CN116976356A - Topological graph repeated node semantic inference method and device - Google Patents
Topological graph repeated node semantic inference method and device Download PDFInfo
- Publication number
- CN116976356A CN116976356A CN202310906269.5A CN202310906269A CN116976356A CN 116976356 A CN116976356 A CN 116976356A CN 202310906269 A CN202310906269 A CN 202310906269A CN 116976356 A CN116976356 A CN 116976356A
- Authority
- CN
- China
- Prior art keywords
- node
- semantic information
- repeated
- nodes
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000011218 segmentation Effects 0.000 claims abstract description 17
- 238000004590 computer program Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 abstract description 14
- 238000010586 diagram Methods 0.000 description 7
- 238000013500 data storage Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000010845 search algorithm Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The application discloses a topological graph repeated node semantic inference method and a device, which relate to the technical field of automatic driving and comprise the following steps: obtaining a topological graph of a constructed road structure, a path starting point and a path ending point, wherein repeated nodes which are already combined are marked in the topological graph, and semantic information of the repeated nodes in different scenes is recorded; according to the topological graph, the path starting point and the path ending point, path searching is carried out to obtain a node sequence of a navigation path; determining repeated nodes in the node sequence, and dynamically calculating target semantic information of the repeated nodes in the current scene based on semantic information of nodes adjacent to the repeated nodes in the node sequence; and carrying out lane segmentation on the navigation path according to the target semantic information of the repeated node in the current scene to obtain each lane and the corresponding node thereof. The application can simplify the construction process of the topological graph and reduce the construction cost of the topological graph.
Description
Technical Field
The application relates to the technical field of automatic driving, in particular to a topological graph repeated node semantic inference method and device.
Background
Topology maps are frequently constructed during autopilot, such as map navigation, module invocation, cross-compilation, and the like. When constructing the topological graph, the same node often has different semantic information under different scenes.
At present, in order to ensure the uniqueness of each node, the uniqueness of the node is ensured by utilizing other information, and a topological graph is constructed based on the unique node. However, this approach may result in an increased number of nodes and edges in the topology, thereby increasing the construction cost of the topology and occupying the storage resources of the data.
Disclosure of Invention
The application provides a topological graph repeated node semantic inference method and device, which mainly can simplify the construction process of a topological graph, reduce the construction cost of the topological graph and reduce the occupation of data storage resources.
According to a first aspect of an embodiment of the present application, there is provided a topology graph repetition node semantic inference method, including:
obtaining a topological graph of a constructed road structure, and a path starting point and a path ending point, wherein repeated nodes which are already combined are marked in the topological graph, and semantic information of the repeated nodes in different scenes is recorded;
according to the topological graph, the path starting point and the path ending point, path searching is carried out to obtain a node sequence of a navigation path;
determining repeated nodes in the node sequence, and dynamically calculating target semantic information of the repeated nodes in the current scene based on semantic information of nodes adjacent to the repeated nodes in the node sequence;
and carrying out lane segmentation on the navigation path according to the target semantic information of the repeated node in the current scene to obtain each lane and the corresponding node thereof.
According to a second aspect of an embodiment of the present application, there is provided a topology graph repetition node semantic inference apparatus, including:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a topological graph of a constructed road structure, a path starting point and a path ending point, wherein the topological graph is marked with repeated nodes which are already combined, and semantic information of the repeated nodes in different scenes is recorded;
the cable unit is used for searching the path according to the topological graph, the path starting point and the path ending point to obtain a node sequence of the navigation path;
the calculating unit is used for determining repeated nodes in the node sequence and dynamically calculating target semantic information of the repeated nodes in the current scene based on semantic information of nodes adjacent to the repeated nodes in the node sequence;
and the segmentation unit is used for carrying out lane segmentation on the navigation path according to the target semantic information of the repeated node in the current scene to obtain each lane and the corresponding node thereof.
According to a third aspect of embodiments of the present application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
obtaining a topological graph of a constructed road structure, and a path starting point and a path ending point, wherein repeated nodes which are already combined are marked in the topological graph, and semantic information of the repeated nodes in different scenes is recorded;
according to the topological graph, the path starting point and the path ending point, path searching is carried out to obtain a node sequence of a navigation path;
determining repeated nodes in the node sequence, and dynamically calculating target semantic information of the repeated nodes in the current scene based on semantic information of nodes adjacent to the repeated nodes in the node sequence;
and carrying out lane segmentation on the navigation path according to the target semantic information of the repeated node in the current scene to obtain each lane and the corresponding node thereof.
According to a fourth aspect of embodiments of the present application, there is provided an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program:
obtaining a topological graph of a constructed road structure, and a path starting point and a path ending point, wherein repeated nodes which are already combined are marked in the topological graph, and semantic information of the repeated nodes in different scenes is recorded;
according to the topological graph, the path starting point and the path ending point, path searching is carried out to obtain a node sequence of a navigation path;
determining repeated nodes in the node sequence, and dynamically calculating target semantic information of the repeated nodes in the current scene based on semantic information of nodes adjacent to the repeated nodes in the node sequence;
and carrying out lane segmentation on the navigation path according to the target semantic information of the repeated node in the current scene to obtain each lane and the corresponding node thereof.
Compared with the prior art, the topology graph of the constructed road structure, the route starting point and the route ending point can be obtained by adding other nodes and edges to ensure the node uniqueness, wherein the topology graph is marked with the repeated nodes which are already combined, the semantic information of the repeated nodes in different scenes is recorded, the route searching is carried out according to the topology graph, the route starting point and the route ending point, the node sequence of the navigation route is obtained, at the same time, the repeated nodes in the node sequence are determined, the target semantic information of the repeated nodes in the current scene is dynamically calculated based on the semantic information of the nodes adjacent to the repeated nodes in the node sequence, and finally the lane segmentation is carried out on the navigation route according to the target semantic information of the repeated nodes in the current scene, so that each lane and the corresponding nodes are obtained. Therefore, the application can avoid adding other nodes and edges to ensure node uniqueness by combining the repeated nodes in advance and dynamically calculating the semantic information of the repeated nodes according to the navigation result when searching paths, thereby simplifying the construction process of the topological graph, reducing the construction cost of the topological graph and reducing the occupation of data storage resources. In addition, the application can precisely segment each lane in the navigation path by dynamically calculating the semantic information of the repeated node, thereby being convenient for inquiring the traffic light information of each lane.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a schematic flow diagram of a topology graph repetition node semantic inference method provided by an embodiment of the present application;
fig. 2 shows a schematic diagram of a topology of a road according to an embodiment of the present application;
FIG. 3 shows a schematic diagram of dynamic computation of semantic information provided by an embodiment of the present application;
fig. 4 is a schematic structural diagram of a topology graph repeating node semantic inference device according to an embodiment of the present application;
FIG. 5 is a schematic structural diagram of another topology graph repeating node semantic inference apparatus according to an embodiment of the present application;
fig. 6 shows a schematic physical structure of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments of the present application and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
The prior art can cause the number of nodes and edges in the topological graph to be increased, thereby increasing the construction cost of the topological graph and occupying the storage resources of data.
To overcome the above drawbacks, an embodiment of the present application provides a topology graph repetition node semantic inference method, as shown in fig. 1, including:
and step 101, obtaining a topological graph of the constructed road structure, and a path starting point and a path ending point.
And marking repeated nodes which are already combined in the topological graph, and recording semantic information of the repeated nodes in different scenes. Furthermore, the coordinates of the duplicate nodes in the topology map are unique, but different semantic information needs to be applied in different scenarios.
The embodiment of the application is mainly suitable for dynamically calculating the scene of the repeated node semantic information. The execution main body of the embodiment of the application is a device or equipment capable of dynamically calculating the semantic information of the repeated node.
For the embodiment of the application, in order to simplify the structure of the topological graph, the repeated nodes are required to be combined and marked as combined repeated nodes in the topological graph, and meanwhile, the semantic information of the repeated nodes in different scenes is recorded, as shown in fig. 2, the node B is the combined repeated node, the semantic information corresponding to the node B comprises a lane 1, a lane 2 and a lane 3, wherein the AB connection is the lane 1, the BC connection is the lane 2, and the BD connection is the lane 3.
In the embodiment of the present application, the semantic information is not limited to the lane information, but may be set to other information according to the actual service requirement, which is not particularly limited in the embodiment of the present application.
Further, before performing the navigation route search, a route start point and a route end point need to be specified according to the constructed topology map so as to perform the route search based on the route start point and the route end point.
Step 102, searching a path according to the topological graph, the path starting point and the path ending point to obtain a node sequence of the navigation path.
For the embodiment of the application, based on the constructed topological graph, the designated path starting point and the designated path ending point, the path searching is carried out by utilizing a preset searching algorithm to obtain the node sequence path= { P1, P2, P3, …, PN } of the navigation path, wherein the node sequence comprises repeated nodes. The preset search algorithm includes a, an expansion algorithm and a dynamic programming algorithm, and may be other search algorithms, which is not specifically limited in the embodiment of the present application.
Step 103, determining repeated nodes in the node sequence, and dynamically calculating target semantic information of the repeated nodes in the current scene based on semantic information of nodes adjacent to the repeated nodes in the node sequence.
For the embodiment of the application, after the navigation path search is performed, the target semantic information of the repeated node in the node sequence in the current scene is dynamically calculated according to the navigation search result, and because the topological graph constructed in the embodiment of the application is related to the road structure, the dynamic semantic information estimation process of the repeated node is essentially to determine which lane the repeated node belongs to under the current scene.
The method comprises the following steps of aiming at a dynamic calculation process of repeated node semantic information: determining a corresponding semantic information pushing mode according to the sequence position of the repeated node in the node sequence; and dynamically calculating target semantic information of the repeated node in the current scene based on the corresponding semantic information pushing mode and the semantic information of the node adjacent to the repeated node.
Specifically, in the embodiment of the application, the repeated nodes are positioned at different sequence positions, and the corresponding semantic information estimation modes are different. In addition, in the semantic information estimation process, it is necessary to determine repeated nodes in the node sequence one by one, and estimate the semantic information of the repeated nodes in the current scene by using the semantic information of the nodes adjacent to the repeated nodes in the node sequence.
When the semantic information is pushed, if the repeated node in the node sequence is a first node, determining target semantic information of the first node in the current scene according to semantic information of a second node in the node sequence; if the repeated node in the node sequence is the last node, determining target semantic information of the last node in the current scene according to semantic information of a previous node corresponding to the last node in the node sequence.
For example, the node sequence path= { P1, P2, P3, …, PN }, if P1 is a duplicate node, the semantic information of P1 is updated to the semantic information of the next node P2, i.e., the semantic information of P2 is regarded as the target semantic information of P1; if PN is a repeated node, the semantic information of PN is updated to the semantic information of PN-1 of the previous node, namely, the semantic information of PN-1 is used as the target semantic information of PN.
Further, if the repeated node in the node sequence is an intermediate node except the first node and the last node, judging whether the adjacent node of the intermediate node is the repeated node, if the adjacent node of the intermediate node is the repeated node, according to the semantic information of the intermediate node in different scenes and the semantic information of the adjacent node of the intermediate node in different scenes, acquiring the intersection of the semantic information of the intermediate node and the adjacent node, and taking the semantic information acquired after the intersection as the target semantic information of the intermediate node and the adjacent node.
For example, if the intermediate node P2 is a repeating node, its corresponding neighboring node P3 is also a repeating node, the semantic information corresponding to P2 includes lane 1 and lane 2, the semantic information corresponding to P3 includes lane 2 and lane 3, and the intersection of the semantic information of P2 and P3 is taken, and the intersection information is lane 2, so that it can be determined that the target semantic information of P2 and P3 is lane 2.
Further, if the neighboring node of the intermediate node is not a duplicate node, determining the target semantic information of the intermediate node according to the semantic information of the previous node or the semantic information of the next node of the intermediate node.
Specifically, if any one of the semantic information of the intermediate node in different scenes is the same as the semantic information of the previous node, determining the semantic information of the previous node as target semantic information of the intermediate node, and inserting a target node behind the intermediate node, wherein the semantic information of the target node is the semantic information of the next node; if any semantic information of the intermediate node in the semantic information of different scenes is the same as the semantic information of the following node, determining the semantic information of the following node as target semantic information of the intermediate node, and inserting a target node in front of the intermediate node, wherein the semantic information of the target node is the semantic information of the previous node.
As shown in fig. 3 (a), assuming that the node B is an intermediate node and is a repeated node, if some semantic information recorded by the node B is the same as the semantic information of the previous node a, determining the semantic information of the node a as target semantic information of the node B, and at the same time, inserting a target node B1 behind the node B, wherein the semantic information of the target node B1 is the semantic information of the node C; as shown in fig. (B), if a certain semantic information recorded by the node B is the same as the semantic information of the following node C, determining the semantic information of the node C as target semantic information of the node B, and inserting a target node B2 in front of the node B, wherein the semantic information of the target node B2 is the semantic information of the node a.
Therefore, according to the method, the semantic information of all repeated nodes in the node sequence path= { P1, P2, P3, … and PN } can be dynamically calculated according to the navigation result, and the uniqueness of the nodes is ensured by adding other nodes and edges when the topological graph is constructed, so that the embodiment of the application can simplify the construction process of the topological graph, reduce the construction cost of the topological graph and reduce the occupation of data storage resources.
And 104, carrying out lane segmentation on the navigation path according to the target semantic information of the repeated node in the current scene to obtain each lane and the corresponding node thereof.
For the embodiment of the application, after the dynamic semantic information of all the repeated nodes in the node sequence is estimated, the lane segmentation can be performed based on the semantic information of each node, and for the process, the method comprises the following steps: and according to the target semantic information of the repeated node in the current scene and the semantic information of other nodes in the node sequence, segmenting the nodes with the same semantic information into the same lane to obtain each lane in the navigation path and the nodes corresponding to each lane.
Specifically, the lane segmentation may be performed according to the current semantic information of each node in the node sequence and the semantic information of the newly inserted node. As shown in fig. 3 (a), since the semantic information of both the node a and the node B is lane 1, the split lane 1 includes the node a and the node B, and the same reason is that the semantic information of both the node B1 and the node C is lane 2, and the split lane 2 includes the node B1 and the node C.
Therefore, the lane can be segmented through semantic information in the mode, and the segmented lane can be guaranteed to be completely matched with an actual geographic structure.
In a specific application scene, signal lamp inquiry can be performed according to each cut lane so as to acquire traffic light information of each lane on a vehicle driving path and avoid traffic violations such as red light running of the vehicle.
According to the semantic inference method for the repeated nodes of the topological graph, which is provided by the embodiment of the application, by combining the repeated nodes in advance and dynamically calculating the semantic information of the repeated nodes according to the navigation result during path searching, the addition of other nodes and edges can be avoided to ensure the node uniqueness, so that the construction process of the topological graph can be simplified, the construction cost of the topological graph is reduced, and the occupation of data storage resources is reduced. In addition, the embodiment of the application can accurately segment each lane in the navigation path by dynamically calculating the semantic information of the repeated node, thereby being convenient for inquiring the traffic light information of each lane.
Further, as a specific implementation of fig. 1, an embodiment of the present application provides a topology graph repeating node semantic inference apparatus, as shown in fig. 4, where the apparatus includes: an acquisition unit 31, a search unit 32, an estimation unit 33, and a segmentation unit 34.
The obtaining unit 31 may be configured to obtain a topology map of the constructed road structure, and a path start point and a path end point, where the topology map is marked with repeated nodes that have completed merging, and semantic information of the repeated nodes in different scenes is recorded.
The searching unit 32 may be configured to perform a path search according to the topology map, the path start point, and the path end point, to obtain a node sequence of the navigation path.
The calculating unit 33 may be configured to determine a repeated node in the node sequence, and dynamically calculate, based on semantic information of a node adjacent to the repeated node in the node sequence, target semantic information of the repeated node in a current scene.
The splitting unit 34 may be configured to split the lanes of the navigation path according to the target semantic information of the repeated node in the current scene, so as to obtain each lane and the corresponding node thereof.
In a specific application scenario, as shown in fig. 5, the calculating unit 33 includes: a determination module 331 and an estimation module 332.
The determining module 331 may be configured to determine a corresponding semantic information pushing manner according to a sequence position of the repeated node in the node sequence.
The calculating module 332 may be configured to dynamically calculate the target semantic information of the repeated node in the current scenario based on the corresponding semantic information pushing manner and the semantic information of the node adjacent to the repeated node.
Further, the calculation module 332 may be specifically configured to determine, if the repeated node in the node sequence is a first node, target semantic information of the first node in the current scene according to semantic information of a second node in the node sequence; if the repeated node in the node sequence is the last node, determining target semantic information of the last node in the current scene according to semantic information of a previous node corresponding to the last node in the node sequence.
Further, the calculation module 332 includes: the device comprises a judgment sub-module, a first determination sub-module and a second determination sub-module.
The judging submodule is used for judging whether the adjacent node of the intermediate node is a repeated node if the repeated node in the node sequence is the intermediate node except the first node and the last node.
The first determining submodule may be configured to, if the neighboring node of the intermediate node is a duplicate node, take the intersection of the semantic information of the intermediate node and the semantic information of the neighboring node according to the semantic information of the intermediate node in different scenes and the semantic information of the neighboring node of the intermediate node in different scenes, and use the semantic information after the intersection as the target semantic information of the intermediate node and the neighboring node.
The second determining submodule may be configured to determine, if the neighboring node of the intermediate node is not a duplicate node, target semantic information of the intermediate node according to semantic information of a previous node or semantic information of a next node of the intermediate node.
Further, the second determining submodule may be specifically configured to determine, if any one of the semantic information of the intermediate node in different scenes is the same as the semantic information of the previous node, the semantic information of the previous node as the target semantic information of the intermediate node, and insert a target node behind the intermediate node, where the semantic information of the target node is the semantic information of the next node; if any semantic information of the intermediate node in the semantic information of different scenes is the same as the semantic information of the following node, determining the semantic information of the following node as target semantic information of the intermediate node, and inserting a target node in front of the intermediate node, wherein the semantic information of the target node is the semantic information of the previous node.
In a specific application scenario, the splitting unit 34 may be specifically configured to split the nodes with the same semantic information into the same lane according to the target semantic information of the repeated node in the current scenario and the semantic information of other nodes in the node sequence, so as to obtain each lane in the navigation path and the nodes corresponding to each lane.
In a specific application scenario, the apparatus further includes: a query unit 35.
The query unit 35 may be configured to query traffic light information corresponding to each lane according to each lane.
It should be noted that, in the other corresponding descriptions of each functional module related to the topology graph repeating node semantic inference device provided by the embodiment of the present application, reference may be made to the corresponding description of the method shown in fig. 1, which is not repeated herein.
Based on the above method as shown in fig. 1, correspondingly, the embodiment of the present application further provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the following steps: obtaining a topological graph of a constructed road structure, and a path starting point and a path ending point, wherein repeated nodes which are already combined are marked in the topological graph, and semantic information of the repeated nodes in different scenes is recorded; according to the topological graph, the path starting point and the path ending point, path searching is carried out to obtain a node sequence of a navigation path; determining repeated nodes in the node sequence, and dynamically calculating target semantic information of the repeated nodes in the current scene based on semantic information of nodes adjacent to the repeated nodes in the node sequence; and carrying out lane segmentation on the navigation path according to the target semantic information of the repeated node in the current scene to obtain each lane and the corresponding node thereof.
Based on the embodiment of the method shown in fig. 1 and the device shown in fig. 4, the embodiment of the application further provides a physical structure diagram of an electronic device, as shown in fig. 6, where the electronic device includes: a processor 41, a memory 42, and a computer program stored on the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43, the processor 41 performing the following steps when said program is executed: obtaining a topological graph of a constructed road structure, and a path starting point and a path ending point, wherein repeated nodes which are already combined are marked in the topological graph, and semantic information of the repeated nodes in different scenes is recorded; according to the topological graph, the path starting point and the path ending point, path searching is carried out to obtain a node sequence of a navigation path; determining repeated nodes in the node sequence, and dynamically calculating target semantic information of the repeated nodes in the current scene based on semantic information of nodes adjacent to the repeated nodes in the node sequence; and carrying out lane segmentation on the navigation path according to the target semantic information of the repeated node in the current scene to obtain each lane and the corresponding node thereof.
According to the embodiment of the application, by combining the repeated nodes in advance and dynamically calculating the semantic information of the repeated nodes according to the navigation result during path searching, the addition of other nodes and edges can be avoided to ensure the node uniqueness, so that the construction process of the topological graph can be simplified, the construction cost of the topological graph can be reduced, and the occupation of data storage resources can be reduced. In addition, the embodiment of the application can accurately segment each lane in the navigation path by dynamically calculating the semantic information of the repeated node, thereby being convenient for inquiring the traffic light information of each lane.
Those of ordinary skill in the art will appreciate that: the drawing is a schematic diagram of one embodiment and the modules or flows in the drawing are not necessarily required to practice the application.
Those of ordinary skill in the art will appreciate that: the modules in the apparatus of the embodiments may be distributed in the apparatus of the embodiments according to the description of the embodiments, or may be located in one or more apparatuses different from the present embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or may be further split into a plurality of sub-modules.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. A topology graph repeating node semantic inference method, comprising:
obtaining a topological graph of a constructed road structure, and a path starting point and a path ending point, wherein repeated nodes which are already combined are marked in the topological graph, and semantic information of the repeated nodes in different scenes is recorded;
according to the topological graph, the path starting point and the path ending point, path searching is carried out to obtain a node sequence of a navigation path;
determining repeated nodes in the node sequence, and dynamically calculating target semantic information of the repeated nodes in the current scene based on semantic information of nodes adjacent to the repeated nodes in the node sequence;
and carrying out lane segmentation on the navigation path according to the target semantic information of the repeated node in the current scene to obtain each lane and the corresponding node thereof.
2. The method according to claim 1, wherein dynamically calculating the target semantic information of the repeated node in the current scene based on the semantic information of the nodes adjacent to the repeated node in the node sequence comprises:
determining a corresponding semantic information pushing mode according to the sequence position of the repeated node in the node sequence;
and dynamically calculating target semantic information of the repeated node in the current scene based on the corresponding semantic information pushing mode and the semantic information of the node adjacent to the repeated node.
3. The method according to claim 2, wherein dynamically calculating the target semantic information of the repeated node in the current scenario based on the corresponding semantic information pushing method and the semantic information of the node adjacent to the repeated node comprises:
if the repeated node in the node sequence is a first node, determining target semantic information of the first node in the current scene according to semantic information of a second node in the node sequence;
if the repeated node in the node sequence is the last node, determining target semantic information of the last node in the current scene according to semantic information of a previous node corresponding to the last node in the node sequence.
4. The method according to claim 2, wherein dynamically calculating the target semantic information of the repeated node in the current scene based on the corresponding semantic information pushing manner and the semantic information of the node adjacent to the repeated node comprises:
if the repeated node in the node sequence is an intermediate node except the first node and the last node, judging whether the adjacent node of the intermediate node is the repeated node or not;
if the adjacent node of the intermediate node is a repeated node, according to the semantic information of the intermediate node in different scenes and the semantic information of the adjacent node of the intermediate node in different scenes, acquiring the intersection of the semantic information of the intermediate node and the adjacent node, and taking the semantic information acquired after the intersection as the target semantic information of the intermediate node and the adjacent node;
if the adjacent node of the intermediate node is not a repeated node, determining target semantic information of the intermediate node according to semantic information of a previous node or semantic information of a next node of the intermediate node.
5. The method of claim 4, wherein determining the target semantic information of the intermediate node based on the semantic information of the previous node or the semantic information of the next node of the intermediate node comprises:
if any semantic information of the intermediate node in the semantic information of different scenes is the same as the semantic information of the previous node, determining the semantic information of the previous node as target semantic information of the intermediate node, and inserting a target node behind the intermediate node, wherein the semantic information of the target node is the semantic information of the next node;
if any semantic information of the intermediate node in the semantic information of different scenes is the same as the semantic information of the following node, determining the semantic information of the following node as target semantic information of the intermediate node, and inserting a target node in front of the intermediate node, wherein the semantic information of the target node is the semantic information of the previous node.
6. The method according to any one of claims 1-5, wherein the performing lane segmentation on the navigation path according to the target semantic information of the repeated node in the current scene to obtain each lane and the corresponding node thereof includes:
and according to the target semantic information of the repeated node in the current scene and the semantic information of other nodes in the node sequence, segmenting the nodes with the same semantic information into the same lane to obtain each lane in the navigation path and the nodes corresponding to each lane.
7. The method according to any one of claims 1-5, further comprising:
and inquiring traffic light information corresponding to each lane according to each lane.
8. A topology graph repeating node semantic inference apparatus, comprising:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a topological graph of a constructed road structure, a path starting point and a path ending point, wherein the topological graph is marked with repeated nodes which are already combined, and semantic information of the repeated nodes in different scenes is recorded;
the searching unit is used for searching the path according to the topological graph, the path starting point and the path ending point to obtain a node sequence of the navigation path;
the calculating unit is used for determining repeated nodes in the node sequence and dynamically calculating target semantic information of the repeated nodes in the current scene based on semantic information of nodes adjacent to the repeated nodes in the node sequence;
and the segmentation unit is used for carrying out lane segmentation on the navigation path according to the target semantic information of the repeated node in the current scene to obtain each lane and the corresponding node thereof.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program when executed by the processor implements the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310906269.5A CN116976356A (en) | 2023-07-24 | 2023-07-24 | Topological graph repeated node semantic inference method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310906269.5A CN116976356A (en) | 2023-07-24 | 2023-07-24 | Topological graph repeated node semantic inference method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116976356A true CN116976356A (en) | 2023-10-31 |
Family
ID=88484421
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310906269.5A Pending CN116976356A (en) | 2023-07-24 | 2023-07-24 | Topological graph repeated node semantic inference method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116976356A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7669147B1 (en) * | 2009-01-02 | 2010-02-23 | International Business Machines Corporation | Reorienting navigation trees based on semantic grouping of repeating tree nodes |
| CN106780735A (en) * | 2016-12-29 | 2017-05-31 | 深圳先进技术研究院 | A kind of semantic map constructing method, device and a kind of robot |
| CN113538950A (en) * | 2021-06-02 | 2021-10-22 | 上海追势科技有限公司 | Parking lot navigation road network generation method for AVP scene |
| CN114116933A (en) * | 2021-11-12 | 2022-03-01 | 同济大学 | Semantic topology joint map building method based on monocular image |
| CN115420296A (en) * | 2022-11-07 | 2022-12-02 | 山东大学 | Path searching method and system based on multi-resolution topological map |
| US20230111516A1 (en) * | 2020-03-27 | 2023-04-13 | Byd Company Limited | Vehicle scheduling method, apparatus and system |
-
2023
- 2023-07-24 CN CN202310906269.5A patent/CN116976356A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7669147B1 (en) * | 2009-01-02 | 2010-02-23 | International Business Machines Corporation | Reorienting navigation trees based on semantic grouping of repeating tree nodes |
| CN106780735A (en) * | 2016-12-29 | 2017-05-31 | 深圳先进技术研究院 | A kind of semantic map constructing method, device and a kind of robot |
| US20230111516A1 (en) * | 2020-03-27 | 2023-04-13 | Byd Company Limited | Vehicle scheduling method, apparatus and system |
| CN113538950A (en) * | 2021-06-02 | 2021-10-22 | 上海追势科技有限公司 | Parking lot navigation road network generation method for AVP scene |
| CN114116933A (en) * | 2021-11-12 | 2022-03-01 | 同济大学 | Semantic topology joint map building method based on monocular image |
| CN115420296A (en) * | 2022-11-07 | 2022-12-02 | 山东大学 | Path searching method and system based on multi-resolution topological map |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11182624B2 (en) | Method, system and memory for constructing transverse topological relationship of lanes in high-definition map | |
| CN108151751B (en) | Path planning method and device based on combination of high-precision map and traditional map | |
| CN112595337B (en) | Obstacle avoidance path planning method and device, electronic device, vehicle and storage medium | |
| US20180149488A1 (en) | Guide route setting apparatus and guide route setting method | |
| US20200262436A1 (en) | Method, device, and terminal apparatus for invoking automatic driving reference line | |
| CN111859587B (en) | Method and device for constructing traffic simulation road network, storage medium and electronic equipment | |
| US20180314901A1 (en) | Non-transitory storage medium storing image transmission program, image transmission device, and image transmission method | |
| CN109726874A (en) | Travel route planing method, calculates equipment and storage medium at device | |
| CN112732844B (en) | Method, apparatus, device and medium for automatically associating road object with road | |
| CN116976356A (en) | Topological graph repeated node semantic inference method and device | |
| CN111483465B (en) | MPP expansion method and device, electronic equipment and storage medium | |
| CN114964293A (en) | Vehicle path planning method and device, electronic equipment and storage medium | |
| CN116295478A (en) | Navigation method and device for vehicle | |
| CN113778102B (en) | AVP global path planning system, method, vehicle and storage medium | |
| CN112344950B (en) | ADAS road network tree fusion method and system, server and medium | |
| CN116045999A (en) | Heterogeneous data matching method and device, vehicle and storage medium | |
| CN117115773B (en) | Stop line generation method, apparatus, electronic device, medium, and program product | |
| CN111486858A (en) | Road network prediction tree construction method and device, electronic equipment and storage medium | |
| CN111486857A (en) | Road network prediction tree construction method and device, electronic equipment and storage medium | |
| CN111811523A (en) | Road network matching error correction method, device and system | |
| CN113255091B (en) | Method and device for establishing path topological relation and related equipment | |
| CN113932795B (en) | Semantic map updating method and device | |
| CN115993124B (en) | Virtual lane line generation method, device, equipment and computer readable storage medium | |
| CN115798218B (en) | Method and device for associating traffic identification information and electronic equipment | |
| CN118293931A (en) | Lane priority determination method, related method and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |