CN114973660A - Traffic decision method of model linearization iteration updating method - Google Patents
Traffic decision method of model linearization iteration updating method Download PDFInfo
- Publication number
- CN114973660A CN114973660A CN202210522052.XA CN202210522052A CN114973660A CN 114973660 A CN114973660 A CN 114973660A CN 202210522052 A CN202210522052 A CN 202210522052A CN 114973660 A CN114973660 A CN 114973660A
- Authority
- CN
- China
- Prior art keywords
- decision
- traffic
- state
- road
- model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 83
- 230000008901 benefit Effects 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 6
- 238000004088 simulation Methods 0.000 claims abstract description 6
- 238000005457 optimization Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 23
- 238000005259 measurement Methods 0.000 claims description 21
- 239000013598 vector Substances 0.000 claims description 13
- 230000003993 interaction Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 3
- 238000005206 flow analysis Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 8
- 230000000694 effects Effects 0.000 abstract description 7
- 238000010276 construction Methods 0.000 abstract description 4
- 238000013461 design Methods 0.000 abstract description 4
- 239000003795 chemical substances by application Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000011900 installation process Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
-
- 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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
A traffic decision method of a model linearization iteration update method relates to the technical field of traffic informatization, and comprises the following specific steps: step 1, calculating traffic state parameters; step 2, establishing a state prediction model; step 3, model iteration updating; step 4, intelligent decision making: and a regional road game algorithm is given, traffic optimization, regional scheduling and traffic jam dredging are implemented, and smooth road is ensured. The method has the advantages of good decision making effect, high processing speed and high noise resistance, and simulation results show that the decision making accuracy is up to more than 90% in a dense target environment; under the medium-density environment, the correct decision rate of the inference decision method is 91.28%, the processing speed is 0.0936s and less than 1s, theoretical ideas and decision support are provided for government construction, city planning, road length and width design and the like, and a target detection and tracking method is also provided for places and departments using video streams.
Description
Technical Field
The invention relates to the technical field of traffic informatization, in particular to a traffic decision method of a model linearization iterative update method.
Background
Along with the high-speed development of economy and society, urban traffic congestion is increasingly serious, particularly, road congestion, congestion and traffic accidents occur frequently in some super-large cities, and state estimation of a highway traffic flow model is also the basis of work such as highway event detection, traffic analysis, traffic forecast and the like.
In order to solve the problems of traffic congestion and blockage, from the 60 th 20 th century, developed countries began to conduct traffic control research, and the main methods of the research are to establish a mathematical model of traffic flow to control and optimize the whole traffic system by applying operational research and optimal control theory. Although these studies have been widely used, the current traffic prediction decision method ignores the factors of randomness and complexity of traffic system and limitations of traffic flow model, resulting in poor decision effect, slow processing speed and poor noise immunity.
Disclosure of Invention
In view of the above situation, in order to overcome the defects of the prior art, the invention provides a traffic decision method of a model linearization iterative update method, which has a better decision effect, a faster processing speed and a stronger anti-noise capability compared with the prior art.
The invention provides the following technical scheme: the method comprises the following steps:
step 1, calculating traffic state parameters: useful data are excavated to carry out actual traffic condition analysis, and the traffic flow, the traffic flow density and the traffic flow speed are calculated;
step 2, establishing a state prediction model: according to the parameters calculated in the step 1, a traffic flow prediction model is established, wherein the traffic flow prediction model comprises the congestion degree and estimation modeling of the influence state of the surrounding road branches in a future period;
step 3, model iteration updating: in traffic flow analysis application, traffic flow data under various conditions are learned, and prediction model parameters are modified until requirements are met;
step 4, intelligent decision making: and a regional road game algorithm is given, traffic optimization, regional scheduling and traffic jam dredging are implemented, and smooth road is ensured.
Preferably, the iterative update in step 3 adopts an iterative update method to perform information interaction fusion on the state models of different segments, and accordingly updates the state, the state error, the measurement error, the process gain value K (K +1) and the covariance P (K +1| K) thereof.
Preferably, the method for re-initializing the status condition of the iterative update method is as follows:
is provided with
Is the probability of the traffic flow state at time k-1,
are known; then set pi ji ＝Pr{m k ＝m (i) |m k-1 ＝m (j) Is formed by m at the time k-1 k-1 M from traffic state to time k k Probability of transition of traffic state, and it is m-dependent k Traffic conditions as known conditions; the predicted probability of the traffic state at the ith time k is defined as follows:
the above formula can be predicted by measuring from the 1 st time to the k-1 st time;
based on all measurements at time k-1, at the next time k, if the state is estimated to be state m k ＝m (i) Then at the current time k-1, state m k-1 ＝m (j) Has a probability of
Definition of
The following were used:
the hybrid estimate of the states is:
the mixed-state error covariance is:
preferably, the specific method of state interaction of the iterative update method is as follows:
predicted state error covariance:
corresponding measurement error covariance:
interactive gain:
the update state is:
the update covariance is:
preferably, the specific method for updating the probability of the state transition of the iterative update method is as follows:
updating state interaction, and calculating state probability to be defined as:
wherein ,
is defined as:
is the measurement error of the traffic flow at the moment k of the ith segment,
is a result of
Error covariance of (2);
the final update of the state prediction is:
updated final gain:
the corresponding state error hybrid total covariance is updated as:
preferably, the specific method for the model iterative update application is as follows: discussing a block with intersections, and only discussing roads with three equal-length road sections, namely an entrance, a driving road section and an exit, for each road in the intersections;
only the first path section inlet section and the third path section outlet section provide detection data of the traffic flow and the average speed as input quantity and output measured value of the state estimation model, and the first path section head end flow q is taken 0 Average velocity v 0 Taking the density rho of the end of the third link as the input 3 Average velocity v 3 The measured value of (d) is used as an output quantity;
according to the model equation, the expression of each section of the state traffic volume is as follows:
wherein ,ρ4 (k)、v 4 (k) Can be compared with the density rho of the previous time of the previous path section 3 (k-1) and velocity v 3 (k-1) approximation.
The definition is as follows:
order:
thus, there are:
order:
and the output quantity is:
the system state equation can be expressed as:
x(k+1)＝f[x(k)]+Γ[x(k)]w(k)，
y(k+1)＝h[x(k+1)]+v(k+1),
wherein Γ [ x (k) ] is a noise drive matrix;
is represented by the formula:
calculating a partial derivative matrix:
wherein ：
can utilize the recursion equation set
the system noise covariance matrix Q (k) and the measurement noise covariance matrix R (k) are obtained by real-time calculation of measurement data generated by simulation.
Preferably, the intelligent decision in step 4 is to give the driver a prediction of the road condition through the decision system from the video at the current moment and to give a clear road near the driving road, further to indicate an exit of the driving road and an entrance of the clear road.
Preferably, the decision rule of the intelligent decision is as follows:
if "condition z is A, decision e is B",
then "if z is a ', and decision e is what should B'? ";
it is possible to define:
that is, conclusion B 'can be synthesized by using A' and the reasoning relation from A to B;
where a is the condition set of the state, and B is the decision set based on the condition a, the above rules can be described simply as follows:
it is known that when a and B, the output is C, i.e. there is an inference rule:
IF A′ AND B′，THEN C′
how much should decision output C ' be when a ' and B '? The following steps may be used:
step (1): first, D is obtained as A × B, and D is xy ＝μ A (x)∧μ B (y) the D matrix is
Step (2): writing D as a column vector DT, i.e. DT ═ D 11 ,d 12 ,…,d 1n ,d 21 ,…d mn ] T ；
And (3): solving a relation matrix R, wherein R is DT multiplied by C;
and (4): obtaining D ' from a ' and B ', D ═ a ' × B ';
and (5): converting D 'into a line vector DT' according to the method in the step (2);
and (6): solving fuzzy inference outputs, i.e.
Preferably, the rule established by the intelligent decision model is as follows:
Q i (t) a vector representing the number of vehicles waiting at the ith intersection at time t, Q i (t)＝[Q i,E (t),Q i,S (t),Q i,W (t),Q i,N (t)]Here Q i,E (t),Q i,S (t),Q i,W (t),Q i,N (t) respectively representing the number of vehicles waiting at the ith intersection in the east, south, west and north directions at the time t;
Q i vector representing number of vehicles threshold at i intersection, Q i ＝[Q i,E ,Q i,S ,Q i,W ,Q i,N ]，
Here Q i,E ,Q i,S ,Q i,W ,Q i,N Threshold values respectively representing the number of waiting vehicles in different directions, wherein the threshold values can be modified according to specific conditions;
s represents the set of all possible policies or actions in a decision, where all possible policies of a decision are a finite set, where all policies are rule sets, and S is set to { S } 1 ,s 2 ,…,s n Each s i The following rules are used:
s 1 : if Q is i,W (t)＞Q i,W And Q i,W (t)＞Q i,W But Q is i,S (t)＜Q i,S And Q i,N (t)＜Q i,N Then the east-west goes straight, and after 10 seconds, the east-west double left turns go straight to 30 seconds east-westAnd the double left-turn red light is lighted;
s 2 : if Q is i,S (t)＞Q i,S And Q i,N (t)＞Q i,N But Q is i,E (t)＜Q i,E And Q i,W (t)＜Q i,W Then the south and north go straight, and after 10 seconds, the south and north double left turns turn until 30 seconds, the south and north and double left turn red lights are lighted;
s 3 : if Q is i,E (t)＜Q i,E And Q i,W (t)＜Q i,W And Q i,N (t)＜Q i,N However Q i,S (t)＞Q i,S Then vehicles turning north and left turning north east are needed to pass;
s 4 : if Q is i,E (t)＞Q i,E And Q i,W (t)＞Q i,W But Q is i,S (t)＞Q i,S And Q i,N (t)＞Q i,N While | Q i,E (t)-Q i,E |＞|Q i,S (t)-Q i,S I and Q i,E (t)-Q i,E |＞|Q i,N (t)-Q i,N I and Q i,W (t)-Q i,W |＞|Q i,S (t)-Q i,S I and Q i,W (t)-Q i,W |＞|Q i,N (t)-Q i,N I, then the east and west go straight,
or the south-north vehicle can select the nearby intersection to shunt into other smooth roads;
s 5 : if Q is i,E (t)＞Q i,E And Q i,W (t)＞Q i,W And Q i,N (t)＞Q i,N But Q is i,S (t)＜Q i,S While | Q i,E (t)-Q i,E |＜|Q i,N (t)-Q i,N I and Q i,W (t)-Q i,W |＜|Q i,N (t)-Q i,N I and Q i,S (t)-Q i,S |＜|Q i,N (t)-Q i,N If the vehicles turn left to the south and the southwest to pass through, or the vehicles turn left to the north and the vehicles turn left to pass through the road, the vehicles can select the nearby intersection to enter other smooth roads;
……。
preferably, the decision coordination rule of the intelligent decision is: dividing the whole traffic coordination process in the region into three levels, wherein the lower level is the coordination between the intersection and the adjacent intersection; the middle layer is the coordination between regional road sections and intersections; the upper layer is the coordination between the zone segment and the adjacent zone segment;
p1, if the vehicle queue number of the intersection 1 exceeds a threshold value, sending a request to an adjacent intersection 2;
p2, responding the request by adjacent intersections, constructing a game tree, representing rule strategies by letters on branches of the game tree, representing the advantages of rule comparison by expression in the block diagram, searching the game tree according to the expression
Finding a balance point;
p3, if the balance exists, the action strategy of the decision is the strategy when the balance is achieved, each decision controls a road junction device according to the strategy, the coordination is finished, and if the balance does not exist, a request is sent to the decision where the decision of the road junction is located;
p4, responding to the request by the regional decision, carrying out game coordination on the decision of the intersection governed by the request, seeking a balance point, and if the balance point does not exist, sending a request to the adjacent decision by the regional decision;
p5. the adjacent section decision responses to the request, game coordination is carried out, equilibrium points are sought, if no equilibrium points exist, the coordination fails, and each decision keeps the original strategy unchanged.
Compared with the prior art, the invention has the beneficial effects that:
the application range is wide: the method has the advantages of accurate prediction estimation value, high prediction speed and good evacuation congestion effect, can fully solve the problem of road congestion, provides theoretical thought and decision support for government construction, city planning, road length and width design and the like, and provides a target detection and estimation method for places and departments using video streams;
(II) high accuracy: in simulation analysis, the method has the advantages of good decision making effect, high processing speed and strong noise resistance, the decision making accuracy is up to more than 90% in a dense target environment, and the correct decision making rate is 91.28% in a medium-density environment and is 8% higher than that of the Agent method in the prior art; the processing speed is 0.0936s and less than 1 s;
and (III) saving resources: the invention can roughly estimate the maximum number of road sections between two detectors on a road, namely estimate the farthest distance between the two detectors, which has direct guiding significance for saving expenditure in the installation process of traffic equipment and reduces resource waste.
Drawings
FIG. 1: the invention provides a system construction process.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the present invention provides a traffic decision method of a model linearization iterative update method, which includes the following steps:
step 1, calculating traffic state parameters: useful data are excavated to carry out actual traffic condition analysis, and the traffic flow, the traffic flow density and the traffic flow speed are calculated;
step 2, establishing a state prediction model: according to the parameters calculated in the step 1, a traffic flow prediction model is established, wherein the traffic flow prediction model comprises the congestion degree and estimation modeling of the influence state of the surrounding road branches in the future period;
step 3, model iteration updating: in the traffic flow analysis application, the traffic flow data under various conditions are learned, and the prediction model parameters are modified until the requirements are met;
step 4, intelligent decision making: and a regional road game algorithm is given, traffic optimization, regional scheduling and traffic jam dredging are implemented, and smooth road is ensured.
Specifically, the traffic flow condition parameters in step 1 are calculated: in the present embodiment, a region is discussedA certain section with crossroad is properly divided into L sections, and the length of each section is delta i In the order of hundreds of meters. The head and tail ends of the whole road are respectively provided with a traffic detector, and actual measurement data is provided as the input of a dynamic model, including traffic flow q i (k) Average velocity v i (k) In that respect The detection period T is 60 seconds, and the period is usually 10-60 seconds. Density of traffic stream ρ i (k) Is formed by the traffic flow q i (k) And average velocity v i (k) Calculated, these several parameters are calculated as follows:
q i (k)＝αρ i (k)v i (k)+(1-α)ρ i+1 (k)v i+1 (k)，
wherein ：
v(ρ)＝v f exp[-(1/b)(ρ/ρ cr ) b ]，
the main variables in the formula have the following meanings: q. q.s i (k) The traffic flow from the i-th section to the i + 1-th section at the moment of kT, rho i (k) Is the density of the traffic stream at the kT time of the i-th section, v i (k) The average speed of the traffic flow space at the ith section kT moment. Delta i For the spatial sampling length, i.e. the segment length of the i-th segment, they are generally taken to be Δ for simplicity. r is i (k) Is the inlet flowrate, s, at the time of kT in the i-th section i (k) The outlet flowrate at time kT of the ith segment.
The parameter in the equation is v f Representing the free running speed of the traffic flow, namely the maximum speed of the current traffic flow; rho cr The density of the traffic flow when the traffic flow reaches the maximum is represented as the critical density; b, tau, gamma, xi, lambda, alpha and the like are adjustment coefficients of the equation.
The formula v (ρ) ═ v f exp[-(1/b)(ρ/ρ cr ) b ]Is a steady-state traffic flow model, describes steady-state traffic intersectionThe speed of the through flow is closely related.
Specifically, step 2, establishing a state prediction model: the following nonlinear system is established for the condition of the traffic flow at the moment k and the measured value thereof:
x(k+1)＝f[x(k)]+Γ[x(k)]w(k)，
y(k+1)＝h[x(k+1)]+v(k+1)，
wherein w (k), v (k) are zero mean noise vectors, and
E[w(k)]＝0,E[w(k)w′(j)]＝Q(k)δ kj ，
E[v(k)]＝0,E[v(k)v′(j)]＝S(k)δ kj ，
q (k) is the system noise variance matrix, S (k) measures the noise matrix, and Γ [ x (k) ] is the noise driving matrix.
Initial state estimation was performed and measured for values as:
the corresponding state covariance is
The error of one measurement is:
the corresponding measurement error covariance is:
the obtained interaction gain is:
the state estimation is updated once as follows:
the primary state covariance update is:
wherein
Given the initial filtered value
And after the initial filtering covariance matrix P (0), the calculation order of the recursion algorithm is:
In order to make the prediction model more accurate in application, the state of the traffic flow model is continuously updated by utilizing the state interaction of each segment, a corresponding partial derivative matrix in a recurrence equation needs to be calculated, an expression which is consistent with the recurrence equation is obtained, and then online recurrence calculation can be carried out, and a system state estimation value at each moment is obtained.
Specifically, in the step 3, an iterative update method is adopted for iterative update of the model, information interaction fusion is performed on different section state models, and accordingly, the state error, the measurement error, the process gain value K (K +1) and the covariance P (K +1| K) are updated.
First, linearization is performed in the vicinity of an interest point, which is a state of a moving target at the time of the i-th stage k in this embodiment, and equations x (k +1) ═ f [ x (k)) ] + Γ [ x (k)) ] w (k) and y (k +1) ═ h [ x (k +1) ] + v (k +1) are linearized as follows:
x i (k+1)＝F i (k)x i (k)+u i (k)+G i (k)w i (k)，
y i (k)＝H i (k)x i (k)+v i (k)。
and performing state updating on different road sections, wherein the updating method comprises the following steps:
(1) and (3) state condition reinitialization of an iterative updating method:
is provided with
Is the probability of the traffic flow state at time k-1,
are known; then set pi ji ＝Pr{m k ＝m (i) |m k-1 ＝m (j) Is formed by m at the time k-1 k-1 M from traffic state to time k k Probability of transition of traffic state, and it is m-dependent k Traffic status as a known condition; the predicted probability of the traffic state at the ith time k is defined as follows:
the above formula can be predicted by measuring from the 1 st time to the k-1 st time;
based on the measurements at all times k-1,at the next time k, if the state is estimated to be state m k ＝m (i) Then at the current time k-1, state m k-1 ＝m (j) Has a probability of
Definition of
The following were used:
the hybrid estimate of the states is:
the mixed-state error covariance is:
(2) the specific method of the state interaction of the iterative update method comprises the following steps:
predicted state error covariance:
corresponding measurement error covariance:
interactive gain:
the update state is:
the updated covariance is:
(3) the specific method for updating the state transition probability of the iterative update method comprises the following steps:
updating state interaction, and calculating state probability to be defined as:
wherein ,
is defined as:
is the measurement error of the traffic flow at the moment k of the ith segment,
is a result of
Error covariance of (2);
the final update of the state prediction is:
updated final gain:
the corresponding state error hybrid total covariance updates are:
the specific method for model iteration update application comprises the following steps: discussing a block with intersections, and only discussing roads with three equal-length road sections, namely an entrance, a driving road section and an exit, for each road in the intersections;
only the first path section inlet section and the third path section outlet section provide detection data of the traffic flow and the average speed as input quantity and output measured value of the state estimation model, and the first path section head end flow q is taken 0 Average velocity v 0 Taking the density rho of the end of the third link as the input 3 Average velocity v 3 The measured value of (d) is used as an output quantity;
according to the model equation, the expression of the state traffic volume of each section is as follows:
wherein ,ρ4 (k)、v 4 (k) Can be compared with the density rho of the previous time of the previous path section 3 (k-1) and velocity v 3 (k-1) approximation.
The definition is as follows:
order:
thus, there are:
order:
and the output quantity is:
the system state equation can be expressed as:
x(k+1)＝f[x(k)]+Γ[x(k)]w(k)，
y(k+1)＝h[x(k+1)]+v(k+1),
wherein Γ [ x (k) ] is a noise drive matrix;
is represented by the formula:
calculating a partial derivative matrix:
wherein ：
can utilize the recursion equation set
the system noise covariance matrix Q (k) and the measurement noise covariance matrix R (k) are obtained by real-time calculation of measurement data generated by simulation.
Specifically, the intelligent decision in step 4 is to give a prediction of the road condition of the driver and give a clear road near the driving road by the decision system provided by the embodiment from the video at the current moment, and further indicate an exit of the driving road and an entrance of the clear road. In the design of the road traffic decision system, the traffic state of each road section in the road must be used as feedback information for determining the control quantity such as speed limit, entrance regulation rate, information distribution and the like.
The decision rule of the intelligent decision is as follows:
if "condition z is A, decision e is B",
then "if z is a ', and decision e is what should B'? ";
it is possible to define:
that is, conclusion B 'can be synthesized by using A' and the reasoning relation from A to B;
where A is the condition set of the state, and B is the decision set based on condition A, the above rules can be described simply as follows:
it is known that when a and B, the output is C, i.e. there is an inference rule:
IF A′ AND B′，THEN C′
how much should decision output C ' be when a ' and B '? The following steps may be used:
step (1): first, D is obtained as A × B, and D is xy ＝μ A (x)∧μ B (y) the D matrix is
Step (2): writing D as a column vector DT, i.e. DT ═ D 11 ,d 12 ,…,d 1n ,d 21 ,…d mn ] T ；
And (3): solving a relation matrix R, wherein R is DT multiplied by C;
and (4): obtaining D ' from a ' and B ', D ═ a ' × B ';
and (5): converting D 'into a line vector DT' according to the method in the step (2);
and (6): solving fuzzy inference outputs, i.e.
The rules established by the intelligent decision model are as follows:
Q i (t) a vector representing the number of vehicles waiting at the ith intersection at time t, Q i (t)＝[Q i,E (t),Q i,S (t),Q i,W (t),Q i,N (t)]Here Q i,E (t),Q i,S (t),Q i,W (t),Q i,N (t) respectively representing the number of vehicles waiting at the ith intersection in the east, south, west and north directions at the time t;
Q i vector representing number of vehicles threshold at i intersection, Q i ＝[Q i,E ,Q i,S ,Q i,W ,Q i,N ]，
Here Q i,E ,Q i,S ,Q i,W ,Q i,N Threshold values respectively representing the number of waiting vehicles in different directions, wherein the threshold values can be modified according to specific conditions;
s represents the set of all possible policies or actions in a decision, where all possible policies of a decision are a finite set, where all policies are rule sets, and S is set to { S } 1 ,s 2 ,…,s n Each s i The following rules are used:
s 1 : if Q is i,W (t)＞Q i,W And Q i,W (t)＞Q i,W However Q i,S (t)＜Q i,S And Q i,N (t)＜Q i,N Then the east-west goes straight, after 10 seconds, the east-west double left turns go 30 seconds, and the double left turn red lights are on;
s 2 : if Q is i,S (t)＞Q i,S And Q i,N (t)＞Q i,N But Q is i,E (t)＜Q i,E And Q i,W (t)＜Q i,W Then the south and north go straight, and after 10 seconds, the south and north double left turns turn until 30 seconds, namely the south and north double left turn red lights are lighted;
s 3 : if Q is i,E (t)＜Q i,E And Q i,W (t)＜Q i,W And Q i,N (t)＜Q i,N However Q i,S (t)＞Q i,S Then vehicles turning north and left turning north east are needed to pass;
s 4 : if Q i,E (t)＞Q i,E And Q i,W (t)＞Q i,W But Q is i,S (t)＞Q i,S And Q i,N (t)＞Q i,N While | Q i,E (t)-Q i,E |＞|Q i,S (t)-Q i,S I and Q i,E (t)-Q i,E |＞|Q i,N (t)-Q i,N I and Q i,W (t)-Q i,W |＞|Q i,S (t)-Q i,S I and Q i,W (t)-Q i,W |＞|Q i,N (t)-Q i,N I, then thingsThe straight-going is carried out,
or the south and north vehicles can select the nearby intersection to shunt into other smooth roads;
s 5 : if Q is i,E (t)＞Q i,E And Q i,W (t)＞Q i,W And Q i,N (t)＞Q i,N But Q is i,S (t)＜Q i,S While | Q i,E (t)-Q i,E |＜|Q i,N (t)-Q i,N I and Q i,W (t)-Q i,W |＜|Q i,N (t)-Q i,N I and Q i,S (t)-Q i,S |＜|Q i,N (t)-Q i,N If the vehicles turn left to the south and the southwest, or the vehicles turning to the north and the east can select the nearby intersection to shunt into other smooth roads;
……。
these rules above are common: since there are 2 cases in which the traffic flow in each direction is compared with the threshold value, four directions are considered simultaneously, and the total is 2 4 Species, like s 1 、s 2 、s 3 A total of 6 of these cases, then 2 remain 4 -6-10 cases need to consider the difference between the traffic flow in each direction and the threshold; however, there are 4 differences, each of which has 3 cases compared with the 3 differences in the other directions, and thus there are 3 × 10 ═ 30 cases, and 30+6 ═ 36 cases, so that there are 36 rules defined, i.e. the set S has 36 elements S i ， i＝1,2,…,36。
At a certain intersection at a certain moment, if a certain rule s i The rule is optimal compared with any rule, so that the road is more smooth, namely the crossing dredging time is short, and then the rule s i Winning game and marking as
The coordination model is a game algorithm as follows.
A game with n rules is described as G ═ S, U, where S is a rule set and U is the advantage of comparing two rules, e.g., making its roads more clear, or the intersection clearing time is short, or congestion is cleared, etc. If there are the beta advantages that exist,then set U to { U ═ U 1 ,u 2 ,…,u β }. If the problem is strategic
Is a Nash equalization, it must satisfy
in the formula ：
strategy representing the ith rule selection;
a policy representing all rules except i; u. of j Indicating the jth advantage. Or the data are sorted according to the advantages, and the balance under Nash balance can be obtained.
The decision coordination rule of the intelligent decision is as follows: dividing the whole traffic coordination process in the region into three levels, wherein the lower level is the coordination between the intersection and the adjacent intersection; the middle layer is the coordination between regional road sections and intersections; the upper layer is the coordination between the zone segment and its adjacent zone segments;
p1, if the vehicle queue number of the intersection 1 exceeds a threshold value, sending a request to an adjacent intersection 2;
p2, responding the request by adjacent intersections, constructing a game tree, representing rule strategies by letters on branches of the game tree, representing the advantages of rule comparison by expression in the block diagram, searching the game tree according to the expression
Finding a balance point;
p3, if the balance exists, the action strategy of the decision is the strategy when the balance is achieved, each decision controls a road junction device according to the strategy, the coordination is finished, and if the balance does not exist, a request is sent to the decision where the decision of the road junction is located;
p4, responding to the request by the regional decision, carrying out game coordination on the decision of the intersection governed by the request, seeking a balance point, and if the balance point does not exist, sending a request to the adjacent decision by the regional decision;
p5. the adjacent section decision responses to the request, carries on game coordination, seeks the equilibrium point, if the equilibrium point does not exist, the coordination fails, each decision keeps the original strategy unchanged.
In simulation analysis, the decision method provided by the invention is better than the existing Agent method, the invention not only has better decision effect and faster processing speed, but also has stronger noise-resistant capability, the decision accuracy rate is up to more than 90% under the dense target environment, and the correct decision rate of the inference decision method is 91.28% under the medium-density environment and is 8% higher than that of the existing Agent method; the processing speed was 0.0936s and less than 1 s.
The invention is applied to roads of three equal-length road sections at each intersection, each road of the intersection is provided with an entrance road, a driving road and an exit road, the prediction of the traffic flow density and the traffic flow speed of the roads of the three road sections is obtained by a prediction model, a method of combining quantification and qualification is adopted, the comprehensive evaluation is carried out, and according to the actual control requirement and the setting of sampling time, the number of the state quantity which can be accurately estimated can be determined by the maximum time and the estimation precision required by calculating the state data once under a certain condition, so that the maximum road section number between two detectors on the road can be roughly estimated, the maximum distance between the two detectors can be actually estimated, and the method has direct guiding significance on the expense saving in the installation process of traffic equipment and reduces the resource waste.
In conclusion, the method has the advantages of accurate prediction estimation value, high prediction speed and good evacuation congestion effect, solves the problem of road congestion, provides theoretical ideas and decision support for government construction, city planning, road length and width design and the like, and provides a target detection and tracking method for places and departments using video streams.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical scope of the present invention by equivalent replacement or change according to the technical solution and the inventive concept of the present invention within the technical scope of the present invention.
Claims (10)
1. A traffic decision method of a model linearization iteration update method is characterized by comprising the following steps:
step 1, calculating traffic state parameters: useful data are excavated to carry out actual traffic condition analysis, and the traffic flow, the traffic flow density and the traffic flow speed are calculated;
step 2, establishing a state prediction model: according to the parameters calculated in the step 1, a traffic flow prediction model is established, wherein the traffic flow prediction model comprises the congestion degree and estimation modeling of the influence state of the surrounding road branches in the future period;
step 3, model iteration updating: in traffic flow analysis application, traffic flow data under various conditions are learned, and prediction model parameters are modified until requirements are met;
step 4, intelligent decision making: and a regional road game algorithm is given, traffic optimization, regional scheduling and traffic jam dredging are implemented, and smooth road is ensured.
2. The traffic decision method of the model linearization iterative update method as claimed in claim 1, wherein the model iterative update in step 3 adopts the iterative update method to perform information interaction fusion on different section state models, and accordingly, the state error, the measurement error, the process gain value K (K +1) and the covariance P (K +1| K) thereof are updated.
3. The traffic decision method of the model linearization iterative update method as claimed in claim 2, wherein the method for reinitializing the status condition of the iterative update method is as follows:
is provided with
Is the probability of the traffic flow state at time k-1,
are known; then set pi ji ＝Pr{m k ＝m (i) |m k-1 ＝m (j) Is formed by m at the time k-1 k-1 M from traffic state to time k k Probability of transition of traffic state, and it is m-dependent k Traffic conditions as known conditions; the predicted probability of the traffic state at the ith time k is defined as follows:
the above formula can be predicted by measuring from the 1 st time to the k-1 st time;
based on all measurements at time k-1, at the next time k, if the state is estimated to be state m k ＝m (i) Then at the current time k-1, state m k-1 ＝m (j) Has a probability of
Definition of
The following:
the hybrid estimate of the states is:
the mixed-state error covariance is:
4. the traffic decision method of the model linearization iterative update method according to claim 2, wherein the specific method of the state interaction of the iterative update method is as follows:
predicted state error covariance:
corresponding measurement error covariance:
interactive gain:
the update state is:
the updated covariance is:
5. the traffic decision method of the model linearization iterative update method as claimed in claim 2, wherein the specific method for updating the probability of the state transition of the iterative update method is:
updating state interaction, and calculating state probability to be defined as:
wherein ,
is defined as:
is the measurement error of the traffic flow at the moment k of the ith segment,
is a result of
Error covariance of (2);
the final update of the state prediction is:
updated final gain:
the corresponding state error hybrid total covariance updates are:
6. the traffic decision method of the model linearization iterative update method according to claim 1, wherein the specific method for applying the model iterative update is as follows: discussing a block with intersections, and only discussing roads with three equal-length road sections, namely an entrance, a driving road section and an exit, for each road in the intersections;
only the inlet section of the first path section and the outlet section of the third path section provide detection data of the traffic flow and the average speed as input quantities of the state estimation modelAnd outputting the measured value, and taking the head end flow q of the first path section 0 Average velocity v 0 Taking the density rho of the end of the third link as the input value 3 Average velocity v 3 The measured value of (d) is used as an output quantity;
according to the model equation, the expression of the state traffic volume of each section is as follows:
wherein ,ρ4 (k)、v 4 (k) Can be compared with the density rho of the previous time of the previous path section 3 (k-1) and velocity v 3 (k-1) approximation.
The definition is as follows:
order:
thus, there are:
order:
and the output quantity is:
the system state equation can be expressed as:
x(k+1)＝f[x(k)]+Γ[x(k)]w(k)，
y(k+1)＝h[x(k+1)]+v(k+1)，
wherein Γ [ x (k) ] is a noise driving matrix;
is represented by the formula:
calculating a partial derivative matrix:
wherein ：
can utilize the recursion equation set
the system noise covariance matrix Q (k) and the measurement noise covariance matrix R (k) are obtained by real-time calculation of measurement data generated by simulation.
7. The traffic decision method according to claim 1, wherein the intelligent decision in step 4 is based on the current video, and the decision system gives the driver a prediction of road conditions and a clear road around the driving road, and further indicates an exit of the driving road and an entrance of the clear road.
8. The traffic decision method of the model linearization iterative update method as claimed in claim 7, wherein the decision rule of the intelligent decision is as follows:
if "condition z is A, decision e is B",
then "if z is a ', and decision e is what should B'? ";
it is possible to define:
that is, conclusion B 'can be obtained by synthesizing A' and the reasoning relationship from A to B;
where a is the condition set of the state, and B is the decision set based on the condition a, the above rules can be described simply as follows:
it is known that when a and B, the output is C, i.e. there is an inference rule:
IF A′ AND B′，THEN C′
how much should decision output C ' be when a ' and B '? The following steps may be used:
step (1): first, D is obtained as A × B, and D is xy ＝μ A (x)^μ B (y) obtaining a D matrix of
Step (2): writing D as a column vector DT, i.e. DT ═ D 11 ,d 12 ,…,d 1n ,d 21 ,…d mn ] T ；
And (3): solving a relation matrix R, wherein R is DT multiplied by C;
and (4): obtaining D ' from a ' and B ', D ═ a ' × B ';
and (5): converting D 'into a line vector DT' according to the method in the step (2);
and (6): finding fuzzy inference outputs, i.e.
9. The traffic decision method of the model linearization iterative update method as claimed in claim 7, wherein the rule established by the intelligent decision model is:
Q i (t) a vector representing the number of vehicles waiting at the ith intersection at time t, Q i (t)＝[Q i,E (t),Q i,S (t),Q i,W (t),Q i,N (t)]Here Q i,E (t),Q i,S (t),Q i,W (t),Q i,N (t) respectively representing the number of vehicles waiting at the ith intersection in the east, south, west and north directions at the time t;
Q i vector representing number of vehicles threshold at i intersection, Q i ＝[Q i,E ,Q i,S ,Q i,W ,Q i,N ]Here Q i,E ,Q i,S ,Q i,W ,Q i,N Threshold values respectively representing the number of waiting vehicles in different directions, wherein the threshold values can be modified according to specific conditions;
s represents the set of all possible policies or actions in a decision, where all possible policies of a decision are a finite set, where all policies are rule sets, and S is set to { S } 1 ,s 2 ,…,s n Each s i The following rules are used:
s 1 : if Q is i,W (t)＞Q i,W And Q i,W (t)＞Q i,W But Q is i,S (t)＜Q i,S And Q i,N (t)＜Q i,N Then the east-west goes straight, after 10 seconds, the east-west double left turns go 30 seconds, and the double left turn red lights are on;
s 2 : if Q is i,S (t)＞Q i,S And Q i,N (t)＞Q i,N But Q is i,E (t)＜Q i,E And Q i,W (t)＜Q i,W Then the south and north go straight, and after 10 seconds, the south and north double left turns turn until 30 seconds, the south and north and double left turn red lights are lighted;
s 3 : if Q i,E (t)＜Q i,E And Q i,W (t)＜Q i,W And Q i,N (t)＜Q i,N But Q is i,S (t)＞Q i,S Then vehicles turning north and left turning north east are needed to pass;
s 4 : if Q is i,E (t)＞Q i,E And Q i,W (t)＞Q i,W But Q is i,S (t)＞Q i,S And Q i,N (t)＞Q i,N While | Q i,E (t)-Q i,E |＞|Q i,S (t)-Q i,S I and Q i,E (t)-Q i,E |＞|Q i,N (t)-Q i,N I and Q i,W (t)-Q i,W |＞|Q i,S (t)-Q i,S I and Q i,W (t)-Q i,W |＞|Q i,N (t)-Q i,N If yes, then the vehicle goes straight, or the vehicles in the south and north can select the nearby intersection to shunt into other smooth roads;
s 5 : if Q is i,E (t)＞Q i,E And Q i,W (t)＞Q i,W And Q i,N (t)＞Q i,N But Q is i,S (t)＜Q i,S While | Q i,E (t)-Q i,E |＜|Q i,N (t)-Q i,N I and Q i,W (t)-Q i,W |＜|Q i,N (t)-Q i,N I and Q i,S (t)-Q i,S |＜|Q i,N (t)-Q i,N If the vehicles turn left to the south and the southwest to pass through, or the vehicles turn left to the north and the vehicles turn left to pass through the road, the vehicles can select the nearby intersection to enter other smooth roads;
……。
10. the traffic decision method of the model linearization iterative update method according to any one of claims 1, 7, 8 and 9, wherein the decision coordination rule of the intelligent decision is: the whole traffic coordination process in the region is divided into three levels, wherein the lower level is the coordination between the intersection and the adjacent intersection; the middle layer is the coordination between regional road sections and intersections; the upper layer is the coordination between the zone segment and its adjacent zone segments;
p1, if the vehicle queue number of the intersection 1 exceeds a threshold value, sending a request to an adjacent intersection 2;
p2, responding the request by adjacent intersections, constructing a game tree, representing rule strategies by letters on branches of the game tree, representing the advantages of rule comparison by expression in the block diagram, searching the game tree according to the expression
Finding a balance point;
p3, if the balance exists, the action strategy of the decision is the strategy when the balance is achieved, each decision controls a road junction device according to the strategy, the coordination is finished, and if the balance does not exist, a request is sent to the decision where the decision of the road junction is located;
p4, responding to the request by the regional decision, carrying out game coordination on the decision of the intersection governed by the request, seeking a balance point, and if the balance point does not exist, sending a request to the adjacent decision by the regional decision;
p5. the adjacent section decision responses to the request, carries on game coordination, seeks the equilibrium point, if the equilibrium point does not exist, the coordination fails, each decision keeps the original strategy unchanged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210522052.XA CN114973660B (en) | 2022-05-13 | 2022-05-13 | Traffic decision method of model linearization iterative updating method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210522052.XA CN114973660B (en) | 2022-05-13 | 2022-05-13 | Traffic decision method of model linearization iterative updating method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114973660A true CN114973660A (en) | 2022-08-30 |
| CN114973660B CN114973660B (en) | 2023-10-24 |
Family
ID=82982520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210522052.XA Active CN114973660B (en) | 2022-05-13 | 2022-05-13 | Traffic decision method of model linearization iterative updating method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114973660B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011157745A1 (en) * | 2010-06-15 | 2011-12-22 | The Provost, Fellows And Scholars Of The College Of The Holy And Undivided Trinity Of Queen Elizabeth, Near Dublin | Decentralised autonomic system and method for use in an urban traffic control environment |
| US20150102945A1 (en) * | 2011-12-16 | 2015-04-16 | Pragmatek Transport Innovations, Inc. | Multi-agent reinforcement learning for integrated and networked adaptive traffic signal control |
| US20190164418A1 (en) * | 2017-11-30 | 2019-05-30 | Volkswagen Ag | System and method for predicting and maximizing traffic flow |
| WO2020087846A1 (en) * | 2018-10-31 | 2020-05-07 | 东南大学 | Navigation method based on iteratively extended kalman filter fusion inertia and monocular vision |
| WO2021109318A1 (en) * | 2019-12-03 | 2021-06-10 | 东南大学 | Method for estimating and predicting short-term traffic circulation state of urban road network |
| CN113053120A (en) * | 2021-03-19 | 2021-06-29 | 宁波亮控信息科技有限公司 | Traffic signal lamp scheduling method and system based on iterative learning model predictive control |
| US20210209939A1 (en) * | 2020-12-08 | 2021-07-08 | Harbin Engineering University | Large-scale real-time traffic flow prediction method based on fuzzy logic and deep LSTM |
| US20210302974A1 (en) * | 2020-03-26 | 2021-09-30 | Mitsubishi Electric Research Laboratories, Inc. | Adaptive Optimization of Decision Making for Vehicle Control |
| WO2021232387A1 (en) * | 2020-05-22 | 2021-11-25 | 南京云创大数据科技股份有限公司 | Multifunctional intelligent signal control system |
| CN113780624A (en) * | 2021-08-09 | 2021-12-10 | 同济大学 | City road network signal coordination control method based on game equilibrium theory |
-
2022
- 2022-05-13 CN CN202210522052.XA patent/CN114973660B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011157745A1 (en) * | 2010-06-15 | 2011-12-22 | The Provost, Fellows And Scholars Of The College Of The Holy And Undivided Trinity Of Queen Elizabeth, Near Dublin | Decentralised autonomic system and method for use in an urban traffic control environment |
| US20150102945A1 (en) * | 2011-12-16 | 2015-04-16 | Pragmatek Transport Innovations, Inc. | Multi-agent reinforcement learning for integrated and networked adaptive traffic signal control |
| US20190164418A1 (en) * | 2017-11-30 | 2019-05-30 | Volkswagen Ag | System and method for predicting and maximizing traffic flow |
| WO2020087846A1 (en) * | 2018-10-31 | 2020-05-07 | 东南大学 | Navigation method based on iteratively extended kalman filter fusion inertia and monocular vision |
| WO2021109318A1 (en) * | 2019-12-03 | 2021-06-10 | 东南大学 | Method for estimating and predicting short-term traffic circulation state of urban road network |
| US20210302974A1 (en) * | 2020-03-26 | 2021-09-30 | Mitsubishi Electric Research Laboratories, Inc. | Adaptive Optimization of Decision Making for Vehicle Control |
| WO2021232387A1 (en) * | 2020-05-22 | 2021-11-25 | 南京云创大数据科技股份有限公司 | Multifunctional intelligent signal control system |
| US20210209939A1 (en) * | 2020-12-08 | 2021-07-08 | Harbin Engineering University | Large-scale real-time traffic flow prediction method based on fuzzy logic and deep LSTM |
| CN113053120A (en) * | 2021-03-19 | 2021-06-29 | 宁波亮控信息科技有限公司 | Traffic signal lamp scheduling method and system based on iterative learning model predictive control |
| CN113780624A (en) * | 2021-08-09 | 2021-12-10 | 同济大学 | City road network signal coordination control method based on game equilibrium theory |
Non-Patent Citations (6)
| Title |
|---|
| DU JI-YONG等: "Game theory based multi-UAV cooperative searching model and fast solution approach", 《JOURNAL OF SHANGHAI JIAO TONG UNIVERSITY》 * |
| 夏新海;许伦辉;: "引入谈判博弈的Q-学习下的城市交通信号协调配时决策", 科学技术与工程, no. 33 * |
| 徐焕良;王珂;任守纲;王浩云;: "基于非合作博弈的分布式模型预测控制优化算法", 计算机工程与科学, no. 07 * |
| 李振龙, 陈德望: "交通信号区域协调优化的多智能体博弈模型", 公路交通科技, no. 01 * |
| 杜继永;张凤鸣;毛红保;刘华伟;杨骥;: "多UAV协同搜索的博弈论模型及快速求解方法", 上海交通大学学报, no. 04 * |
| 邢珊珊;谷远利;沈立杰;杨骁路;庄广新;: "基于速度的城市快速路交通拥堵预测研究", 交通信息与安全, no. 02 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114973660B (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670277B (en) | Travel time prediction method based on multi-mode data fusion and multi-model integration | |
| WO2021218235A1 (en) | Road traffic jam early warning method and system | |
| Lebacque et al. | Introducing buses into first-order macroscopic traffic flow models | |
| CN103996289B (en) | A kind of flow-speeds match model and Travel Time Estimation Method and system | |
| CN101639978B (en) | Method capable of dynamically partitioning traffic control subregion | |
| CN104615897B (en) | Road section travel time estimation method based on low-frequency GPS data | |
| CN103593535A (en) | Urban traffic complex self-adaptive network parallel simulation system and method based on multi-scale integration | |
| CN107310550A (en) | Road vehicles travel control method and device | |
| CN103927887A (en) | Array type FPGA traffic state prediction and control system combined with discrete speed model | |
| CN108399763A (en) | A kind of intersection traffic Signalized control algorithm based on neural network | |
| Mahut et al. | Calibration and application of a simulation-based dynamic traffic assignment model | |
| Guan et al. | Integrated decision and control: Towards interpretable and computationally efficient driving intelligence | |
| CN110930693A (en) | Online short-term traffic flow prediction method for road section | |
| Zhu et al. | Research on highway traffic flow prediction model and decision-making method | |
| CN113408189B (en) | Urban multipoint circulating emergency evacuation and simulation deduction method based on variable cells | |
| Prontri et al. | Traffic signal control using fuzzy logic | |
| CN106571034A (en) | City expressway traffic state rolling prediction method based on fusion data | |
| Clara Fang et al. | Computer simulation modeling of driver behavior at roundabouts | |
| Mehr et al. | A game theoretic model for aggregate bypassing behavior of vehicles at traffic diverges | |
| CN111915880A (en) | Method for estimating effective traffic capacity of accident point of highway abnormal event | |
| CN114973660A (en) | Traffic decision method of model linearization iteration updating method | |
| CN108647835B (en) | Method for realizing R language design of urban discrete traffic network based on design speed | |
| Chen et al. | Coordinated ramp metering based on real-time OD information | |
| CN109741597A (en) | A kind of bus section runing time prediction technique based on improvement depth forest | |
| Zang et al. | An intelligent control method for urban traffic signal based on fuzzy neural network |
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 |