CN110276973A - A kind of crossing traffic rule automatic identifying method - Google Patents
A kind of crossing traffic rule automatic identifying method Download PDFInfo
- Publication number
- CN110276973A CN110276973A CN201910659720.1A CN201910659720A CN110276973A CN 110276973 A CN110276973 A CN 110276973A CN 201910659720 A CN201910659720 A CN 201910659720A CN 110276973 A CN110276973 A CN 110276973A
- Authority
- CN
- China
- Prior art keywords
- crossing
- track
- data point
- vehicle data
- traffic
- 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.)
- Granted
Links
Classifications
-
- 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
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
- G08G1/096725—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information generates an automatic action on the vehicle control
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
A kind of crossing traffic rule automatic identifying method, belongs to field of intelligent transportation technology.Method includes step S01, according to the driving trace that the track of vehicle data point of each vehicle ID according to time sequence is formed, determines the tracing point that vehicle heading changes；Step S02 calculates the difference of tracing point with the track of vehicle data point before driving direction change, determines the track of vehicle data point that tracing point is crossing turning and is retained；Step S03 is clustered for the track of vehicle data point of crossing turning, identifies traffic intersection and crossing type；Step S04, to the quantity of track of vehicle data point that each traffic intersection statistics turns left, turns right, turns around, and whether the traffic rules of determination traffic intersection are no turning left, no turning right, no turning around.The present invention can automatically identify the control information at all traffic intersections and crossing, provide the application demand of accurate safety navigation in real time to be automatically unmanned, avoid traffic congestion, reduce pollution, protection environment.
Description
Technical field
The invention belongs to field of intelligent transportation technology, especially a kind of crossing traffic rule automatic identifying method.
Background technique
The research of automatic Pilot technology has attracted extensive concern, becomes the hot spot of the research of associated specialist scholar.
Wherein vehicle driving safety is one of house keeper's problem in automatic Pilot, if safe in road network environment to autonomous driving vehicle
Self-navigation is also the emphasis of brainstrust research, therefore real-time route planning is a key technology of autonomous driving vehicle.Automatically it leads
The traffic capacity that boat system can guide car that optimal path is selected to increase existing road network by avoiding congested link.And
In real-time navigation system, traffic rules, crossing especially is in urban environment in traffic control system, traffic rules performer
Important role.However, not only having one-way road, two-way street, multilevel traffic etc. in city road network.With the increasing of car quantity
Add, congestion is inevitable.Some traffic controls can be usually arranged in the excessive congestion in some section, traffic management department in order to prevent
The traffic pressure in some section, such as no left turn are alleviated in measure, and no right turn, no turns.For example it is set at some crossing
It sets: 6:00 to 18:00 no left turn.This traffic control measure is likely to be interim a period of time effectively, or suddenly some
Add such control measure in crossing.It updates once within the update of map general 3-6 months, therefore navigation system can not obtain in time
These information, to will not take into account this information when selecting optimal path, it is possible to just forbid leading to comprising this
Walking along the street diameter.It can generate if it is autonomous driving vehicle and drive in violation of rules and regulations, and for manned automobile, it also faces and has to temporarily
Change and walk other roads, not only increase running time in this way, it is also possible to congestion is caused, the problems such as environmental pollution.
At the beginning of application for a patent for invention CN201610458509.X discloses a kind of K-means for taxi track data
Beginning cluster centre selection method, by the matched road network of car, then according to whether there is a large amount of tracks of vehicle to be not matched to ground
On the road network of figure, to detect to newly increase road.This mode is only used for updating information of the map about new added road, can not
Know the different control of traffic intersection.
Summary of the invention
In view of the problems of the existing technology the present invention, proposes a kind of crossing traffic rule automatic identifying method, can be certainly
The control information at the dynamic all traffic intersections for identifying city road network and crossing, to provide real-time standard to be automatically unmanned
The application demand of true safety navigation, it is possible to prevente effectively from traffic congestion occurs, and reduces pollution, protects environment.
The technical scheme is that:
The present invention provides a kind of crossing traffic rule automatic identifying method, comprising:
Step S01 determines vehicle row according to the driving trace that the track of vehicle data point of each vehicle ID according to time sequence is formed
Sail the tracing point of direction change；
Step S02 calculates the difference of tracing point with the track of vehicle data point before driving direction change, determines that tracing point is road
The track of vehicle data point of mouth turning is simultaneously retained；
Step S03 is clustered for the track of vehicle data point of crossing turning, identifies traffic intersection and crossing type；
Step S04, to the quantity of track of vehicle data point that each traffic intersection statistics turns left, turns right, turns around, and determination traffic
Whether the traffic rules at crossing are no turning left, no turning right, no turning around.
The present invention collects a large amount of GPS track information using vehicle travel process, to mention to the application based on track data
Extensive prospect is supplied.This method can automatically identify city road by mining analysis one day track of vehicle data
All traffic intersections of net and the control information at crossing.
Preferably, the method for the present invention further includes step S05, the traffic rules and intersection information are sent to navigation system
System.
Preferably, the step S01 includes:
Step S11 acquires vehicle track data point according to each vehicle ID and according to time sequence forms the traveling rail of each vehicle
Mark；
Step S12 searches the track of vehicle data point that vehicle heading changes in each vehicle driving trace, and this is determined
For tracing point.
Preferably, track of vehicle data point includes GPS coordinate, travel speed, traveling angle, time.
Preferably, the step S02 includes:
The operating range of step S21, calculating tracing point and the track of vehicle data point before driving direction change is poor, travels angle
Difference, time difference；
Step S22 then confirms track when operating range is poor, travels differential seat angle, the time difference respectively meets crossing turning condition
Point is the track of vehicle data point of crossing turning, is otherwise not belonging to the track of vehicle data point of crossing turning；
Step S23, filtering are not belonging to the track of vehicle data point of crossing turning and retain the track of vehicle data point of crossing turning.
Preferably, the crossing turning condition are as follows: travel speed difference is 20-60 seconds；It travels differential seat angle and is greater than 90 degree；Row
Distance is sailed more than 100 meters.
Preferably, the step S03 includes:
Step S31, for the track of vehicle data point of crossing turning, density-based algorithms are clustered；
Step S32 automatically identifies urban road crossing and crossing type according to clustering algorithm, and crossing type includes crossroad, X
Shape crossing, Y shape crossing, road circuits, T shape crossing.
Preferably, the step S04 includes:
Step S41, according to the different directions of traffic intersection, count left-hand rotation differential seat angle be -90 spend, right-hand rotation differential seat angle is 90 degree, falls
Head differential seat angle is the quantity of the track of vehicle data point of 180 degree；
Step S42, if the quantity that left-hand rotation differential seat angle is the track of vehicle data points of -90 degree is equal to 0, traffic intersection herein
Traffic rules are no left turn；If the quantity for the track of vehicle data point that right-hand rotation differential seat angle is 90 degree is equal to 0, traffic herein
The traffic rules at crossing are no right turn；If the differential seat angle that turns around is equal to 0 for the quantity of the track of vehicle data point of 180 degree, this
The traffic rules for locating traffic intersection are that no turns.
Preferably, the track of vehicle data point is obtained by being equipped with the vehicle real-time detection of GPS.
The invention has the following advantages:
A kind of crossing traffic rule automatic identifying method of the present invention,
1, there is real-time, it is only necessary to which outlet traffic control information both can detecte according to one day Floating Car track data.
To provide accurate navigation information for the navigation of automatic Pilot, avoid in violation of rules and regulations.And traditional navigation system, it is necessary to rely on map
Update could update navigation information.
2, the traffic intersection of urban road can be found automatically.It is handed over by density-based algorithms real-time detection city
The type at access mouth and crossing.
3, it does not need to carry out bus or train route matching primitives, traditional method needs to be matched to road to the tracing point of car first
On, there are two disadvantages, first is that calculating is at high cost, but precision is low, and bus or train route matching is restricted by urban canyons or GPS point precision,
It is not high to match accuracy.
4, real-time traffic control information can be provided for unmanned self-navigation, so that traffic violations are avoided, it can also
To provide accurate real-time navigation for normal driver, so that section of avoiding that no through traffic, reduces traffic congestion, reduces carbon emission, section
The about energy.
Detailed description of the invention
Fig. 1 is a kind of overall block flow diagram of crossing traffic rule automatic identifying method of the present invention；
Fig. 2 is the schematic diagram of crossing turning path point.
Specific embodiment
Following is a specific embodiment of the present invention in conjunction with the accompanying drawings, technical scheme of the present invention will be further described,
However, the present invention is not limited to these examples.
Such as Fig. 1, a kind of crossing traffic rule automatic identifying method of the present invention, comprising:
Step S01 determines vehicle row according to the driving trace that the track of vehicle data point of each vehicle ID according to time sequence is formed
Sail the tracing point of direction change；
Step S02 calculates the difference of tracing point with the track of vehicle data point before driving direction change, determines that tracing point is road
The track of vehicle data point of mouth turning is simultaneously retained；
Step S03 is clustered for the track of vehicle data point of crossing turning, identifies traffic intersection and crossing type；
Step S04, to the quantity of track of vehicle data point that each traffic intersection statistics turns left, turns right, turns around, and determination traffic
Whether the traffic rules at crossing are no turning left, no turning right, no turning around.
The track of vehicle data point of this method is to acquire acquisition in real time using the vehicle for being equipped with GPS gathers terminal.Vehicle
A large amount of GPS track information are collected in the process of moving.
Specifically, the step S01 includes:
Step S11 acquires vehicle track data point according to each vehicle ID and according to time sequence forms the traveling rail of each vehicle
Mark；
Step S12 searches the track of vehicle data point that vehicle heading changes in each vehicle driving trace, and this is determined
For tracing point.
The track of vehicle data point includes GPS coordinate, travel speed, traveling angle, time.Each vehicle has correspondence
Vehicle ID, the track of vehicle data point under corresponding vehicle ID is all with vehicle ID index.For this purpose, can be seen according to time-sequencing
Track of vehicle data point under to corresponding vehicle ID arranges to form driving trace with time sequencing.Driving trace is limited due to road
System, and there are on-rectilinear movement track, if crossing is turned, offset of turning as caused by lane change, as road it is not straight caused by
Situations such as traveling turning deviates, and traveling turning deviates caused by the position as travelled destination.In the case, for adjacent
Vehicle heading variation occurs for the track of vehicle data point of time, then the track of vehicle data of driving direction variation will occur
Point is determined as tracing point.
Since there are the offsets of above-mentioned various situations, if only detection travels differential seat angle to judge whether tracing point is that crossing turns
If curved track of vehicle data point, it is possible that detection error, such as by the track of vehicle data point of lane change in normally travel
Or the track of vehicle data point into parking lot or the track of vehicle data point into gas station etc. other be not belonging to crossing turning vehicle
Track data point considers then count error at that, can not effectively carry out subsequent crossing traffic rule and identify.For this purpose, not
Only to consider to travel differential seat angle, it is also contemplated that other factors.
Specifically, the step S02 includes:
The operating range of step S21, calculating tracing point and the track of vehicle data point before driving direction change is poor, travels angle
Difference, time difference；
Step S22 then confirms track when operating range is poor, travels differential seat angle, the time difference respectively meets crossing turning condition
Point is the track of vehicle data point of crossing turning, is otherwise not belonging to the track of vehicle data point of crossing turning；
Step S23, filtering are not belonging to the track of vehicle data point of crossing turning and retain the track of vehicle data point of crossing turning.
The crossing turning condition are as follows: travel speed difference is 20-60 seconds；It travels differential seat angle and is greater than 90 degree；Operating range is super
Cross 100 meters.Only the case where three's condition is all satisfied, above-mentioned special case could be excluded, it is ensured that qualified tracing point is road
The track of vehicle data point of mouth turning.
The operating range difference is calculated by Pythagorean theorem and is obtained using the GPS coordinate of two track of vehicle data points,
Also the product that can use travel speed difference and running time difference calculates.
Specifically, the step S03 includes:
Step S31, for the track of vehicle data point of crossing turning, density-based algorithms are clustered；
Step S32 automatically identifies urban road crossing and crossing type according to clustering algorithm, and crossing type includes crossroad, X
Shape crossing, Y shape crossing, road circuits, T shape crossing.
DBSCAN clustering algorithm can be used in density-based algorithms.First using each data point as the center of circle, with
Eps describes a circle for radius.This circle is referred to as the eps neighborhood of xi.Secondly, being carried out to the point for including in this circle
It counts.If the number of the point inside a circle has been more than density threshold MinPts, the center of circle of the circle is denoted as core
Heart point, also known as kernel object.If the number put in the eps neighborhood of some point is less than density threshold but falls in core point
In neighborhood, then the point is referred to as boundary point.It is exactly noise spot neither core point is also not the point of boundary point.Third, core point
All points in the eps neighborhood of xi are all that the direct density of xi is through.Finally, if making xi and xj for xk
Can be reachable by xk density, then, just xi with xj density is claimed to be connected.The point that density is connected is linked together, is just formed
Our clustering cluster.All traffic intersections and crossing type of city road network are formed after cluster.Traffic intersection, crossing class
Type constitutes intersection information.
Under an embodiment, the step S04 includes:
Step S41, according to the different directions of traffic intersection, count left-hand rotation differential seat angle be -90 spend, right-hand rotation differential seat angle is 90 degree, falls
Head differential seat angle is the quantity of the track of vehicle data point of 180 degree；
Step S42, if the quantity that left-hand rotation differential seat angle is the track of vehicle data points of -90 degree is equal to 0, traffic intersection herein
Traffic rules are no left turn；If the quantity for the track of vehicle data point that right-hand rotation differential seat angle is 90 degree is equal to 0, traffic herein
The traffic rules at crossing are no right turn；If the differential seat angle that turns around is equal to 0 for the quantity of the track of vehicle data point of 180 degree, this
The traffic rules for locating traffic intersection are that no turns.
When having the case where left-hand rotation, turn right, turn around there is no track of vehicle data point, then it is assumed that this crossing is to forbid a left side
Turn, turn right, turn around.
However in this case, there may be crossing type be T junction, can only turn right or keep straight on from a crossing
When, necessarily there is no the possibility turned left, then when the quantity for the track of vehicle data point that left-hand rotation differential seat angle is -90 degree is equal to 0, then
The traffic rules of Jia Tonglukou herein are judged as no left turn, there is misjudgment, i.e., the friendship of no left turn is not present herein
Drift is then.
For this purpose, can first judge crossing type and crossing driving direction before judging quantity.Judge whether crossing type is T
If then judging vehicle intersection driving direction, if driving direction only has straight and turning left, no right turn is not present in word crossing,
It reduces the quantity of such situation automatically when carrying out subsequent right-hand rotation angle difference amount statistics or driving direction is only kept straight on and the right side
Turn, reduces the quantity of such situation automatically when carrying out subsequent left-hand rotation differential seat angle quantity statistics.For other crossing types, then press
According to above-mentioned steps normal statistics quantity.
The method of the present invention further include: step S05, the traffic rules and intersection information are sent to navigation system.In the presence of
The crossing of traffic rules, updated information are sent to navigation system, and then about all traffic intersections on real-time update map
Control information, in order to it is automatic it is unmanned can accurate safety navigation.
It should be understood by those skilled in the art that foregoing description and the embodiment of the present invention shown in the drawings are only used as illustrating
And it is not intended to limit the present invention.The purpose of the present invention completely effectively realizes.Function and structural principle of the invention is in reality
It applies and shows and illustrate in example, under without departing from the principle, embodiments of the present invention can have any deformation or modification.
Claims (9)
1. a kind of crossing traffic rule automatic identifying method characterized by comprising
Step S01 determines vehicle row according to the driving trace that the track of vehicle data point of each vehicle ID according to time sequence is formed
Sail the tracing point of direction change；
Step S02 calculates the difference of tracing point with the track of vehicle data point before driving direction change, determines that tracing point is road
The track of vehicle data point of mouth turning is simultaneously retained；
Step S03 is clustered for the track of vehicle data point of crossing turning, identifies traffic intersection and crossing type；
Step S04, to the quantity of track of vehicle data point that each traffic intersection statistics turns left, turns right, turns around, and determination traffic
Whether the traffic rules at crossing are no turning left, no turning right, no turning around.
2. a kind of crossing traffic rule automatic identifying method according to claim 1, which is characterized in that further include step
S05, the traffic rules and intersection information are sent to navigation system.
3. a kind of crossing traffic rule automatic identifying method according to claim 1, which is characterized in that the step S01
Include:
Step S11 acquires vehicle track data point according to each vehicle ID and according to time sequence forms the traveling rail of each vehicle
Mark；
Step S12 searches the track of vehicle data point that vehicle heading changes in each vehicle driving trace, and this is determined
For tracing point.
4. a kind of crossing traffic rule automatic identifying method according to claim 1, which is characterized in that track of vehicle data
Point includes GPS coordinate, travel speed, traveling angle, time.
5. a kind of crossing traffic rule automatic identifying method according to claim 4, which is characterized in that the step S02
Include:
The operating range of step S21, calculating tracing point and the track of vehicle data point before driving direction change is poor, travels angle
Difference, time difference；
Step S22 then confirms track when operating range is poor, travels differential seat angle, the time difference respectively meets crossing turning condition
Point is the track of vehicle data point of crossing turning, is otherwise not belonging to the track of vehicle data point of crossing turning；
Step S23, filtering are not belonging to the track of vehicle data point of crossing turning and retain the track of vehicle data point of crossing turning.
6. a kind of crossing traffic rule automatic identifying method according to claim 5, which is characterized in that the crossing turning
Condition are as follows: travel speed difference is 20-60 seconds；It travels differential seat angle and is greater than 90 degree；Operating range is more than 100 meters.
7. a kind of crossing traffic rule automatic identifying method according to claim 1, which is characterized in that the step S03
Include:
Step S31, for the track of vehicle data point of crossing turning, density-based algorithms are clustered；
Step S32 automatically identifies urban road crossing and crossing type according to clustering algorithm, and crossing type includes crossroad, X
Shape crossing, Y shape crossing, road circuits, T shape crossing.
8. a kind of crossing traffic rule automatic identifying method according to claim 1, which is characterized in that the step S04
Include:
Step S41, according to the different directions of traffic intersection, count left-hand rotation differential seat angle be -90 spend, right-hand rotation differential seat angle is 90 degree, falls
Head differential seat angle is the quantity of the track of vehicle data point of 180 degree；
Step S42, if the quantity that left-hand rotation differential seat angle is the track of vehicle data points of -90 degree is equal to 0, traffic intersection herein
Traffic rules are no left turn；If the quantity for the track of vehicle data point that right-hand rotation differential seat angle is 90 degree is equal to 0, traffic herein
The traffic rules at crossing are no right turn；If the differential seat angle that turns around is equal to 0 for the quantity of the track of vehicle data point of 180 degree, this
The traffic rules for locating traffic intersection are that no turns.
9. a kind of crossing traffic rule automatic identifying method according to claim 1, which is characterized in that the track of vehicle
Data point is obtained by being equipped with the vehicle real-time detection of GPS.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910659720.1A CN110276973B (en) | 2019-07-22 | 2019-07-22 | Automatic intersection traffic rule identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910659720.1A CN110276973B (en) | 2019-07-22 | 2019-07-22 | Automatic intersection traffic rule identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110276973A true CN110276973A (en) | 2019-09-24 |
| CN110276973B CN110276973B (en) | 2021-03-19 |
Family
ID=67964983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910659720.1A Active CN110276973B (en) | 2019-07-22 | 2019-07-22 | Automatic intersection traffic rule identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110276973B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112489450A (en) * | 2020-12-21 | 2021-03-12 | 北京百度网讯科技有限公司 | Traffic intersection vehicle flow control method, road side equipment and cloud control platform |
| CN112562315A (en) * | 2020-11-02 | 2021-03-26 | 鹏城实验室 | Method, terminal and storage medium for acquiring traffic flow information |
| CN112712696A (en) * | 2020-12-30 | 2021-04-27 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining road section with illegal parking |
| CN113375685A (en) * | 2021-03-31 | 2021-09-10 | 福建工程学院 | Urban intersection center identification and intersection turning rule extraction method based on sub-track intersection |
| CN113370997A (en) * | 2021-08-11 | 2021-09-10 | 北京赛目科技有限公司 | Control method and device for automatic driving of vehicle, electronic equipment and storage medium |
| CN113823082A (en) * | 2021-06-07 | 2021-12-21 | 腾讯科技（深圳）有限公司 | Navigation data processing method, device, equipment and storage medium |
| WO2022093119A1 (en) * | 2020-11-02 | 2022-05-05 | Grabtaxi Holdings Pte. Ltd. | Processing apparatus and method for traffic management of a network of roads |
| CN116052453A (en) * | 2022-12-30 | 2023-05-02 | 广州小鹏自动驾驶科技有限公司 | Road junction determining method, device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663890A (en) * | 2012-06-01 | 2012-09-12 | 北京航空航天大学 | Method for determining left-turning forbiddance traffic limitation intersection by using floating car data |
| CN103262137A (en) * | 2011-01-19 | 2013-08-21 | 株式会社善邻 | Regulation information analysis system |
| CN103413437A (en) * | 2013-07-31 | 2013-11-27 | 福建工程学院 | Method and system for identifying road intersection steering based on vehicle data collection |
| CN105023431A (en) * | 2014-04-29 | 2015-11-04 | 高德软件有限公司 | Method and device for determining traffic restriction information |
| CN105788273A (en) * | 2016-05-18 | 2016-07-20 | 武汉大学 | Urban intersection automatic identification method based on low precision space-time trajectory data |
| CN106205120A (en) * | 2015-05-08 | 2016-12-07 | 北京四维图新科技股份有限公司 | A kind of method and device extracting road cross traffic restriction |
-
2019
- 2019-07-22 CN CN201910659720.1A patent/CN110276973B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103262137A (en) * | 2011-01-19 | 2013-08-21 | 株式会社善邻 | Regulation information analysis system |
| CN102663890A (en) * | 2012-06-01 | 2012-09-12 | 北京航空航天大学 | Method for determining left-turning forbiddance traffic limitation intersection by using floating car data |
| CN103413437A (en) * | 2013-07-31 | 2013-11-27 | 福建工程学院 | Method and system for identifying road intersection steering based on vehicle data collection |
| CN105023431A (en) * | 2014-04-29 | 2015-11-04 | 高德软件有限公司 | Method and device for determining traffic restriction information |
| CN106205120A (en) * | 2015-05-08 | 2016-12-07 | 北京四维图新科技股份有限公司 | A kind of method and device extracting road cross traffic restriction |
| CN105788273A (en) * | 2016-05-18 | 2016-07-20 | 武汉大学 | Urban intersection automatic identification method based on low precision space-time trajectory data |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112562315A (en) * | 2020-11-02 | 2021-03-26 | 鹏城实验室 | Method, terminal and storage medium for acquiring traffic flow information |
| CN112562315B (en) * | 2020-11-02 | 2022-04-01 | 鹏城实验室 | Method, terminal and storage medium for acquiring traffic flow information |
| WO2022093119A1 (en) * | 2020-11-02 | 2022-05-05 | Grabtaxi Holdings Pte. Ltd. | Processing apparatus and method for traffic management of a network of roads |
| CN112489450A (en) * | 2020-12-21 | 2021-03-12 | 北京百度网讯科技有限公司 | Traffic intersection vehicle flow control method, road side equipment and cloud control platform |
| CN112712696A (en) * | 2020-12-30 | 2021-04-27 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining road section with illegal parking |
| CN113375685A (en) * | 2021-03-31 | 2021-09-10 | 福建工程学院 | Urban intersection center identification and intersection turning rule extraction method based on sub-track intersection |
| CN113823082A (en) * | 2021-06-07 | 2021-12-21 | 腾讯科技（深圳）有限公司 | Navigation data processing method, device, equipment and storage medium |
| CN113823082B (en) * | 2021-06-07 | 2023-08-18 | 腾讯科技（深圳）有限公司 | Navigation data processing method, device, equipment and storage medium |
| CN113370997A (en) * | 2021-08-11 | 2021-09-10 | 北京赛目科技有限公司 | Control method and device for automatic driving of vehicle, electronic equipment and storage medium |
| CN116052453A (en) * | 2022-12-30 | 2023-05-02 | 广州小鹏自动驾驶科技有限公司 | Road junction determining method, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110276973B (en) | 2021-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110276973A (en) | A kind of crossing traffic rule automatic identifying method | |
| CN104819724B (en) | A kind of autonomous travel assist system of Unmanned Ground Vehicle based on GIS | |
| CN100580735C (en) | Real-time dynamic traffic information processing method based on car detecting technique | |
| CN102298851B (en) | Navigation system for vehicle and navigation service method | |
| CN110111566A (en) | Trajectory predictions method, apparatus and storage medium | |
| CN107490384B (en) | Optimal static path selection method based on urban road network | |
| US20050004753A1 (en) | Method of representing road lanes | |
| CN110861650A (en) | Vehicle path planning method and device, vehicle-mounted equipment and storage medium | |
| CN102074110B (en) | Floating vehicle data-based traffic flow intersection turn delay acquisition system and method | |
| CN113155145B (en) | Lane-level path planning method for automatic driving lane-level navigation | |
| EP3822945B1 (en) | Driving environment information generation method, driving control method, driving environment information generation device | |
| CN110400461B (en) | Road network change detection method | |
| CN104897168A (en) | Intelligent vehicle path search method and system based on road risk assessment | |
| JP4874513B2 (en) | How to display road lanes | |
| CN110789578B (en) | Train rapid positioning method and system | |
| US11697429B2 (en) | System, method, and computer program product for topological planning in autonomous driving using bounds representations | |
| US11618455B2 (en) | Driving data used to improve infrastructure | |
| Blazquez et al. | Simple map-matching algorithm applied to intelligent winter maintenance vehicle data | |
| CN113375685B (en) | Urban intersection center recognition and intersection turning rule extraction method based on sub-track intersection | |
| CN108351220A (en) | The polymerization of lane information for numerical map service | |
| Aryal | Optimization of geometric road design for autonomous vehicle | |
| CN111033591B (en) | Method and server device for determining the course of a road lane of a road network | |
| CN106845476A (en) | A kind of HOV Lane regulation system and methods based on the Big Dipper and image recognition technology | |
| CN114663992B (en) | Multisource data fusion expressway portal positioning method | |
| EP3967978B1 (en) | Detecting a construction zone by a lead autonomous vehicle (av) and updating routing plans for following autonomous vehicles (avs) |
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 |