Road network static map construction method, program product, equipment and medium

Abstract

The embodiment of the invention provides a road network static map construction method, a program product, equipment and a medium, and relates to the technical field of automatic driving. The road network static map construction method comprises the following steps: identifying a road according to static information of a target road network, and constructing a plurality of road objects; identifying a road connection relationship and a lane connection relationship on the road according to the plurality of road objects, and constructing intersection objects; under the condition that at least one intersection object is constructed, constructing a first static map of the target road network; wherein the first static map comprises a plurality of road objects and at least one intersection object; under the condition that the intersection object is not constructed, constructing a second static map of the target road network; wherein the second static map comprises a plurality of road objects. According to the embodiment of the invention, the technical effect of automatically constructing the road network static map based on the marked static information can be realized.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and more specifically, to a method, program product, device, and medium for constructing a static map of a road network. Background Art

[0002] Autonomous driving simulation testing mainly implements the testing and verification of the autonomous driving system through software simulation of static road network maps.

[0003] Currently, many simulation platforms use static road network maps, such as those in the OpenDRIVE format, which are built based on high-precision map data. This makes it difficult to automatically construct static road network maps directly from collected raw data such as point clouds, real-life images, and vector maps. This limitation prevents the automated closed-loop flow of raw data throughout the autonomous driving system development lifecycle (i.e., raw data collection - perception information annotation - system algorithm model training - and overall system simulation testing). Consequently, companies often rely on manual construction of static road network maps before autonomous driving simulation testing, increasing the time and cost of autonomous driving system development. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a method, program product, device and medium for constructing a road network static map, so as to achieve the technical effect of automatically constructing a road network static map based on annotated static information.

[0005] In a first aspect, an embodiment of the present application provides a method for constructing a static road network map, comprising: Identify roads based on the static information of the target road network and construct multiple road objects; Identifying road connection relationships and lane connection relationships on the roads based on the plurality of road objects, and constructing an intersection object; When at least one intersection object is constructed, a first static map of the target road network is constructed; wherein the first static map includes the plurality of road objects and the at least one intersection object; Without constructing the intersection object, a second static map of the target road network is constructed; wherein the second static map includes the plurality of road objects.

[0006] In the above implementation process, by identifying roads based on the static information of the target road network, constructing multiple road objects, identifying road connection relationships and lane connection relationships on the roads based on the multiple road objects, and constructing intersection objects, when at least one intersection object is constructed, a first static map of the target road network including multiple road objects and at least one intersection object is constructed; when no intersection object is constructed, a second static map of the target road network including multiple road objects is constructed. The road network static information can be automatically structured into road objects in the road network static map, or intersection objects, thereby realizing the automatic construction of the road network static map based on the annotated static information.

[0007] Furthermore, the static information of the target road network includes topological information of multiple lanes; The identifying of roads based on the static information of the target road network and constructing a plurality of road objects includes: Selecting any lane from the plurality of lanes as a target lane, and traversing the plurality of lanes based on topological information of the target lane until determining the frontmost rightmost lane associated with the target lane; Traversing the multiple lanes based on the topological information of the frontmost rightmost lane until a lane segment is determined; wherein the current lane segment includes a left lane group, a right lane group, and a road centerline, each left lane in the left lane group is in the same direction as the frontmost rightmost lane, each right lane in the right lane group is in the opposite direction to the frontmost rightmost lane, and the road centerline is a left boundary line of the leftmost lane associated with the frontmost rightmost lane; Constructing a road object according to the current lane segment; wherein the current road object includes the current lane segment; If it is determined that there is a successor lane segment associated with the current lane segment, and the current lane segment and the successor lane segment belong to the same road, adding the successor lane segment to the current road object to update the current road object; In the case that there is an untraversed lane among the multiple lanes, the untraversed lane is determined as a new target lane to construct a new road object.

[0008] In the above implementation process, by selecting any lane from multiple lanes as the target lane, traversing multiple lanes based on the topological information of the target lane until the frontmost right lane associated with the target lane is determined, traversing multiple lanes based on the topological information of the frontmost right lane until the current lane segment is determined, constructing a road object according to the current lane segment, and when it is determined that there is a successor lane segment associated with the current lane segment, and the current lane segment and the successor lane segment belong to the same road, adding the successor lane segment to the current road object to update the current road object, and when there is an untraversed lane among the multiple lanes, the untraversed lane is determined as a new target lane to construct a new road object. On the one hand, the longitudinal topological relationship and the lateral topological relationship of the target lane can be fully considered to accurately construct the road object, and on the other hand, it can ensure that the road objects are constructed for all roads of the target road network to avoid the problem of missing road objects.

[0009] Furthermore, after determining a lane segment, the method further includes: traversing the plurality of lanes based on the topological information of the frontmost rightmost lane until the rightmost lane associated with the subsequent lane of the frontmost rightmost lane is determined or the traversal of the plurality of lanes is completed; When it is determined that the rightmost lane exists, traversing the multiple lanes based on topological information of the rightmost lane to determine the subsequent lane segment, and determining whether the current lane segment and the subsequent lane segment belong to the same road; In the case where it is determined that the rightmost lane does not exist, it is determined that the subsequent lane segment does not exist.

[0010] In the above implementation process, after determining the current lane segment, traversing multiple lanes based on the topological information of the frontmost and rightmost lane until the rightmost lane associated with the successor lane of the frontmost and rightmost lane is determined or the traversal of multiple lanes is completed, when it is determined that there is a rightmost lane, traversing multiple lanes based on the topological information of the rightmost lane, determining the subsequent lane segment, and determining whether the current lane segment and the subsequent lane segment belong to the same road, when it is determined that there is no rightmost lane, determining that there is no subsequent lane segment, and whether there is a subsequent lane segment associated with the current lane segment and belonging to the same road can be fully and accurately determined.

[0011] Furthermore, after determining that there is a subsequent lane segment associated with the current lane segment, the method further includes: determining whether the lane of the current lane segment and the lane of the subsequent lane segment are front and rear lanes of each other; If so, determining that the current lane segment and the subsequent lane segment belong to the same road; If not, it is determined that the current lane segment and the subsequent lane segment do not belong to the same road.

[0012] In the above implementation process, by judging whether the lanes of the current lane segment and the lanes of the subsequent lane segment are the front and rear lanes of each other, it is determined whether the current lane segment and the subsequent lane segment belong to the same road, which can ensure accurate determination of whether the current lane segment and the subsequent lane segment belong to the same road.

[0013] Furthermore, each of the plurality of road objects includes at least one lane segment; and identifying road connection relationships and lane connection relationships on the roads based on the plurality of road objects and constructing an intersection object includes: For each pair of road objects formed by combining any two of the plurality of road objects, obtaining a lane group at both ends of the first road object and a lane group at both ends of the second road object; wherein the current pair of road objects is formed by combining the first road object and the second road object, the lane group at both ends of the first road object is a lane group at both ends of the lane segments at the start and end of the first road object, and the lane group at both ends of the second road object is a lane group at both ends of the lane segments at the start and end of the second road object; If the successor lane of any end lane in the two end lane groups of the first road object exists in the two end lane groups of the second road object, construct an intersection object; wherein the current intersection object includes a road connection node between the first road object and the second road object, and a lane connection node between the end lane and the successor lane; If the successor lane of each lane in the lane groups at both ends of the first road object does not exist in the lane groups at both ends of the second road object, no intersection object is constructed.

[0014] In the above implementation process, for each pair of road objects obtained by any two combinations of multiple road objects, the two end lane groups of the first road object and the two end lane groups of the second road object are obtained to identify the road connection relationship and the lane connection relationship on the road. If the successor lane of any end lane in the two end lane groups of the first road object exists in the two end lane groups of the second road object, an intersection object is constructed; otherwise, no intersection object is constructed. The connection relationship between roads can be determined accurately down to the lanes on the road, ensuring the accurate construction of the intersection object.

[0015] Furthermore, the static information of the target road network includes attribute information of a plurality of lanes; and the method further includes: Adding attribute information of the multiple lanes to the static map; wherein the static map is the first static map or the second static map.

[0016] In the above implementation process, by adding the attribute information of multiple lanes included in the static information of the target road network to the static map of the target road network, the expression information of the static map of the road network can be enriched, which is conducive to the simulation platform to comprehensively test and verify the autonomous driving system.

[0017] Furthermore, the method further comprises: Using a simulation platform to verify the compatibility of the static map; wherein the static map is the first static map or the second static map; If the static map passes the compatibility verification, the static map is output.

[0018] In the above implementation process, the compatibility of the static map is verified by using a simulation platform. When the static map passes the compatibility verification, the static map is output, which can further verify the compatibility of the simulation platform with the static map and ensure the validity of the static map.

[0019] In a second aspect, an embodiment of the present application provides a road network static map construction device, comprising: A road object construction module, configured to identify roads based on static information of a target road network and construct a plurality of road objects; wherein each of the plurality of road objects includes at least one lane segment; An intersection object construction module, configured to identify road connection relationships and lane connection relationships on the roads based on the plurality of road objects, and construct an intersection object; Static map building blocks for: When at least one intersection object is constructed, a first static map of the target road network is constructed; wherein the first static map includes the plurality of road objects and the at least one intersection object; Without constructing the intersection object, a second static map of the target road network is constructed; wherein the second static map includes the plurality of road objects.

[0020] In a third aspect, an embodiment of the present application provides a computer program product, which includes instructions. When the instructions are executed by a computer, the computer implements the method as described above.

[0021] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor; when the processor executes the computer program, the method described above is implemented.

[0022] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A schematic diagram of a process for constructing a static road network map according to the first embodiment of the present application; Figure 2 A schematic diagram of a local area in the target road network exemplified in the first embodiment of the present application; Figure 3 This is a schematic structural diagram of a road object exemplified in the first embodiment of the present application; Figure 4 A schematic diagram of the structure of a road network static map construction device provided in the second embodiment of the present application; Figure 5 A schematic structural diagram of an electronic device provided in the third embodiment of the present application. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0026] It should be noted that in the description of this application, the terms "first" and "second" are used only to distinguish descriptions and should not be understood to indicate or imply relative importance. Furthermore, the step numbers herein are used only to facilitate the explanation of the embodiments of this application and do not limit the order in which the steps are to be executed.

[0027] In the field of autonomous driving technology, developers acquire raw data such as point clouds, real-life images, and vector maps collected by their vehicles as they navigate the traffic network. This data is then used to train autonomous driving algorithm models and design autonomous driving systems. To enable the algorithm models to fully understand the traffic environment in which the vehicle operates, perceptual information needs to be annotated on the raw data. Perceptual information is categorized into two types: static and dynamic. Static information includes information about stationary objects in the traffic network, such as lane topology, structure, and attributes. Dynamic information includes information about other moving objects in the traffic network that participate in traffic activities alongside the vehicle, such as the speed and location of pedestrians. Static information helps the algorithm models accurately understand the road structure of the traffic network and rationally plan the vehicle's driving path. Therefore, static information is particularly important in designing autonomous driving systems.

[0028] After developers design an autonomous driving system, they conduct simulation tests on it. This testing primarily involves software simulation of a static map of the traffic network to verify the system.

[0029] However, in related technologies, static road network maps used by many simulation platforms, such as those in the OpenDRIVE format, are built based on high-precision map data. This makes it difficult to automatically construct static road network maps directly from collected raw data such as point clouds, real-life images, and vector maps. This limitation prevents the automated closed-loop flow of raw data throughout the autonomous driving system development lifecycle (i.e., raw data collection - perception information annotation - system algorithm model training - and overall system simulation testing). Consequently, companies often rely on manual construction of static road network maps before autonomous driving simulation testing, increasing the time and cost of autonomous driving system development.

[0030] To this end, an embodiment of the present application provides a method for constructing a road network static map, by identifying roads based on the static information of the target road network, constructing multiple road objects, identifying road connection relationships and lane connection relationships on the roads based on the multiple road objects, and constructing intersection objects. When at least one intersection object is constructed, a first static map of the target road network including multiple road objects and at least one intersection object is constructed. When no intersection object is constructed, a second static map of the target road network including multiple road objects is constructed. The road network static information can be automatically structured into road objects in the road network static map, or intersection objects, thereby realizing the automatic construction of a road network static map based on the annotated static information.

[0031] The method provided in the embodiment of the present application can be executed by a relevant terminal device, and the following description will be given using a server as an example of the execution entity.

[0032] Please see Figure 1 , Figure 1 The first embodiment of the present application provides a method for constructing a static map of a road network, including steps S101 to S104: S101. Identify roads based on static information of a target road network and construct multiple road objects.

[0033] As an example, in a static road network map used by a simulation platform, such as a static road network map in the OpenDRIVE format, roads are the core element, and roads are composed of lanes.

[0034] According to actual business needs, select the target road network and obtain the static information of the target road network.

[0035] It should be noted that the static information of the target road network is obtained by annotating the original data collected for the target road network. The original data collected for the target road network includes one or more of point clouds, real-life images, and vector images.

[0036] Identify roads based on the static information of the target road network, and construct a road object road for each identified road, thereby obtaining multiple road objects, such as {road[0],road[1],...,road[n]}.

[0037] S102: Identify road connection relationships and lane connection relationships on the roads based on multiple road objects, and construct an intersection object.

[0038] As an example, after obtaining multiple road objects, the road connection relationship and the lane connection relationship on the road are identified based on the multiple road objects, and a junction object junction is constructed based on the identified road connection relationship and the lane connection relationship on the connected roads, so as to determine whether to construct the junction object.

[0039] In actual application scenarios, there may or may not be intersections between multiple roads in the target road network. Therefore, an intersection object may or may not be constructed for an identified road connection relationship and the lane connection relationship on the connected roads.

[0040] S103: When at least one intersection object is constructed, construct a first static map of the target road network; wherein the first static map includes a plurality of road objects and at least one intersection object.

[0041] As an example, after obtaining multiple road objects and at least one intersection object, they are connected according to the topological relationship between the multiple road objects and the at least one intersection object to construct a first static map of the target road network, so that the first static map of the target road network includes multiple road objects and at least one intersection object.

[0042] S104: Without constructing the intersection object, construct a second static map of the target road network; wherein the second static map includes a plurality of road objects.

[0043] As an exemplary embodiment, after obtaining multiple road objects and determining that no intersection object is constructed, multiple road objects are connected according to the topological relationship between them to construct a second static map of the target road network, so that the static map of the target road network includes multiple road objects.

[0044] In practical applications, the file format of the first static map or the second static map of the target road network may be OpenDRIVE format.

[0045] The embodiment of the present application identifies roads based on static information of the target road network, constructs multiple road objects, identifies road connection relationships and lane connection relationships on the roads based on the multiple road objects, and constructs intersection objects. When at least one intersection object is constructed, a first static map of the target road network including multiple road objects and at least one intersection object is constructed. When no intersection object is constructed, a second static map of the target road network including multiple road objects is constructed. The static information of the road network can be automatically structured into road objects or intersection objects in the static map of the road network, thereby realizing the automatic construction of the static map of the road network based on the annotated static information.

[0046] In an optional embodiment, the static information of the target road network includes topological information of multiple lanes; identifying roads based on the static information of the target road network and constructing multiple road objects includes: selecting any lane from the multiple lanes as the target lane, traversing the multiple lanes based on the topological information of the target lane until the frontmost rightmost lane associated with the target lane is determined; traversing the multiple lanes based on the topological information of the frontmost rightmost lane until a lane segment is determined; wherein the current lane segment includes a left lane group, a right lane group and a road centerline, and each left lane in the left lane group is in the same direction as the frontmost rightmost lane, Each right lane in the right lane group is opposite to the front rightmost lane, and the centerline of the road is the left boundary line of the leftmost lane associated with the front rightmost lane; a road object is constructed based on the current lane segment; wherein the current road object includes the current lane segment; when it is determined that there is a subsequent lane segment associated with the current lane segment, and the current lane segment and the subsequent lane segment belong to the same road, the subsequent lane segment is added to the current road object to update the current road object; when there is an untraversed lane among multiple lanes, the untraversed lane is determined as a new target lane to construct a new road object.

[0047] As an example, suppose that the local area in the selected target road network is as follows Figure 2 As shown in the figure, a road is based on a road reference line. A road is composed of lanes. On the same road, based on the direction of the road reference line, the lanes on the right side of the road reference line are numbered as negative numbers, such as "-1", "-2" and "-3", respectively, and the lanes on the left side of the road reference line are numbered as positive numbers, such as "1", "2" and "3". The number of lanes on the same road may change. For example, near an intersection, a two-lane area may become a three-lane area. In this case, the road can be divided into two lane segments, that is, Figure 2 Two lane segments are divided by a vertical black line.

[0048] Obtain static information of the target road network. The static information of the target road network includes topological information of each lane among multiple lanes.

[0049] It should be noted that the lane topology information includes one or more of the lane's predecessor lanes (prev_lanes), successor lanes (next_lanes), left lane (left_lane), and right lane (right_lane). The predecessor lanes (prev_lanes) of a lane are the one or more lanes preceding the lane in the direction of travel; the successor lanes (next_lanes) of a lane are the one or more lanes following the lane in the direction of travel; the left lane (left_lane) of a lane is the lane adjacent to the left of the lane in the direction of travel; and the right lane (right_lane) of a lane is the lane adjacent to the right of the lane in the direction of travel.

[0050] The static information of the target road network may further include structural information of each of the multiple lanes.

[0051] It should be noted that the lane structure information includes the lane centerline center_line, the lane left boundary line left_line, and the lane right boundary line right_line.

[0052] In practical applications, in order to integrate the annotation information of the same lane, the lane can be annotated with the lane's centerline center_line, so that the lane's centerline center_line carries the lane's topological information, as well as the lane's left boundary line left_line and lane's right boundary line right_line.

[0053] After obtaining the static information of the target road network, considering that right-hand drive traffic rules are adopted in actual application scenarios, any lane is selected from multiple lanes as the target lane. Based on the topological information of the target lane, multiple lanes are traversed until the frontmost right lane associated with the target lane is determined.

[0054] The process of selecting any lane from multiple lanes as a target lane and traversing the multiple lanes based on the topological information of the target lane until the frontmost rightmost lane associated with the target lane is determined can be as follows: 1. Select the first lane lane[0] from multiple lanes as the target lane, which is the current lane currLane: "currLane = lanes[0]".

[0055] 2. Based on the topological information of the current lane currLane, traverse forward and rightward in multiple lanes until the frontmost rightmost lane associated with the current lane currLane is determined. Update the current lane currLane to this frontmost rightmost lane: "prevLane = lanes.find((lane) =>currLane.prev_lanes.includes(lane.id)) while (prevLane) { currLane = prevLane prevLane = lanes.find((lane) =>currLane.prev_lanes.includes(lane.id)) } rightLane = lanes.find((lane) =>currLane.right === lane.id) while (rightLane) { currLane = rightLane rightLane = lanes.find((lane) =>currLane.right === lane.id) }".

[0056] It can be understood that in the above step 2, assuming that the topological information of the current lane currLane, that is, lane lane[0], includes the predecessor lane prev_lanes, the successor lane next_lanes, the left lane left_lane, and the right lane right_lane of lane lane[0], then multiple lanes lanes are traversed along the predecessor direction of lane lane[0]. Specifically, since lane lane[0] has a predecessor lane, the predecessor lane prev_lanes of lane lane[0] will be traversed along the predecessor direction of lane lane[0]. At this time, according to the topological information of the predecessor lane prev_lanes of lane lane[0], it is determined whether the predecessor lane prev_lanes of lane lane[0] has a predecessor lane. If not, the predecessor lane prev_lanes of lane lane[0] is determined as the most predecessor lane associated with lane lane[0]. If yes, the traversal continues to the next predecessor lane until the most predecessor lane associated with lane lane[0] is determined. Update the current lane currLane from lane[0] to the frontmost successor lane. Traverse multiple lanes along the right direction of the frontmost successor lane. Specifically, determine whether the frontmost successor lane has a right lane based on the topological information of the frontmost successor lane. If not, determine the frontmost successor lane as the frontmost rightmost lane associated with lane[0]. If so, continue traversing to the right lane of the frontmost successor lane until the rightmost lane of the frontmost successor lane is determined, that is, the frontmost rightmost lane associated with lane[0]. Update the current lane currLane to the frontmost rightmost lane.

[0057] In actual applications, based on the topological information of the target lane, forward traversal can be performed first in multiple lanes and then right traversal can be performed until the frontmost rightmost lane associated with the target lane is determined. Based on the topological information of the target lane, right traversal can be performed first in multiple lanes and then forward traversal can be performed until the frontmost rightmost lane associated with the target lane is determined. Based on the topological information of the target lane, forward traversal and right traversal can be performed separately in multiple lanes until the frontmost rightmost lane associated with the target lane is determined.

[0058] After obtaining the frontmost rightmost lane, multiple lanes are traversed based on the topological information of the frontmost rightmost lane until a lane segment is determined, wherein the determined current lane segment includes a left lane group, a right lane group and a road centerline, each left lane in the left lane group is in the same direction as the frontmost rightmost lane, each right lane in the right lane group is in the opposite direction to the frontmost rightmost lane, and the road centerline is the left boundary line of the leftmost lane associated with the frontmost rightmost lane.

[0059] The process of traversing multiple lanes based on the topological information of the frontmost right lane until a lane segment is determined can be as follows: The current lane currLane is the frontmost right lane. Based on the current lane currLane, get the first lane segment laneSection: "laneSection = getLaneSection(currLane)".

[0060] A lane segment includes a left lane group, a right lane group, and a road centerline. Based on the topological information of the frontmost right lane, the process of traversing multiple lanes to determine the left lane group, the right lane group, and the road centerline can be as follows: 1. Put the current lane currLane into the left queue: "laneSection.left.push(lane)".

[0061] 2. Based on the topological information of the current lane currLane, traverse the multiple lanes to the left. Place all lanes to the left of the current lane currLane in the left queue. The resulting left queue is the left lane group. Each left lane in the left lane group is in the same direction as the current lane currLane, which is the frontmost right lane. "currLane = lane leftLane = lanes.find((lane) =>currLane.left === lane.id) while (leftLane) { currLane = leftLane laneSection.left.push(currLane) leftLane = lanes.find((lane) =>currLane.left === lane.id) }".

[0062] 3. After traversing all lanes to the left of the current lane currLane, the left boundary line of the leftmost lane associated with the current lane currLane is determined as the road centerline: "laneSection.center = lines.find((line) =>currLane.left_line ===line.id)".

[0063] 4. Determine the direction of the road centerline and the direction of the leftmost lane associated with the current lane, currLane. If the two are in the same direction, then the direction of the road centerline is reversed. If the two are in opposite directions, then there is no need to reverse the direction of the road centerline: "consistent = isDirectionConsistent(laneSection.center, currLane) if (consistent) { laneSection.center.shape.reverse() }".

[0064] 5. Search for another lane whose left boundary is also the road centerline among the multiple lanes. If there is one, it indicates that the lane is the oncoming lane. Update the current lane currLane to that lane. Based on the topological information of that lane, traverse the multiple lanes rightward. Put all lanes to the right of the current lane currLane that have been traversed into the right queue. The resulting right queue is the right lane group. Each right lane in the right lane group is in the opposite direction of the frontmost right lane: "oppositeLane = lanes.find((lane) =>laneSection.center.id ===lane.left_line) while (oppositeLane) { currLane = oppositeLane laneSection.right.push(currLane) oppositeLane = lanes.find((lane) =>currLane.right_lane === lane.id) }” 6. Return the current lane segment laneSection, which includes the left lane group, the road centerline, and the right lane group.

[0065] After obtaining the current lane segment, a road object is constructed according to the current lane segment, wherein the current road object includes the current lane segment.

[0066] After obtaining the current lane segment or the current road object, it is determined whether there is a subsequent lane segment associated with the current lane segment. If it is determined that there is a subsequent lane segment associated with the current lane segment, it is further determined whether the current lane segment and the subsequent lane segment belong to the same road.

[0067] When it is determined that there is a subsequent lane segment associated with the current lane segment, and the current lane segment and the subsequent lane segment belong to the same road, the subsequent lane segment is added to the current road object to update the current road object.

[0068] When it is determined that there is no successor lane segment associated with the current lane segment, or when it is determined that there is a successor lane segment associated with the current lane segment but the current lane segment and the successor lane segment do not belong to the same road, the current road object is constructed.

[0069] In practical applications, the number of subsequent lane segments associated with the current lane segment may be one or more.

[0070] After constructing a road object, it is detected whether there is an untraversed lane among multiple lanes.

[0071] When there are untraversed lanes among multiple lanes, it is considered that these lanes may belong to a new road. Any lane from all the untraversed lanes is selected as a new target lane, and a new road object is constructed according to the above operations until it is determined that multiple lanes have been traversed, thereby obtaining multiple road objects.

[0072] In an embodiment of the present application, any lane is selected from multiple lanes as a target lane, and based on the topological information of the target lane, multiple lanes are traversed until the frontmost right lane associated with the target lane is determined. Based on the topological information of the frontmost right lane, multiple lanes are traversed until the current lane segment is determined. A road object is constructed according to the current lane segment. When it is determined that there is a subsequent lane segment associated with the current lane segment, and the current lane segment and the subsequent lane segment belong to the same road, the subsequent lane segment is added to the current road object to update the current road object. When there is an untraversed lane among the multiple lanes, the untraversed lane is determined as a new target lane to construct a new road object. On the one hand, the longitudinal topological relationship and the lateral topological relationship of the target lane can be fully considered to accurately construct the road object. On the other hand, it can ensure that road objects are constructed for all roads of the target road network to avoid the problem of missing road objects.

[0073] In an optional embodiment, after determining a lane segment, the method further includes: traversing multiple lanes based on the topological information of the front and rightmost lane until the rightmost lane associated with the successor lane of the front and rightmost lane is determined or the traversal of multiple lanes is completed; when it is determined that there is a rightmost lane, traversing multiple lanes based on the topological information of the rightmost lane, determining the subsequent lane segment, and determining whether the current lane segment and the subsequent lane segment belong to the same road; when it is determined that there is no rightmost lane, determining that there is no subsequent lane segment.

[0074] As an example, after obtaining a lane segment, that is, the current lane segment, it is determined whether there is a subsequent lane segment associated with the current lane segment. If it is determined that there is a subsequent lane segment associated with the current lane segment, it is further determined whether the current lane segment and the subsequent lane segment belong to the same road.

[0075] In actual application scenarios, if there are successor lane segments associated with the current lane segment and belonging to the same road, there may be one or more successor lane segments. For example, the n successor lane segments associated with the current lane segment and belonging to the same road include: a successor lane segment associated with the current lane segment and belonging to the same road, that is, the first successor lane segment associated with the current lane segment and belonging to the same road; a successor lane segment associated with the first lane segment and belonging to the same road, that is, the second successor lane segment associated with the current lane segment and belonging to the same road; ...; a successor lane segment associated with the n-1th lane segment and belonging to the same road, that is, the nth lane segment associated with the current lane segment and belonging to the same road.

[0076] After obtaining a successor lane segment associated with the current lane segment and belonging to the same road, the current lane segment is updated to the successor lane segment, and a determination is continued as to whether there is a successor lane segment associated with the current lane segment. If a successor lane segment associated with the current lane segment is determined, a determination is continued as to whether the current lane segment and the successor lane segment belong to the same road.

[0077] Among them, the process of determining whether there are all subsequent lane segments associated with the current lane segment and belonging to the same road can be: the current lane currLane is the frontmost rightmost lane, and based on the topological information of the current lane currLane, that is, the frontmost rightmost lane, first traverse backward and then traverse rightward in multiple lanes until the rightmost lane associated with the successor lane of the frontmost rightmost lane is determined or the traversal of multiple lanes is completed. After the rightmost lane is determined, referring to the above-mentioned determination process of the current lane segment, based on the topological information of the rightmost lane, traverse multiple lanes to determine the first subsequent lane segment associated with the current lane segment, and determine whether the current lane segment and the first subsequent lane segment belong to the same road. If so, the current lane segment is updated to the first subsequent lane segment, and the above operations are repeated until it is determined that there is no subsequent lane segment associated with the current lane segment and belonging to the same road; after completing the traversal of multiple lanes and determining that there is no rightmost lane, it is directly determined that there is no subsequent lane segment.

[0078] After obtaining the current lane section laneSection, the process of determining whether there are all subsequent lane sections nextLaneSection associated with the current lane section and belonging to the same road is as follows: "roadResult = getRoad(laneSection) roads.push(roadResult.road) nextLaneStection = roadResult.nextLaneSection".

[0079] Subsequently, the next road nextRoad can be directly obtained based on the subsequent lane segment nextLaneSection until nextLaneSection does not exist: "while (nextLaneSection) { nextRoadResult = getRoad(nextLaneSection) roads.push(nextRoadResult.road nextLaneSection = nextRoadResult.nextLaneSection }".

[0080] In practical applications, the process of constructing a road object road according to the current lane segment laneSection and determining the subsequent lane segment nextLaneSection can be as follows: 1. Put the current lane segment laneSection into the road object road: "road.lanes.push(laneSection)".

[0081] 2. Take the first lane in the left lane group of the current lane segment laneSection, that is, the rightmost lane. Based on the topological information of the rightmost lane, find the rightmost lane nextLane among all subsequent lanes of the rightmost lane (judgment method: the rightmost lane has no right neighbor): "nextLanes = laneSection.left[0].next_lanes.map((nextLaneId) =>lanes.find((lane) =>nextLaneId === lane.id)) nextLane = nextLanes.find((lane) =>!lane.right_lane)".

[0082] 3. If nextLane exists, the lane segment it is in is determined as the successor lane segment nextLaneSection based on nextLane as the reference, and a determination is made as to whether the successor lane segment nextLaneSection and the current lane segment laneSection belong to the same road. If they do, the successor lane segment nextLaneSection is placed in the current road object road, and the current lane segment laneSection is updated to the successor lane segment nextLaneSection.

[0083] 4. Repeat steps 2-3. If you are sure that the two lanes do not belong to the same road, proceed to step 5: "while (nextLane) { nextLaneSection = getLaneSection(nextLane) sameRoad = isSameRoad(laneSection, nextLaneSection) if (sameRoad) { road.lanes.push(nextLaneSection) laneSection = nextLaneSection nextLane = Refer to step 2 } else { nextLane = null } }".

[0084] 5. Return the current road object road and the next lane segment nextLaneSection obtained last.

[0085] For example, the structural diagram of the constructed road object is as follows Figure 3 As shown, Figure 3 The "left" in the _track_map represents the left lane group, the "center" represents the road centerline, and the "right" represents the right lane group.

[0086] The road object mainly contains the following two contents: 1. PlanView: This describes the road reference line of the road object. By traversing each laneSections, taking the center line of each laneSection and connecting them end to end, the geometric information of the road reference line is obtained; 2. Lanes: By traversing each laneSections, the lane width of each lane included in it is calculated based on its lane boundary lines.

[0087] In the embodiment of the present application, after determining the current lane segment, multiple lanes are traversed based on the topological information of the frontmost and rightmost lane until the rightmost lane associated with the successor lane of the frontmost and rightmost lane is determined or the traversal of multiple lanes is completed. If it is determined that there is a rightmost lane, multiple lanes are traversed based on the topological information of the rightmost lane to determine the successor lane segment, and it is determined whether the current lane segment and the successor lane segment belong to the same road. If it is determined that there is no rightmost lane, it is determined that there is no successor lane segment. This embodiment of the present application can comprehensively and accurately determine whether there is a successor lane segment associated with the current lane segment and belonging to the same road.

[0088] In an optional embodiment, after determining that there is a subsequent lane segment associated with the current lane segment, the method further includes: determining whether the lane of the current lane segment and the lane of the subsequent lane segment are the front and rear lanes of each other; if so, determining that the current lane segment and the subsequent lane segment belong to the same road; if not, determining that the current lane segment and the subsequent lane segment do not belong to the same road.

[0089] As an example, after determining that there is a subsequent lane segment associated with the current lane segment, it is determined whether the lanes of the current lane segment and the lanes of the subsequent lane segment are the front and rear lanes of each other. If so, it is considered that the current lane segment and the subsequent lane segment extend on the same road, and it is determined that the current lane segment and the subsequent lane segment belong to the same road. Otherwise, it is determined that the current lane segment and the subsequent lane segment do not belong to the same road.

[0090] The embodiment of the present application determines whether the current lane segment and the subsequent lane segment belong to the same road by judging whether the lanes of the current lane segment and the lanes of the subsequent lane segment are the front and rear lanes of each other, which can ensure accurate determination of whether the current lane segment and the subsequent lane segment belong to the same road.

[0091] In an optional embodiment, each of the multiple road objects includes at least one lane segment; and identifying the road connection relationship and the lane connection relationship on the road based on the multiple road objects to construct an intersection object includes: for each pair of road objects obtained by combining any two of the multiple road objects, obtaining the two end lane groups of the first road object and the two end lane groups of the second road object; wherein the current pair of road objects is obtained by combining the first road object and the second road object, the two end lane groups of the first road object are the lane groups in the starting and ending lane segments of the first road object, and the two end lane groups of the second road object are the lane groups in the starting and ending lane segments of the second road object; if the successor lane of any end lane in the two end lane groups of the first road object exists in the two end lane groups of the second road object, then an intersection object is constructed; wherein the current intersection object includes the road connection node between the first road object and the second road object, and the lane connection node between the end lane and the successor lane; if the successor lane of each lane in the two end lane groups of the first road object does not exist in the two end lane groups of the second road object, then no intersection object is constructed.

[0092] As an example, after the above processing, each road object in the plurality of road objects includes at least one lane segment.

[0093] Combine any two of the multiple road objects, and for each pair of road objects obtained by combining any two of the multiple road objects, obtain the lane groups at both ends of the first road object and the lane groups at both ends of the second road object, wherein the current pair of road objects is obtained by combining the first road object and the second road object, the lane groups at both ends of the first road object are the lane groups in the lane segments at the starting and ending ends of the first road object, and the lane groups at both ends of the second road object are the lane groups in the lane segments at the starting and ending ends of the second road object.

[0094] It is understood that the lane groups at both ends of the first road object include the left lane group and the right lane group in the starting lane segment of the first road object, as well as the left lane group and the right lane group in the ending lane segment of the first road object. Similarly, the lane groups at both ends of the second road object include the left lane group and the right lane group in the starting lane segment of the second road object, as well as the left lane group and the right lane group in the ending lane segment of the second road object.

[0095] For each endpoint lane in the two end lane groups of the first road object, based on the topological information of the current endpoint lane and the topological information of each endpoint lane in the two end lane groups of the second road object, determine whether the subsequent lane of the current endpoint lane is the same lane as any endpoint lane in the two end lane groups of the second road object. If so, it is considered that the current endpoint lane exists in the two end lane groups of the second road object; otherwise, it is considered that the current endpoint lane does not exist in the two end lane groups of the second road object.

[0096] If the successor lane of any end lane in the two end lane groups of the first road object exists in the two end lane groups of the second road object, then a road intersection object is constructed, where the current road intersection object includes the road connection node between the first road object and the second road object, and the lane connection node between the current end lane and the successor lane of the current end lane.

[0097] If the successor lane of each lane in the two end lane groups of the first road object does not exist in the two end lane groups of the second road object, no intersection object is constructed.

[0098] The junction object defines the connection between roads. An intersection contains multiple connections, each of which consists of an incoming road (incomingRoad) and a connecting road (connectingRoad). Within each connection, the start (from) and end (to) relationships between the incoming road lanes and the connecting road lanes must also be defined.

[0099] In actual applications, after obtaining multiple road objects, the road connection relationship and the lane connection relationship on the road can be found based on the identified road information. The search method can be as follows: 1. Take any two combinations from multiple road objects to get a pair of road objects, such as road1 and road2.

[0100] 2. Get the starting lane segment startLaneSection1 and the ending lane segment endLaneSection1 of road1, and get the starting lane segment startLaneSection2 and the ending lane segment endLaneSection2 of road2.

[0101] 3. Get all the starting lanes of road1 from startLaneSection1, and get all the ending lanes of road1 from endLaneSection1, and integrate them into the end lane group of road1.

[0102] 4. Traverse each end lane in the two end lane groups of road1 and determine whether the successor lane next_lanes of the current end lane is in startLaneSection2 and endLaneSection2. If so, add a connecting lane between the current end lane and its successor lane next_lanes for road1 and road2.

[0103] 5. Continue to execute step 1 until all road objects are judged pairwise.

[0104] After the above search is completed, the connecting lanes between all road objects can be determined. Based on these connecting lanes, the intersection object juction can be constructed. The intersection object juction mainly includes the road connection node connection and the lane connection node laneLink.

[0105] In the embodiment of the present application, for each pair of road objects obtained by any combination of two of a plurality of road objects, the lane groups at both ends of the first road object and the lane groups at both ends of the second road object are obtained to identify the road connection relationship and the lane connection relationship on the road. If the successor lane of any end lane in the lane groups at both ends of the first road object exists in the lane groups at both ends of the second road object, an intersection object is constructed; otherwise, no intersection object is constructed. The connection relationship between roads can be determined down to the lanes on the road, ensuring accurate construction of the intersection object.

[0106] In an optional embodiment, the static information of the target road network includes attribute information of multiple lanes; the method further includes step S105: S105. Add attribute information of multiple lanes to a static map; wherein the static map is a first static map or a second static map.

[0107] As an example, the static information of the target road network may further include attribute information of each lane among the multiple lanes.

[0108] It should be noted that the lane attribute information includes lane driving direction, lane width and lane type, among which lane types include motor vehicle lanes, non-motor vehicle lanes and bus lanes.

[0109] After obtaining the static map of the target road network, that is, the first static map or the second static map, attribute information of each lane of the multiple lanes is added to the static map of the target road network.

[0110] In practical applications, for each lane segment in each road object, the lane centerline of each lane in the lane segment may carry respective attribute information.

[0111] The embodiment of the present application enriches the expression information of the static map of the road network by adding the attribute information of multiple lanes included in the static information of the target road network to the static map of the target road network, which is conducive to the simulation platform to conduct comprehensive testing and verification of the autonomous driving system.

[0112] In an optional embodiment, the method further includes steps S106-S107: S106: Using a simulation platform to verify the compatibility of the static map; wherein the static map includes a first static map or a second static map; S107 : If the static map passes the compatibility verification, output the static map.

[0113] As an example, a simulation platform is selected based on actual business needs.

[0114] After obtaining the static map of the target road network, that is, the first static map or the second static map, the simulation platform is used to verify the compatibility of the static map. If the static map passes the compatibility verification, it is considered that the simulation platform is compatible with the static map, and the static map is allowed to be output at this time. If the static map fails the compatibility verification, it is considered that the simulation platform is incompatible with the static map. At this time, the static map of the target road network can be rebuilt, or a notification message of failure to build the static map of the target road network can be directly output.

[0115] The embodiment of the present application uses a simulation platform to verify the compatibility of the static map. When the static map passes the compatibility verification, the static map is output, which can further verify the compatibility of the simulation platform with the static map and ensure the validity of the static map.

[0116] Please see Figure 4 , Figure 4 A schematic structural diagram of a road network static map construction device provided in the second embodiment of the present application. The second embodiment of the present application provides a road network static map construction device, comprising: a road object construction module 201, configured to identify roads based on static information of a target road network and construct a plurality of road objects; an intersection object construction module 202, configured to identify road connection relationships and lane connection relationships on roads based on a plurality of road objects and construct intersection objects; a static map construction module 203, configured to: construct a first static map of the target road network when at least one intersection object is constructed; wherein the first static map includes a plurality of road objects and at least one intersection object; and construct a second static map of the target road network when no intersection object is constructed; wherein the second static map includes a plurality of road objects.

[0117] In an optional embodiment, the static information of the target road network includes topological information of multiple lanes; identifying roads based on the static information of the target road network and constructing multiple road objects includes: selecting any lane from the multiple lanes as the target lane, traversing the multiple lanes based on the topological information of the target lane until the frontmost rightmost lane associated with the target lane is determined; traversing the multiple lanes based on the topological information of the frontmost rightmost lane until a lane segment is determined; wherein the current lane segment includes a left lane group, a right lane group and a road centerline, and each left lane in the left lane group is in the same direction as the frontmost rightmost lane, Each right lane in the right lane group is opposite to the front rightmost lane, and the centerline of the road is the left boundary line of the leftmost lane associated with the front rightmost lane; a road object is constructed based on the current lane segment; wherein the current road object includes the current lane segment; when it is determined that there is a subsequent lane segment associated with the current lane segment, and the current lane segment and the subsequent lane segment belong to the same road, the subsequent lane segment is added to the current road object to update the current road object; when there is an untraversed lane among multiple lanes, the untraversed lane is determined as a new target lane to construct a new road object.

[0118] In an optional embodiment, the road object construction module 201 is further configured to, after determining a lane segment, traverse multiple lanes based on the topological information of the frontmost and rightmost lane until the rightmost lane associated with the successor lane of the frontmost and rightmost lane is determined or the traversal of multiple lanes is completed; if it is determined that there is a rightmost lane, traverse multiple lanes based on the topological information of the rightmost lane to determine the successor lane segment, and determine whether the current lane segment and the successor lane segment belong to the same road; if it is determined that there is no rightmost lane, determine that there is no successor lane segment.

[0119] In an optional embodiment, the road object construction module 201 is further configured to, after determining that there is a subsequent lane segment associated with the current lane segment, determine whether the lanes of the current lane segment and the lanes of the subsequent lane segment are front and rear lanes of each other; if so, determine that the current lane segment and the subsequent lane segment belong to the same road; if not, determine that the current lane segment and the subsequent lane segment do not belong to the same road.

[0120] In an optional embodiment, each of the multiple road objects includes at least one lane segment; and identifying the road connection relationship and the lane connection relationship on the road based on the multiple road objects to construct an intersection object includes: for each pair of road objects obtained by combining any two of the multiple road objects, obtaining the two end lane groups of the first road object and the two end lane groups of the second road object; wherein the current pair of road objects is obtained by combining the first road object and the second road object, the two end lane groups of the first road object are the lane groups in the starting and ending lane segments of the first road object, and the two end lane groups of the second road object are the lane groups in the starting and ending lane segments of the second road object; if the successor lane of any end lane in the two end lane groups of the first road object exists in the two end lane groups of the second road object, then an intersection object is constructed; wherein the current intersection object includes the road connection node between the first road object and the second road object, and the lane connection node between the end lane and the successor lane; if the successor lane of each lane in the two end lane groups of the first road object does not exist in the two end lane groups of the second road object, then no intersection object is constructed.

[0121] In an optional embodiment, the static information of the target road network includes attribute information of multiple lanes; the static map construction module 203 is further used to add attribute information of multiple lanes to the static map; wherein the static map is the first static map or the second static map.

[0122] In an optional embodiment, the device further includes: a static map output module, configured to: perform compatibility verification on the static map using a simulation platform; wherein the static map is the first static map or the second static map; and output the static map if the static map passes the compatibility verification.

[0123] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0124] The third embodiment of the present application provides a computer program product, which includes instructions. When the instructions are executed by a computer, the computer implements the method described in the first embodiment of the present application and can achieve the same beneficial effects.

[0125] The method described in the first embodiment of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in each embodiment of the present application are executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, a core network device, an OAM (Open Application Model), or other programmable device.

[0126] A computer program or instruction can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, a computer program or instruction can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. A computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that integrates one or more available media. Available media can be magnetic media, such as floppy disks, hard disks, or magnetic tapes; optical media, such as digital video disks; or semiconductor media, such as solid-state drives. The computer-readable storage medium can be volatile or non-volatile, or can include both volatile and non-volatile types of storage media.

[0127] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of an electronic device provided in the fourth embodiment of the present application. The fourth embodiment of the present application provides an electronic device 30, comprising a processor 301, a memory 302, and a computer program stored in the memory 302 and configured to be executed by the processor 301; when the processor 301 executes the computer program, it implements the method described in the first embodiment of the present application and can achieve the same beneficial effects as described above.

[0128] In which, when the processor 301 reads the computer program from the memory 302 through the bus 303 and executes the computer program, it can implement the method of any embodiment included in the method described in the first embodiment of the present application.

[0129] Processor 301 can process digital signals and can include various computing architectures, such as a complex instruction set computer architecture, a reduced instruction set computer architecture, or an architecture that implements a combination of multiple instruction sets. In some examples, processor 301 can be a microprocessor.

[0130] The memory 302 can be used to store instructions executed by the processor 301 or data related to the execution of instructions. These instructions and / or data may include code for implementing some or all functions of one or more modules described in the embodiments of this application. The processor 301 of the embodiment of the present disclosure can be used to execute the instructions in the memory 302 to implement the method described in the first embodiment of this application. The memory 302 includes dynamic random access memory, static random access memory, flash memory, optical storage, or other memory known to those skilled in the art.

[0131] The fifth embodiment of the present application provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method described in the first embodiment of the present application, and can achieve the same beneficial effects as the method.

[0132] In summary, the embodiments of the present application provide a method, program product, device, and medium for constructing a static map of a road network. The method includes: identifying roads based on static information of a target road network and constructing multiple road objects; wherein each of the multiple road objects includes at least one lane segment; identifying road connection relationships and lane connection relationships on the roads based on the multiple road objects and constructing intersection objects; when at least one intersection object is constructed, constructing a first static map of the target road network; wherein the first static map includes multiple road objects and at least one intersection object; when no intersection object is constructed, constructing a second static map of the target road network; wherein the second static map includes multiple road objects. The embodiment of the present application identifies roads based on static information of the target road network, constructs multiple road objects, identifies road connection relationships and lane connection relationships on the roads based on the multiple road objects, and constructs intersection objects. When at least one intersection object is constructed, a first static map of the target road network including multiple road objects and at least one intersection object is constructed. When no intersection object is constructed, a second static map of the target road network including multiple road objects is constructed. The static information of the road network can be automatically structured into road objects or intersection objects in the static map of the road network, thereby realizing the automatic construction of the static map of the road network based on the annotated static information.

[0133] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0134] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0135] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0136] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for constructing a road network static map, characterized in that: include: Identify roads based on the static information of the target road network and construct multiple road objects; Identifying road connection relationships and lane connection relationships on the roads based on the plurality of road objects, and constructing an intersection object; When at least one intersection object is constructed, a first static map of the target road network is constructed; wherein the first static map includes the plurality of road objects and the at least one intersection object; Without constructing the intersection object, a second static map of the target road network is constructed; wherein the second static map includes the plurality of road objects.

2. The method according to claim 1, characterized in that The static information of the target road network includes topological information of multiple lanes; The identifying of roads based on the static information of the target road network and constructing a plurality of road objects includes: Selecting any lane from the plurality of lanes as a target lane, and traversing the plurality of lanes based on topological information of the target lane until determining the frontmost rightmost lane associated with the target lane; Traversing the multiple lanes based on the topological information of the frontmost rightmost lane until a lane segment is determined; wherein the current lane segment includes a left lane group, a right lane group, and a road centerline, each left lane in the left lane group is in the same direction as the frontmost rightmost lane, each right lane in the right lane group is in the opposite direction to the frontmost rightmost lane, and the road centerline is a left boundary line of the leftmost lane associated with the frontmost rightmost lane; Constructing a road object according to the current lane segment; wherein the current road object includes the current lane segment; If it is determined that there is a successor lane segment associated with the current lane segment, and the current lane segment and the successor lane segment belong to the same road, adding the successor lane segment to the current road object to update the current road object; In the case that there is an untraversed lane among the multiple lanes, the untraversed lane is determined as a new target lane to construct a new road object.

3. The method according to claim 2, characterized in that After determining a lane segment, the method further includes: traversing the plurality of lanes based on the topological information of the frontmost rightmost lane until the rightmost lane associated with the subsequent lane of the frontmost rightmost lane is determined or the traversal of the plurality of lanes is completed; When it is determined that the rightmost lane exists, traversing the multiple lanes based on topological information of the rightmost lane to determine the subsequent lane segment, and determining whether the current lane segment and the subsequent lane segment belong to the same road; In the case where it is determined that the rightmost lane does not exist, it is determined that the subsequent lane segment does not exist.

4. The method according to claim 2, characterized in that After determining that there is a subsequent lane segment associated with the current lane segment, the method further includes: determining whether the lane of the current lane segment and the lane of the subsequent lane segment are front and rear lanes of each other; If so, determining that the current lane segment and the subsequent lane segment belong to the same road; If not, it is determined that the current lane segment and the subsequent lane segment do not belong to the same road.

5. The method according to claim 1, wherein Each of the plurality of road objects includes at least one lane segment; and identifying road connection relationships and lane connection relationships on the roads based on the plurality of road objects and constructing an intersection object includes: For each pair of road objects formed by combining any two of the plurality of road objects, obtaining a lane group at both ends of the first road object and a lane group at both ends of the second road object; wherein the current pair of road objects is formed by combining the first road object and the second road object, the lane group at both ends of the first road object is a lane group at both ends of the lane segments at the start and end of the first road object, and the lane group at both ends of the second road object is a lane group at both ends of the lane segments at the start and end of the second road object; If the successor lane of any end lane in the two end lane groups of the first road object exists in the two end lane groups of the second road object, construct an intersection object; wherein the current intersection object includes a road connection node between the first road object and the second road object, and a lane connection node between the end lane and the successor lane; If the successor lane of each lane in the lane groups at both ends of the first road object does not exist in the lane groups at both ends of the second road object, no intersection object is constructed.

6. The method according to claim 1, wherein The static information of the target road network includes attribute information of multiple lanes; the method further includes: Adding attribute information of the multiple lanes to the static map; wherein the static map is the first static map or the second static map.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Using a simulation platform to verify the compatibility of a static map; wherein the static map is the first static map or the second static map; If the static map passes the compatibility verification, the static map is output.

8. A computer program product, characterized in that The computer program product comprises instructions which, when executed by a computer, cause the computer to implement the method according to any one of claims 1 to 7.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor; when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

Images