location information based on the high-precision map information corresponding to the target road section.

[0121] In some optional implementations, the prediction module 704 may include: a processing unit 7041, used to vectorize the digital map information and the historical high-precision map information respectively to obtain a digital map vector and a high-precision map vector; a prediction unit 7042, used to input the digital map vector and the high-precision map vector into a pre-trained high-precision map prediction model to obtain a predicted high-precision map vector; a generation unit 7043, used to obtain the high-precision map information corresponding to the target road section based on the predicted high-precision map vector.

[0122] In some optional implementations, the high-precision map prediction model can be pre-trained according to the following steps: determining a set of sampling points on a digital map or a road in a high-precision map; for a sampling point in the sampling point set, determining the future digital map information corresponding to the sampling point from the digital map, and vectorizing the future digital map information to obtain a future digital map vector; determining the historical high-precision map information and future high-precision map information corresponding to the sampling point from the high-precision map, and vectorizing the historical high-precision map information and the future high-precision map information respectively to obtain a historical high-precision map vector and a future high-precision map vector; taking the future digital map vector and the historical high-precision map vector corresponding to the sampling point in the sampling point set as input, and taking the future high-precision map vector corresponding to the input sampling point as the expected output, to train the high-precision map prediction model.

[0123] In some optional implementations, the second determination module 703 may include: an acquisition unit 7031, used to obtain the first historical high-precision map information generated at the target historical moment; a search unit 7032, used to search for the second historical high-precision map information corresponding to the road section represented by the first historical high-precision map information from a preset high-precision map database; a determination unit 7033, used to determine the historical high-precision map information corresponding to the current location information based on the search result.

[0124] In some optional implementations, the determination unit 7033 can be further used to: if the search result indicates that the second historical high-precision map information can be found, fuse the corresponding data in the first historical high-precision map information and the second historical high-precision map information to obtain the historical high-precision map information corresponding to the current location information.

[0125] In some optional implementations, the determination unit 7033 can be further used to: extract at least one data pair corresponding to the first historical high-precision map information and the second historical high-precision map information; determine the fused data corresponding to each data pair in the at least one data pair; and generate the target historical high-precision map information corresponding to the current location information based on the at least one fused data obtained.

[0126] In some optional implementations, the determination unit 7033 can be further used to: for each data pair in at least one data pair, if the gap between the data pairs meets the preset conditions, determine the weighted average of the data pairs to obtain fused data; if the data pair does not meet the preset conditions, determine the data from the second historical high-precision map information in the data pair as fused data.

[0127] The high-precision map information prediction device provided by the above-mentioned embodiment of the present disclosure obtains digital map information corresponding to the target road section that the vehicle is about to travel on from a digital map based on the current position information of the vehicle, then determines the historical high-precision map information corresponding to the current position information, and finally predicts the high-precision map information corresponding to the target road section based on the digital map information and the historical high-precision map information, thereby realizing the combination of the digital map information of the road that the vehicle is about to pass and the historical high-precision map information. When predicting the high-precision map information, more known information can be introduced, which greatly improves the accuracy of the predicted high-precision map information, provides prior information for the subsequent real-time generation of high-precision maps, is conducive to improving the accuracy of the real-time generated high-precision maps, and reduces the subsequent time, labor costs, and computing resource investment.

[0128] Exemplary electronic devices

[0129] Below, reference Figure 9 To describe the electronic device according to the embodiment of the present disclosure. The electronic device may be as follows Figure 1 Any one or both of the terminal device 101 and the server 103 shown, or a stand-alone device independent of them, can communicate with the terminal device 101 and the server 103 to receive the collected input signals from them.

[0130] Figure 9 A block diagram of an electronic device according to an embodiment of the present disclosure is illustrated.

[0131] like Figure 9 As shown, electronic device 900 includes one or more processors 901 and memory 902 .

[0132] The processor 901 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 900 to perform desired functions.

[0133] The memory 902 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. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. 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 a computer-readable storage medium, and the processor 901 may execute the program instructions to implement the high-precision map information prediction method of each embodiment of the present disclosure above and / or other desired functions. Various contents such as current location information, digital map information, high-precision map information, etc. may also be stored in the computer-readable storage medium.

[0134] In one example, the electronic device 900 may further include an input device 903 and an output device 904 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0135] For example, when the electronic device is the terminal device 101 or the server 103 , the input device 903 may be a device such as a mouse or a keyboard for inputting map information, various commands, etc. When the electronic device is a standalone device, the input device 903 may be a communication network connector for receiving input map information, various commands, etc. from the terminal device 101 and the server 103 .

[0136] The output device 904 can output various information to the outside, including the generated high-precision map information. The output device 904 can include, for example, a display, a speaker, a printer, a communication network and its connected remote output device, etc.

[0137] Of course, to simplify, Figure 9 Only some of the components related to the present disclosure in the electronic device 900 are shown, and components such as buses, input / output interfaces, etc. are omitted. In addition, the electronic device 900 may further include any other appropriate components according to specific application scenarios.

[0138] Exemplary computer program products and computer-readable storage media

[0139] In addition to the above-mentioned methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the high-precision map information prediction method according to various embodiments of the present disclosure described in the above-mentioned "Exemplary Method" section of this specification.

[0140] The computer program product may be written in any combination of one or more programming languages ​​to implement the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as C or similar programming languages. The program code may 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.

[0141] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to execute the steps of the high-precision map information prediction method according to various embodiments of the present disclosure described in the above "Exemplary Method" section of this specification.

[0142] The computer-readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can, for example, include but is not limited to a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0143] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this disclosure are merely illustrative and not restrictive, and should not be construed as necessarily possessed by each embodiment of the present disclosure. Furthermore, the specific details disclosed above are provided for illustrative purposes and to facilitate understanding, rather than as limitations. These details do not limit the present disclosure to necessarily being implemented using these specific details.

[0144] Each embodiment in this specification is described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. References to the same or similar parts between the various embodiments are sufficient. For system embodiments, since they largely correspond to method embodiments, their description is relatively simple. For relevant parts, references to the description of the method embodiments are sufficient.

[0145] The block diagrams of the devices, devices, equipment, and systems involved in this disclosure 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 will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0146] The methods and apparatus of the present disclosure may be implemented in many ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present disclosure may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers recording media that store programs for executing the methods according to the present disclosure.

[0147] It should also be noted that in the apparatus, device, and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0148] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure 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.

[0149] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example 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 high-precision map information prediction method, comprising: Determine the current location information of the vehicle; acquiring, from a digital map, digital map information corresponding to a target road section on which the vehicle is about to travel, based on the current position information, wherein the digital map information corresponding to the target road section is used to characterize features of the target road section; Determining historical high-precision map information corresponding to the current location information, where the historical high-precision map information represents characteristics of a section of road that the vehicle has passed through at the current location; Based on the digital map information and the historical high-precision map information, the high-precision map information corresponding to the target road section is predicted.

2. The method according to claim 1, wherein After predicting the high-precision map information corresponding to the target road section, the method further includes: Based on the high-precision map information corresponding to the target road section, the real-time high-precision map information corresponding to the current location information is determined.

3. The method according to claim 1, wherein The predicting of the high-precision map information corresponding to the target road section based on the digital map information and the historical high-precision map information includes: Performing vectorization processing on the digital map information and the historical high-precision map information respectively to obtain a digital map vector and a high-precision map vector; Inputting the digital map vector and the high-precision map vector into a pre-trained high-precision map prediction model to obtain a predicted high-precision map vector; Based on the predicted high-precision map vector, high-precision map information corresponding to the target road section is obtained.

4. The method according to claim 3, wherein: The high-precision map prediction model is pre-trained according to the following steps: Determine a set of sampling points on a road in a digital map or a high-precision map; For a sampling point in the sampling point set, determining future digital map information corresponding to the sampling point from the digital map, and performing vectorization processing on the future digital map information to obtain a future digital map vector; determining historical high-precision map information and future high-precision map information corresponding to the sampling point from the high-precision map, and performing vectorization processing on the historical high-precision map information and the future high-precision map information, respectively, to obtain a historical high-precision map vector and a future high-precision map vector; The high-precision map prediction model is obtained by training by taking the future digital map vectors and historical high-precision map vectors corresponding to the sampling points in the sampling point set as input, and the future high-precision map vectors corresponding to the input sampling points as expected output.

5. The method according to claim 1, wherein The determining of the historical high-precision map information corresponding to the current location information includes: Obtain the first historical high-precision map information generated at the target historical moment; Searching a preset high-precision map database for second historical high-precision map information corresponding to the road segment represented by the first historical high-precision map information; Based on the search results, determine the historical high-precision map information corresponding to the current location information.

6. The method according to claim 5, wherein: Determining the historical high-precision map information corresponding to the current location information based on the search result includes: If the search result indicates that the second historical high-precision map information can be found, the corresponding data in the first historical high-precision map information and the second historical high-precision map information are fused to obtain the historical high-precision map information corresponding to the current location information.

7. The method according to claim 6, wherein: The fusing corresponding data in the first historical high-precision map information and the second historical high-precision map information to obtain the historical high-precision map information corresponding to the current location information includes: Extracting at least one corresponding data pair from the first historical high-precision map information and the second historical high-precision map information; Determining fused data corresponding to each data pair in the at least one data pair; Based on the at least one fused data obtained, target historical high-precision map information corresponding to the current location information is generated.

8. A high-precision map information prediction device, comprising: A first determining module, configured to determine the current location information of the vehicle; an acquisition module, configured to acquire, from a digital map, digital map information corresponding to a target road section on which the vehicle is about to travel, based on the current location information, wherein the digital map information corresponding to the target road section is used to characterize features of the target road section; A second determination module is configured to determine historical high-precision map information corresponding to the current location information, wherein the historical high-precision map information represents characteristics of a section of road that the vehicle has passed through at the current location; A prediction module is used to predict the high-precision map information corresponding to the target road section based on the digital map information and the historical high-precision map information.

9. A computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 7.

10. An electronic device, comprising: processor; a memory for storing instructions executable by the processor; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method according to any one of claims 1 to 7.

Images