CN106652497A - Scheduling method for intelligent transportation by fusing self-regression forecast model - Google Patents
Scheduling method for intelligent transportation by fusing self-regression forecast model Download PDFInfo
- Publication number
- CN106652497A CN106652497A CN201710085572.8A CN201710085572A CN106652497A CN 106652497 A CN106652497 A CN 106652497A CN 201710085572 A CN201710085572 A CN 201710085572A CN 106652497 A CN106652497 A CN 106652497A
- Authority
- CN
- China
- Prior art keywords
- traffic
- crossing
- flow
- fitness
- iteration
- 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
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The invention discloses a scheduling method for intelligent transportation by fusing a self-regression forecast model. According to the method, traffic lights are intelligently scheduled, the waiting time of a bus in large passenger capacity is prioritized, and the traffic jam problem is relieved. The method comprises the following steps: firstly, performing gene coding and initializing, representing a horizontal traffic flow with '0', and representing a vertical traffic flow with '1'; adopting a prediction model for predicting the traffic flow at each intersection within the next unit time, and adopting an objective function for evaluating adaptability; operating a genetic operator and judging if meeting an iteration ending condition, if yes, quitting, and if not, continuing iteration; and finally, decoding. According to the invention, the optimal traffic scheduling scheme is generated within each unit time. According to the invention, a self-regression model is adopted for predicting the traffic flow and the prediction effect is promoted, so that a better traffic light scheduling scheme can be searched out.
Description
Technical field
The invention belongs to intelligent traffic light dispatching algorithm technical field, more particularly to a kind of fusion Self-regression Forecast Model
Intelligent traffic dispatching method.
Background technology
Urban transport problems, road traffic obstruction, tail gas pollution and traffic accident etc., have become global difficulty
The scheme of the positive hardy searching solution problem of one of topic, national governments and field of traffic scholar brainstrust, and I
State just proposed and has formulated Progress in Transport Science and Technologies strategic objective early in 2006.In traffic system research field, one of them
Important field of research is exactly intelligent transportation system (Intelligent Traffic System, ITS), and ITS systems are considered as
It is one of effective ways of solution Traffic Problems.The transport need rapid development of China, traffic is lived for people
Also come more important.Meanwhile, easily traffic is also a country or flourishing and science and technology prosperity the mark of regional economy.So
And, more and more easily transportation condition drive it is economical while, urban highway traffic choking phenomenon is increasingly common, to ring
Border, personal safety and socio-economic development bring bad impact.Therefore, the reform of Traffic Systems and optimization gesture
Must go.
The essence of city traffic signal lamp is exactly to ensure traffic order, it is ensured that vehicle pass-through safety.Traffic lights make
With tracing back to 1868, it changes the magnitude of traffic flow to control and dispatch each crossing by the circulation of traffic signals.So
And, original urban transportation lamp system cannot solve increasingly common urban traffic road congestion problems.Conventional traffic signal
Lamp state conversion time dynamic cannot change, and the display time of traffic lights can not be according to the real-time traffic flow amount at each crossing come dynamic
Adjustment.Therefore such situation would generally occur：In a traffic intersection, there is wagon flow congestion, vertical track in horizontal track
Wagon flow is but very rare, but traffic lights are the conversion of machinery, it is impossible to pay the utmost attention to the Real-Time Scheduling traffic of congestion track
Lamp.In addition, the public transport of some big passengers traffic volume is (such as：Tramcar) it is the important means for solving urban traffic blocking, it is not
Carry out the development trend of urban transportation, because such traffic passenger carrying capacity is huge, should preferentially guarantee that its stand-by period is as short as possible.
Some are had at present with regard to the research work of intelligent dispatching algorithm, can be used to make traffic lights have more flexible tune
Degree is interval, and these algorithms are intended to improve the traffic efficiency of whole road network.At present one of most common method is exactly according to friendship in real time
It is through-flow arranging traffic light status.Optimal scheduling scheme can significantly reduce the traffic jam situations at each crossing of road network, each
The Mean Residence vehicle number at crossing is fewer, shows that the dispatching algorithm is more effective.Intelligent dispatching algorithm is incorporated into traffic lights scheduling field
Intelligent traffic light dispatching algorithm is formed in scape, is had great significance to being obviously improved the increasingly serious traffic problems of China.
For preferably maneuver traffic lamp, optimize road network traffic flow, forecasting traffic flow is particularly significant.Forecasting traffic flow is always
It is considered a big difficult point of ITS systems.In order to seek optimal prediction effect, many machine learning algorithms are brought research conduct
Forecast model.Machine learning is a kind of by using data, model is trained, then using the method for model prediction.Engineering
Habit is the key technology using data value, and traffic flow historical data is modeled by using machine learning algorithm, can be with
The prediction of traffic flow is realized well.
The content of the invention
A kind of fusion Self-regression Forecast Model that the purpose of the present invention is in view of the shortcomings of the prior art and provides
Intelligent traffic dispatching method, the method neatly dispatches each crossing traffic lamp shape according to each crossing arithmetic for real-time traffic flow come intelligence
State, so as to alleviate traffic pressure, improves each going through ability of city road network.
The object of the present invention is achieved like this：
A kind of intelligent traffic dispatching method of fusion Self-regression Forecast Model, the method is comprised the following steps：
Step 1：Gene code is carried out, with ' 0 ' in binary code horizontal wagon flow is represented, with ' 1 ' vertical wagon flow is represented,
Then initialize, initial population of the definition comprising number of individual；
Step 2：Fitness evaluation is carried out, with variable P fitness is represented, define the quantity that P is that crossing waits vehicle, wherein
The weight of big passenger traffic volume public transport is more than other vehicles；Define fitness function so that the P sums at each crossing are minimum；Fitness
Function is as follows：
min{Σmax(VP(ti+1),HP(ti+1))}
Wherein, ti+1Represent the current one time the next unit interval, VP and HP represent respectively vertically and horizontally etc.
Vehicle fleet size is treated, is predicted by autoregression model and is obtained；
Step 3：Operation genetic operator, including select, intersect and make a variation；
Step 4：Judge whether to meet stopping criterion for iteration, if being unsatisfactory for, continue iteration, if meeting iteration is exited,
And decoded, each character is converted into into the traffic lights scheduling scheme at the crossing.
Autoregression model described in step 2 of the present invention, it is as follows：
Wherein, ytRepresent the vehicle flowrate of t unit interval, θiRepresent i-th parameter, yt-iRepresent the wagon flow of t-i unit interval
Amount, εtIt is possess the Gaussian white noise that average is that 0, variance is δ；
Selection described in step 3 of the present invention：Finger guarantees that best gene is selected and passes to follow-on population, often
A generation is all a traffic scheduling scheme, and every generation is ranked up according to fitness, eliminates those fitness low；Described
Intersect：Refer to by combining and destroying individual gene to carry out the exchange of gene information between individuality；Described variation：It is little general
Rate event, if it happens, changes on certain genic value that can be on genes of individuals string.
If morphing, randomly select a bit：' 1 ' becomes ' 0 ', ' 0 ' becomes ' 1 '；After mutation operation, one new is produced
Body.
Described population refers to wants the possible potential disaggregation of solve problem, namely initial generation, such as
" 010101010001111100000111000010111100001111000 " is a population, and it is therein each 0 or 1
It is an individual, a population just obtains a generation after a genetic operator operation.
Beneficial effects of the present invention：The present invention pays the utmost attention to big in the case where all vehicle stand-by period are considered
The stand-by period of passenger traffic volume public transport, while by model prediction, can obtain being optimal next unit interval traffic flow
Current traffic lamp scheduling scheme, so as to improve crossing traffic efficiency, reduce the flat of vehicle especially big passenger traffic volume vehicle
The stand-by period, time of the wagon flow by traffic lights crossing is have compressed, optimize traffic flow.The present invention improves perfect intelligent friendship
Way system technology frame, improves citizens' activities quality and alleviates the problems such as traffic jam.
Description of the drawings
Fig. 1 is the configuration diagram for implementing the present invention；
Fig. 2 is flow chart of the present invention；
Fig. 3 is embodied as flow chart for the present invention；
Fig. 4 is somewhere subregion street intersections rough schematic view in the present invention；
Fig. 5 is traffic flow main direction schematic diagram in the present invention；
Fig. 6 is traffic intersection type map in the present invention；
Fig. 7 is autoregression model FPE criterion function curve synoptic diagrams in the present invention；
Fig. 8 is s- in the present invention>The next unit interval vehicle flowrate schematic diagram in k paths；
Fig. 9 is that traffic flow diagram is detained at crossing of the present invention.
Specific embodiment
With reference to specific examples below and accompanying drawing, the present invention is described in further detail.The process of the enforcement present invention,
Condition, experimental technique etc., in addition to the following content for specially referring to, are the universal knowledege and common knowledge of this area, this
It is bright that content is not particularly limited.
Refering to Fig. 1 and Fig. 2, implement the instance graph of framework of the present invention, comprising three big modules：Traffic lights network, traffic fluxion
According to cloud and scheduler.The traffic flow situation at each crossing of the sensor meeting Real-time Collection at each crossing in traffic lights network, and in fact
When pass to traffic flow data cloud storage and get off.Receiver then receives the traffic lights scheduling strategy for carrying out child scheduler, while arranging each
The traffic light status at individual crossing.Three data acquisition systems are stored in traffic flow data cloud：Real-time traffic flow data set, training set and pre-
Survey collection.Real-time traffic flow data set as its name suggests, stores the real time data from sensor, and provides algorithm in real time to scheduler
Required real-time traffic flow data.Historical data out of date is then stored in training set as training data.Training set can
Prediction model parameterses are trained to provide historical data to forecast model.Forecast set is then stored and predicted down from prediction algorithm
The traffic flow data of one unit interval, and the fitness function being supplied in scheduler.Scheduler is whole scheduling architecture
Core.It processes real-time traffic flow data and prediction data in traffic flow data cloud by control algolithm, while producing
Raw scheduling scheme simultaneously the receiver of traffic lights network to of sending.Flow process of the present invention is as follows：1) gene code is carried out, is entered with two
In code processed ' 0 ' represents horizontal wagon flow, and with ' 1 ' vertical wagon flow is represented, and then initializes, and definition is initial comprising number of individual
Population；2. fitness evaluation is carried out, and the wherein parameter in fitness function is calculated by forecast model；3) heredity is operated to calculate
Son, including select, intersect and make a variation；4) judge whether to meet stopping criterion for iteration, if being unsatisfactory for, continue iteration, if meeting
Iteration is then exited, and is decoded, each character is converted into into the traffic lights scheduling scheme at the crossing.Corresponding data flow is such as
Under：Sensor transmits real-time traffic flow data, in being stored in traffic flow data cloud.In cloud real-time traffic flow data set on the one hand to
The present invention provides data, and on the one hand historical data is put in training set.Prediction algorithm in scheduler is instructed using in data cloud
Practice the historical data of collection training prediction model parameterses, and forecast set prediction data being stored in data cloud.Forecast set to
Dispatching algorithm provides prediction data.Scheduler generation optimal scheduling scheme, and send the receiver of traffic lights network to, so as to turn
Change traffic light status.
Refering to Fig. 3, from 6 points of morning at 8 points in evening, 14 hours altogether were test period of the present invention per 30 seconds
One unit interval T, common 1680T.In each unit interval T, scheduler all can be calculated optimum using the present invention
Traffic lights scheduling scheme.The present invention can produce the traffic scheduling scheme of optimum in each unit interval, and this can be regarded as
Real-Time Scheduling controls the traffic light status at each crossing.
Refering to Fig. 4, traffic scene includes altogether 45 crossings, and crossing type is divided into crossroad and T junction.In order to
45 crossings are carried out initialization coding by the present invention using binary system used in the traffic scene, and ' 0 ' represents crossing wagon flow master
Body direction is level, and ' 1 ' represents that the crossing wagon flow main direction is vertical.First, 45 crossings in experiment have been all
There is respective identification name, encode for convenience, need to respectively give order ID to this 45 crossings, can be obtained by order ID
Know position of the corresponding character in crossing in coded string.Illustrate：Tl4 orders ID are 3, then show in coded string
After the decoding of 4th character (coded string first character subscript is from the beginning of 0) it is corresponding be crossing tl4 phenotype.Its
It is secondary, using binary coding, realize the mapping from phenotype to genotype.
" 010101010001111100000111000010111100001111000 " is that individual an of random initializtion is right in population
The binary coding answered, comprising 45 characters, corresponds to respectively 45 crossings in experiment scene.In character string after each Character decoder
Phenotype it is corresponding be exactly each crossing in road network vehicle flowrate direction state, then according to the vehicle flowrate direction at each crossing
The traffic light status at the crossing just can be set.
Refering to Fig. 5, in emulation traffic intersection scene, according to street rough schematic view (Fig. 4), traffic flow main direction can
To be divided into two kinds：Horizontal wagon flow and vertical wagon flow, the figure is shown crossroad access wagon flow main direction schematic diagram.According to
Crossing wagon flow main direction can since the traffic light status at each crossing are set, it is possible to use wagon flow main direction is used as table
Existing type.Using binary coding representation genotype, horizontal wagon flow is represented with ' 0 ', ' 1 ' represents vertical wagon flow.So, from phenotype
Mapping to genotype is exactly horizontal wagon flow corresponding ' 0 ', vertical wagon flow correspondence ' 1 '.
Refering to Fig. 6, the type at crossing is divided into five kinds, and it is exactly T junction that each crossing type is not crossroad.Cross
Crossing includes 4 paths, and T junction includes 3 paths.
Refering to Fig. 7, experiment determines autoregression model exponent number using FPE criterion functions, and concrete operations are as follows：According to from low
Rank to the mode of high-order sets up AR models, and calculates corresponding FPE values, the exponent number for therefrom selecting the FPE values of minimum to be tackled
As the exponent number of model.With the rising of model order, FPE value general trends are to decline.
Refering to Fig. 8, when the purpose of the present invention is exactly to lure next unit into by the traffic lights scheduling of current one time
Between in road network global traffic flow still can be optimal.In order to be advanced by each crossing traffic stream mode of solution next moment,
Need to predict vehicle flowrate of the next unit interval into each crossing per paths.This paths from crossing s to crossing k
On, wherein：
A () waits wagon flow (SF) to represent the vehicle flowrate stopped in the unit interval；
B () straight line wagon flow (SIF), left wagon flow (LF) and right wagon flow (RF) are represented in the unit interval at s crossings from other
Path is upper to s->Vehicle flowrate on k this paths；
(c) pre- flow measurement (PF) represent the next unit interval predicted by forecast model on this path may stream come in
Vehicle flowrate；
Remaining vehicle flowrate of this path after the scheduling of current time unit be SF, SIF, LF and RF and, it is and next single
The vehicle flowrate that possible stream is come on this path of time of position is PF.So to sum up, special bus of this path in the next unit interval
Flow is the wagon flow that the remaining vehicle flowrate after the scheduling of current time unit is come in possible stream on the next one this path of unit interval
The summation of amount.
This paths of crossing s to crossing k are as follows in the special bus flow rate calculation formula of next unit interval：
Flow(s->k)(ti+1)=SF (ti)+RF(ti)
+SIF(ti)+LF(ti)
+PF(s->k)(ti+1)。
Refering to Fig. 9, it is shown that 5 crossings, s, k, l, m, n.For the k of crossing, its vertical direction is detained traffic current
The size of amount is that this two paths is detained vehicle number sum to crossing k for crossing m to crossing k and crossing n, and its horizontal direction is detained friendship
The size of flow of being open to traffic is crossing l to crossing k and crossing s this two paths is detained vehicle number sum to crossing k, wherein the present invention
Define a big passenger traffic volume car and be detained big passenger traffic cars delay non-equal to five.Vertically and horizontally it is detained traffic current gauge
Calculate formula as follows：
(1)VP(ti+1)=Flow (m->k)(ti+1)+Flow(n->k)(ti+1)
(2)HP(ti+1)=Flow (s->k)(ti+1)+Flow(l->k)(ti+1)
The protection content of the present invention is not limited to above example.Under the spirit and scope without departing substantially from inventive concept, this
Art personnel it is conceivable that change and advantage be all included in the present invention, and with appending claims as protect
Shield scope.
Claims (4)
1. it is a kind of fusion Self-regression Forecast Model intelligent traffic dispatching method, it is characterised in that comprise the following steps：
Step 1：Gene code is carried out, with ' 0 ' in binary code horizontal wagon flow is represented, represent vertical wagon flow with ' 1 ', then
Initialization, initial population of the definition comprising number of individual；
Step 2：Fitness evaluation is carried out, with variable P fitness is represented, define the quantity that P is that crossing waits vehicle, wherein bus
The weight of freight volume public transport is more than other vehicles；Define fitness function so that the P sums at each crossing are minimum；Fitness function
It is as follows：
min{∑max(VP(ti+1), HP (ti+1))}
Wherein, ti+1The next unit interval of current one time is represented, VP and HP represents respectively wait car vertically and horizontally
Quantity, is predicted by autoregression model；
Step 3：Operation genetic operator, including select, intersect and make a variation；
Step 4：Judge whether to meet stopping criterion for iteration, if being unsatisfactory for, continue iteration, if meeting iteration is exited, go forward side by side
Row decoding, by each character the traffic lights scheduling scheme at the crossing is converted into.
2. intelligent traffic dispatching method as claimed in claim 1, it is characterised in that the autoregression model described in step 2 is as follows
It is shown：
Wherein, yt represents the vehicle flowrate of t unit interval, and θ i represent i-th parameter, and yt-i represents the vehicle flowrate of t-i unit interval,
ε t are that possess the Gaussian white noise that average is that 0, variance is δ.
3. intelligent traffic dispatching method as claimed in claim 1, it is characterised in that the selection described in step 3：Finger guarantees best
Gene be selected and pass to follow-on population, per a generation be all a traffic scheduling scheme, according to fitness to every
A generation is ranked up, and eliminates those fitness low；Described intersection：Refer to by combining and destroying individual gene to carry out
The exchange of gene information between individuality；Described variation：It is small probability event, if it happens, certain of meeting on genes of individuals string
Change on genic value.
4. intelligent traffic dispatching method as claimed in claim 3, it is characterised in that if morphing, randomly select a bit：
' 1 ' becomes ' 0 ', ' 0 ' becomes ' 1 '；After mutation operation, a new individuality is produced.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710085572.8A CN106652497A (en) | 2017-02-17 | 2017-02-17 | Scheduling method for intelligent transportation by fusing self-regression forecast model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710085572.8A CN106652497A (en) | 2017-02-17 | 2017-02-17 | Scheduling method for intelligent transportation by fusing self-regression forecast model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106652497A true CN106652497A (en) | 2017-05-10 |
Family
ID=58846132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710085572.8A Pending CN106652497A (en) | 2017-02-17 | 2017-02-17 | Scheduling method for intelligent transportation by fusing self-regression forecast model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106652497A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108831181A (en) * | 2018-05-04 | 2018-11-16 | 东南大学 | A kind of method for establishing model and system for Forecasting of Travel Time for Public Transport Vehicles |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081853A (en) * | 2010-12-03 | 2011-06-01 | 合肥工业大学 | Self-adaptive multi-level radio network signal lamp system and control method thereof |
| JP2013016075A (en) * | 2011-07-05 | 2013-01-24 | Kumamoto Univ | Information processor, information processing method and program |
| CN103150911A (en) * | 2013-02-07 | 2013-06-12 | 江苏大学 | Method for optimizing signal timing of single intersection based on genetic algorithm |
| CN104408914A (en) * | 2014-10-31 | 2015-03-11 | 重庆大学 | Signal intersection single vehicle stopping delay time estimating method and system based on GPS data |
| CN105869417A (en) * | 2016-06-16 | 2016-08-17 | 兰州理工大学 | Traffic signal control method and system based on combined control |
-
2017
- 2017-02-17 CN CN201710085572.8A patent/CN106652497A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081853A (en) * | 2010-12-03 | 2011-06-01 | 合肥工业大学 | Self-adaptive multi-level radio network signal lamp system and control method thereof |
| JP2013016075A (en) * | 2011-07-05 | 2013-01-24 | Kumamoto Univ | Information processor, information processing method and program |
| CN103150911A (en) * | 2013-02-07 | 2013-06-12 | 江苏大学 | Method for optimizing signal timing of single intersection based on genetic algorithm |
| CN104408914A (en) * | 2014-10-31 | 2015-03-11 | 重庆大学 | Signal intersection single vehicle stopping delay time estimating method and system based on GPS data |
| CN105869417A (en) * | 2016-06-16 | 2016-08-17 | 兰州理工大学 | Traffic signal control method and system based on combined control |
Non-Patent Citations (1)
| Title |
|---|
| 赵彪: "面向全路网交通流优化的交通灯调度方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108831181A (en) * | 2018-05-04 | 2018-11-16 | 东南大学 | A kind of method for establishing model and system for Forecasting of Travel Time for Public Transport Vehicles |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100444210C (en) | Mixed controlling method of single dot signal controlling crossing | |
| CN106548645B (en) | Vehicle route optimization method and system based on deep learning | |
| He et al. | PAMSCOD: Platoon-based arterial multi-modal signal control with online data | |
| CN103593989B (en) | Urban highway traffic public transport priority signal control method | |
| CN107705592A (en) | Towards the coordinating control of traffic signals optimization method of emergency relief vehicle driving path | |
| CN104408948B (en) | Vehicle-mounted-GPS-based public transport priority signal control method of urban road traffic | |
| CN112258841B (en) | Intelligent vehicle risk assessment method based on vehicle track prediction | |
| CN105006158A (en) | Single road intersection traffic signal control method based on real-time traffic information | |
| Doi et al. | Transitioning to safer streets through an integrated and inclusive design | |
| CN115662113A (en) | Signalized intersection people-vehicle game conflict risk assessment and early warning method | |
| CN108573600A (en) | A kind of induction of driving behavior and the flow-optimized method of local traffic | |
| Alam et al. | Intellegent traffic light control system for isolated intersection using fuzzy logic | |
| Li et al. | Optimization model of transit signal priority control for intersection and downstream bus stop | |
| CN108711285A (en) | A kind of mixed traffic analogy method based on road cross | |
| Zhu et al. | Can automated driving prevent crashes with distracted Pedestrians? An exploration of motion planning at unsignalized Mid-block crosswalks | |
| CN106652497A (en) | Scheduling method for intelligent transportation by fusing self-regression forecast model | |
| CN112562363B (en) | Intersection traffic signal optimization method based on V2I | |
| Tomar et al. | Neural network based lane change trajectory predictions for collision prevention | |
| Horng et al. | Traffic congestion reduce mechanism by adaptive road routing recommendation in smart city | |
| Li et al. | Biobjective optimization and evaluation for transit signal priority strategies at bus stop-to-stop segment | |
| Dong et al. | Determining E-bike drivers’ decision-making mechanisms during signal change interval using the hidden Markov driving model | |
| CN109191836A (en) | A kind of real-time divided lane vehicle delay prediction technique based on IQA | |
| CN113284338A (en) | Method for calculating influence of motor vehicle emergency avoidance no-lamp control pedestrian crossing on traffic flow | |
| Shahriar et al. | Intersection traffic efficiency enhancement using deep reinforcement learning and V2X communications | |
| Li et al. | Modeling and analysis of the impact of urban and rural road reconstruction construction on vehicle capacity. |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |
|
| RJ01 | Rejection of invention patent application after publication |