CN110310516A - A kind of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction - Google Patents
A kind of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction Download PDFInfo
- Publication number
- CN110310516A CN110310516A CN201910522080.XA CN201910522080A CN110310516A CN 110310516 A CN110310516 A CN 110310516A CN 201910522080 A CN201910522080 A CN 201910522080A CN 110310516 A CN110310516 A CN 110310516A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- driving trace
- track
- prediction
- merging area
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
-
- 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
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction, and its step are as follows: (1) in the built-in vertical two-dimensional coordinate system of interflow region；(2) priority of track of vehicle data set processing sequence is divided according to the time；(3) classify to the driving trace data set of the merging area vehicle of the initial time in same priority, (4) it is based on vehicle driving trace data set, vehicle driving trace point prediction is carried out to each vehicle on each lane using Kalman filtering method；(5) linear fit is carried out to above-mentioned coordinate points and is then based on function expression drafting track of vehicle line；(6) conflict judgement is carried out to above-mentioned track cross point；This method, which innovatively carries out highway merging area vehicle from track of vehicle angle, whether there is the differentiation of traffic conflict, and tracing point space time information founding mathematical models is combined to carry out Function Fitting, it is ensured that the reliability and feasibility of method.
Description
Technical field
The present invention relates to a kind of field of traffic safety, specifically, being to be related to a kind of traffic in expressway safety field
Conflict area method of discrimination method is especially to be related to a kind of highway merging area friendship based on vehicle driving trace prediction
Logical conflict method of discrimination.
Background technique
With the continuous development of China's expressway construction cause, the importance of the safety management problem in highway
Increasingly prominent, when especially vehicle imports highway major trunk roads by merging area by expressway access, it may cause and hand over
Logical collision problem.Traffic conflict refers to that under the conditions of observable, 2 or 2 or more traffic participants are on room and time
It is close to each other, so that if one side of any of them does not change its driving trace, it will there is the risk to collide.And merging area
It is the common high-incidence region of traffic conflict accident of highway, is closed if can be differentiated by certain technological means sensed in advance
The when and where that the traffic conflict in stream area may occur, it will help greatly promote safety, the drop of highway merging area
The probability that low merging area traffic accident occurs.
Currently, the research of the traffic conflict under Signalized control is focused primarily upon in the prior art, for the friendship of merging area
Logical Conflict Studies are relatively fewer, in terms of the building for being largely focused on Safety Index System Assessment and evaluation method, and use
Model method is complex, it is difficult to directly use in practical applications.
Therefore, it is necessary to this vacancy is filled up, therefore the present invention considers the convenience of practical application, by the practical vehicle of merging area
The traffic conflict discrimination of driving process is converted into the coincidence discrimination of merging area movement locus of object, it is contemplated that practical
The factors such as the fluctuation of the size of vehicle and practical wagon flow, using vehicle driving trace crosspoint as the center of circle, with the small vapour of standard
Vehicle vehicle commander is that radius determines a border circular areas, the determination for the existence that further conflicts.
Summary of the invention
Problem to be solved by this invention is to fill up the blank of the merging area vehicle collision discrimination technology convenient for practical application,
Provide a kind of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction.
In order to solve the above technical problems, the present invention is achieved by the following technical scheme:
Based on vehicle driving trace prediction highway merging area traffic conflict method of discrimination the step of it is as follows:
Step 1: in the built-in vertical two-dimensional coordinate system of interflow region；
One is established within the scope of merging area with the outermost lane center of major trunk roads and ring road near the road of major trunk roads
The intersection point of the extended line of shoulder is origin, is hung down using the outermost lane line of highway major trunk roads as horizontal axis, to cross origin and horizontal axis
Straight line is the two-dimensional coordinate system of the longitudinal axis.
Step 2: dividing the priority of track of vehicle data set processing sequence according to the time；
Refer to the angular divisions track of vehicle from the time according to the priority that the time divides track of vehicle data processing sequence
The sequencing of data set processing, the principle for dividing priority are to be introduced into the vehicle of merging area first to carry out trajectory predictions, vehicle
The expression-form of track data is the coordinates table that the driving trace point of center of vehicle is carried out based on above-mentioned two-dimensional coordinate system
Show；
Step 3: dividing the driving trace data set of the merging area vehicle of the initial time in same priority
Class；
It is every for vehicle driving trace data set and ring road of the outermost on the lane of ring road of merging area major trunk roads
Two class of driving trace data set of vehicle on one lane, every kind of track data collection include the transverse direction of vehicle, the i.e. side X
To, positional value, velocity component, component of acceleration；And longitudinal direction, i.e. Y-direction, positional value, velocity component, acceleration point
Amount；
Step 4: being based on vehicle driving trace data set, driving trace point is carried out to each vehicle on each lane
Prediction；
Carrying out the method that driving trace point prediction is used to each vehicle on each lane is Kalman filtering method, card
Kalman Filtering prediction locus has main steps that: (a) determining motion model parameters according to state equation and observational equation, and initial
Change parameter；(b) oneself knows optimal State Estimation value and estimation error variance battle array under initial time, and is predicted according to state equation
Subsequent time detects track of vehicle predicted value out, while obtaining estimation error covariance battle array；(c) according to the sight under subsequent time
Measured value obtain it optimal State Estimation value and optimal estimation error covariance matrix, complete a step filtering；Successively iteration obtains
To the optimal State Estimation of previous moment, filtering is completed；(d) estimated according to the optimum state for the previous moment being previously obtained
The observation at meter and current time predicts the tracing point position of subsequent time, and future position and real trace point are carried out
Compare, calculates prediction error；It is repeated in the prediction that Future Trajectory point is completed in operation, prediction error mean is calculated；
Step 5: carrying out linear fit to above-mentioned coordinate points handles to obtain the letter between the ordinate of tracing point and abscissa
Number expression formula is then based on function expression and draws track of vehicle line；
Step 6: carrying out conflict judgement to above-mentioned track cross point
In highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction, to above-mentioned track cross
The specific sub-step that point carries out conflict existence judgement is as follows:
(a) the prediction driving trace line of two vehicles of the judgement not on same lane whether there is crosspoint, if not
Then being considered as this two cars there are crosspoint, there is no traffic conflicts；If it exists, then using crosspoint as the center of circle, with the small vapour of standard
Vehicle vehicle commander is radius, delimits a border circular areas, remembers that this border circular areas is conflict area；
(b) judge whether this two cars can all reach in conflict area in certain time threshold value, if so, determining thus
Within the scope of this time of region, there are traffic conflicts for the two vehicles of merging area, and otherwise there is no conflicts.
Compared with prior art, the beneficial effects of the present invention are:
1. the present invention innovatively carries out traffic conflict from vehicle of the vehicle driving trace angle to highway merging area
Differentiate, specifically, being a kind of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction, and ties
The space time information for closing vehicle carries out mathematical modeling, it is ensured that the reliability and feasibility of the conflict method of discrimination has filled up existing
Merging area traffic conflict discrimination technology be not easy to the blank of practice.
2. Kalman filtering used in highway merging area traffic conflict area judging method of the present invention
Algorithm, which is particularly suitable for motion state, frequently to be changed, and has uncertain and different motion mode track data, can be to being
System state carries out optimal estimation, can be realized the estimation and prediction of real-time running state, even if considering the operation of actual vehicle
The change for the motion state being frequent in the process can also carry out higher adaptivity adjustment.
Detailed description of the invention
Invention is further described with reference to the accompanying drawing:
Fig. 1 is the highway merging area traffic conflict method of discrimination of the present invention based on vehicle driving trace prediction
Flow diagram；
Fig. 2 is the highway merging area traffic conflict method of discrimination of the present invention based on vehicle driving trace prediction
Coordinate system schematic diagram；
Fig. 3 is the highway merging area traffic conflict method of discrimination of the present invention based on vehicle driving trace prediction
Vehicle priority divide schematic diagram.
Specific embodiment
In order to make it easy to understand, doing following statement to specific implementation step of the invention here in connection with attached drawing.
This specific real-time mode is related to a kind of highway merging area traffic conflict based on vehicle driving trace prediction and sentences
Other method, as shown in Figure 1, described method includes following steps:
Step 1: establishing two coordinate systems in on-ramp
As shown in Figure 2, it is contemplated that subsequent step needed when trajectory predictions the coordinate system where uniform data with
Just it performs mathematical calculations, therefore, it is of the present invention to refer in the built-in vertical two-dimensional coordinate system of interflow region in merging area model
Enclose the intersection point of the interior extended line for establishing a road shoulder with the outermost lane center of major trunk roads and ring road near major trunk roads
It is horizontal axis, the line vertical with horizontal axis using origin excessively as the two of the longitudinal axis using the outermost lane line of highway major trunk roads for origin
Tie up coordinate system.
Step 2: dividing the priority of track of vehicle data set processing sequence according to the time；
The priority of the present invention for dividing track of vehicle data processing sequence according to the time refers to the angle from the time
The sequencing of track of vehicle data set processing is divided according to certain principle, the principle for dividing priority is to be introduced into merging area
Vehicle first carry out trajectory predictions, the expression-form of track of vehicle data is the center that vehicle is carried out based on above-mentioned two-dimensional coordinate system
The coordinate representation of the driving trace point of position, is expressed as (xi,yi)。
The reason of carrying out above-mentioned processing allows for processing merging area track of vehicle in the step of subsequent progress trajectory predictions
When data, if brought not to the division in track data process time there are vehicle flowrate is huge in certain time
The many and diverse possibility for influencing data-handling efficiency of data, in order to avoid the generation of above situation, therefore carries out track of vehicle data processing
The priority of sequence divides.
Step 3: classifying to the driving trace data set of the merging area vehicle of the initial time in same priority
As shown in figure 3, waiting in the specific implementation, division priority is carried out from the angle of time, it is first determined an initial T
Moment corresponding time window remembers that the vehicle in this time window is the first priority vehicle；Then, the T+1 moment is set
Corresponding time window remembers that the vehicle in this time window is the second priority vehicle；Then, when the T+2 moment is corresponding
Between window, remember that the vehicle in this time window is third priority vehicle, in this way, N priority vehicle can be obtained successively
?.When carrying out traffic conflict identification, first the first priority vehicle is handled, then handles the second priority vehicle
, third priority vehicle is then handled, successively handles the vehicle of different priorities in this way.
It is of the present invention in same priority initial time merging area vehicle driving trace data set into
Row classification refers to classifies according to the major trunk roads and ring road of merging area, in detail, refers to and is divided into merging area major trunk roads most
The driving trace of vehicle driving trace data set of the outside on the lane of ring road and the vehicle on ring road each lane
Two class of data set, every kind of track data collection include the positional value of the transverse direction (namely X-direction) of vehicle, velocity component, add
Positional value, velocity component, the component of acceleration of velocity component and longitudinal direction (namely Y-direction).
Step 4: being based on vehicle driving trace data set, driving trace point is carried out to each vehicle on each lane
Prediction；
It is of the present invention to be based on vehicle driving trace data set, traveling rail is carried out to each vehicle on each lane
The method that mark point prediction is used is Kalman filtering method, carries out driving trace point prediction use to each vehicle on each lane
The method arrived is Kalman filtering method, and Kalman filtering algorithm is applied to the advantage major embodiment of merging area track of vehicle prediction
At following two aspects: (1) complicated movement of merging area vehicle is changeable uncertain high, and Kalman filtering algorithm is especially suitable
Frequently change in motion state, the track data with uncertain and different motion mode, system mode can be carried out most
Excellent estimation can be realized the estimation and prediction of real-time running state, and be suitable for the space-time rail of finite dimensional linear and nonlinear
Mark；(2) when carrying out the prediction of merging area track of vehicle, real-time and accuracy to prediction result have very high
It is required that prediction deviation is excessive or predicted position point inaccurately will lead to prediction failure, and by Kalman filtering algorithm application
There is the high advantage of real-time in trajectory predictions, to the mobile object of frequent changes motion state adaptivity with higher,
It is a kind of pervasive machine learning method.
Kalman prediction track has main steps that: (a) determining motion model according to state equation and observational equation
Parameter, and initiation parameter；(b) oneself knows optimal State Estimation value and estimation error variance battle array under initial time, and according to
State equation predicts subsequent time detection track of vehicle predicted value, while obtaining estimation error covariance battle array；(c) under
For the moment the observation inscribed obtain it optimal State Estimation value and optimal estimation error covariance matrix, complete step filter
Wave；Successively iteration obtains the optimal State Estimation of previous moment, completes filtering；(d) according to the previous moment being previously obtained
Optimal State Estimation and the observation at current time predict the tracing point position of subsequent time, and by future position and true
Real tracing point is compared, and calculates prediction error；It is repeated in the prediction that Future Trajectory point is completed in operation, prediction is calculated
Error mean.
It is as follows using the concrete operation process description of Kalman prediction track of vehicle:
First setting needs to carry out the start position of the target vehicle of trajectory predictions, and here in order to describe conveniently, setting needs
The starting point of the target vehicle of prediction locus be apart from 200 meters of merging area entrance at, meanwhile, reference axis is divided when prediction locus
Set the exam worry, and carries out individually Kalman Algorithm to each reference axis and predict, in this way, can convert two-dimensional prediction to one-dimensional
Prediction, helps to improve forecasting efficiency.
Operation displaying is carried out by taking Kalman's trajectory predictions in X-direction as an example below.
If needing to carry out the state vector in the X-direction of the vehicle of trajectory predictions indicates are as follows:
In formula (1): x1It (n) is the positional value at the n-th moment of target vehicle in the X direction；x2It (n) is target vehicle in the side X
The velocity amplitude at the n-th upward moment；x3It (n) is the acceleration value at the n-th moment of target vehicle in the X direction.
The center movement status system equation of target vehicle are as follows:
X (n+1)=A*X (n)+ε (n) (2)
In formula (2):For system noise；For state transition equation；τ is data upload
Time interval.
The covariance matrix of system noise are as follows:
Measurement equation are as follows:
Z (n)=C*X (n)+η (n) (4)
In formula (4): C=[1 0 0] is measurement matrix；η (n)=v (n) is to measure noise, then the variance for measuring noise isHere it sets
As known from the above, the previous moment that target vehicle must be first found out before recursive operation starts to carry out predicts covariance
The initial value of matrix needs first to select continuous three target vehicles within the selected period to find out above-mentioned initial value
Center position x (t), x (t+1), x (t+2) and according to obtaining vector estimated matrix:
State true value when n=t+2 can be found out out by the state equation and measurement equation of system are as follows:
Again by the estimate vector of formula (3)Acquire mean square deviation matrix:
Subsequent time is predicted again later, being still and obtaining predicted value according to above-mentioned equation, predicted value includes position
Value, velocity amplitude, acceleration value.The Kalman Prediction of Y-direction also similarly, can obtain the predicted value of Y-direction, and predicted value includes position
Value, velocity amplitude, acceleration value.
In order to further ensure the accuracy of trajectory predictions, the geometric space of prediction locus point and actual path point is missed
Difference is calculated using root-mean-square error RMSE:
Wherein, (xi,yi) --- the position coordinates of actual path point；
(x′i,y′i) --- the position coordinates of prediction locus point；
K --- the quantity of prediction locus point.
When trajectory predictions are completed, closed according to the size of root-mean-square error RMSE and given threshold value (threshold value is set as 3m)
It is to determine whether trajectory predictions result is accurate, then belongs to prediction accurately when root-mean-square error RMSE value is less than threshold value, hit track
Point；Otherwise, belong to and do not hit, if not hitting, then abandon this future position, readjust relevant parameter and predicted.
Step 5: these are carried out time and processing spatially by the tracing point predicted, obtain on every lane
The vehicle driving trace obtained after the prediction of each car；
Above-mentioned space-time processing carried out to each vehicle, the coordinate of the driving trace point of available prediction, then
Linear fit processing is carried out to these coordinate points using one-variable linear regression, handles the ordinate and horizontal seat of available tracing point
Function expression between mark: yi=f (xi)=a*xi+ b then draws track of vehicle line based on function expression.
Actual coordinate point and prediction coordinate points to aforementioned obtained target vehicle carry out linear fit processing, in order to more preferable
Ground obtains the function expression between the ordinate and abscissa of target vehicle tracing point, based on minimum when being fitted
Square law carries out one-variable linear regression and is fitted, and carries out linear fit processing to these coordinate points, handles available track
Function expression between the ordinate and abscissa of point then draws track of vehicle line based on function expression, needs one
Under, it, can be to each vehicle on every lane of merging area in order to preferably carry out the judgement of subsequent conflict existence
All carry out above-mentioned space-time processing.
Step 6: carrying out conflict differentiation.
In vehicle when by merging area, there is the ground intersected in the trajectory line for certainly existing the vehicle in different lanes
Side, namely there are track cross point, these crosspoints are potential conflict points, namely there is the possibility that traffic conflict occurs but not
It is bound to that traffic conflict occurs.The judgement for the existence that conflicts between progress merging area vehicle and vehicle below.Then track is handed over
Crunode carries out conflict judgement, and specific sub-step is as follows:
(a) the prediction driving trace line of two vehicles of the judgement not on same lane whether there is crosspoint, if not
Then being considered as this two cars there are crosspoint, there is no traffic conflicts；If it exists, then using crosspoint as the center of circle, with the small vapour of standard
Vehicle vehicle commander is radius, delimits a border circular areas, remembers that this border circular areas is conflict area；
(b) judge whether this two cars can all reach in conflict area in certain time threshold value, if so, determining thus
Within the scope of this time of region, there are traffic conflicts for the two vehicles of merging area, and otherwise there is no conflicts.
Above is only the optimal technical scheme of this patent, its purpose is to illustrate the invention of this patent essence,
All modifications that this patent is carried out under invention design, such as to the replacement, change, deletion of certain elements due to it
The inventive concept of this patent is not departed from, therefore should all be brought within the protection scope of this patent.
Claims (1)
1. a kind of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction, which is characterized in that institute
The step of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction stated, is as follows:
Step 1: in the built-in vertical two-dimensional coordinate system of interflow region；
A road shoulder with the outermost lane center of major trunk roads and ring road near major trunk roads is established within the scope of merging area
The intersection point of extended line be origin, using the outermost lane line of highway major trunk roads as horizontal axis, with cross origin it is vertical with horizontal axis
Line is the two-dimensional coordinate system of the longitudinal axis.
Step 2: dividing the priority of track of vehicle data set processing sequence according to the time；
Refer to the angular divisions track of vehicle data from the time according to the priority that the time divides track of vehicle data processing sequence
Collect the sequencing of processing, the principle for dividing priority is to be introduced into the vehicle of merging area first to carry out trajectory predictions, track of vehicle
The expression-form of data is the coordinate representation that the driving trace point of center of vehicle is carried out based on above-mentioned two-dimensional coordinate system；
Step 3: classifying to the driving trace data set of the merging area vehicle of the initial time in same priority；
For vehicle driving trace data set and ring road each of the outermost on the lane of ring road of merging area major trunk roads
Two class of driving trace data set of vehicle on lane, every kind of track data collection include the transverse direction of vehicle, i.e. X-direction,
Positional value, velocity component, component of acceleration；And longitudinal direction, i.e. Y-direction, positional value, velocity component, component of acceleration；
Step 4: being based on vehicle driving trace data set, driving trace point prediction is carried out to each vehicle on each lane；
Carrying out the method that driving trace point prediction is used to each vehicle on each lane is Kalman filtering method, Kalman
Filter forecasting track has main steps that: (a) determining motion model parameters according to state equation and observational equation, and initializes ginseng
Number；(b) oneself knows optimal State Estimation value and estimation error variance battle array under initial time, and is predicted down according to state equation
One moment detected track of vehicle predicted value, while obtaining estimation error covariance battle array；(c) according to the observation under subsequent time
Obtain it optimal State Estimation value and optimal estimation error covariance matrix, complete a step filtering；Before successively iteration obtains
The optimal State Estimation at one moment completes filtering；(d) optimal State Estimation for the previous moment that basis is previously obtained, with
And the observation at current time predicts the tracing point position of subsequent time, and future position is compared with real trace point,
Calculate prediction error；It is repeated in the prediction that Future Trajectory point is completed in operation, prediction error mean is calculated；
Step 5: carrying out linear fit to above-mentioned coordinate points handles to obtain the function table between the ordinate of tracing point and abscissa
Up to formula, it is then based on function expression and draws track of vehicle line；
Step 6: carrying out conflict judgement to above-mentioned track cross point
In highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction, above-mentioned track cross is clicked through
The specific sub-step of row conflict existence judgement is as follows:
(a) the prediction driving trace line of two vehicles of the judgement not on same lane whether there is crosspoint, if it does not exist
Crosspoint is then considered as this two cars, and there is no traffic conflicts；If it exists, then using crosspoint as the center of circle, with a standard car vehicle
A length of radius delimit a border circular areas, remember that this border circular areas is conflict area；
(b) judge whether this two cars can all reach in conflict area in certain time threshold value, if so, determining region thus
Within the scope of this time, there are traffic conflicts for the two vehicles of merging area, and otherwise there is no conflicts.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910522080.XA CN110310516A (en) | 2019-06-17 | 2019-06-17 | A kind of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction |
| CN202010150537.1A CN111415531B (en) | 2019-06-17 | 2020-03-06 | Expressway confluence area traffic conflict discrimination method based on travel track prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910522080.XA CN110310516A (en) | 2019-06-17 | 2019-06-17 | A kind of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110310516A true CN110310516A (en) | 2019-10-08 |
Family
ID=68077574
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910522080.XA Pending CN110310516A (en) | 2019-06-17 | 2019-06-17 | A kind of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction |
| CN202010150537.1A Expired - Fee Related CN111415531B (en) | 2019-06-17 | 2020-03-06 | Expressway confluence area traffic conflict discrimination method based on travel track prediction |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010150537.1A Expired - Fee Related CN111415531B (en) | 2019-06-17 | 2020-03-06 | Expressway confluence area traffic conflict discrimination method based on travel track prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN110310516A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110781774A (en) * | 2019-10-10 | 2020-02-11 | 江苏理工学院 | Level crossing intelligent guiding system and method based on deep learning |
| CN110825090A (en) * | 2019-11-29 | 2020-02-21 | 苏州智加科技有限公司 | Method, device and storage medium for dividing prediction priority of automatic driving vehicle |
| CN110855789A (en) * | 2019-11-18 | 2020-02-28 | 东软集团股份有限公司 | Position relation determining method and device, storage medium and equipment |
| CN111145569A (en) * | 2019-11-22 | 2020-05-12 | 京东数字科技控股有限公司 | Road monitoring and vehicle running control method and device and vehicle-road cooperative system |
| CN112133089A (en) * | 2020-07-21 | 2020-12-25 | 西安交通大学 | Vehicle track prediction method, system and device based on surrounding environment and behavior intention |
| CN113012425A (en) * | 2019-12-18 | 2021-06-22 | 丰田自动车株式会社 | Confluence assistance information transmission device and method, confluence assistance system, and computer program |
| CN113353080A (en) * | 2021-06-01 | 2021-09-07 | 上海网车科技有限公司 | Highway automatic lane changing method based on travelable area |
| CN113706927A (en) * | 2021-08-16 | 2021-11-26 | 中汽创智科技有限公司 | Vehicle early warning method, device, electronic equipment, storage medium and program product |
| CN113741443A (en) * | 2021-08-26 | 2021-12-03 | 北京京东乾石科技有限公司 | Method and device for controlling rail guided vehicle, storage medium and electronic equipment |
| CN113963537A (en) * | 2021-10-19 | 2022-01-21 | 东软睿驰汽车技术（上海）有限公司 | Vehicle track prediction method for intersection and related device |
| CN114333419A (en) * | 2021-12-28 | 2022-04-12 | 杭州海康威视***技术有限公司 | Traffic conflict determination method, device, equipment and readable storage medium |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2021024423A (en) * | 2019-08-05 | 2021-02-22 | 本田技研工業株式会社 | Vehicle control device, vehicle control method, and program |
| CN112927512B (en) * | 2021-02-24 | 2022-03-29 | 山东科技大学 | Expressway ramp confluence control system and method |
| CN114120639B (en) * | 2021-11-09 | 2023-04-11 | 广州文远知行科技有限公司 | Vehicle traffic control method, device and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104882025B (en) * | 2015-05-13 | 2017-02-22 | 东华大学 | Crashing detecting and warning method based on vehicle network technology |
| CN105894856B (en) * | 2016-05-10 | 2018-01-30 | 浙江树人大学 | A kind of vehicle collision avoidance method based on truck traffic |
| CN109275121B (en) * | 2018-08-20 | 2021-08-03 | 浙江工业大学 | Vehicle trajectory tracking method based on adaptive extended Kalman filtering |
| CN109118786B (en) * | 2018-08-20 | 2020-08-04 | 浙江工业大学 | Vehicle speed prediction method based on quantization adaptive Kalman filtering |
| CN109859500B (en) * | 2018-12-17 | 2021-02-02 | 浙江海康智联科技有限公司 | High-speed confluence area safety early warning method based on vehicle-road cooperation |
-
2019
- 2019-06-17 CN CN201910522080.XA patent/CN110310516A/en active Pending
-
2020
- 2020-03-06 CN CN202010150537.1A patent/CN111415531B/en not_active Expired - Fee Related
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110781774A (en) * | 2019-10-10 | 2020-02-11 | 江苏理工学院 | Level crossing intelligent guiding system and method based on deep learning |
| CN110855789B (en) * | 2019-11-18 | 2022-07-08 | 东软集团股份有限公司 | Position relation determining method and device, storage medium and equipment |
| CN110855789A (en) * | 2019-11-18 | 2020-02-28 | 东软集团股份有限公司 | Position relation determining method and device, storage medium and equipment |
| CN111145569A (en) * | 2019-11-22 | 2020-05-12 | 京东数字科技控股有限公司 | Road monitoring and vehicle running control method and device and vehicle-road cooperative system |
| CN110825090A (en) * | 2019-11-29 | 2020-02-21 | 苏州智加科技有限公司 | Method, device and storage medium for dividing prediction priority of automatic driving vehicle |
| CN113012425A (en) * | 2019-12-18 | 2021-06-22 | 丰田自动车株式会社 | Confluence assistance information transmission device and method, confluence assistance system, and computer program |
| CN113012425B (en) * | 2019-12-18 | 2022-12-09 | 丰田自动车株式会社 | Confluence assistance information transmission device and method, confluence assistance system, and storage medium |
| CN112133089A (en) * | 2020-07-21 | 2020-12-25 | 西安交通大学 | Vehicle track prediction method, system and device based on surrounding environment and behavior intention |
| CN112133089B (en) * | 2020-07-21 | 2021-11-19 | 西安交通大学 | Vehicle track prediction method, system and device based on surrounding environment and behavior intention |
| CN113353080A (en) * | 2021-06-01 | 2021-09-07 | 上海网车科技有限公司 | Highway automatic lane changing method based on travelable area |
| CN113706927A (en) * | 2021-08-16 | 2021-11-26 | 中汽创智科技有限公司 | Vehicle early warning method, device, electronic equipment, storage medium and program product |
| CN113706927B (en) * | 2021-08-16 | 2023-02-28 | 中汽创智科技有限公司 | Vehicle early warning method, device, electronic equipment, storage medium and program product |
| CN113741443A (en) * | 2021-08-26 | 2021-12-03 | 北京京东乾石科技有限公司 | Method and device for controlling rail guided vehicle, storage medium and electronic equipment |
| CN113963537A (en) * | 2021-10-19 | 2022-01-21 | 东软睿驰汽车技术（上海）有限公司 | Vehicle track prediction method for intersection and related device |
| CN114333419A (en) * | 2021-12-28 | 2022-04-12 | 杭州海康威视***技术有限公司 | Traffic conflict determination method, device, equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111415531B (en) | 2021-08-24 |
| CN111415531A (en) | 2020-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110310516A (en) | A kind of highway merging area traffic conflict method of discrimination based on vehicle driving trace prediction | |
| Guo et al. | Urban traffic signal control with connected and automated vehicles: A survey | |
| CN108550279B (en) | Vehicle drive behavior prediction method based on machine learning | |
| Essa et al. | Simulated traffic conflicts: do they accurately represent field-measured conflicts? | |
| CN102646332B (en) | Traffic state estimation device and method based on data fusion | |
| CN107807542A (en) | Automatic Pilot analogue system | |
| CN104395944B (en) | The identification in orientation track | |
| CN105550789A (en) | Method for predicting bus taking passenger flow | |
| CN106097755A (en) | For identifying the method parked place and/or vacate place | |
| CN109544932A (en) | A kind of city road network flow estimation method based on GPS data from taxi Yu bayonet data fusion | |
| CN109460023A (en) | Driver's lane-changing intention recognition methods based on Hidden Markov Model | |
| CN104750963B (en) | Intersection delay duration method of estimation and device | |
| CN110047276A (en) | Method and device for determining congestion state of obstacle vehicle and related product | |
| CN105740505A (en) | GPS-RTK technology based road space line shape recovery method | |
| CN108091137A (en) | A kind of evaluation method and device of Signalized control scheme | |
| CN103606272A (en) | System and method for predicting rapid bus arriving time based on passenger volumes | |
| CN111325187B (en) | Lane position identification method and device | |
| CN107808524A (en) | A kind of intersection vehicle checking method based on unmanned plane | |
| CN104773190A (en) | Auxiliary traction control system for train | |
| CN107886739A (en) | Traffic flow of the people automatic collecting analysis system | |
| CN114926984B (en) | Real-time traffic conflict collection and road safety evaluation method | |
| CN103927437B (en) | The method measuring space headway in non-rectilinear section | |
| CN110517484A (en) | Diamond interchange area planar crossing sign occlusion prediction model building method | |
| Langer et al. | An improved moving observer method for traffic flow estimation at signalized intersections | |
| CN106651061A (en) | Real-time fusion method based on DSRC data and point detector data |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191008 |
|
| WD01 | Invention patent application deemed withdrawn after publication |