CN114446050B - Distributed lane-level guide line construction method and device - Google Patents
Distributed lane-level guide line construction method and device Download PDFInfo
- Publication number
- CN114446050B CN114446050B CN202111649348.XA CN202111649348A CN114446050B CN 114446050 B CN114446050 B CN 114446050B CN 202111649348 A CN202111649348 A CN 202111649348A CN 114446050 B CN114446050 B CN 114446050B
- Authority
- CN
- China
- Prior art keywords
- lane
- tracks
- intersection
- track
- level
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096855—Systems involving transmission of navigation instructions to the vehicle where the output is provided in a suitable form to the driver
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/0969—Systems involving transmission of navigation instructions to the vehicle having a display in the form of a map
Abstract
The invention relates to a distributed lane-level guide line construction method and a device, wherein intersections and driving-in and driving-out roads thereof are used as an independent unit, all tracks passing through the intersections are collected in each unit in an intersection range, the driving-in roads and the driving-out roads where each track is located are traversed, the driving-in lanes and the driving-out lanes at lane levels are used as grouping labels, and the collection tracks in each group of driving-in and driving-out lanes are counted; finally, according to a set screening strategy, screening a track with universal driving habits from a plurality of tracks as a guide line for communicating the lane; and by analogy, constructing the lane-level communication in each intersection unit so as to complete the construction of the lane-level guide line of the high-precision map. The intersection and the driving-in and driving-out roads connected with the intersection are used as units for division, a single task is basically balanced, a large map can be automatically split into a plurality of mutually balanced tasks, and the lane-level guide line manufacturing efficiency is greatly improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of high-precision maps, in particular to a method and a device for constructing a distributed lane-level guide line.
Background
At present, in the field of automatic driving, lane-level guide lines are used as priori knowledge, a navigation engine is matched to complete lane-level path planning, and then a sensor on an intelligent driving vehicle is matched to sense and match an intelligent driving decision system, so that the automatic driving is decided in real time, and the method is a popular and feasible development direction at present. The lane-level guide line is an indispensable loop, is a main reference for driving a vehicle intelligently under the condition that no obstacles exist nearby, and is unique in a crowdsourcing mode of collecting data through a plurality of vehicles with low-cost collecting equipment on the technical difficulty of quickly generating and updating the lane-level guide line. In a crowd-sourced map, a data source can be covered, can be track data of a floating car of a travel company, can also be data of a passenger car carrying low-cost acquisition equipment and the like, and how to process and digest the data and convert the data into a lane-level guide line in a high-precision map is unrealistic by simply depending on traditional manual drawing. Countermeasures against this background are an automated patterning system capable of reducing labor costs and a distributed system capable of coping with a large amount of data.
At present, in the field of constructing high-precision crowd-sourced maps, a traditional method still divides a large amount of collected data into different scenes such as high-speed scenes, urban scenes and the like according to regions or projects, then divides the scenes into a plurality of small tasks, distributes the small tasks to corresponding cartographers, and finally merges the tasks to finally obtain a high-precision map of a specified region. The defects of the drawing scheme are that the labor cost is too high, the drawing period is too long, the balance degree of distributed tasks is difficult to control, the number of tasks is too large when a single task is too small, frequent drawing task distribution and switching can be caused, and the problem that the load of a single machine and drawing software can support when the single task is too large needs to be considered.
Disclosure of Invention
The invention provides a method and a device for constructing a distributed lane-level guide line, aiming at the technical problems in the prior art.
In order to solve the above technical problem, in a first aspect, an embodiment of the present invention provides a method for constructing a distributed lane-level guide line, including:
s1, traversing intersection data in a high-precision map, constructing a task unit by intersections, and an incoming road and an outgoing road corresponding to the intersections, and dividing the high-precision map into groups;
s2, in each task unit, constructing an intersection buffer area in an intersection shape, collecting all tracks passing through the intersection buffer area, counting an incoming lane and an outgoing lane which each track passes through, carrying out track classification for corresponding tracks based on the combination of the incoming lane and the outgoing lane, and determining lane-level guide lines in each task unit based on different track classifications;
and S3, carrying out same-name road and same-name lane matching on each task unit so as to fuse the task units.
Preferably, the step S1 specifically includes:
and searching road junction points in the high-precision map, taking the road junction points as intersection nodes and roads connected with the intersection nodes as directed edges, and constructing independent task units based on each intersection node and the corresponding directed edge.
Preferably, after collecting all the tracks passing through the intersection buffer in step S2, the method further includes:
performing shape point extraction processing on the track through a Douglas segue algorithm based on a sliding window, and performing shape point encryption on the track;
based on the linear characteristic of the track, the track is subjected to linear clustering analysis through a Fraunhofer distance algorithm, and the flying track is eliminated.
Preferably, in step S2, the classifying the trajectories based on the combination of the entering lane and the exiting lane as the corresponding trajectories specifically includes:
taking a combination of a driving lane and a driving lane at a lane level as a grouping label to classify all the tracks;
classifying each group, cutting the track according to an intersection buffer area, keeping the tracks in the group to have the same driving-in boundary and driving-out boundary, and calculating median points, average points, track lengths, speeds and curvatures of all track points in the group to construct a characteristic matrix;
and marking the optimal grade and the suboptimal grade of each group of classified tracks, performing multi-classification model training based on a characteristic matrix of the tracks, and predicting the optimal track as an alternative guide line of a lane-grade guide line.
Preferably, in step S2, after the predicted optimal trajectory is a candidate guidance line of the lane-level guidance line, the method further includes:
the candidate guideline is classified based on different speed intervals to determine an optimal lane-level guideline for the different speed intervals.
Preferably, the step S3 specifically includes:
and matching every two task units with the same road, and matching every two matched task units until all the task units are matched.
Preferably, in step S2, the labeling of the optimal level and the suboptimal level for the trajectory of each group of classifications specifically includes:
and (4) carrying out true value calibration on the tracks, carrying out priority grade labeling on the tracks classified in each group, selecting 10% of the tracks as an optimal grade, selecting 20% of the tracks as a suboptimal grade, and marking the rest tracks as non-recommended.
In a second aspect, an embodiment of the present invention provides a distributed lane-level guide line constructing apparatus, including:
the multi-task dividing module is used for traversing intersection data in the high-precision map, constructing a task unit by the intersection, an incoming road and an outgoing road corresponding to the intersection, and dividing the high-precision map in groups;
the single-task lane level guide line construction module is used for constructing an intersection buffer area in an intersection shape in each task unit, collecting all tracks passing through the intersection buffer area, counting an incoming lane and an outgoing lane which each track passes through, carrying out track classification on the corresponding tracks based on the combination of the incoming lane and the outgoing lane, and determining a lane level guide line in each task unit based on different track classifications;
and the multi-task fusion module is used for matching the same-name roads and the same-name lanes of the task units so as to fuse the task units.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the distributed lane-level guideline construction method according to the embodiment of the first aspect of the present invention when executing the program.
In a fourth aspect, embodiments of the present invention provide a non-transitory computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the distributed lane-level guideline construction method according to embodiments of the first aspect of the present invention.
The invention has the beneficial effects that: the track with universality is screened as a lane-level guide line of the crowdsourcing map through deep learning and statistical analysis models of mass track data, so that the manufacturing efficiency is greatly improved; compared with the traditional mapping based on task division and distribution of cartographers, the intersection and the driving-in and driving-out roads connected with the intersection are divided as units, a single task is basically balanced, and a large map can be automatically split into a plurality of mutually balanced tasks; the lane-level guide line screened by the deep learning and statistical analysis model of a plurality of collected vehicle track data is more real than the guide line fitted by a logic algorithm, and is more in line with the driving habits of human beings.
Drawings
FIG. 1 is a flow chart of a distributed lane-level guideline construction method according to an embodiment of the invention;
FIG. 2 is a detailed flowchart of a method for constructing a distributed lane-level guideline according to an embodiment of the invention;
FIG. 3 is a schematic diagram of an electronic device according to an embodiment of the invention;
fig. 4 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, in the field of constructing high-precision crowd-sourced maps, a traditional method still divides a large amount of collected data into different scenes such as high-speed scenes, urban scenes and the like according to regions or projects, then divides the scenes into a plurality of small tasks, distributes the small tasks to corresponding cartographers, and finally merges the tasks to finally obtain a high-precision map of a specified region. The defects of the drawing scheme are that the labor cost is too high, the drawing period is too long, the balance degree of distributed tasks is difficult to control, the number of tasks is too large when a single task is too small, frequent distribution and switching of drawing tasks can be caused, and the problem that the load of a single machine and drawing software can support when the single task is too large needs to be considered.
In order to realize the lane-level guide line for generating a high-precision map by quickly allocating tasks at low cost, the embodiment of the invention provides a method and a device for constructing a distributed lane-level guide line, which divide a crossing and an incoming and outgoing road connected with the crossing as units, wherein a single task is basically balanced, and a large map can be automatically split into a plurality of mutually balanced tasks; the lane-level guide line screened by the deep learning and statistical analysis model of a plurality of collected vehicle track data is more real than the guide line fitted by a logic algorithm, and is more in line with the driving habits of human beings. The following description and description will proceed with reference being made to several embodiments.
Fig. 1 to fig. 2 provide a method for constructing a distributed lane-level guide line according to an embodiment of the present invention, including:
s1, traversing intersection data in a high-precision map, constructing a task unit by using intersections, and incoming roads and outgoing roads corresponding to the intersections, and dividing the high-precision map into groups;
collecting and sorting road-level elements, mainly comprising intersections, roads and topological communication in the roads, searching road junction points in a high-precision map, taking the road junction points as intersection nodes and the roads connected with the intersection nodes as directed edges, and constructing independent task units based on each intersection node and the corresponding directed edge.
In the embodiment, the intersection (road junction) and the driving-in road and the driving-out road thereof are taken as an independent task unit; based on the idea of the directed graph structure, road junction points are used as intersection nodes, connected roads are used as directed edges of the intersection nodes, each intersection node and the directed edge connected with the intersection node are independent task units, and the construction of the whole directed graph structure can be completed by the connection of the directed edges with the same name. In this embodiment, the intersection data is traversed, the incoming roads and the outgoing roads of each intersection are counted, and the intersections are grouped according to the intersections, wherein each intersection is a task unit.
S2, in each task unit, constructing an intersection buffer area in an intersection shape, collecting all tracks passing through the intersection buffer area, counting an incoming lane and an outgoing lane which each track passes through, carrying out track classification for corresponding tracks based on the combination of the incoming lane and the outgoing lane, and determining lane-level guide lines in each task unit based on different track classifications;
in a single task unit, a buffer area with a certain distance is built in a crossing shape, all tracks passing through the buffer area are collected according to the range of the buffer area, and in consideration of the multi-source of crowdsourcing data sources, the situations that the space and precision of the tracks in different data are unstable, flying possibly exists, a large number of repeated points are caused by parking, the point space caused by signal difference is unstable, and the like, some denoising pretreatment needs to be carried out on the track data. In the embodiment, firstly, the track is subjected to thinning through a Douglas-Puck (Douglas-Peuker) algorithm based on a sliding window, the problem that the distance between a repetition point and a point is too close is solved, and on the basis of thinning of track points, the track is subjected to shape point encryption, wherein the step mainly aims at an excessively sparse area, for example, only two points, namely the head and the tail, are left in a straight section, so that the track is ensured to keep the close shape point distance in a curve, and the straight track is ensured to keep the relatively uniform and moderate shape point distance. And then according to the linear characteristic of the track, performing clustering analysis on the track through Frechet Distance, and removing the obviously flying track.
And counting the entering lanes and the exiting lanes penetrated by each track, and classifying all tracks by taking the combination of the entering lanes and the exiting lanes at lane level as a grouping label. And for each group of classified tracks, cutting the tracks according to the intersection buffer area, keeping the tracks in the group to have the same driving-in boundary and driving-out boundary, calculating information such as median points and average points of all track points in the group, the length of the tracks, the speed and curvature of the tracks and the like, and constructing a feature matrix of a track screening model according to the information, and screening and predicting.
In the embodiment, the real-valued calibration is performed on the tracks, priority levels are labeled on the tracks of each group of classified tracks, 10% of the tracks are selected to be labeled as the optimal level, 20% of the tracks are labeled as the suboptimal level, the rest of the tracks are not recommended, a multi-classification model is used for training according to the characteristic matrix of the tracks, and the tracks predicted as the optimal level are all alternative guide lines of lane-level guide lines. And subsequently, adding sub-classification based on the speed interval to provide an optimal lane-level guide line for different speed intervals.
Collecting all tracks passing through the intersection in an intersection range, traversing the number one lane of an incoming road and the number one lane of an outgoing road where each track is located, taking lane-level incoming lanes and lane-level outgoing lanes as grouping labels, and counting the collected tracks in each group of incoming and outgoing lanes; and finally, screening a track with universal driving habits from a plurality of tracks as a guide line for communicating the lane according to a set screening strategy. By analogy, under the condition that the lane-level communication in each intersection unit is constructed, a lane-level guide line of a high-precision map can be constructed.
And S3, carrying out same-name road and same-name lane matching on each task unit so as to fuse the task units.
A plurality of task units divided by intersections can be quickly executed in the distributed system, the time required for processing complete data is proportional to the number of nodes of the distributed system, and when the distributed nodes are transversely expanded, the efficiency is not used.
Aiming at data fusion of a plurality of task units, the embodiment of the invention matches the same-name roads and the same-name lanes, can regard each task unit as an element by virtue of the idea of stacking and sorting, and the fusion process is that every two task units with the same-name lanes are matched and then matched with other task units with the same-name lanes until the fusion is completed.
The embodiment of the present invention further provides a distributed lane-level guide line constructing device, and the distributed lane-level guide line constructing method based on the embodiment includes:
the multi-task dividing module is used for traversing intersection data in the high-precision map, constructing a task unit by the intersection, an incoming road and an outgoing road corresponding to the intersection, and dividing the high-precision map in groups;
the single-task lane level guide line construction module is used for constructing an intersection buffer area in an intersection shape in each task unit, collecting all tracks passing through the intersection buffer area, counting an incoming lane and an outgoing lane which each track passes through, classifying the tracks for the corresponding tracks based on the combination of the incoming lane and the outgoing lane, and determining the lane level guide lines in each task unit based on different track classifications;
and the multi-task fusion module is used for matching the same-name roads and the same-name lanes of each task unit so as to fuse the plurality of task units.
Referring to fig. 3, fig. 3 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the invention. As shown in fig. 3, an embodiment of the present invention provides an electronic device 500, which includes a memory 510, a processor 520, and a computer program 511 stored in the memory 520 and capable of running on the processor 520, where the processor 520 executes the computer program 511 to implement the following steps:
s1, traversing intersection data in a high-precision map, constructing a task unit by using intersections, and incoming roads and outgoing roads corresponding to the intersections, and dividing the high-precision map into groups;
s2, in each task unit, constructing an intersection buffer area in an intersection shape, collecting all tracks passing through the intersection buffer area, counting an incoming lane and an outgoing lane which each track passes through, carrying out track classification for corresponding tracks based on the combination of the incoming lane and the outgoing lane, and determining lane-level guide lines in each task unit based on different track classifications;
and S3, matching the same-name roads and the same-name lanes of each task unit so as to fuse a plurality of task units.
Referring to fig. 4, fig. 4 is a schematic diagram illustrating an embodiment of a computer-readable storage medium according to the present invention. As shown in fig. 4, the present embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored, the computer program 611 implementing the following steps when executed by a processor:
s1, traversing intersection data in a high-precision map, constructing a task unit by intersections, and an incoming road and an outgoing road corresponding to the intersections, and dividing the high-precision map into groups;
s2, in each task unit, constructing an intersection buffer area in an intersection shape, collecting all tracks passing through the intersection buffer area, counting an incoming lane and an outgoing lane which each track passes through, carrying out track classification on the basis of the combination of the incoming lane and the outgoing lane as corresponding tracks, and determining lane-level guide lines in each task unit on the basis of different track classifications;
and S3, matching the same-name roads and the same-name lanes of each task unit so as to fuse a plurality of task units.
It should be noted that, in the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to relevant descriptions of other embodiments for parts that are not described in detail in a certain embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. A distributed lane-level guideline construction method, comprising:
s1, traversing intersection data in a high-precision map, constructing a task unit by using intersections, and incoming roads and outgoing roads corresponding to the intersections, and dividing the high-precision map into groups;
s2, in each task unit, constructing an intersection buffer area in an intersection shape, collecting all tracks passing through the intersection buffer area, counting an entering lane and an exiting lane which each track passes through, and classifying the tracks for corresponding tracks based on the combination of the entering lane and the exiting lane, wherein the method specifically comprises the following steps:
taking a combination of a driving lane and a driving lane at a lane level as a grouping label to classify all the tracks;
classifying each group, cutting the tracks according to the intersection buffer area, keeping the tracks in the group to have the same entrance boundary and exit boundary, and calculating median points, average points, track lengths, speeds and curvatures of all track points in the group to construct a characteristic matrix;
marking the optimal grade and the suboptimal grade of each group of classified tracks, performing multi-classification model training based on a characteristic matrix of the tracks, predicting the optimal track as a candidate guide line of a lane-grade guide line, and classifying the candidate guide line based on different speed intervals to determine the optimal lane-grade guide line of the different speed intervals;
to determine lane-level guidelines within each task unit based on different trajectory classifications;
and S3, carrying out same-name road and same-name lane matching on each task unit so as to fuse the task units.
2. The method for constructing a distributed lane-level guidance line according to claim 1, wherein the step S1 specifically comprises:
and searching road junction points in the high-precision map, taking the road junction points as intersection nodes and roads connected with the intersection nodes as directed edges, and constructing independent task units based on each intersection node and the corresponding directed edge.
3. The method for constructing distributed lane-level guidance lines according to claim 1, wherein in step S2, after collecting all the tracks passing through the intersection buffer, the method further comprises:
performing shape point extraction processing on the track through a sliding window-based Douglas pock algorithm, and performing shape point encryption on the track;
based on the linear characteristic of the track, the track is subjected to linear clustering analysis through a Fraunhofer distance algorithm, and the flying track is eliminated.
4. The distributed lane-level guideline construction method of claim 1, wherein the step S3 specifically comprises:
and matching every two task units with the same road name, and matching every two matched task units until all the task units are matched.
5. The method for constructing a distributed lane-level guideline according to claim 1, wherein in step S2, the marking of the optimal level and the suboptimal level is performed on each group of classified tracks, and specifically comprises:
and (4) carrying out true value calibration on the tracks, carrying out priority grade labeling on the tracks classified in each group, selecting 10% of the tracks as an optimal grade, 20% of the tracks as a suboptimal grade, and marking the rest tracks as not recommended.
6. A distributed lane-level guideline constructing apparatus, comprising:
the multi-task dividing module is used for traversing intersection data in the high-precision map, constructing a task unit by the intersection, an incoming road and an outgoing road corresponding to the intersection, and dividing the high-precision map in groups;
the single-task lane level guide line building module builds an intersection buffer area in an intersection shape in each task unit, collects all tracks passing through the intersection buffer area, counts an entering lane and an exiting lane which each track passes through, and classifies the tracks for the corresponding tracks based on the combination of the entering lane and the exiting lane, and specifically comprises the following steps:
taking a combination of a driving lane and a driving lane at a lane level as a grouping label to classify all the tracks;
classifying each group, cutting the track according to an intersection buffer area, keeping the tracks in the group to have the same driving-in boundary and driving-out boundary, and calculating median points, average points, track lengths, speeds and curvatures of all track points in the group to construct a characteristic matrix;
marking the optimal grade and the suboptimal grade of each group of classified tracks, performing multi-classification model training based on a characteristic matrix of the tracks, predicting the optimal track as a candidate guide line of a lane-grade guide line, and classifying the candidate guide line based on different speed intervals to determine the optimal lane-grade guide line of the different speed intervals;
to determine lane-level guidelines within each task unit based on different trajectory classifications;
and the multi-task fusion module is used for matching the same-name roads and the same-name lanes of each task unit so as to fuse the plurality of task units.
7. An electronic device, comprising:
a memory for storing a computer software program;
a processor for reading and executing the computer software program, thereby implementing the distributed lane-level guideline construction method of any one of claims 1-5.
8. A non-transitory computer readable storage medium, characterized in that the storage medium has stored therein a computer software program for implementing the distributed lane-level guideline construction method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111649348.XA CN114446050B (en) | 2021-12-29 | 2021-12-29 | Distributed lane-level guide line construction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111649348.XA CN114446050B (en) | 2021-12-29 | 2021-12-29 | Distributed lane-level guide line construction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114446050A CN114446050A (en) | 2022-05-06 |
| CN114446050B true CN114446050B (en) | 2023-01-13 |
Family
ID=81366406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111649348.XA Active CN114446050B (en) | 2021-12-29 | 2021-12-29 | Distributed lane-level guide line construction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114446050B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105651295A (en) * | 2016-01-15 | 2016-06-08 | 武汉光庭信息技术股份有限公司 | Connection curve algorithm for constructing intersection entry and exit lane Links based on Bezier curve |
| DE102018209978A1 (en) * | 2018-06-20 | 2019-12-24 | Robert Bosch Gmbh | Automatic crossing of an intersection area |
| CN111177927A (en) * | 2019-12-31 | 2020-05-19 | 武汉中海庭数据技术有限公司 | Vehicle reference driving line construction method, electronic device and storage medium |
| CN111238497A (en) * | 2018-11-29 | 2020-06-05 | 华为技术有限公司 | High-precision map construction method and device |
| CN112487128A (en) * | 2020-12-12 | 2021-03-12 | 武汉中海庭数据技术有限公司 | Intersection guide line generation method and system, electronic device and storage medium |
| CN113168762A (en) * | 2018-12-06 | 2021-07-23 | 日立安斯泰莫株式会社 | Vehicle travel support method, vehicle travel support device, and automatic driving system |
| WO2021169993A1 (en) * | 2020-02-29 | 2021-09-02 | 华为技术有限公司 | Method for constructing self-driving map and related device |
| CN113701777A (en) * | 2021-08-28 | 2021-11-26 | 浙江省测绘科学技术研究院 | High-precision map lane associated trajectory line automatic generation method based on space vector |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102267563B1 (en) * | 2018-11-29 | 2021-06-23 | 한국전자통신연구원 | Autonomous Driving Method and the System |
| KR20210097869A (en) * | 2020-01-30 | 2021-08-10 | 현대자동차주식회사 | Method and apparatus for controlling a driving guideline of vehicle moving object |
| CN112504286B (en) * | 2020-11-14 | 2022-03-25 | 武汉中海庭数据技术有限公司 | Path planning method and system based on guideline layer, server and medium |
-
2021
- 2021-12-29 CN CN202111649348.XA patent/CN114446050B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105651295A (en) * | 2016-01-15 | 2016-06-08 | 武汉光庭信息技术股份有限公司 | Connection curve algorithm for constructing intersection entry and exit lane Links based on Bezier curve |
| DE102018209978A1 (en) * | 2018-06-20 | 2019-12-24 | Robert Bosch Gmbh | Automatic crossing of an intersection area |
| CN111238497A (en) * | 2018-11-29 | 2020-06-05 | 华为技术有限公司 | High-precision map construction method and device |
| CN113168762A (en) * | 2018-12-06 | 2021-07-23 | 日立安斯泰莫株式会社 | Vehicle travel support method, vehicle travel support device, and automatic driving system |
| CN111177927A (en) * | 2019-12-31 | 2020-05-19 | 武汉中海庭数据技术有限公司 | Vehicle reference driving line construction method, electronic device and storage medium |
| WO2021169993A1 (en) * | 2020-02-29 | 2021-09-02 | 华为技术有限公司 | Method for constructing self-driving map and related device |
| CN112487128A (en) * | 2020-12-12 | 2021-03-12 | 武汉中海庭数据技术有限公司 | Intersection guide line generation method and system, electronic device and storage medium |
| CN113701777A (en) * | 2021-08-28 | 2021-11-26 | 浙江省测绘科学技术研究院 | High-precision map lane associated trajectory line automatic generation method based on space vector |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114446050A (en) | 2022-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108364467B (en) | Road condition information prediction method based on improved decision tree algorithm | |
| EP2410294A1 (en) | Method and device for providing cost information associated with junctions and method of determining a route | |
| CN109902899B (en) | Information generation method and device | |
| CN101965601B (en) | Driving support device and driving support method | |
| CN109459045B (en) | Improved interactive voting matching method for low-frequency GPS track | |
| CN108961758B (en) | Road junction widening lane detection method based on gradient lifting decision tree | |
| CN110634299B (en) | Urban traffic state fine division and identification method based on multi-source track data | |
| CN110232335A (en) | Driving Scene classification method and electronic equipment | |
| CN111351499B (en) | Path identification method and device, computer equipment and computer readable storage medium | |
| CN110716529A (en) | Automatic generation method and device for automatic driving test case | |
| CN111554105A (en) | Intelligent traffic identification and statistics method for complex traffic intersection | |
| CN113989784A (en) | Road scene type identification method and system based on vehicle-mounted laser point cloud | |
| CN110021161B (en) | Traffic flow direction prediction method and system | |
| CN103680185B (en) | A kind of vehicle travel level precise division method | |
| CN114724377A (en) | Unmanned vehicle guiding method and system based on vehicle-road cooperation technology | |
| CN110675646B (en) | Method and device for acquiring position of bus station | |
| CN109489679A (en) | A kind of arrival time calculation method in guidance path | |
| CN115795808A (en) | Automatic driving decision dangerous scene generation method, system, equipment and medium | |
| Park et al. | Intelligent speed profile prediction on urban traffic networks with machine learning | |
| CN114446050B (en) | Distributed lane-level guide line construction method and device | |
| CN109670085B (en) | Method for judging vehicle collision accident grade | |
| CN111368465A (en) | Unmanned decision-making method based on ID3 decision tree | |
| CN115718702A (en) | Automatic driving test scene library construction method and system | |
| CN114495486A (en) | Microscopic traffic flow prediction system and method based on hierarchical reinforcement learning | |
| CN114462609A (en) | Floating car data track reduction method based on hidden Markov model |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |