Determination of road topology information, electronic map data processing method and electronic device

Abstract

The application provides a determination method of road topology information, an electronic map data processing method and an electronic device. According to the embodiment of the application, the topology of road information is constructed. The determination method of road topology information comprises: obtaining road boundary information of a target road corresponding to to-be-processed map data according to the to-be-processed map data, wherein the to-be-processed map data comprises trajectory data and road vector data; obtaining a road representative line of the target road according to the trajectory data and the road vector data, wherein the road vector data comprises lane line vector data, and the road representative line is used for representing the position and direction of the target road; determining a target area corresponding to the target road based on the road boundary information and the road representative line; and determining road topology information based on the target area.

Description

Technical Field

[0001] This application relates to the field of electronic map technology, and in particular to a method for determining road topology information, electronic map data processing, and electronic equipment. Background Technology

[0002] High-precision maps have extremely high requirements for freshness, meaning the timeliness of data updates. The speed of map updates directly affects the safety of autonomous driving functions and also directly determines the commercial value of high-precision maps. Traditional surveying and mapping methods cannot meet these needs, making crowdsourced data collection methods relying on vehicle-side perception and on-device computing an inevitable trend. In recent years, with the development of basic capabilities such as data collection sensors, on-device computing, and network communication, intelligent perception and computing technologies have become increasingly widespread. In addition to transmitting trajectories, crowdsourced data collection terminals can also transmit real-time perceived road vector elements such as lane lines. Road skeleton and topology information are the most basic information in high-precision maps, containing the most basic cognition, understanding, and information expression of roads. Therefore, how to use useful data to construct road skeleton information in a timely and rapid manner is the primary issue facing high-precision map creation and updating, and it is also the foundation for ensuring map quality. Summary of the Invention

[0003] This application provides a method for determining road topology information, processing electronic map data, and an electronic device to construct accurate road architecture data.

[0004] In a first aspect, embodiments of this application provide a method for determining road topology information, including:

[0005] Based on the map data to be processed, obtain the road boundary information of the target road corresponding to the map data to be processed, wherein the map data to be processed includes trajectory data and road vector data;

[0006] Based on the trajectory data and the road vector data, a road representative line of the target road is obtained, wherein the road vector data includes lane line vector data, and the road representative line is used to characterize the position and direction of the target road;

[0007] Based on the road boundary information and the road representative line, the target area corresponding to the target road is determined;

[0008] Road topology information is determined based on the target area.

[0009] Secondly, embodiments of this application provide an electronic map data processing method, including:

[0010] Obtain road topology information; the road topology information is generated by the method for determining road topology information provided in any embodiment of this application;

[0011] Based on the road topology information, update or create electronic map data.

[0012] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor implements any of the methods described above when executing the computer program.

[0013] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the methods described above.

[0014] Compared with the prior art, this application has the following advantages:

[0015] Using the map data to be processed, a road representative line of the target road is constructed. The road representative line is then used to determine the road topology information of the target road. The location of the target road and the direction of vehicle travel are reflected in the road topology information. This enables the construction of the main information of the road architecture and the extraction of key information, which helps to provide location-based services (LBS) based on the road topology information in the future.

[0016] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application, it can be implemented according to the contents of the specification. In order to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0017] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments according to this application and should not be construed as limiting the scope of this application.

[0018] Figure 1 This is a schematic diagram illustrating an application scenario of the method for determining road topology information according to an embodiment of this application;

[0019] Figure 2 This is a flowchart illustrating the method for determining road topology information according to an embodiment of this application;

[0020] Figure 3 This is a schematic diagram illustrating a method for determining road topology information as exemplified in this application;

[0021] Figure 4 This is a schematic diagram illustrating a method for determining road topology information, as another example of this application.

[0022] Figure 5 This is a schematic diagram illustrating the determination of road boundaries and extent as an example of this application;

[0023] Figure 6 This is a schematic diagram of a road representative line generated as an example of this application;

[0024] Figure 7 This is a schematic diagram illustrating the construction of a road closure area as an example of this application;

[0025] Figure 8A , Figure 8B This is a schematic diagram illustrating the construction of topology groups in an example topology relationship of this application;

[0026] Figure 9 This is a schematic diagram illustrating the construction of topology information for a highway entrance / exit scenario in one example of this application.

[0027] Figure 10 This is a schematic diagram illustrating the construction of topology information for a main-auxiliary road intersection scenario in one example of this application;

[0028] Figure 11 This is a schematic diagram illustrating the construction of topology information for a T-shaped intersection scenario in one example of this application;

[0029] Figure 12 This is a schematic diagram illustrating the construction of topology information for a four-way intersection scenario in one example of this application;

[0030] Figure 13 A schematic diagram illustrating the construction of topology information for a roundabout scene in one example of this application;

[0031] Figure 14 This is a schematic diagram of the structure of the road topology information determination device according to an embodiment of this application; and

[0032] Figure 15 This is a block diagram of an electronic device used to implement embodiments of this application. Detailed Implementation

[0033] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the concept or scope of this application. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0034] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and all of them fall within the protection scope of the embodiments of this application.

[0035] Figure 1 This is a schematic diagram illustrating an application scenario for implementing the method of the embodiments of this application. For example... Figure 1 As shown, the method for determining road topology information in this application embodiment can be applied to a system with a data acquisition terminal and a road topology information determination device 101. The data acquisition terminal may include a crowdsourced vehicle 102, a dedicated map data acquisition terminal 103, or other user terminals. The crowdsourced vehicle 102 can be a vehicle equipped with a road raw data acquisition module and a road raw data analysis module. The road raw data acquisition module and the road raw data analysis module can be configured on the vehicle terminal by the vehicle provider, so that during vehicle operation, the road raw data acquisition module can collect raw road data of the road segment traveled by the vehicle. The raw road data may include video, images, laser point clouds, etc. For video and image-type raw road data, the road raw data acquisition module can acquire the data through sensors and other devices. The sensors may include cameras, GNSS (Global Navigation Satellite System), inertial navigation sensors, etc. The vehicle's trajectory can be obtained through GNSS and inertial navigation sensors. The road raw data analysis module can analyze the raw data collected by the road raw data acquisition module to obtain vectorized road data with less memory usage. This vectorized data is then used to generate crowdsourced data, which is sent to the road topology information determination device 101. The dedicated map data acquisition terminal 103 may include a LiDAR point cloud data acquisition vehicle or a road image acquisition vehicle. The road topology information determination device 101 summarizes the crowdsourced data acquired by multiple crowdsourced vehicles 102 and the data acquired by the dedicated map data acquisition terminal 103, and uses the road topology information determination method provided in this embodiment to obtain the corresponding road topology information. In this embodiment, the crowdsourced data is high-precision map crowdsourced information generated by collecting road information using the user's intelligent connected vehicle.

[0036] This application provides a method for determining road topology information, including, as follows: Figure 2 The process shown includes steps S201-S204. Figure 2 The process shown can be executed on either the terminal or the server. When executed on the server, the server can... Figure 2 The road topology information obtained during the process is used to update electronic map data or to create electronic map data.

[0037] In step S201, based on the map data to be processed, the road boundary information of the target road corresponding to the map data to be processed is obtained, wherein the map data to be processed includes trajectory data and road vector data.

[0038] In this embodiment, the map data may include raw crowdsourced data acquired by crowdsourced vehicles (i.e., raw data described below), and may also include image and video data acquired by dashcams. The map data to be processed may include data obtained after processing and transformation of the raw data acquired by the crowdsourced vehicles. It may also include point cloud data collected by a dedicated map data acquisition terminal. The raw data acquired by the crowdsourced vehicles may include multiple trajectory points determined by positioning during the crowdsourced vehicles' operation, as well as road images or videos captured during the operation. In this embodiment, the crowdsourced vehicles may include autonomous vehicles, such as those at Level 2 or higher. The raw data is processed with the assistance of autonomous vehicles to obtain vector data, and then the vector data is transmitted back, thus enabling the transmitted data to be used as data to be processed. The crowdsourced vehicles may also include social vehicles with custom cameras specifically configured to obtain raw data.

[0039] In this embodiment, road boundary information may include the location information and shape information of the road boundary, which are related information about the road coverage area. For example, by annotating the image information collected by crowdsourced vehicles with vector data, a curve extending along the road boundary can be generated, and the curve represents the location information and shape information of the road boundary. As another example, by annotating the image information collected by a specific vehicle with vector data, straight line segments extending along and connecting each other along the road boundary can be generated, and the straight line segments represent the location information and shape information of the road boundary. The road vector data in this embodiment may or may not include directional information.

[0040] In another implementation, the data to be processed may also include navigation data uploaded by users' mobile phones or other terminals. Generally, mobile phones and other user terminals are equipped with devices such as cameras, GNSS sensors, and inertial navigation sensors, which can obtain trajectory data with relatively low computing power and extract road vector data from the raw image data.

[0041] In one implementation, the terminal configured on the crowdsourced vehicle can process the collected raw data to obtain map data to be processed. This map data can be considered intermediate data between the raw data and the road data analysis results. Video and image data collected by the crowdsourced vehicle occupy a large amount of storage space and are difficult to transmit. Therefore, the raw data such as videos and images can be processed to generate smaller map data to be processed. For example, the map data to be processed can be road vector data generated from road images. The terminal configured on the crowdsourced vehicle analyzes the roads in the images and videos, converting road edge lines, lane lines, road surface arrows, and other line data into road vector data, and associating it with the trajectory points generated during image and video acquisition to obtain the map data to be processed.

[0042] In one implementation, the data acquired by the dedicated map data acquisition terminal can be used as map data to be processed, such as laser point cloud data collected by a laser point cloud acquisition vehicle, or intermediate data generated after converting and processing the laser point cloud data.

[0043] Based on the map data to be processed, the road boundary information of the target road corresponding to the map data to be processed is obtained. This may include extracting trajectory data and road vector data based on the line vector data and trajectory information in the map data to be processed. The road vector data may include line vector data. Line vector data can be any type of vector data, including road boundaries, road lane lines, road surface arrows, and other data that can be expressed using lines or directional arrows.

[0044] In another implementation, obtaining the road boundary information of the target road corresponding to the map data to be processed may include filtering out the line vector data representing the road boundary and road lane lines in the map data to be processed as road vector data; filtering out the laser point cloud data representing the road boundary and road lane lines in the data to be processed as the road boundary information of the target road, and generating road vector data based on the road boundary information; and determining the trajectory data based on the extension direction of the trajectory.

[0045] In another implementation, the map data to be processed may include data related to the target road and other roads. Obtaining the road boundary information of the target road corresponding to the map data to be processed may further include: extracting map data related to the target road from the map data containing information on multiple roads, and obtaining the road boundary information of the target road based on the map data related to the target road.

[0046] In this embodiment, the target road can be one of several roads that need to be analyzed in the actual environment.

[0047] In step S202, a road representative line of the target road is obtained based on the trajectory data and the road vector data, wherein the road vector data includes lane line vector data, and the road representative line is used to characterize the position and direction of the target road.

[0048] In this embodiment, the road representative line of the target road is obtained based on the trajectory data and the road vector data. This may include dividing the target road into multiple regions along the road boundary; constructing a road representative line for each region; and obtaining the road representative line of the target road based on the road representative lines of all regions.

[0049] In this embodiment, the road representative line can be a straight line, a curve, or a long, narrow shape with a certain width. The location of the target road can include its planar location, i.e., its coordinate location in a geographic coordinate system, and its vertical relative position to other roads. Furthermore, the location of the target road can include its geographical location and width information. The direction of the target road can also include its extension direction and the main traffic direction of vehicles on it. If the target road includes a main road and auxiliary roads, the direction of the target road can include the extension direction of the main road, the main traffic direction of vehicles on the main road, and the extension direction of the auxiliary road, and the main traffic direction of vehicles on the auxiliary road.

[0050] In step S203, the target area corresponding to the target road is determined based on the road boundary information and the road representative line.

[0051] In this embodiment, the road boundary information may include the left side boundary information and the right side boundary information.

[0052] In this embodiment, determining the target area corresponding to the target road based on the road boundary information and the road representative line may include dividing the target road based on the road boundary information and the road representative line to form at least one target area. The target area in step S203 above can be a closed area, which can be used to represent the segmentation of the target road, and may include the boundary of the target road, the intersection position information when the target road intersects with other roads, the position information of both ends of the target road, etc.

[0053] Determining the target area corresponding to the target road based on the road boundary information and the road representative line may include determining the position information of both ends of the target road based on the road boundary information and the road representative line; and determining the target area corresponding to the target road based on the road boundary information and the position information of both ends of the target road.

[0054] In step S204, road topology information is determined based on the target area.

[0055] Topology is the study of properties of geometric figures or spaces that remain invariant after continuous changes in shape. Topology considers only the positional relationships between objects, not their shapes and sizes. In this embodiment, the topological information refers to information about the road geometry and road space that remain invariant after continuous changes in shape.

[0056] In this embodiment, the road topology information may include at least one of the following: the relationship between different regions, the inclusion and being included relationship between the target road and the target region, the relationship between the road representative lines between different target regions included by the target road, the relationship between the target road and other connected roads, and the relationship between each target region of the target road and the target regions included by other roads connecting the target road.

[0057] The relationships between the target areas included in the target road can be obtained from the driving trajectories included in the data to be processed.

[0058] In another embodiment, the road topology information may further include the target area included by the target road and a set of representative lines corresponding to the target area included by the target road.

[0059] In this embodiment, determining road topology information based on the target area may include: using the set of topology information corresponding to all target areas of the target road as the road information analysis result. It may also include: determining the road topology information of a single target area, and the association information of the road topology information of adjacent target areas; using the road topology information and the association information of a single target area as the road topology information.

[0060] In this embodiment, the unprocessed data generated from the original data of the target road is used to construct the road boundary information and the road representative line of the target road. The road representative line is used to reflect the location of the target road and the direction of vehicle travel, thereby realizing the construction of the road architecture and the extraction of key information. This helps to provide location-based services (LBS) based on the road topology information in the future.

[0061] In one implementation, obtaining the road boundary information of the target road corresponding to the map data to be processed, based on the map data to be processed, includes:

[0062] Based on the trajectory data and the road vector data, at least one area included by the target road is determined;

[0063] Based on at least one area included in the target road, the road boundary information of the target road is obtained.

[0064] In this embodiment, the area included by the target road and the target area included by the target road can be the area obtained by dividing the target road at different execution stages of the method for determining road topology information in this embodiment.

[0065] In this embodiment, road vector data may include non-line vector data and line vector data. Non-line vector data may include vector data of non-linear markings such as planar patterns drawn on the surface of the target road or traffic signs. Line vector data may include vector data of linear markings such as lane lines, boundary lines, and guardrails. The trajectory related to the target road may include a trajectory that passes through the target road, a trajectory that passes through the start and end points of the target road, or a trajectory that does not pass through the target road but overlaps with the target road in latitude and longitude (e.g., on or under a bridge).

[0066] The road vector data in this embodiment can be obtained by processing and extracting vectors from image data containing road information at the acquisition terminal. Road vector data can be data representing the position and shape of map graphics or geographic entities using x and y coordinates in Cartesian coordinates. Road vector data can generally represent the spatial location of geographic entities as accurately as possible by recording coordinates. In the road vector data structure, point data can be directly described by coordinate values; line data can be described by a chain of sequential coordinates (multiple coordinate points) with uniform or non-uniform intervals; and area data (or polygon data) can be described by boundary lines. The organization of road vector data can use arc segments as the basic logical unit, with each arc segment constrained by two or more intersecting nodes and described by the attributes of two adjacent polygons. In computers, using vector data has the advantages of small storage requirements and the ability to extract certain features from point coordinate chains to obtain the topological relationships between data items. In a vector data system, geometric information can be used to describe spatial geometric positions, and topological information can be used to describe spatial connections, adjacencies, and inclusion relationships, thereby clearly expressing the structure between spatial features. Therefore, the road vector data in this embodiment has the characteristic of clearly expressing the spatial characteristics and structure of roads.

[0067] In this embodiment, the target area of ​​the target road and at least one area included in the target road are different, and are obtained by dividing the target road at different execution stages by the determination method provided in this application embodiment. The at least one area included in the target road may include the start and end positions divided in the target road and the closed area defined by the two side boundaries of the target road.

[0068] In this embodiment, road boundary information of the target road can be obtained from the vector data, thereby enabling the construction of the target road's topology information based on the boundary information.

[0069] In one embodiment, the trajectory data includes at least one trajectory, each trajectory including multiple target trajectory points related to the target road; the road vector data includes road boundary vectors; the step of obtaining the road boundary information of the target road corresponding to the map data to be processed, based on the map data to be processed, includes:

[0070] Based on the trajectory data, determine the position of the target trajectory point;

[0071] At the location of the target trajectory point, based on the direction of travel of the trajectory data, determine the road boundary vectors on both sides of the target trajectory point that are closest to the target trajectory point, and use them as the target road boundary vectors;

[0072] The road boundary information of the target road is determined based on the target road boundary vectors corresponding to multiple target trajectory points.

[0073] In this embodiment, the trajectory data may include multiple trajectories, and each trajectory may include multiple target trajectory points. When the data for each target trajectory point is generated, the generation time, positioning data, and signal strength at the time of generation are recorded. Therefore, the direction of travel of the target trajectory can be determined based on the chronological order.

[0074] In this embodiment, the road boundary vector may include a vector representing the location and extended shape of the road boundary. It can be a straight line vector, a curved vector, or a two-dimensional or three-dimensional vector.

[0075] In this embodiment, the information of the target trajectory point may include the target trajectory point's location, positioning accuracy, and signal strength record at the time of trajectory point generation. The road boundary vectors closest to the target trajectory point on both sides may include at least one of the road boundary vector to the left of the target trajectory's direction of travel and the road boundary vector to the right of the target trajectory's direction of travel.

[0076] In the embodiments of this application, left, right, front, and back can all be referenced to the direction of travel.

[0077] The distance between the road boundary vector and the target trajectory point can be the distance from the target trajectory point to the road boundary vector, that is, the distance from the point to the line.

[0078] At the location of the target trajectory point, based on the direction of travel of the target trajectory, determine the road boundary vectors on both sides of the target trajectory point that are closest to the target trajectory point, as the target road boundary vectors. This may include determining the corresponding left road boundary vector and / or right road boundary vector for each target trajectory point.

[0079] In this embodiment, at least one region included by the target road can be determined based on the road boundary vector, thereby enabling the construction of the topology information of the target road based on at least one region included by the target road.

[0080] In one implementation, determining the road boundary information of the target road based on the target road boundary vectors corresponding to the plurality of target trajectory points includes:

[0081] Determine the left road boundary vector and right road boundary vector corresponding to multiple target trajectory points; the target road boundary vector includes the left road boundary vector and the right road boundary vector;

[0082] When it is determined that the left road boundary vectors corresponding to multiple target trajectory points represent the same road boundary, and the right road boundary vectors corresponding to the multiple target trajectory points also represent the same road boundary, the road boundary information of the target road is determined based on at least one of the left road boundary vector and the right road boundary vector. The left road boundary vector represents the left boundary of the road, and the right road boundary vector represents the right boundary of the road.

[0083] In this embodiment, it can be determined whether the left road boundary vectors corresponding to multiple target trajectory points represent the same road boundary based on whether the difference in the direction of the left road boundary vectors corresponding to multiple target trajectory points is greater than a preset threshold.

[0084] Similarly, it can be determined whether the right-side road boundary vectors corresponding to multiple target trajectory points represent the same road boundary by checking whether the difference in the direction of the right-side road boundary vectors corresponding to multiple target trajectory points is greater than a preset threshold.

[0085] In this embodiment, the road boundary information of the target road can be determined based on whether the road boundary vector represents the same road boundary. This allows for the accurate determination of the positions of both ends of the target road using the information of the road boundary vector. Furthermore, by combining the left and right boundaries of the target road, the boundary of the target road can be obtained.

[0086] In one embodiment, determining the road boundary information of the target road based on at least one of the left-hand road boundary vector and the right-hand road boundary vector includes:

[0087] The start and end positions of at least one region included by the target road are determined based on at least one of the road boundary vector to the left of the target trajectory point and the road boundary vector to the right of the target trajectory point.

[0088] The road boundary information of the target road is obtained based on the start and end positions, the left road boundary vector, and the right road boundary vector.

[0089] Based on the start and end positions, the left road boundary vector, and the right road boundary vector, the road boundary information of the target road can be obtained, which may include:

[0090] Obtain the sub-region of the target road defined by the adjacent start and end positions, and the left and right road boundary vectors between the adjacent start and end positions;

[0091] The sub-region is extended by a set buffer distance at the start and end positions along the extension direction of the target road to obtain the extended sub-region;

[0092] The expanded sub-region is used as the region included in the target road to obtain the road boundary information of the target road.

[0093] In this embodiment, the left road boundary vector of the target trajectory point can be the road boundary vector closest to target trajectory point A on the left side of the road opposite to the direction of travel of A, determined for each target trajectory point A. Similarly, the right road boundary vector of the target trajectory point can be the road boundary vector closest to target trajectory point A on the right side of the road opposite to the direction of travel of A, for each target trajectory point A.

[0094] In this embodiment, the region encompassed by the target road can be determined based on whether the road boundary vectors closest to the nearest target trajectory point on both sides of the target trajectory point represent the same road boundary, thus obtaining accurate information about the region of the target road. When calculating the road representative line, if the region of the target road, used as the basic unit of calculation, is too short, it may increase the number of calculations, reduce computational efficiency, and increase unnecessary computational difficulty. In this embodiment, the sub-regions are expanded to obtain the region encompassed by the target road, ensuring that adjacent regions are interconnected and also preventing excessively short regions.

[0095] In one implementation, determining the start and end positions of at least one region encompassed by the target road based on at least one of the road boundary vector to the left of the target trajectory point and the road boundary vector to the right of the target trajectory point includes:

[0096] In the case where there are at least two left road boundary vectors representing different road boundaries, a first change point between adjacent different road boundaries is determined, and the start and end positions of the target road area are determined based on the first change point.

[0097] And / or, in the case where there are at least two right-side road boundary vectors representing different road boundaries, determine a second change point between adjacent different road boundaries, and determine the start and end positions of the target road area based on the second change point;

[0098] And / or, if the heading of at least one target trajectory point changes more than a preset threshold from the heading of an adjacent target trajectory point in front or behind, the start and end positions of the target road area are determined based on the trajectory points whose heading changes more than the preset threshold.

[0099] In this embodiment of the application, different road boundaries may include road boundaries with different directions.

[0100] In this embodiment, the starting and ending positions of the target road area are determined based on the points where the boundary changes and the trajectory points where the heading changes. This allows the inflection points of the target road or the intersection points of the target road with other roads to be determined based on the shape characteristics of the target road. It also allows road segments of the target road that conform to certain shape rules to be divided into the same area, which facilitates the construction of topology information.

[0101] In one embodiment, the method for determining road topology information further includes: using the outermost solid line vector on the left within the set range as the left road boundary vector of the target trajectory point; and / or using the outermost solid line vector on the right within the set range as the right road boundary vector of the target trajectory point.

[0102] The above embodiments can be applied to situations where there are no road boundary vectors on the left and / or right sides of the road.

[0103] In this embodiment, the outermost solid line vector can be lane line vector data or solid line vectors drawn on the road surface in the road edge area.

[0104] In this embodiment, if there is no road boundary vector to the left or right of the target trajectory point, the outermost solid line vector of the trajectory point can be used as the road boundary vector to ensure that there is a road boundary in each area of ​​the target road.

[0105] In one embodiment, the trajectory data includes data on trajectories exiting the target road and / or trajectories entering the target road, as well as data on trajectories at the start and end points of the area traversing the target road.

[0106] In this embodiment, the trajectories of vehicles entering and leaving the target road, as well as the trajectories of the starting and ending points of the areas passing through the target road, are included as part of the target trajectory related to the target road. This allows for the generation of more comprehensive representative information about the target road based on the target trajectory.

[0107] In one embodiment, obtaining the road representative line of the target road by curve fitting the trajectory data and the road vector data includes:

[0108] Based on the trajectory data, the target road is segmented to obtain multiple fitted segments of the target road;

[0109] For each fitted segment, curve fitting is performed on the trajectory data and road vector data within the fitted segment to obtain the segmented road representative line of the target road within the fitted segment;

[0110] The road representative line is determined based on the segmented road representative line.

[0111] In this embodiment, when calculating the road representative line of the target road, the target road can be segmented, and the segmented road representative lines in each fitting segment can be fitted separately. Thus, during the fitting process, the road can be divided according to the shape characteristics of the road extension, and the fitting of irregular curves can be transformed into the fitting of multiple regular curves or straight lines as much as possible, reducing the fitting difficulty and ensuring the accuracy of the fitted representative line.

[0112] In another embodiment of this application, the target road may not be segmented. Instead, the trajectory data and road vector data are directly fitted to obtain a curve representing the direction of travel within the target road. This minimizes the total distance from the trajectory points of the trajectory data within the target road to the road representative line. Then, the curve is translated to minimize the total distance from the lane lines within the target road to the curve. The translated curve is then used as the road representative line.

[0113] In one implementation, the step of obtaining a segmented road representative line of the target road within each fitted segment by performing curve fitting on the trajectory data and road vector data within the fitted segment includes:

[0114] Within the fitting segment, a line segment representing the direction of travel is fitted such that the total distance from all target trajectory points within the fitting segment to the line segment is minimized.

[0115] Within the fitted segment, the line segment is translated such that the total distance from all lane lines within the fitted segment to the line segment is minimized.

[0116] The translated line segment is used as the segmented road representative line of the target road within the fitted segment.

[0117] Determining the road representative line based on the segmented road representative line may include, if the target road includes a region, merging the segmented road representative lines of each segment in the region and using the merged representative line as the road representative line of the target road; if the target road includes multiple regions, for each region, merging the segmented road representative lines of each segment in the region and using the merged segmented representative line as the corresponding road representative line of at least one region included by the target road.

[0118] In this embodiment, the road is segmented so that when there are road bends, the curved road can be approximated as multiple small segments of straight road to simplify the calculation.

[0119] In this embodiment, when fitting line segments representing the direction of travel within a segment, the target trajectory that is too curved or incomplete within the segment can be filtered out to obtain a more regular target trajectory (such as a straight line trajectory) for fitting line segments representing information.

[0120] In this embodiment, within a segment, translating the line segment to minimize the total distance from all lane lines to the line segment can include translating the line segment based on the points of each lane line within the segment, so that the total distance from the points of the lane lines to the line segment is minimized.

[0121] In this embodiment, lane lines are used to verify line segments, which can correct inaccurate positioning of target trajectory points.

[0122] In this embodiment, within each segment, a line segment representing the direction of travel is fitted, including performing the operation of fitting line segments within each segment. The line segment may include one of the following: a curved line segment, a straight line segment, or a combination of curves and straight lines.

[0123] In one embodiment, fitting a line segment representing the direction of travel within the fitted segment includes:

[0124] Within the fitted segment, the trajectory data and lane lines within the fitted segment are translated to the reference origin;

[0125] Based on the translated trajectory data and lane lines, a line segment representing the direction of travel is fitted at the reference origin.

[0126] In this embodiment, a line segment representing the direction of travel is fitted based on the reference origin, so that the road representative line of the target road can smoothly transition within the closed area.

[0127] In one implementation, determining the road topology information based on the target area includes:

[0128] The vertices of the topology information are determined based on the road representative lines corresponding to the target area, and the edges of the topology information are determined based on the traffic relationships between the target areas, thus obtaining the topology information of the target area.

[0129] The topological information of multiple target areas is merged to obtain road topological information.

[0130] In this embodiment, the relationships between regions used to construct the topological information can be descriptive information that constructs the travel relationships between regions. For example, regions A and B can be used as vertices, and the travel relationships from A to B can be used as edges.

[0131] In this embodiment, by using topological information, the relationships between the regions included in the target road can be recorded in the topological relationships when the target road comprises multiple regions. The relationships between the target road and other roads can also be recorded through the topological relationships. In this embodiment, the relationships between regions can include connectivity, intersection, etc., and the relationships between roads can include connectivity, intersection, parallel, reverse traffic, etc.

[0132] In one specific implementation, map navigation can be performed based on the road topology information generated in any embodiment of this application. When an autonomous vehicle navigates based on high-precision map data, the road topology information can be used to generate a vehicle driving plan, ensuring that the planned trajectory is consistent with the road topology information during the vehicle's journey, thereby improving the efficiency of route determination and driving safety.

[0133] This application also provides an electronic map data processing method, including:

[0134] Obtain road topology information; the road topology information is generated by the method for determining road topology information provided in any embodiment of this application;

[0135] Based on the analysis results of road information, update or create electronic map data.

[0136] In this embodiment, updating or creating electronic map data based on road information analysis results may include incorporating the road information analysis results as part of the electronic map data, so that the road information analysis results can be referenced when using the electronic map data.

[0137] This application also provides a navigation request processing method, including:

[0138] During navigation, obtain the terminal's location information;

[0139] Obtain road topology information corresponding to the terminal location information and generate navigation information; the road information analysis result is generated by the road topology information determination method provided in any embodiment of this application.

[0140] Send navigation information to the terminal.

[0141] The navigation request processing method described above can be applied to the map data server side.

[0142] The navigation request processing method described above is based on high-precision map data.

[0143] This application also provides a navigation request processing method, including:

[0144] During navigation, the terminal location information is sent to the server.

[0145] The system receives navigation information sent by the server based on the terminal's location information; the navigation information is generated based on road topology information corresponding to the terminal's location information; the road topology information is generated by the method for determining road topology information provided in any embodiment of this application.

[0146] Based on the navigation information, generate user-oriented navigation prompts.

[0147] The above navigation request processing method can be applied to user terminals and to scenarios where high-precision maps are used for navigation.

[0148] Road framework and topology information are among the most fundamental and crucial pieces of information in a map. In this embodiment, when constructing road topology using crowdsourced data, raw data can be obtained through crowdsourcing, and the data to be processed can be derived from the raw data obtained through crowdsourcing and other methods. The lane vector line information in the raw data is fully utilized to analyze the road topology information, obtaining the road framework and road relationship description data. The method provided in this embodiment utilizes the characteristics of trajectories and lane vector lines; the two mutually constrain and complement each other, improving the robustness and refinement of the road framework, and thus enhancing its quality. Simultaneously, it reduces the requirements for the number of times the crowdsourced data trajectory and lane coverage are used, shortening the basic data update cycle of the electronic map data and improving the freshness (timeliness) of the electronic map data.

[0149] The embodiments of this application can be applied to high-precision maps and lane-level electronic map data, and can generate SD (Standard Definition) or HD (High Definition) images.

[0150] In this embodiment, the road skeleton can be a geographic information representation used to describe the shape of the main road. The high-precision road skeleton information also includes road boundary information and can distinguish fine road structures, such as separation of main and auxiliary roads and dedicated right-turn lanes.

[0151] In this embodiment of the application, the topological information of the road can be a mathematical expression describing the connectivity between road segments.

[0152] High-precision maps have very high requirements for freshness. The speed at which electronic map data is updated directly affects the safety of high-precision maps' assisted autonomous driving functions and also directly determines the commercial value of high-precision maps. Relying on general surveying and mapping methods cannot meet the needs, and crowdsourced data collection methods that rely on vehicle-side perception and on-device computing (terminals) have become an inevitable trend.

[0153] In recent years, with the development of fundamental technologies such as data acquisition sensors, edge computing, and network communication, branch technologies such as intelligent sensing computing have become increasingly popular in mass-market products. Crowdsourced data acquisition terminals employing intelligent sensing computing technology can obtain some of the raw data needed for processing. In the example of this application, in addition to transmitting trajectories, the crowdsourced data acquisition terminal can also transmit real-time perceived road vector elements such as lane lines.

[0154] In this embodiment, the target road includes representative information from multiple areas, including skeleton information that reflects the external characteristics of the target road. This skeleton information is the most basic information in electronic map data for high-precision maps, containing the most basic understanding and information expression of the road. Therefore, how to use crowdsourced data to construct road skeleton information is the primary issue facing high-precision map creation and updating, and it is also the foundation for ensuring map quality.

[0155] Generally, trajectories fed back from crowdsourced data can be clustered and fitted to generate road skeletons and topologies. However, this method requires a high level of coverage and frequency of trajectories obtained by crowdsourced data collection terminals. Because trajectories obtained solely through crowdsourcing are insufficient for certain special road topology information (such as road turning points, interchanges between main and auxiliary roads, etc.), where vehicles pass infrequently, the trajectories obtained through crowdsourced data collection terminals cannot cover these areas. Furthermore, considering the quality issues of single trajectories (such as potential accuracy drift, missing trajectories, or invalid trajectories), accurately representing the topology information of special scenes or areas on the road requires multiple actual drives by crowdsourced data collection terminals, repeatedly covering the data with a large number of trajectories. When the number and activity of crowdsourced data collection terminals are not high enough, the required number of trajectories cannot be met within a certain period, directly affecting the update cycle and efficiency of electronic map data. Additionally, this method struggles to obtain more detailed information such as road edges and road boundaries (e.g., the boundary between main and auxiliary roads). Due to the limitations of the trajectories, the boundary lines between main and auxiliary roads and other road boundaries cannot be accurately represented, resulting in insufficient detail in the description of the road skeleton.

[0156] In this embodiment, the crowdsourced data collection terminal can acquire data such as images, and obtain vector data of roads from the images and other data. At the same time, during the process of the crowdsourced data collection terminal collecting raw data, at least one trajectory is generated. The crowdsourced data collection terminal can transmit back trajectory data and vector data, so that road boundary lines can be extracted from the trajectory data and vector data and the road range can be constructed. Then, the trajectory and lane lines within the road range are clustered and fitted to obtain the road representative line. Based on the road representative line and boundary key points (equivalent to the first change point and the second change point in the aforementioned embodiment), a closed road segment region can be constructed. Finally, by expressing the topological information of the closed road segment region, the topological relationship of the road can be accurately described.

[0157] In one example of this application, the method for determining road topology information may include, for example: Figure 3The steps are as shown. Specifically, they include: Step S301: Generating road boundary lines and constructing the road extent from the trajectory and road boundary line vectors; Step S302: Using trajectory and lane line vector data, performing cluster fitting to generate a road representative line; Step S303: Constructing a closed road segment region from the road representative line and boundary lines; Step S304: Generating the road topology from the road segment region and its connectivity. The road extent in Step S301 can be equivalent to the road boundary information in the aforementioned embodiments. The road segment region in Step S303 can be equivalent to the region included by the target road in the aforementioned embodiments. Figure 3 In the example shown, the road area can be equivalent to the aforementioned Figure 2 Road boundary information in the illustrated embodiment. The road boundary line vector data is as described above. Figure 2 The road boundary vectors included in the road vector data of the map data to be processed in the illustrated embodiment. The road segment area can be equivalent to... Figure 2 The target area in the illustrated embodiment. The road topology can be equivalent to the aforementioned... Figure 2 Road topology information in the illustrated embodiment.

[0158] In another example of this application, the determination of road topology information may include, for example: Figure 4 The steps shown include: determining road boundaries and limits; generating road representative lines; constructing closed areas for road segments; and generating road topology. Figure 4 In the example shown, the road boundaries and extent are equivalent to those described above. Figure 2 Road boundary information in the illustrated embodiment. The closed area of ​​a road segment is equivalent to... Figure 2 The target area in the illustrated embodiment. The road topology is equivalent to... Figure 2 Road topology information in the illustrated embodiment.

[0159] Still combined Figure 4 In the process of determining road boundaries and limits, changes in trajectory heading and lane line vector data (i.e., Figure 4 The boundary line changes in the vector lane lines are analyzed by first filtering the entry and exit roads (right-turn lanes, ramps, U-turn lanes), and then determining the boundary vectors of the roads on both sides corresponding to the entry (exit) trajectory points (i.e., Figure 4 The vector boundary lines in the diagram are typically the vectors of the road boundaries formed by hard barriers; then, straight lane lines are used to determine the remaining road boundary pairs (which may include solid line barriers). The specific operation process is as follows: Figure 5 As shown, the returned trajectory and vector data are used as map data to be processed. The exit (entry) road trajectory lines and road boundaries are determined. The exit (entry) trajectory lines are included as part of the trajectory data, and the road boundaries are included as part of the road vector data. Among the trajectory lines related to the road (target road), the normal straight-ahead trajectory lines and road boundary pairs are determined.

[0160] In this step, for each trajectory point in the exit (entry) trajectory line, extend along the left and right directions, associate the nearest boundary intersection point so that the line connecting the intersection point and the trajectory point is perpendicular to the nearest boundary, and calculate the trajectory heading change rate based on the line connecting the trajectory point and the intersection point and the trajectory driving direction.

[0161] Reference Figure 5 As shown in section 501, special trajectory points in the trajectory line are determined based on factors such as the rate of change of heading. In the analysis process corresponding to 501, the heading is used to represent the direction of travel of the trajectory, and a set A of trajectory points with abrupt changes in heading and a set B of trajectory points with abrupt changes in the position of associated boundary points are obtained. The abrupt trajectory points correspond to the first change point or the second change point in the aforementioned embodiment, and can be points on the same trajectory where the attribute difference before and after is greater than a threshold.

[0162] Reference Figure 5 As shown in section 502, based on the changes in heading and associated boundary points, the lane change trajectories in the exit (entry) trajectory lines are filtered to select reliable exit (entry) trajectory lines (when entering or exiting, the distance to the left side of the road boundary corresponding to the left turn trajectory point should remain basically unchanged, the distance to the right side of the road boundary corresponding to the right turn trajectory point should remain basically unchanged, and the trajectories before and after the lane change should be almost parallel).

[0163] exist Figure 5 Based on part 502, the connectivity between different trajectory points is determined according to the road boundaries to the left and right of the trajectory points. If the left and right boundary lines of the trajectory points are the same, then the trajectory points are connected, and the connectivity is stored as a set C.

[0164] Reference Figure 5 As shown in section 503, if there are exit (entry) trajectory points in the trajectory-boundary abrupt change point connectivity set C, then this set is a multi-road set, and the corresponding region is a multi-road region. A multi-road region can be a region belonging to the same road or a region belonging to different roads. Based on the determination of the multi-road region, the reliability of the exit (entry) trajectory line can be determined again.

[0165] Reference Figure 5 As shown in section 504, the left and right boundaries of the road area are filtered according to the heading direction of the exit (entry) trajectory line and the boundary point of the nearest road boundary of each trajectory point in the trajectory; then, according to the trajectory point where the heading changes abruptly, the trajectory point corresponding to the boundary change point, and the boundary endpoint of the target area of ​​the road, the start and end positions of the exit (entry) road area are determined, and finally the exit (entry) road boundary set D is obtained.

[0166] exist Figure 5 Based on section 504, the road boundary is filtered according to the endpoint closed interval E to determine whether the lane line is within the endpoint closed interval E, and the exit (entry) lane line F is obtained.

[0167] In determining the normal straight-ahead trajectory and the road boundary, refer to Figure 6 As shown in section 601, the aforementioned exit (entry) trajectory lines, road boundaries at the road boundary endpoints, and lane lines related to the exit (entry) trajectory lines are removed from the set. The lane lines are divided into up and down directions according to their relationship to the trajectory direction. It is determined whether boundary lines exist on both the left and right sides of the trajectory line. If no boundary line exists within a longitudinal distance greater than 10m (or other set values ​​between 1-20m) and it is not near the exit separation point, the outermost solid line is used as the road boundary. The straight-ahead road boundary is closed to obtain interval G. The set H of normal straight-ahead lane lines is then filtered based on G.

[0168] In the process of generating road representative lines, the road representative lines (lines that represent the road's location and direction of travel) are obtained by fitting the trajectory together with lane line vector data. Specifically, this includes: Figure 6 The process shown in 602-604.

[0169] Reference Figure 6 As shown in Part 602, along the exit (entry) trajectory line, at a certain longitudinal distance D ( Figure 6 The distance corresponding to the dashed box in section 602 is used to longitudinally divide the lane lines and exit (entry) trajectory lines within a road segment to obtain the fitted segment.

[0170] Reference Figure 6 In section 603, for each fitted segment, all lane lines and trajectory starting points are translated to the origin, and the curve equation corresponding to the fitted segment is calculated together to minimize the distance from all trajectory points and lane lines to the curve equation representing the curve. This curve equation is then used as the road representative line for the fitted segment.

[0171] Reference Figure 6 In section 604, the starting point of the equation of the representative line of all segmented roads is used as a parameter, the curve equation is fixed, the optimal starting point position is estimated, and the distance from all lane lines to the curve is minimized. The curve obtained in this way is the representative line of the road.

[0172] In the process of constructing closed regions, based on the road representative lines and road boundary lines generated above, closed regions are constructed, which results in small fitted segments. Figure 7 In the process shown, closed areas are constructed in the multi-road area, and the closed areas are equivalent to the aforementioned Figure 2 The target area in the illustrated embodiment.

[0173] Reference Figure 7 As shown in section 701, the boundaries of different roads are extended to intersect until the first intersection ends, ensuring that the boundaries are closed.

[0174] Reference Figure 7 As shown in section 702, the intersection points between different road boundaries are determined when different road boundaries exist. (Refer to...) Figure 7 As shown in section 703, based on the intersections between different road boundaries, find the nearest point on the road representative line corresponding to each intersection point. (Refer to...) Figure 7 As shown in 704, after finding the nearest point, the buff (buffer) is expanded before and after the nearest point to obtain the closed target area. For the case where a road includes multiple consecutive target areas, the expansion buff at the boundary between adjacent consecutive target areas is 0 (to avoid consecutive road forks such as intersections being combined into one area), resulting in the four areas A, B, C and D of 704.

[0175] In this application example, a closed target region is constructed for a single road. When a single road exists between closed target regions, only the boundary lines of the closed target regions need to be closed. Shorter regions can be merged into adjacent target regions in the direction of travel. All trajectory points are divided according to the closed target regions.

[0176] In the process of constructing topological relationships, descriptive information of road topology relationships is built based on each closed target region and the trajectory traffic relationships it contains. Each target region is used as a vertex, and the descriptive information of the relationships between target regions is used as an edge. This generates road topology information, which further includes vertices and edges, and can be used to describe the traffic relationships between closed regions.

[0177] Reference Figure 8A As shown, after establishing road topology information, topology groups can be created based on the sequential order of trajectory points of all trajectory lines and their associated closed regions. These topology groups include the traffic relationships between different individual closed target regions. For example... Figure 8B Trajectory 1 in the topology group shown illustrates the travel relationship of the trajectory in region A as A->B->C; Trajectory 2 illustrates the travel relationship of the trajectory in region A as A->B->D. Figure 8B The topological relationships of the two trajectories shown are merged to obtain Figure 8B The merged information of the two trajectories shown reflects a scenario where roads are separated (intersections exist) in area A.

[0178] Other scenarios' topology information construction diagrams are as follows: Figure 9-13 As shown, Figure 9-13 The letters in the diagram represent regions, and the arrows between the nodes corresponding to the letters represent the communication relationships between regions. Figure 9 This is a schematic diagram of converting a topological view of a highway entrance / exit into a topological map. Figure 10 This is a diagram showing the transformation of a topological view of a main and auxiliary road intersection into a topological map. Figure 11This is a schematic diagram of converting a topological view of a T-shaped intersection into a topological map. Figure 12 This is a schematic diagram of converting a topological view of a four-way intersection into a topological map. Figure 13 This is a diagram illustrating the transformation of a topological view of a roundabout into a topological map. Different scenes have different topological structures, which can also be used to distinguish the characteristics of different scenes.

[0179] Road vector data includes road boundary vector data and lane line vector data. Since road boundary vector data also contains road traffic information, such as guide lines between auxiliary roads, curbs near U-turns, and fences, this application's embodiments do not rely entirely on the trajectory; that is, road topology information for these specific scenarios can be supplemented from the road vector data. Simultaneously, lane line vector data also serves as a supplementary verification of the trajectory, to some extent compensating for quality issues such as drift and trajectory loss caused by low trajectory accuracy, thereby improving the quality of road skeleton information.

[0180] Since the road boundary vector data can be further extracted to determine the road boundary range, the method provided in this application makes the road skeleton information more refined, which helps to determine the relationship between adjacent roads, such as spatially adjacent main and auxiliary roads, which cannot be distinguished by trajectory alone.

[0181] The method provided in this application improves the robustness and refinement of the road skeleton by utilizing the characteristics of trajectory and lane vector line data, thereby enhancing the quality of the road skeleton. Simultaneously, it reduces the requirement for the number of times crowdsourced data coverage is required, shortens the update cycle, and improves the freshness of high-precision maps. The method in this application, which uses road representative lines to divide closed areas and then constructs road topology, is highly versatile and adaptable to complex and diverse road topology structures.

[0182] Corresponding to the application scenario of the road information analysis method provided in the embodiments of this application, the embodiments of this application also provide a device for determining road topology information, such as... Figure 14 As shown, it includes:

[0183] The extraction module 1401 is used to obtain the road boundary information of the target road corresponding to the map data to be processed, wherein the map data to be processed includes trajectory data and road vector data.

[0184] The road representation line construction module 1402 is used to obtain the road representation line of the target road based on the trajectory data and the road vector data, wherein the road vector data includes lane line vector data, and the road representation line is used to characterize the position and direction of the target road;

[0185] The region determination module 1403 is used to determine the target region corresponding to the target road based on the road boundary information and the road representative line;

[0186] The topology information determination module 1404 is used to determine road topology information based on the target area.

[0187] In one implementation, the extraction module is further configured to:

[0188] Based on the trajectory data and the road vector data, at least one area included by the target road is determined;

[0189] Based on at least one area included in the target road, the road boundary information of the target road is obtained.

[0190] In one embodiment, the trajectory data includes at least one trajectory, each trajectory including multiple target trajectory points related to the target road; the road vector data includes road boundary vectors; the extraction module is further configured to:

[0191] Based on the trajectory data, determine the position of the target trajectory point;

[0192] At the location of the target trajectory point, based on the direction of travel of the trajectory data, determine the road boundary vectors on both sides of the target trajectory point that are closest to the target trajectory point, and use them as the target road boundary vectors;

[0193] The road boundary information of the target road is determined based on the target road boundary vectors corresponding to multiple target trajectory points.

[0194] In one implementation, the extraction module is further configured to:

[0195] Determine the left road boundary vector of multiple target trajectory points and the right road boundary vector corresponding to the right side of the multiple target trajectory points; the target road boundary vector includes the left road boundary vector and the right road boundary vector;

[0196] When it is determined that the left road boundary vectors corresponding to multiple target trajectory points represent the same road boundary, and the right road boundary vectors corresponding to the multiple target trajectory points represent the same road boundary, the road boundary information of the target road is determined based on at least one of the left road boundary vectors of the target trajectory points and the right road boundary vectors of the target trajectory points.

[0197] In one implementation, the extraction module is further configured to:

[0198] In the case where there are at least two left road boundary vectors representing road boundaries in different directions, a first change point between adjacent different road boundaries is determined, and the start and end positions of the target road area are determined based on the first change point.

[0199] And / or, in the case where there are at least two right-side road boundary vectors representing different road boundaries, determine a second change point between adjacent different road boundaries and determine the start and end positions of the area of ​​the target road based on the second change point;

[0200] And / or, if the heading of at least one target trajectory point changes more than a preset threshold from the heading of an adjacent target trajectory point in front or behind, the start and end positions of the target road area are determined based on the trajectory points whose heading changes more than the preset threshold.

[0201] In one implementation, the extraction module is further configured to:

[0202] Obtain the sub-region of the target road defined by the adjacent start and end positions, and the left and right road boundary vectors between the adjacent start and end positions;

[0203] The sub-region is extended outward by a set buffer distance from the starting and ending positions along the direction of the target road to obtain the extended sub-region.

[0204] The expanded sub-region is used as the region included in the target road to obtain the road boundary information of the target road.

[0205] In one embodiment, the trajectory data includes data on trajectories exiting the target road and / or trajectories entering the target road, as well as data on trajectories at the start and end points of the area traversing the target road.

[0206] In one implementation, the representative information construction module is further configured to:

[0207] Based on the trajectory data, the target road is segmented to obtain multiple fitted segments of the target road;

[0208] For each fitted segment, curve fitting is performed on the trajectory data and road vector data within the fitted segment to obtain the segmented road representative line of the target road within the fitted segment;

[0209] The road representative line is determined based on the segmented road representative line.

[0210] In one implementation, the representative information construction module is further configured to:

[0211] Within the fitting segment, a line segment representing the direction of travel is fitted such that the total distance from all target trajectory points within the fitting segment to the line segment is minimized.

[0212] Within the fitted segment, the line segment is translated such that the total distance from all lane lines within the fitted segment to the line segment is minimized.

[0213] The translated line segment is used as the segmented road representative line of the target road within the fitted segment.

[0214] In one implementation, the representative information construction module is further configured to:

[0215] Within the fitted segment, the trajectory data and lane lines within the fitted segment are translated to the reference origin;

[0216] Based on the translated trajectory data and lane lines, a line segment representing the direction of travel is fitted at the reference origin.

[0217] In one implementation, the analysis results module is further configured to:

[0218] The topological information vertices are determined based on the road representative lines corresponding to the target area, and the topological information edges are determined based on the traffic relationships between the target areas, thus obtaining the topological information of the target area.

[0219] The topology information of the target area is merged to obtain the road topology information.

[0220] This application also provides an electronic map data processing device, including:

[0221] Obtain road topology information; the road topology information is generated by the apparatus provided in any embodiment of this application;

[0222] Based on the road topology information, update or create electronic map data.

[0223] The functions of each module in each device in the embodiments of this application can be found in the corresponding description in the above method, and they have corresponding beneficial effects, which will not be repeated here.

[0224] This disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods provided in this disclosure.

[0225] Figure 15 This is a block diagram of an electronic device used to implement embodiments of this application. For example... Figure 15As shown, the electronic device includes a memory 610 and a processor 620. The memory 610 stores a computer program that can run on the processor 620. When the processor 620 executes the computer program, it implements the methods described in the above embodiments. The number of memories 610 and processors 620 can be one or more.

[0226] The electronic device also includes:

[0227] The communication interface 630 is used to communicate with external devices and perform data exchange and transmission.

[0228] If the memory 610, processor 620, and communication interface 630 are implemented independently, they can be interconnected via a bus to communicate with each other. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 15 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0229] Optionally, in a specific implementation, if the memory 610, processor 620, and communication interface 630 are integrated on a single chip, then the memory 610, processor 620, and communication interface 630 can communicate with each other through an internal interface.

[0230] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method provided in this application.

[0231] This application also provides a chip including a processor for calling and executing instructions stored in a memory, causing a communication device with the chip installed to perform the method provided in this application.

[0232] This application also provides a chip, including: an input interface, an output interface, a processor, and a memory. The input interface, output interface, processor, and memory are connected through an internal connection path. The processor is used to execute code in the memory. When the code is executed, the processor is used to execute the method provided in the application embodiment.

[0233] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting Advanced Reduced Instruction Set Machines (ARM) architecture.

[0234] Further, optionally, the aforementioned memory may include read-only memory and random access memory. The memory may be volatile memory or non-volatile memory, or may include both. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available. Examples include Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

[0235] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0236] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0237] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0238] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process. Furthermore, the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functionality involved.

[0239] The logic and / or steps described in the flowchart or otherwise herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0240] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. All or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware, the program being stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiments.

[0241] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. This storage medium can be a read-only memory, a disk, or an optical disk, etc.

[0242] The above are merely exemplary embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope described in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for determining road topology information, characterized in that, include: Based on the map data to be processed, obtain the road boundary information of the target road corresponding to the map data to be processed, wherein the map data to be processed includes trajectory data and road vector data, and the road vector data includes lane line vector data; Based on the trajectory data, the target road is segmented to obtain multiple fitted segments of the target road; for each fitted segment, curve fitting is performed on the trajectory data and road vector data within the fitted segment to obtain the segmented road representative line of the target road within the fitted segment; based on the segmented road representative line, the road representative line of the target road is determined, wherein the road representative line is used to characterize the position and direction of the target road; Based on the road boundary information and the road representative line, the target area corresponding to the target road is determined; The vertices of the topology information are determined based on the road representative lines corresponding to the target area, and the edges of the topology information are determined based on the traffic relationships between the target areas, thus obtaining the topology information of the target area. The topological information of multiple target areas is merged to obtain road topological information; Specifically, for each fitted segment, obtaining a segmented road representative line of the target road within the fitted segment by performing curve fitting on the trajectory data and road vector data within the fitted segment includes: Within the fitting segment, a line segment representing the direction of travel is fitted such that the total distance from all target trajectory points within the fitting segment to the line segment is minimized. Within the fitted segment, the line segment is translated such that the total distance from all lane lines within the fitted segment to the line segment is minimized. The translated line segment is used as the segmented road representative line of the target road within the fitted segment.

2. The method according to claim 1, characterized in that, The step of obtaining the road boundary information of the target road corresponding to the map data to be processed includes: Based on the trajectory data and the road vector data, at least one area included by the target road is determined; Based on at least one area included in the target road, the road boundary information of the target road is obtained.

3. The method according to claim 2, characterized in that, The trajectory data includes at least one trajectory, and each trajectory includes multiple target trajectory points related to the target road; the road vector data includes road boundary vectors; the step of obtaining the road boundary information of the target road corresponding to the map data to be processed, based on the map data to be processed, includes: Based on the trajectory data, determine the position of the target trajectory point; At the location of the target trajectory point, based on the direction of travel of the trajectory data, determine the road boundary vectors on both sides of the target trajectory point that are closest to the target trajectory point, and use them as the target road boundary vectors; The road boundary information of the target road is determined based on the target road boundary vectors corresponding to multiple target trajectory points.

4. The method according to claim 3, characterized in that, The step of determining the road boundary information of the target road based on the target road boundary vectors corresponding to multiple target trajectory points includes: Determine the left and right road boundary vectors corresponding to multiple target trajectory points; the target road boundary vectors include the left and right road boundary vectors. If it is determined that the left road boundary vectors corresponding to the plurality of target trajectory points represent the same road boundary, and the right road boundary vectors corresponding to the plurality of target trajectory points represent the same road boundary, the road boundary information of the target road is determined based on at least one of the left road boundary vectors and the right road boundary vectors.

5. The method according to claim 4, characterized in that, Determining the road boundary information of the target road based on at least one of the left road boundary vector and the right road boundary vector includes: The start and end positions of at least one area included by the target road are determined based on at least one of the left road boundary vector and the right road boundary vector. Obtain the sub-region of the target road defined by the adjacent start and end positions, and the left and right road boundary vectors between the adjacent start and end positions; The sub-region is extended by a set buffer distance at the start and end positions along the extension direction of the target road to obtain the extended sub-region; The expanded sub-region is used as the region included in the target road to obtain the road boundary information of the target road.

6. The method according to claim 5, characterized in that, Determining the start and end positions of at least one region included by the target road based on at least one of the left road boundary vector and the right road boundary vector includes: In the case where there are at least two left road boundary vectors representing different road boundaries, determine the first change point between adjacent different road boundaries, and determine the start and end positions of the target road area based on the first change point; And / or, in the case where there are at least two right-side road boundary vectors representing different road boundaries, determine a second change point between adjacent different road boundaries, and determine the start and end positions of the target road area based on the second change point; And / or, if the heading of at least one target trajectory point changes more than a preset threshold from the heading of an adjacent target trajectory point in front or behind, the start and end positions of the target road area are determined based on the trajectory points whose heading changes more than the preset threshold.

7. The method according to claim 2, characterized in that, The trajectory data includes data on trajectories exiting the target road and / or entering the target road, as well as data on trajectories at the start and end points of the area traversed by the target road.

8. The method according to claim 1, characterized in that, Within the fitted segment, fitting a line segment representing the direction of travel includes: Within the fitted segment, the trajectory data and lane lines within the fitted segment are translated to the reference origin; Based on the translated trajectory data and lane lines, a line segment representing the direction of travel is fitted at the reference origin.

9. A method for processing electronic map data, characterized in that, include: Obtain road topology information; The road topology information is generated by the method described in any one of claims 1-8; Based on the road topology information, update or create electronic map data.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory, wherein the processor, when executing the computer program, implements the method of any one of claims 1-9.

11. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the method of any one of claims 1-9.

Images