CN117606469A

CN117606469A - Method and device for generating turn-around intersection, electronic equipment and storage medium

Info

Publication number: CN117606469A
Application number: CN202311744305.9A
Authority: CN
Inventors: 何云燕; 仇建华
Original assignee: Autonavi Software Co Ltd
Current assignee: Autonavi Software Co Ltd
Priority date: 2023-12-18
Filing date: 2023-12-18
Publication date: 2024-02-27

Abstract

The embodiment of the disclosure discloses a method, a device, electronic equipment and a storage medium for generating a u-turn intersection, wherein the method comprises the following steps: acquiring high-precision map data; identifying a turning area on a road based on the high-precision map data; generating an area center line of the turning area; and generating a turning intersection in the standard navigation map data based on the area center line. According to the technical scheme, the turning intersection in the standard navigation map data can be automatically generated, the accuracy is high, the generation efficiency of the turning intersection can be improved, and the manufacturing cost of the standard navigation map data can be reduced.

Description

Method and device for generating turn-around intersection, electronic equipment and storage medium

Technical Field

The disclosure relates to the technical field of maps, in particular to a method and a device for generating a turning intersection, electronic equipment and a storage medium.

Background

The target map data includes both standard navigation map data and high-definition map data. Standard navigation map data and high-precision map data are produced separately by two independent production lines. Standard navigation map data can be understood as an electronic map or dataset containing spatial location geographical coordinates that can be combined with a spatial location information system to accurately guide a navigated object from a departure location to a destination. The high-precision map data can be understood as being composed of element data such as a road traffic network, a lane traffic network, road traffic marks and marks, road other facilities and the like which are high in position precision and rich in semantics, and is basic data for realizing auxiliary driving, automatic driving, intelligent vehicle-road coordination, intelligent traffic fine management and related test application. In the prior art, the turning intersection in the standard navigation map is manufactured by manually referring to field acquisition data of the standard navigation map data, and the processing efficiency is low.

Therefore, a solution capable of automatically making a turn-around intersection in standard navigation map data is required to improve the processing efficiency.

Disclosure of Invention

The embodiment of the disclosure provides a method, a device, electronic equipment and a storage medium for generating a u-turn intersection.

In a first aspect, an embodiment of the present disclosure provides a method for generating a u-turn intersection, where the method includes:

acquiring high-precision map data;

identifying a turning area on a road based on the high-precision map data;

generating an area center line of the turning area;

and generating a turning intersection in the standard navigation map data based on the area center line.

In a second aspect, an embodiment of the present invention provides a u-turn intersection generating device, including:

an acquisition module configured to acquire high-precision map data;

an identification module configured to identify a turning area on a road based on the high-precision map data;

a first generation module configured to generate a region center line of the u-turn region;

and the second generation module is configured to generate a turning intersection in the standard navigation map data based on the area center line.

The functions may be implemented by hardware, or may be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above.

In one possible design, the structure of the above apparatus includes a memory for storing one or more computer instructions for supporting the above apparatus to perform the corresponding method, and a processor configured to execute the computer instructions stored in the memory. The apparatus may further comprise a communication interface for the apparatus to communicate with other devices or a communication network.

In a third aspect, an embodiment of the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored on the memory, where the processor executes the computer program to implement the method of any one of the above aspects.

In a fourth aspect, embodiments of the present disclosure provide a computer-readable storage medium storing computer instructions for use by any one of the above-described apparatuses, which when executed by a processor, are configured to implement the method of any one of the above-described aspects.

In a fifth aspect, embodiments of the present disclosure provide a computer program product comprising computer instructions for implementing the method of any one of the above aspects when executed by a processor.

The technical scheme provided by the embodiment of the disclosure can comprise the following beneficial effects:

According to the embodiment of the disclosure, in order to automatically generate the turning intersection in the standard navigation map data, the turning area on the road is identified based on the high-precision map data by acquiring the high-precision data, so that the area center line in the turning area is generated, and the turning intersection is generated based on the area center line. The method not only can automatically generate the turning intersection in the standard navigation map data, but also has high accuracy, can improve the generation efficiency of the turning intersection, and can also reduce the manufacturing cost of the standard navigation map data.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

Other features, objects and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments, taken in conjunction with the accompanying drawings. In the drawings:

fig. 1 illustrates a flowchart of a u-turn intersection generation method according to an embodiment of the present disclosure.

Fig. 2A-2C illustrate schematic effect diagrams of identifying a turning area based on high-precision map data according to an embodiment of the present disclosure.

Fig. 3A-3D illustrate schematic effect diagrams of a target road segment, a projected road segment, and a u-turn area according to an embodiment of the present disclosure.

Fig. 4A-4D illustrate effect diagrams of a generated u-turn intersection according to an embodiment of the present disclosure.

Fig. 5 shows a block diagram of a u-turn intersection generating device according to an embodiment of the present disclosure.

Fig. 6 shows a block diagram of an electronic device according to an embodiment of the present disclosure.

Fig. 7 is a schematic diagram of a computer system suitable for use in implementing a u-turn junction generation method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, portions irrelevant to description of the exemplary embodiments are omitted in the drawings.

In this disclosure, it should be understood that terms such as "comprises" or "comprising," etc., are intended to indicate the presence of features, numbers, steps, acts, components, portions, or combinations thereof disclosed in this specification, and do not preclude the presence or addition of one or more other features, numbers, steps, acts, components, portions, or combinations thereof.

In addition, it should be noted that, without conflict, the embodiments of the present disclosure and features of the embodiments may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

User information (including but not limited to user equipment information such as location information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in this disclosure are both information and data that is authorized by the user or is sufficiently authorized by parties, and the collection, use and processing of relevant data requires compliance with relevant laws and regulations and standards of the relevant country and region, and is provided with corresponding access to the user for selection of authorization or denial.

Details of embodiments of the present disclosure are described in detail below with reference to specific embodiments.

Fig. 1 illustrates a flowchart of a u-turn intersection generation method according to an embodiment of the present disclosure. As shown in fig. 1, the method for generating the u-turn intersection comprises the following steps:

in step S101, high-precision map data is acquired;

in step S102, identifying a turning area on a road based on the high-precision map data;

in step S103, generating a region center line of the u-turn region;

in step S104, a u-turn intersection in the standard navigation map data is generated based on the region center line.

In this embodiment, the method for generating a u-turn intersection may be executed on a server. The high-precision map data is a data storage mode taking lanes as storage objects, and mainly comprises the following contents: high-precision road data, high-precision lane data (lane lines, types, relationships, etc.), high-precision component data (ground signs, facilities, etc.), and the like. Based on the high-precision map data, each lane line on the road and the attributes of the lane, such as the position of each shape point on the lane line, whether the lane line is a solid line or a broken line, the passing direction of the lane, whether the lane has a turning function and other attribute information, can be determined. Therefore, it is possible to identify the turning area on each road based on the high-precision map data. The turning area has the obvious characteristic that the roads communicated with the two ends of the turning area are parallel to each other and have opposite running directions.

Because the standard navigation map data is a data storage mode which takes roads as storage objects, the content mainly comprises: basic road network data, attribute information (electronic eyes, guide lines, prohibition information, etc.) on roads, public travel information such as riding steps, etc. Therefore, the turn-around intersection to be generated is also stored in the standard navigation map data in the form of a road and the attribute possessed by the road. In standard navigation map data, roads are typically represented by line segments.

For this reason, after the turning-around area is determined based on the high-precision map data, an area center line of the turning-around area may be generated, and then a turning-around intersection in the standard navigation map data may be generated based on the area center line. In some embodiments, the turn-around intersection may be composed of a line segment and two endpoints of the line segment, which may be a line segment determined based on the region center line. In the embodiment of the disclosure, the generated turning intersection can be fused into the existing standard navigation map data, so that the attribute of the turning intersection can be expressed in the standard navigation map data, and the navigated object can be accurately guided to turn around at a proper position in the navigation process.

In an optional implementation manner of this embodiment, step S102, that is, the step of identifying a u-turn area on the road based on the high-precision map data, may be implemented as follows:

extracting a candidate lane comprising a turning lane type attribute from the high-precision map data;

and if the candidate lane meets the setting condition of the turning intersection, determining a turning area based on the candidate lane.

In this alternative implementation, in order to identify a turning area on a road based on the high-precision map data, a candidate lane may be screened from the high-precision map data, and the attribute of the candidate lane may include a turning lane type attribute. In the related art, the high-precision map data is not obtained by covering the entire area, but is generated for a part of the area. Therefore, in the embodiment of the present disclosure, a turning-around area can be identified for the area where high-precision map data is produced.

After extracting the candidate lane from the high-precision map data, it is also possible to verify whether the candidate lane is actually a u-turn lane segment by using the geometric features of the candidate lane. The geometry of the candidate lane may depend on the location of the various shape points on the two-sided lane line based on the candidate lane, the direction of traffic, etc.

As described above, a u-turn lane has an obvious feature that two roads or lanes topologically connected to both ends of a road to which the u-turn lane belongs are parallel to each other and the passing directions are opposite. For this reason, the entry road and the exit road of the road to which the candidate lane belongs can be found from the high-precision map data.

In the case of manufacturing high-precision map data, for convenience of manufacturing, a complete road in the real world is divided into a plurality of high-precision road segments, and then each high-precision road segment is manufactured separately. In order to represent the connection relationship of each high-precision road segment in the real world in the high-precision map data, a topological connection relationship between the high-precision road segments is usually produced in the map compiling process, and the topological connection relationship between the high-precision road segments is used for representing the connection relationship between the high-precision road segments.

It should be further noted that each high-precision road section includes a set of high-precision lane sections adjacent in the lateral direction, and lane section data of a plurality of high-precision lane sections is also stored in the high-precision map data. The lane segment data may include, but is not limited to, attribute information of a lane segment, a lane line segment, etc. included on the high-definition road section, and the type of the lane line segment may be included in the attribute information of the lane line segment, such as in a solid line, a broken line, etc. The attribute information of the lane segment may include a type of the lane segment, such as whether the lane segment is a u-turn lane type.

As described above, the topological connection relationship between road segments is recorded in the high-definition map data. The topological communication relationship between the high-precision road segments may include, but is not limited to, an entry road segment and an exit road segment of the current high-precision road segment, the entry road segment may be understood as a previous high-precision road segment that meets the current high-precision road segment in a traveling direction of the high-precision road segment, and the exit road segment may be understood as a next high-precision road segment that meets the current high-precision road segment in the traveling direction of the high-precision road segment. That is, when a vehicle or an intelligent driving object travels along the traveling direction of the high-precision road section in the real world, the vehicle or the intelligent driving object enters the current high-precision road section from the entrance road section and then enters the exit road section after exiting from the current high-precision road section.

Accordingly, the road to which the candidate lane belongs may be a road segment to which the candidate lane belongs in the high-definition map data, and the entry road and the exit road may be an entry road segment and an exit road segment of the road segment to which the candidate lane belongs, which are stored in the high-definition map data. The entry road segment and the exit road segment of the road to which the candidate lane belongs are stored in the road topology communication relationship in the high-precision map data. If the candidate lane belongs to a u-turn lane, the entering road section and the exiting road section are parallel to each other and the traffic directions are opposite.

In some embodiments, a setting condition of the u-turn intersection may be preset, where the setting condition may include that an entering road and an exiting road of a road to which the candidate lane belongs are parallel to each other, and the traffic directions are opposite. If the geometric characteristics of the candidate lane meet the setting conditions of the u-turn intersection, the candidate lane can be determined to be in the u-turn area, and the u-turn area can be determined based on the candidate lane. In some embodiments, the candidate lane may be directly determined as a u-turn area, such as determining a start position of the candidate lane as a start position of the u-turn area, and determining an end position of the candidate lane as an end position of the u-turn area, where two lane lines of the candidate lane are boundary lines of the u-turn area. The start position and the end position of the candidate lane may be obtained from the high-precision map data.

If the candidate lane does not meet the setting condition of the turn-around intersection, the candidate lane is not a turn-around lane and therefore can be discarded, so that the turn-around intersection in the standard navigation map data is not generated based on the candidate lane.

In an alternative implementation manner of this embodiment, step S103, that is, the step of generating the area center line of the u-turn area, may be implemented as follows:

generating a center line of the candidate lane based on the geometry of the candidate lane, and determining the center line of the candidate lane as the area center line.

In this alternative implementation, if the candidate lane meets the setting condition of the u-turn intersection, the candidate lane may be directly determined as the u-turn area. Because the high-precision map data stores geometric information of the lane line segments forming the lane segments, the geometric information comprises positions, passing directions and the like of various shape points on the lane line segments. Therefore, the center line of the candidate lane, namely the area center line of the turning area, can be obtained based on the positions of the various shape points on the lane line segments on the two sides of the candidate lane.

In some embodiments, the projection may be made to one of the lane line segments on the other side based on the location of the shape point on that lane line segment, and the midpoint of the projected line segment may be the point on the center line of the lane candidate. The center line of the candidate lane, namely the area center line of the turning area, can be formed by fitting the midpoints of the projection line segments corresponding to the shape points on the lane line segment at one side.

In an optional implementation manner of this embodiment, step S104, that is, the step of generating the u-turn intersection in the standard navigation map data based on the region center line, may be implemented as follows:

acquiring the road center lines of an entering road and an exiting road corresponding to the road to which the candidate lane belongs;

after extending two end points of the central line of the area, intersecting the two end points with the central lines of the entering road and the exiting road respectively, and obtaining two intersecting points;

and generating the U-turn intersection based on the attribute of the candidate lane, the two intersection points, the center line of the area and the extension line segment.

In this alternative implementation, the entry road and the exit road of the road to which the candidate lane belongs may be determined based on the entry road section and the exit road section of the road section to which the candidate lane belongs stored in the high-precision map data. In addition, road boundary lines of the entry road section and the exit road section are also stored in the high-definition map data. The road centerlines of the entering road section and the exiting road section can thus be determined based on the road borderlines on both sides. For example, a shape point on one road boundary line may be projected onto another road boundary line, and the midpoints of the projected line segments corresponding to the obtained shape points may be fitted to form a road center line.

It should be noted that, because the real road is broken into each road segment in the high-precision map data, the entering road segment and the exiting road segment may be shorter, or when the area center line extends outwards from both ends due to the non-correspondence in position, the area center line may not intersect with the road center line of the entering road segment and/or the exiting road segment.

And (3) extending two end points of the regional center line outwards and then intersecting the regional center line with the two road center lines to obtain two intersection points, and generating a U-turn intersection based on the two intersection points, the regional center line and the extension line.

In some embodiments, the region center line and the extension line may be connected and then smoothed, and the road smoothing method may be a smoothing method used when making standard navigation map data, which is not particularly limited in the present disclosure. The generated standard navigation map data can comprise coordinates of two intersection points and a line segment obtained by road section smoothing, and can also be endowed with a turning-around road attribute and a passing direction of the turning-around intersection, wherein the passing direction is consistent with the passing direction of a corresponding candidate lane segment in the high-precision map data.

In an optional implementation manner of this embodiment, step S102, that is, the step of identifying a u-turn area on the road based on the high-precision map data, may be further implemented as follows:

extracting two adjacent candidate roads from the high-precision map data; the trend, the passing direction and the mutual distance of the two adjacent candidate roads meet a first preset condition;

and identifying the turning area corresponding to the two adjacent candidate roads based on the road boundary line on the opposite side of the two adjacent candidate roads and the attribute information of the first lane boundary line on the opposite side.

In this alternative implementation, it may be understood that all attribute information on the real world road is not necessarily made in the high-precision map data, for example, some lanes on the road may be u-turn lanes in the real world, but the u-turn attribute may not be given to the u-turn lanes in the high-precision map data due to the fact that the u-turn identifier is not provided on the real road, and the like.

For this reason, in addition to using the above-described, the embodiments of the present disclosure identify a u-turn region based on the u-turn lane type attribute, two adjacent candidate roads may be identified from the high-precision map data, and the u-turn region may be identified by the two adjacent candidate roads; the two adjacent candidate roads comprise two candidate roads, and the trend, the passing direction and the mutual distance of the two candidate roads meet a first preset condition.

In some embodiments, if there is a u-turn road segment between two adjacent candidate roads, the trends of the two adjacent candidate roads are generally parallel, and the lengths of the road segments parallel to each other are not too short, such as not shorter than 100 meters; in addition, the traffic directions of the two adjacent candidate roads are opposite, and the distance between the two candidate roads is not too large, such as not more than 10 meters. Thus, the first preset condition may include, but is not limited to, the two adjacent candidate roads having parallel trends, the parallel road segments having lengths greater than or equal to the first preset length, opposite traffic directions, and a distance less than or equal to the second preset length.

It can be understood that multiple sets of two adjacent candidate roads can be extracted from the high-precision map data, and for each set of two adjacent candidate roads, the turning area corresponding to each set of two adjacent candidate roads can be identified based on the road boundary line on the opposite side of the two adjacent candidate roads and the attribute information of the first lane boundary line. The opposite side of two adjacent candidate roads is understood to be the side of two adjacent candidate roads that are close to each other, i.e. from the left side of each candidate road when seen in the direction of traffic.

It should be noted that if a u-turn area exists between two adjacent candidate roads, the type attribute of the road boundary line and the first lane boundary line on the opposite side of the two adjacent candidate roads in the u-turn area may be a "crossing boundary" attribute, that is, the corresponding road boundary line segment and the first lane boundary line segment in the u-turn area are dotted lines or left-virtual-right-real lane lines. Based on the principle, the turning-around area between two adjacent candidate roads can be identified.

It can be understood that, in the embodiment of the present disclosure, the solution for identifying the u-turn area based on the u-turn lane type attribute in the other embodiments may not be adopted, but the solution for extracting two adjacent candidate roads in the embodiment may be directly adopted to identify the u-turn area, or after the solution for identifying the u-turn area based on the u-turn lane type attribute in the other embodiments is adopted, the solution for extracting two adjacent candidate roads in the embodiment may be adopted for identifying the remaining roads in which the u-turn area is not identified.

In an optional implementation manner of this embodiment, the step of identifying the u-turn area corresponding to the two adjacent candidate roads based on the attribute information of the road boundary line on the opposite side of the two adjacent candidate roads and the first lane boundary line on the opposite side may be implemented as follows:

selecting a target road section of which attribute information of the road boundary line on the opposite side and the first lane boundary line meets a second preset condition from one of the two adjacent candidate roads;

selecting a projected section of the target section from another of the two adjacent candidate roads;

and if the projection road section meets a third preset condition, determining a turning area based on the target road section and the projection road section.

In this alternative implementation manner, after two adjacent candidate roads are extracted from the high-precision map data, the u-turn area may be further identified based on the road boundary line on the opposite side of the two adjacent candidate roads and the attribute information of the first lane boundary line on the opposite side.

In this embodiment, a target link whose attribute information of the lane boundary line and the first lane boundary line on the opposite side satisfies the second preset condition may be selected from one of the two adjacent candidate roads. For example, the second preset condition may be that the road boundary line on the opposite side of the target road segment and the first lane boundary line are of the "spanable boundary" type, and the road boundary line on the opposite side of the target road segment corresponding to the front-rear topology communication road segment (i.e., the entering road segment and the exiting road segment of the target road segment) and the first lane boundary line are of the "non-spanable boundary" type. That is, in one of the two adjacent candidate roads, the road boundary line and the first lane boundary line of the entry road section and the exit road section on the opposite sides are both of the "non-crossing boundary" type, and the target section becomes the "crossing boundary" type when the target section becomes the "crossing boundary" type, in which case the target section is the target section to be selected.

After finding a target road segment on one of the two adjacent candidate roads, the target road segment may be projected toward the other of the two adjacent candidate roads to obtain a projected road segment.

If the projected link satisfies a third preset condition, a u-turn area may be determined based on the target link and the projected link. The third preset condition may be understood as a condition to be satisfied by the projected link when the area between the target link and the projected link can be regarded as a u-turn area. In some embodiments, the third preset condition may include that no physical boundary exists on a side of the projected road segment opposite to the target road segment, and the length of the area where no physical boundary exists is greater than or equal to a certain value, such as 5 meters. It should be noted that whether or not a physical boundary exists may be determined based on whether or not the projected link has a physical boundary type attribute with respect to a road boundary on the side of the target link. If the projected link does not have a physical boundary type attribute with respect to the road boundary on the side of the target link, it can be considered that there is a u-turn area between the projected link and the target link. If the projected link does not have a non-physical boundary with respect to the target link side or a non-physical boundary exists, but the length of the non-physical boundary is less than a certain value, it may be considered that there is no u-turn area between the target link and the projected link.

Fig. 2A-2C illustrate schematic effect diagrams of identifying a turning area based on high-precision map data according to an embodiment of the present disclosure. As shown in fig. 2A and 2B, one set of two adjacent candidate roads a and B extracted from the high-precision map data have parallel trends and opposite traffic directions, and simultaneously satisfy the following conditions:

the maximum distance between the road A and the road B is less than or equal to 10 meters; and the length of the parallel road section of the road A and the road B is more than or equal to 100 meters.

Based on the types of the left road side boundary line and the left first lane boundary line of the road A in the high-precision map data, a target road section a1 on the road A is selected, wherein the target road section a1 meets the following conditions:

when the types of the left road side boundary line and the left first lane boundary line are changed from the 'non-crossing boundary' to the 'crossing boundary', and then are changed to the 'non-crossing boundary', the road section in the 'crossing boundary' section is selected as the target road section, and the target road section a1 of the road A is obtained. Wherein, the non-crossing boundary refers to: the boundary type is a physical boundary or a solid line, where the solid line includes: single solid line, double solid line, drain line. The crossing boundary may refer to: boundary types are broken lines, including single broken lines, left-right broken lines, virtual lines (i.e., no real world standard lines on real roads). In fig. 2A, the left first lane boundary line is a single broken line, and in fig. 2B, the left first lane boundary line is a solid left-right broken line.

As shown in fig. 2C, although the road a has a road boundary line on the left side changed from "non-crossing boundary" to "crossing boundary" and then to "non-crossing boundary", the first lane boundary line on the upper left side of the road a is a single solid line and belongs to the lane boundary line of "non-crossing boundary", and therefore the road is not the target road.

The target link a1 shown in fig. 2A and 2B is projected onto the road B, and the projection link B1 corresponding to the road B is acquired. Judging the types of the left road side boundary line and the left first lane boundary line of the projection road section b1 based on the high-precision map data, and if a non-physical boundary exists and the length of the non-physical boundary road section is more than 5 meters, determining that a u-turn intersection exists between the projection road section b1 and the target road section a 1; if there is no non-physical boundary or a non-physical boundary exists on the projected link but the length of the non-physical boundary is <5 meters, it is determined that no u-turn is possible between the projected link b1 and the target link a 1.

Fig. 3A-3D illustrate schematic effect diagrams of a target road segment, a projected road segment, and a u-turn area according to an embodiment of the present disclosure. As shown in fig. 3A, opposite sides of the road a and the road B have a road boundary of a crossing type, and the first lane boundary lines on the left sides of the road a and the road B are both dotted lines, and are also lane boundaries of the crossing type, so that after the target road a has the target road segment a1 and the target road segment a1 is projected onto the road B to obtain the projected road segment B1, it is determined that the projected road segment B1 has a road boundary of a crossing type and a first lane boundary with respect to the road boundary on the side of the road a and the first lane boundary, and the road boundary and the first lane boundary are greater than 5 meters, so that a turning-around area capable of turning around from the road a to the road B and from the road B to the road a exists between the projected road segment B1 and the target road segment a1, as shown in fig. 3B.

As shown in fig. 3C, a road boundary of a straddlable type exists on one side of the road a relative to the road B, and the first lane boundary on the left side is a virtual-real line, which is also a straddlable type lane boundary, so that there is a target road segment a1 on the road a, and after the target road segment a1 is projected onto the road B to obtain a projected road segment B1, it is determined that the projected road segment B1 is opposite to the road boundary on one side of the road a and the first lane boundary, and because there is a straddlable type road boundary, but the first lane boundary is a solid line and belongs to a non-straddlable type lane boundary, there is a u-turn region between the projected road segment B1 and the target road segment a1, and there is no u-turn region from the road B to the road a, as shown in fig. 3D.

It should be noted that, for two adjacent candidate roads, one candidate road may be selected at will to select a target road section, and projection is performed to the other candidate road, and a u-turn intersection is generated. And then, selecting a target road section for another candidate road, discarding the target road section when the target road section intersects with the determined projection road section, continuing to project the target road section which is finally reserved on the candidate road by adopting the mode, judging whether the projection road section exists or not, and generating a turning intersection under the condition that the projection road section exists. Through the mode, the two-way turning intersection and the one-way turning intersection between the two adjacent candidate roads can be completely generated.

obtaining the road center lines of the two adjacent candidate roads;

and generating straight lines which pass through the center position of the turning-around area and are respectively perpendicular to the road center lines of two adjacent candidate roads as the area center lines.

In this alternative implementation, since the u-turn area is the area between the target road section and the projected road section in this embodiment, the u-turn area may be a rectangular area. Therefore, straight lines perpendicular to the road center lines of two adjacent candidate roads can be directly generated at the center position of the turning-around area as the area center lines. The center position of the turning area is the center point of the rectangular area.

In this embodiment, the road center lines of two adjacent candidate roads may be acquired first. The road boundary lines on both sides of the two adjacent candidate roads may be obtained from the high-precision map data, and the road center line of the two adjacent candidate roads may be determined based on the road boundary lines on both sides. For example, a shape point on one road boundary line may be projected onto another road boundary line, and the midpoints of the projected line segments corresponding to the obtained shape points may be fitted to form a road center line.

Since the real road is broken into each road segment in the high-definition map data, two adjacent candidate roads may be long roads obtained by connecting road segments that are topologically connected in front and back, and the road center line is also obtained based on the shape points on each road segment.

extending two end points of the central line of the region outwards, and intersecting the two end points with the central lines of the two adjacent candidate roads respectively to obtain two intersection points;

and generating the U-turn intersection based on the attributes of the two adjacent candidate lanes, the two intersection points and the extended area center line.

In this optional implementation manner, the area center line in this embodiment is a straight line perpendicular to the road center lines of two adjacent candidate roads, and after the straight line is extended, the intersection point is compared with the road center lines of two adjacent candidate roads, and based on the two intersection points and the extended area center line, a u-turn intersection can be generated. The u-turn intersection in the generated standard navigation map data can comprise coordinates of two intersection points and an extended region center line segment, and in addition, the u-turn intersection can be endowed with attributes of the u-turn intersection and a passing direction of the u-turn intersection, and the passing direction is determined based on the attributes of two adjacent candidate roads. In some embodiments, the traffic direction of the u-turn intersection may be determined based on the attributes of the road boundary line and the first lane boundary line at the area corresponding to the u-turn intersection, i.e., the u-turn area, on the two adjacent candidate roads. If the road boundary line and the first lane boundary line of each road in two adjacent candidate roads are both of a type of crossing the boundary, the passing direction of the turning intersection is a bidirectional turning direction; and if the road boundary line and the first lane boundary line of one of the two adjacent candidate roads are of a 'crossing boundary' type and the road boundary line of the other road is of a non-physical boundary, and the first lane boundary line is of a 'non-crossing boundary' type, the passing direction of the u-turn intersection is a unidirectional u-turn direction, namely a u-turn direction from the road corresponding to the 'crossing boundary' type to the road corresponding to the 'non-crossing boundary' type.

Fig. 4A-4D illustrate effect diagrams of a generated u-turn intersection according to an embodiment of the present disclosure. As shown in fig. 4A, a candidate lane shown as a semi-ellipse in the figure is screened out based on a turning lane type attribute in the high-precision map data, after the candidate lane is determined as a turning area, an area central line u shown as a black solid line is generated according to the geometric shape of the candidate lane, the area central line extends outwards to a road central line m and a road central line n of an entering road and an exiting road shown as virtual boxes in the figure, the two points intersect, and then a line segment shown as the black solid line in fig. 4B can be obtained after a line segment between the two intersection points is smoothed, the two intersection points and the line segment can be used as position data of the turning intersection in the standard navigation map data, and in addition, the turning intersection can be endowed with the turning intersection attribute, the road passing direction and the like.

As shown in fig. 4C, in the u-turn area identified based on the geometric features on each road in the high-precision map data, an area center line u as shown by a black solid line in the figure may be generated at the center position, and after the area center line extends outwards to the road center lines m and n of two adjacent candidate roads, the two points intersect to obtain a line segment as shown by the black solid line in fig. 4D, where the two intersection points and the line segment may be used as the position data of the u-turn intersection in the standard navigation map data, and in addition, the u-turn intersection may be given the attribute of the u-turn road, the road passing direction, and the like.

The following are device embodiments of the present disclosure that may be used to perform method embodiments of the present disclosure.

Fig. 5 shows a block diagram of a u-turn intersection generating device according to an embodiment of the present disclosure. The apparatus may be implemented as part or all of an electronic device by software, hardware, or a combination of both. As shown in fig. 5, the u-turn intersection generating device includes:

an acquisition module 501 configured to acquire high-precision map data;

an identification module 502 configured to identify a turning area on a road based on the high-precision map data;

a first generating module 503 configured to generate a region center line of the u-turn region;

a second generation module 504 is configured to generate a u-turn intersection in the standard navigation map data based on the region center line.

In this embodiment, the u-turn intersection generating device may be executed on a server. The high-precision map data is a data storage mode taking lanes as storage objects, and mainly comprises the following contents: high-precision road data, high-precision lane data (lane lines, types, relationships, etc.), high-precision component data (ground signs, facilities, etc.), and the like. Based on the high-precision map data, each lane line on the road and the attributes of the lane, such as the position of each shape point on the lane line, whether the lane line is a solid line or a broken line, the passing direction of the lane, whether the lane has a turning function and other attribute information, can be determined. Therefore, it is possible to identify the turning area on each road based on the high-precision map data. The turning area has the obvious characteristic that the roads communicated with the two ends of the turning area are parallel to each other and have opposite running directions.

In an alternative implementation manner of this embodiment, the identification module may be implemented as follows:

As described above, the topological connection relationship between road segments is recorded in the high-definition map data. The topological communication relationship between the high-precision road segments may include, but is not limited to, an entry road segment and an exit road segment of the current high-precision road segment, the entry road segment may be understood as a preceding high-precision road segment that is longitudinally adjacent to the current high-precision road segment in a traveling direction of the high-precision road segment, and the exit road segment may be understood as a next high-precision road segment that is longitudinally adjacent to the current high-precision road segment in the traveling direction of the high-precision road segment. That is, when a vehicle or an intelligent driving object travels along the traveling direction of the high-precision road section in the real world, the vehicle or the intelligent driving object enters the current high-precision road section from the entrance road section and then enters the exit road section after exiting from the current high-precision road section.

In an alternative implementation manner of this embodiment, the first generating module may be implemented as follows:

In an alternative implementation manner of this embodiment, the second generating module may be implemented as follows:

In some embodiments, the region center line and the extension line may be connected and then smoothed, and the road smoothing device may be a smoothing device used when making standard navigation map data, which is not particularly limited in the present disclosure. The generated standard navigation map data can comprise coordinates of two intersection points and a line segment obtained by road section smoothing, and can also be endowed with a turning-around road attribute and a passing direction of the turning-around intersection, wherein the passing direction is consistent with the passing direction of a corresponding candidate lane segment in the high-precision map data.

In an alternative implementation manner of this embodiment, the identification module may be further implemented as follows:

In an optional implementation manner of this embodiment, the identifying the u-turn area corresponding to the two adjacent candidate roads based on the attribute information of the road boundary line on the opposite side of the two adjacent candidate roads and the first lane boundary line on the opposite side may be implemented as follows:

In an alternative implementation manner of this embodiment, the first generating module may be further implemented as follows:

obtaining the road center lines of the two adjacent candidate roads;

In an optional implementation manner of this embodiment, the second generating module may be further implemented as follows:

The present disclosure also discloses an electronic device, fig. 6 shows a block diagram of the electronic device according to an embodiment of the present disclosure, and as shown in fig. 6, the electronic device 600 includes a memory 601 and a processor 602; wherein,

the memory 601 is used to store one or more computer instructions that are executed by the processor 602 to implement the method steps described above.

As shown in fig. 7, the computer system 700 includes a processing unit 701, which may be implemented as a processing unit such as CPU, GPU, FPGA, NPU. The processing unit 701 may perform various processes in the embodiments of any of the above methods of the present disclosure according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM703, various programs and data required for the operation of the computer system 700 are also stored. The processing unit 701, the ROM702, and the RAM703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

The following components are connected to the I/O interface 705: an input section 706 including a keyboard, a mouse, and the like; an output portion 707 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 708 including a hard disk or the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. The drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read therefrom is mounted into the storage section 708 as necessary.

In particular, according to embodiments of the present disclosure, any of the methods described above with reference to embodiments of the present disclosure may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing any of the methods of embodiments of the present disclosure. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 709, and/or installed from the removable medium 711.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units or modules described in the embodiments of the present disclosure may be implemented by software, or may be implemented by hardware. The units or modules described may also be provided in a processor, the names of which in some cases do not constitute a limitation of the unit or module itself.

As another aspect, the present disclosure also provides a computer-readable storage medium, which may be a computer-readable storage medium included in the apparatus described in the above embodiment; or may be a computer-readable storage medium, alone, that is not assembled into a device. The computer-readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the present disclosure.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention referred to in this disclosure is not limited to the specific combination of features described above, but encompasses other embodiments in which any combination of features described above or their equivalents is contemplated without departing from the inventive concepts described. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).

Claims

1. A U-turn intersection generation method comprises the following steps:

acquiring high-precision map data;

identifying a turning area on a road based on the high-precision map data;

generating an area center line of the turning area;

2. The method of claim 1, wherein the identifying a turn-around area on a road based on the high-precision map data comprises:

3. The method of claim 2, wherein the generating the zone center line of the u-turn zone comprises:

4. A method according to claim 2 or 3, wherein the generating a turn around intersection in standard navigational map data based on the zone centre line comprises:

5. A method according to any one of claims 1-3, wherein the identifying a u-turn area on a road based on the high-precision map data comprises:

6. The method of claim 5, wherein identifying the u-turn region corresponding to the two adjacent candidate roads based on the road boundary line on the opposite side of the two adjacent candidate roads and the attribute information of the first lane boundary line on the opposite side comprises:

7. The method of claim 5, wherein generating a zone center line of the u-turn zone comprises:

obtaining the road center lines of the two adjacent candidate roads;

8. The method of claim 5, wherein generating a turn around intersection in standard navigational map data based on the zone centerline comprises:

9. A u-turn intersection generation apparatus, comprising:

an acquisition module configured to acquire high-precision map data;

10. An electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the method of any of claims 1-8.

11. A computer readable storage medium having stored thereon computer instructions, wherein the computer instructions, when executed by a processor, implement the method of any of claims 1-8.