CN107067764B - Self-adaptive control method for variable guide lane of urban intersection - Google Patents
Self-adaptive control method for variable guide lane of urban intersection Download PDFInfo
- Publication number
- CN107067764B CN107067764B CN201710168676.5A CN201710168676A CN107067764B CN 107067764 B CN107067764 B CN 107067764B CN 201710168676 A CN201710168676 A CN 201710168676A CN 107067764 B CN107067764 B CN 107067764B
- Authority
- CN
- China
- Prior art keywords
- lane
- time
- straight
- turn
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The invention discloses a self-adaptive control method for a variable guide lane at an urban intersection, which comprises the following steps of firstly giving an attribute suggested value of the variable guide lane of an entrance lane; then, calibrating a correlation coefficient of a discriminant analysis function by using a discriminant analysis method according to the historical traffic data and the attribute suggested value of the variable guide lane; secondly, predicting future short-time traffic by using k-nearest neighbor nonparametric regression according to historical traffic data and real-time traffic data detected by a detector; obtaining an attribute suggested value of a future variable guide lane according to a discriminant analysis function, wherein the correlation coefficient of the discriminant analysis function is updated in real time; and finally, selecting the time of the steering function change of the variable guide lane, and calculating the emptying time of the variable guide lane, so that the timing coordination of lane function change and main pre-signal of the signal controller is realized. The invention improves the utilization rate of the variable guide lane, shortens the average delay of the intersection and relieves the urban traffic jam.
Description
Technical Field
The invention relates to the field of road traffic control, in particular to a self-adaptive control method for a variable guide lane at an urban intersection.
Background
For the management and control of the signal control intersection, under the condition of keeping the lane function unchanged, the actual traffic demand is adapted by using a signal phase adjustment mode. The control mode has certain limitation, and especially when the fluctuation of each turning traffic flow in different time periods is obvious, unnecessary waste of space-time resources is often caused, or traffic jam is caused. In recent years, variable guide lanes are arranged at part of urban intersections, however, the change of the steering function of the variable guide lanes is often regulated and controlled by an on-duty traffic police in a mode of manual control or a lane change scheme in a fixed time period, so that the problem of low utilization rate of the variable guide lanes is caused due to strong subjectivity.
The prior research mainly aims at the condition that the traffic flow at a signal control intersection has tidal characteristics, but the research is less aiming at the condition that the left turn and straight traffic flow on the same entrance road fluctuate obviously in different time periods, and related documents propose methods such as manual timing control, induction control, double-stop control, main and pre-signal control and the like, but the proposed flow has poor operability in actual execution, the acquisition and collection of parameters are difficult, the conversion of the steering function of a variable guide lane in real time is difficult to realize, and a proper timing coordination scheme between main and pre-signals is not adopted.
Disclosure of Invention
The invention aims to provide an adaptive control method for a variable guide lane at an urban intersection, which can realize the change of the steering function of the variable guide lane.
In order to solve the technical problem, the invention provides an urban intersection variable guide lane self-adaptive control method, which comprises the following steps:
(1) observation and collection of historical and real-time traffic flow data;
(2) performing integration of a traffic volume database, selection of state vectors, selection of a similar mechanism, determination of neighbor number and construction of a regression function on the historical and real-time traffic flow data obtained in the step (1) based on k neighbor nonparametric regression to obtain short-time traffic volume prediction data;
(3) according to the historical traffic volume data obtained in the step (1), obtaining historical variable guide lane attribute suggested values by calculating and comparing the congestion degree of left-turn and straight traffic flow of each entrance lane;
(4) obtaining a discriminant analysis function corresponding to left-turn and straight-going attributes of the variable guide lane based on the historical traffic volume data obtained in the step (1) and the historical variable guide lane attribute suggested value obtained in the step (3) and based on a discriminant analysis method;
(5) obtaining a real-time variable guide lane attribute suggested value by using the short-time traffic flow data obtained in the step (2) and the discriminant analysis function obtained in the step (4);
(6) and (5) obtaining a real-time variable guide lane attribute suggested value according to the step (5), realizing timing coordination between main pre-signals of the variable guide lane by a signal controller, including selection of the change time of the steering function of the variable guide lane and calculation of emptying time, and controlling display of a corresponding main pre-signal lamp by the signal controller.
Preferably, the traffic volume index selected in the step (1) is used as a characteristic parameter for analyzing the flow proportion of the left-turn vehicle and the straight-going vehicle, and comprises historical and real-time traffic flow data, wherein the real-time traffic volume data is obtained by field detection of an induction coil detector, the number of vehicles of vehicle types separated on the left-turn lane and the straight-going lane of the entrance lane is counted in each signal period, and the data are uploaded to a control center in real time; the historical traffic volume data is accumulated by real-time traffic volume data, so that the storage and calculation of the data are facilitated, and the real-time property of lane attribute conversion is ensured.
Preferably, the k-nearest neighbor non-parametric regression in the step (2) is implemented in the control center, and the processing of the traffic data specifically includes the following steps:
(21) integrating a traffic flow database, namely integrating a historical traffic flow database and a real-time traffic flow database into a composite database, wherein data in the composite database is dynamically updated;
(22) selecting a state vector, defining the state vector:
X＝[vh(t),vh(t-1),vh(t-2),v(t),v(t-1),v(t-2)] (1)
wherein, v (t) represents the real-time traffic volume of the time period t in the composite database, and the unit is: pcu/h;
vh(t) represents the historical traffic volume in the composite database for time period t, in units: pcu/h;
(23) selecting a similar mechanism, and defining similarity by adopting Euclidean distance:
wherein d isiThe Euclidean distance between the real-time traffic volume and the historical traffic volume of three adjacent time intervals in the composite database is represented by the following unit: pcu/h; d is the Euclidean distance of k nearest neighbors in the composite database, and the unit is as follows: pcu/h;
(24) the determination of the number of neighbors, generally k, is set between 1 and 20, specifically satisfying:
wherein L ismin(k) Representing the sum of squares of residuals between actual traffic and regression predicted trafficK corresponding to the hour, namely the optimal neighbor number;
(25) constructing a regression function, and calculating a formula of the traffic flow K (t +1) in the next time period:
wherein v ishi(t) is the traffic volume of the ith neighbor of the t period, i ═ 1,2, …, k, in units: pcu/h;
βithe regression coefficient of the k-th neighbor.
Preferably, the step (3) is implemented in a control center, and the method specifically includes the following steps:
(31) calculating the design traffic capacity of each lane,
wherein N islWhen a special left-turn lane is arranged for an entrance lane and a special right-turn lane is not arranged, the design traffic capacity of the special left-turn lane is as follows, unit: pcu/h;
Nsfor the design traffic capacity of the straight lane, the unit: pcu/h;
Nsrdesigning the sum of the traffic capacity for a straight lane and a straight right lane, wherein the unit is as follows: pcu/h;
βlthe left-turn vehicle proportion is shown in the figure;
ψsthe traffic capacity reduction coefficient of the straight lane can adopt 0.9;
tggreen time in a signal period, unit: s;
t1for the time after the first vehicle started and passed the stop line after turning to green, the unit: s, 2.3s can be adopted;
tisaverage interval time for straight or right-going vehicles to pass the stop-line, unit: s/pcu;
tcfor signal period, unit: s;
(32) calculating the saturation of left-turn and straight-going lanesSiRespectively is as follows:
Si＝Qi/Ni (6)
wherein, i ═ l, s, respectively represent left turn and straight;
Qithe unit is the traffic volume in a single signal cycle of the lane: pcu/h;
Nithe unit is pcu/h for the designed traffic capacity of the lane.
Selecting the saturation of 0.8 as the threshold value of the lane attribute conversion includes:
(33) and (4) judging: if the saturation of the two lanes is less than 0.8, the two lanes do not reach the congestion state at the moment, and the original attribute of the variable guide lane is kept; if the saturation of the left-turn lane is greater than 0.8 and the saturation of the straight lane is less than 0.8, setting the recommended attribute of the historical variable guide lane as left-turn corresponding to the situation that the left-turn lane reaches the congestion state but the straight lane does not reach the congestion state; if the saturation of the straight lane is greater than 0.8 and the saturation of the left-turn lane is less than 0.8, setting the recommended attribute of the historical variable guide lane as straight, wherein the corresponding straight lane reaches the congestion state but the left-turn lane does not reach the congestion state; if the saturation of the two lanes is greater than 0.8, the two lanes reach a congestion state, and the original attribute of the variable guide lane is still maintained in order to avoid delay of an additional intersection possibly caused by the attribute conversion of the lanes.
Preferably, the step (4) is implemented in a control center, and the method specifically includes the following steps:
(41) two discrimination types are defined, namely the attribute of the variable guide lane is left turn or straight running, and are respectively set asClass and
class, corresponding to two observationsIndicators, i.e. left-hand traffic and direct traffic, wherein
A class has s sets of data,there are t groups of data in the class;
(42) these data are written in matrix form, with:
wherein, aijIs composed of
The value of j variable in i-th group of data in class i, i 1,2, … s, j 1,2, unit: pcu/h;
bijis composed of
The value of j variable in i-th group of data in class i, i 1,2, … t, j 1,2, unit: pcu/h; calculating the average value of each kind of data:
wherein the content of the first and second substances,
respectively represent
Class and
mean value of j-th variable of class data, unit: pcu/h; a matrix A, B of the difference of the two types of data matrices and the corresponding mean values is made:
thus, the dispersion matrix S of two types of data can be obtained by the following formula:
solving a system of binary equations:
namely, it is
This gives:
the first formula is a discrimination function corresponding to an object to be discriminated, and the unit is as follows: pcu/h;
the second and third formulas are used for calculation
Class and
discrimination average of class data, unit: pcu/h;
the fourth formula is used to calculate the discrimination threshold in units: pcu/h;
(43) judging the object to be judged, and if there is an object to be judged, the data is X (X)1,x2) If the value is y ═ c, then the discrimination value is1x1+c2x2The unit: pcu/h if y is satisfiedA>yBThen, a criterion is proposed: if y>y0Then it can be determined
Otherwise, it can be determinedIf y is satisfiedA<yBThen, a criterion is proposed: if y>y0，
It can be decided
Otherwise, it can be determinedI.e. can be simplified to the following criteria:
since the discriminant analysis function is determined based on the historical traffic volume data and the historical variable guide lane attributes, and the historical traffic volume database is updated every half month and is maintained as the traffic volume data of the latest month, the obtained discriminant analysis function is also a parameter updated every half month.
Preferably, in step (6), the obtained real-time variable guidance lane attribute is converted by the signal controller, and is stored in the control center, and in order to prevent the lane attribute from being frequently switched, if and only if the recommended attribute of three consecutive periods is different from the current situation, the variable guidance lane attribute is changed, specifically:
when the variable guidance lane attribute is changed from straight to left turn, in order to clear straight vehicles on the road between the main pre-signal stop lines before the main signal left-turn green light is turned on, the straight red light of the pre-signal needs to be cut off in advance, and in order to make up for the green light time loss when the main pre-signal left-turn green light is turned on simultaneously, the left-turn green light of the pre-signal needs to be turned on in advance:
wherein, t1The straight red light for the pre-signal needs to be cut off in advance, unit: s;
t2the green light for the left turn of the pre-signal needs to be turned on in advance for a time, unit: s;
v is the average speed of the vehicle, in units: m/s;
l1distance between the main signal stop line and the pre-signal stop line, unit: m;
a is the average starting acceleration of the vehicle, unit: m/s2；
When the variable guidance lane attribute is changed from left turn to straight run, in order to clear left turn vehicles on the road between the main pre-signal stop lines before the main pre-signal straight run green light is turned on, the pre-signal left turn red light needs to be turned off in advance, and in order to make up for the green light time loss when the main pre-signal straight run green light is turned on simultaneously, the pre-signal straight run green light needs to be turned on in advance:
wherein, t3The left turn red light for the pre-signal requires a lead-in time, unit: s;
t4the green light of the straight line for the pre-signal needs to be turned on in advance for a time, unit: s;
gLtime for turning left to green of main signal, unit: s;
qLarrival rate for left-turn cars, unit: pcu/s;
c is the signal period, unit: s;
SLsaturation flow rate for left-turn cars, unit: pcu/s.
The invention has the beneficial effects that: (1) the real-time transformation of the steering function of the variable guide lane can be realized, and when a k-nearest neighbor nonparametric regression and discriminant analysis method is adopted, the historical traffic volume data and the historical variable guide lane attribute suggested value are not fixed and are continuously updated by the real-time traffic volume data; parameters in a discriminant analysis function obtained from historical data are also dynamically changed, and are continuously adjusted in a rolling mode according to real-time traffic data and real-time variable guide lane attribute values, so that the utilization rate of the variable guide lane can be improved, and delay of vehicles at the intersection is reduced; (2) the timing coordination among the main pre-signals can be realized, the calculation of the emptying time when the steering function of the variable guide lane is changed is provided for dissipating vehicles among the main pre-signal stop lines, the early starting time of the pre-signals is set for preventing the corresponding green light time loss, the right of the vehicles on the variable guide lane is determined, the driving direction of a driver can be adjusted in time, and the unnecessary waiting time is reduced.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
Fig. 2 is a schematic diagram showing the relationship between the lane distribution of the entrance lane and the position of the main pre-signal stop line according to the present invention.
FIG. 3 is a flow chart of the k-nearest neighbor non-parametric regression method of the present invention.
Fig. 4 is a curve diagram illustrating that the sum of squared residuals of left turn and straight line changes with k when the values of k are different in the optimized k-nearest neighbor non-parametric regression method of the present invention.
Fig. 5 is a schematic diagram illustrating the accuracy of the traffic data when the variable guidance lane attribute of the present invention is left turn and straight driving.
Fig. 6(a) is a schematic diagram of the correlation between the signal cycle chart and the variable guidance lane attribute of the present invention when changing from straight driving to left turning.
Fig. 6(b) is a schematic diagram showing the correlation between the timing of changing the variable guidance lane steering function and the signal cycle chart according to the present invention.
Fig. 6(c) is a schematic diagram of the correlation between the signal cycle chart and the variable guidance lane attribute of the present invention when the left turn is changed into the straight run.
Fig. 6(d) is a schematic diagram showing the correlation between the time of changing the steering function of the variable guide lane and the signal cycle chart according to the present invention.
Detailed Description
The invention provides an adaptive control algorithm for a variable guide lane at an urban intersection, which has a flow chart shown in the attached figure 1 and mainly comprises the following steps:
(1) observation and collection of historical and real-time traffic data.
The training and testing of the adaptive control algorithm of the variable guide lane at the urban intersection adopt the traffic data of the south approach of the Hangzhou city pool and the south approach of the afterglow. The intersection comprises four lanes in a south entrance way, wherein the first lane is a left-turn lane, the second lane is a left-turn/straight-going variable lane, the third lane is a straight-going lane, and the fourth lane is a straight-right lane from inside to outside. The relationship of the lane distribution, the position of the main pre-signal stop line and the like of the embodiment of the invention is shown in figure 2. At present, the change of the variable lane is manually controlled by a traffic police, the variable lane is a left-turn lane in the rush hour from seven to nine am on a working day, and the variable lane is a straight-going lane in the rest time. Historical traffic data are acquired directly from related departments, real-time traffic data are investigated in a mode of combining manual investigation and detection of an induction coil detector, the geometric dimension of an intersection is investigated manually, and when signals are matched, traffic flow data of left turn and straight going of the entrance way are output at intervals of unit time of each signal period, wherein the unit is pcu/h. The embodiment of the invention adopts 268 groups for training and 12 groups of data for verification, and the proportion description of each steering traffic volume is shown in a table 1:
TABLE 1 proportion of the traffic in each turn used in the examples of the present invention
(2) The short-time traffic data is obtained by integrating a traffic database, selecting a state vector, selecting a similar mechanism, determining the number of neighbors and constructing a regression function on historical and real-time traffic data based on k-neighbor nonparametric regression, and the flow of the k-neighbor nonparametric regression method disclosed by the embodiment of the invention is detailed in an attached figure 3. According to the training data, the residual square sum L of left turn and straight line when the number k of adjacent neighbors is between 1 and 20 is respectively calculatedLeft turn of min(k)、LGo straight for min(k) See table 2, and figure 4 is plotted. Combining Table 2 and the accompanying drawings4, it was found that the predicted optimal number of neighbors for left turn, straight, short time traffic of the present example was 2.
Table 2 relation of residual sum of squares and number of neighbors in embodiments of the present invention
(3) And calculating and comparing the saturation of the left-turn and straight traffic flow of each entrance lane according to the historical traffic volume data to obtain the historical variable guide lane attribute suggested value.
In the embodiment of the invention, the reduction coefficient psi of the traffic capacity of the straight lanesWith a green time t of 0.9, signal periodg70s, time t when the first vehicle started and passed the stop line after the signal light turned green1With 2.3s, average interval time t of straight or right-hand vehicles passing the stop-lineisIs 2.4s/pcu, signal period tcThe left-turn vehicle proportion is 180sl0.383, the designed traffic capacities of the straight lane, the straight right lane and the special left-turn lane are as follows:
according to historical traffic data and the designed traffic capacity of each lane, the saturation of the left-turn lane and the saturation of the straight lane are respectively calculated, the suggested value of the historical variable guide lane attribute is judged, and the table 3 is a partial data judgment result.
TABLE 3 determination of historical variable guide lane attributes
(4) And obtaining the discriminant analysis functions of the left turn and the straight movement attributes of the variable guide lane of the entrance lane based on the historical traffic data and the historical variable guide lane attribute suggested values and on the basis of a discriminant analysis method.
In the formula, x1、x2The unit of left turn and straight traffic on the entrance to be distinguished is pcu/h;
L0、L1the attributes representing the variable guide lane are left turn and straight, respectively.
(5) And obtaining a real-time variable guide lane attribute suggested value by using the short-time traffic data and the discriminant analysis function.
The accuracy of the verification data set of the embodiment of the present invention is obtained by comparing the historical variable guidance lane attribute values with the real-time variable guidance lane attribute suggested values, as shown in fig. 5.
(6) According to the variable guide lane attribute suggestion value, the timing coordination between the main pre-signals of the variable guide lane is set according to the attribute of the variable guide lane at the current moment, as shown in the figure 6.
In the embodiment of the invention, the distance l between the main signal stop line and the pre-signal stop line190m, the average speed v of the vehicle is 12m/s2Average starting acceleration v of vehicle is 12m/s2Therefore, the direct red light of the pre-signal needs to be cut off in advance
Pre-signaled left-turn green light requiring a time of turning on in advance
Time g for main signal to turn left to greenL74s, arrival rate q of left-turn carL0.11pcu/S, saturation flow rate S of left-hand vehicleL0.53pcu/s and 180s, therefore, the left turn red light of the pre-signal needs to be cut off in advanceThe green light of the direct line of the pre-signal needs to be turned on for a time t in advance4＝t2＝5s。
The invention provides an adaptive control algorithm for a variable guide lane at an urban intersection. Predicting the short-time traffic flow based on k neighbor nonparametric regression; obtaining a discriminant relation between the traffic data and the attribute value of the variable guide lane by using a discriminant analysis method, and obtaining a real-time attribute suggested value of the variable guide lane; an early off-time and an early on-time between the main pre-signals are set. The accuracy of the model is high, the real-time transformation of the steering function of the variable guide lane can be realized, the timing coordination of the main pre-signal is ensured, the utilization rate of the variable guide lane is improved, and the average delay of the intersection is shortened.
While the invention has been shown and described with respect to the preferred embodiments, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the scope of the invention as defined in the following claims.
Claims (5)
1. A self-adaptive control method for a variable guide lane at an urban intersection is characterized by comprising the following steps:
(1) observation and collection of historical and real-time traffic flow data;
(2) performing integration of a traffic volume database, selection of state vectors, selection of a similar mechanism, determination of neighbor number and construction of a regression function on the historical and real-time traffic flow data obtained in the step (1) based on k neighbor nonparametric regression to obtain short-time traffic volume prediction data; the k-nearest neighbor nonparametric regression is realized in a control center, and the processing of the traffic data specifically comprises the following steps:
(21) integrating a traffic flow database, namely integrating a historical traffic flow database and a real-time traffic flow database into a composite database, wherein data in the composite database is dynamically updated;
(22) selecting a state vector, defining the state vector:
X＝[vh(t),vh(t-1),vh(t-2),v(t),v(t-1),v(t-2)] (1)
wherein, v (t) represents the real-time traffic volume of the time period t in the composite database, and the unit is: pcu/h;
vh(t) representation of the Compound databaseHistorical traffic volume in the middle t period, unit: pcu/h;
(23) selecting a similar mechanism, and defining similarity by adopting Euclidean distance:
wherein d isiThe Euclidean distance between the real-time traffic volume and the historical traffic volume of three adjacent time intervals in the composite database is represented by the following unit: pcu/h; d is the Euclidean distance of k nearest neighbors in the composite database, and the unit is as follows: pcu/h;
(24) the determination of the number of neighbors, generally k, is set between 1 and 20, specifically satisfying:
wherein L ismin(k) Representing k corresponding to the minimum sum of squares of residuals between the actual traffic volume and the traffic volume obtained by regression prediction, namely the optimal neighbor number;
(25) constructing a regression function, and calculating a formula of the traffic flow K (t +1) in the next time period:
wherein v ishi(t) is the traffic volume of the ith neighbor of the t period, i ═ 1,2, …, k, in units: pcu/h;
βiregression coefficients for the kth neighbor;
(3) according to the historical traffic volume data obtained in the step (1), obtaining historical variable guide lane attribute suggested values by calculating and comparing the congestion degree of left-turn and straight traffic flow of each entrance lane;
(4) obtaining a discriminant analysis function corresponding to left-turn and straight-going attributes of the variable guide lane based on the historical traffic volume data obtained in the step (1) and the historical variable guide lane attribute suggested value obtained in the step (3) and based on a discriminant analysis method;
(5) obtaining a real-time variable guide lane attribute suggested value by using the short-time traffic flow data obtained in the step (2) and the discriminant analysis function obtained in the step (4);
(6) and (5) obtaining a real-time variable guide lane attribute suggested value according to the step (5), realizing timing coordination between main pre-signals of the variable guide lane by a signal controller, including selection of the change time of the steering function of the variable guide lane and calculation of emptying time, and controlling display of a corresponding main pre-signal lamp by the signal controller.
2. The self-adaptive control method for the variable guide lanes at the urban intersection according to claim 1, characterized in that the traffic volume index selected in the step (1) is used as a characteristic parameter for analyzing the flow proportion of left-turn vehicles and straight-going vehicles, and comprises historical and real-time traffic flow data, wherein the real-time traffic volume data is obtained by field detection of an induction coil detector, the number of vehicles of different types on the left-turn vehicle and the straight-going vehicle of the entrance lane is counted in each signal period, and the data is uploaded to the control center in real time; the historical traffic volume data is accumulated by real-time traffic volume data, so that the historical traffic volume database is updated every half month and is kept as the traffic volume data of the latest month in order to facilitate the storage and calculation of the data and ensure the real-time property of lane attribute conversion.
3. The urban intersection variable-guidance lane self-adaptive control method according to claim 1, wherein the step (3) is implemented in a control center, and the method specifically comprises the following steps:
(31) calculating the design traffic capacity of each lane,
wherein N islWhen a special left-turn lane is arranged for an entrance lane and a special right-turn lane is not arranged, the design traffic capacity of the special left-turn lane is as follows, unit: pcu/h;
Nsfor straight drivingDesign traffic capacity of the lane, unit: pcu/h;
Nsrdesigning the sum of the traffic capacity for a straight lane and a straight right lane, wherein the unit is as follows: pcu/h;
βlthe left-turn vehicle proportion is shown in the figure;
ψsthe traffic capacity reduction coefficient of the straight lane can adopt 0.9;
tggreen time in a signal period, unit: s;
t1for the time after the first vehicle started and passed the stop line after turning to green, the unit: s, 2.3s can be adopted;
tisaverage interval time for straight or right-going vehicles to pass the stop-line, unit: s/pcu;
tcfor signal period, unit: s;
(32) calculating the saturation S of left-turn and straight-going lanesiRespectively is as follows:
Si＝Qi/Ni (6)
wherein, i ═ l, s, respectively represent left turn and straight;
Qithe unit is the traffic volume in a single signal cycle of the lane: pcu/h;
Nipcu/h is the designed traffic capacity of the lane;
selecting the saturation of 0.8 as the threshold value of the lane attribute conversion includes:
(33) and (4) judging: if the saturation of the two lanes is less than 0.8, the two lanes do not reach the congestion state at the moment, and the original attribute of the variable guide lane is kept; if the saturation of the left-turn lane is greater than 0.8 and the saturation of the straight lane is less than 0.8, setting the recommended attribute of the historical variable guide lane as left-turn corresponding to the situation that the left-turn lane reaches the congestion state but the straight lane does not reach the congestion state; if the saturation of the straight lane is greater than 0.8 and the saturation of the left-turn lane is less than 0.8, setting the recommended attribute of the historical variable guide lane as straight, wherein the corresponding straight lane reaches the congestion state but the left-turn lane does not reach the congestion state; if the saturation of the two lanes is greater than 0.8, the two lanes reach a congestion state, and the original attribute of the variable guide lane is still maintained in order to avoid delay of an additional intersection possibly caused by the attribute conversion of the lanes.
4. The urban intersection variable-guidance lane self-adaptive control method according to claim 1, wherein the step (4) is implemented in a control center, and the method specifically comprises the following steps:
(41) two discrimination types are defined, namely the attribute of the variable guide lane is left turn or straight running, and are respectively set asClass and
class, corresponding to two observation indicators, i.e. left-hand traffic and direct traffic, wherein
A class has s sets of data,
there are t groups of data in the class;
(42) these data are written in matrix form, with:
wherein, aijIs composed ofThe value of j variable in i-th group of data in class i, i 1,2, … s, j 1,2, unit: pcu/h;
bijis composed of
The value of j variable in i-th group of data in class i, i 1,2, … t, j 1,2, unit: pcu/h;
calculating the average value of each kind of data:
wherein the content of the first and second substances,respectively represent
Class and
mean value of j-th variable of class data, unit: pcu/h;
a matrix A, B of the difference of the two types of data matrices and the corresponding mean values is made:
thus, the dispersion matrix S of two types of data can be obtained by the following formula:
solving a system of binary equations:
namely, it is
This gives:
the first formula is a discrimination function corresponding to an object to be discriminated, and the unit is as follows: pcu/h;
the second and third formulas are used for calculation
Class and
discrimination average of class data, unit: pcu/h;
the fourth formula is used to calculate the discrimination threshold in units: pcu/h;
(43) judging the object to be judged, and if there is an object to be judged, the data is X (X)1,x2) If the value is y ═ c, then the discrimination value is1x1+c2x2The unit: pcu/h if y is satisfiedA＞yBThen, a criterion is proposed: if y > y0Then it can be determined
Otherwise, it can be determined
If y is satisfiedA＜yBThen, a criterion is proposed: if y > y0Then it can be determined
Otherwise, it can be determinedI.e. can be simplified to the following criteria:
since the discriminant analysis function is determined based on the historical traffic volume data and the historical variable guide lane attributes, and the historical traffic volume database is updated every half month and is maintained as the traffic volume data of the latest month, the obtained discriminant analysis function is also a parameter updated every half month.
5. The adaptive control method for the variable guide lane at an urban intersection according to claim 1, wherein in step (6), the obtained real-time variable guide lane attribute is converted by the signal control machine, and is stored in the control center, and in order to prevent the lane attribute from being frequently switched, the variable guide lane attribute is changed when the recommended attribute of three consecutive periods is different from the current condition, specifically:
when the variable guidance lane attribute is changed from straight to left turn, in order to clear straight vehicles on the road between the main pre-signal stop lines before the main signal left-turn green light is turned on, the straight red light of the pre-signal needs to be cut off in advance, and in order to make up for the green light time loss when the main pre-signal left-turn green light is turned on simultaneously, the left-turn green light of the pre-signal needs to be turned on in advance:
wherein, t1The straight red light for the pre-signal needs to be cut off in advance, unit: s;
t2the green light for the left turn of the pre-signal needs to be turned on in advance for a time, unit: s;
v is the average speed of the vehicle, in units: m/s;
l1distance between the main signal stop line and the pre-signal stop line, unit: m;
a is the average starting acceleration of the vehicle, unit: m/s2；
When the variable guidance lane attribute is changed from left turn to straight run, in order to clear left turn vehicles on the road between the main pre-signal stop lines before the main pre-signal straight run green light is turned on, the pre-signal left turn red light needs to be turned off in advance, and in order to make up for the green light time loss when the main pre-signal straight run green light is turned on simultaneously, the pre-signal straight run green light needs to be turned on in advance:
wherein, t3The left turn red light for the pre-signal requires a lead-in time, unit: s;
t4the green light of the straight line for the pre-signal needs to be turned on in advance for a time, unit: s;
gLtime for turning left to green of main signal, unit: s;
qLarrival rate for left-turn cars, unit: pcu/s;
c is the signal period, unit: s;
SLsaturation flow rate for left-turn cars, unit: pcu/s.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710168676.5A CN107067764B (en) | 2017-03-21 | 2017-03-21 | Self-adaptive control method for variable guide lane of urban intersection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710168676.5A CN107067764B (en) | 2017-03-21 | 2017-03-21 | Self-adaptive control method for variable guide lane of urban intersection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107067764A CN107067764A (en) | 2017-08-18 |
| CN107067764B true CN107067764B (en) | 2020-01-03 |
Family
ID=59617820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710168676.5A Active CN107067764B (en) | 2017-03-21 | 2017-03-21 | Self-adaptive control method for variable guide lane of urban intersection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107067764B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109920244A (en) * | 2017-12-12 | 2019-06-21 | 上海宝康电子控制工程有限公司 | Changeable driveway real-time control system and method |
| CN108198441B (en) * | 2018-01-26 | 2021-06-29 | 杨立群 | Rapid intelligent traffic system and method |
| CN108281017A (en) * | 2018-03-16 | 2018-07-13 | 武汉理工大学 | A kind of intersection traffic modulating signal control method based on bus or train route cooperative system |
| CN108281013A (en) * | 2018-03-22 | 2018-07-13 | 安徽八六物联科技有限公司 | A kind of road traffic monitoring system |
| CN108510735A (en) * | 2018-04-09 | 2018-09-07 | 宁波工程学院 | A kind of urban road intersection morning evening peak divides the prediction technique of steering flow |
| CN108983771A (en) * | 2018-07-03 | 2018-12-11 | 天津英创汇智汽车技术有限公司 | Vehicle lane-changing decision-making technique and device |
| CN109448371A (en) * | 2018-11-05 | 2019-03-08 | 王晨 | A kind of real-time variable lane control method and control system |
| CN109559513B (en) * | 2018-12-12 | 2021-07-20 | 武汉理工大学 | Adaptive signal control method based on adjacent period flow difference prediction |
| CN110097752B (en) * | 2019-03-27 | 2021-04-27 | 杭州远眺科技有限公司 | Intelligent variable guide lane calculation method |
| CN111145564B (en) * | 2020-01-03 | 2021-09-17 | 山东大学 | Self-adaptive variable lane control method and system for signal control intersection |
| CN111915894B (en) * | 2020-08-06 | 2021-07-27 | 北京航空航天大学 | Variable lane and traffic signal cooperative control method based on deep reinforcement learning |
| CN112017434B (en) * | 2020-08-19 | 2021-09-24 | 公安部交通管理科学研究所 | Variable lane control method and system based on space-time cooperation |
| CN115171402B (en) * | 2022-06-24 | 2023-08-29 | 东南大学 | Method for setting reverse variable guiding lanes between adjacent T-shaped intersections |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2668631B1 (en) * | 1990-10-29 | 1995-02-10 | Silec Liaisons Elec | METHOD FOR CONTROLLING THE SIGNAL LIGHTS OF A CROSSROAD. |
| CN102034350B (en) * | 2009-09-30 | 2012-07-25 | 北京四通智能交通***集成有限公司 | Short-time prediction method and system of traffic flow data |
| JP5604963B2 (en) * | 2010-05-07 | 2014-10-15 | 住友電気工業株式会社 | Signal control apparatus and computer program |
| CN102938204A (en) * | 2012-08-03 | 2013-02-20 | 东南大学 | Variable guiding lane steering function conversion control method of city intersections |
| CN103700273B (en) * | 2014-01-06 | 2016-01-06 | 东南大学 | Based on the signal timing optimization method of variable guided vehicle road |
| CN104464320B (en) * | 2014-12-15 | 2016-09-07 | 东南大学 | Based on true road network characteristic and the shortest path abductive approach of dynamic travel time |
| CN105336163B (en) * | 2015-10-26 | 2017-09-26 | 山东易构软件技术股份有限公司 | A kind of Short-time Traffic Flow Forecasting Methods based on three layers of k nearest neighbor |
| CN106297326A (en) * | 2016-10-27 | 2017-01-04 | 深圳榕亨实业集团有限公司 | Based on holographic road network tide flow stream Lane use control method |
-
2017
- 2017-03-21 CN CN201710168676.5A patent/CN107067764B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107067764A (en) | 2017-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107067764B (en) | Self-adaptive control method for variable guide lane of urban intersection | |
| CN111434554B (en) | Controlling an autonomous vehicle based on passenger and context aware driving style profiles | |
| WO2021051870A1 (en) | Reinforcement learning model-based information control method and apparatus, and computer device | |
| CN108665715B (en) | Intelligent traffic studying and judging and signal optimizing method for intersection | |
| CN108583578A (en) | The track decision-making technique based on multiobjective decision-making matrix for automatic driving vehicle | |
| CN112037507B (en) | Supersaturated traffic state trunk line adaptive signal coordination design method and device | |
| CN108470461B (en) | Traffic signal controller control effect online evaluation method and system | |
| CN111332283B (en) | Method and system for controlling a motor vehicle | |
| US9180883B2 (en) | Method and module for determining of at least one reference value for a vehicle control system | |
| CN105046987A (en) | Road traffic signal lamp coordination control method based on reinforcement learning | |
| US20140343818A1 (en) | Method and module for determining of at least one reference value for a vehicle control system | |
| CN111028504A (en) | Urban expressway intelligent traffic control method and system | |
| EP2794379A1 (en) | Method and module for controlling a vehicle's speed based on rules and/or costs | |
| CN108335496A (en) | A kind of City-level traffic signal optimization method and system | |
| CN110634293B (en) | Trunk intersection control method based on fuzzy control | |
| CN110194041B (en) | Self-adaptive vehicle body height adjusting method based on multi-source information fusion | |
| CN113296513B (en) | Rolling time domain-based emergency vehicle dynamic path planning method in networking environment | |
| CN112026782A (en) | Automatic driving decision method and system based on switch type deep learning network model | |
| CN115246393A (en) | Method and device for controlling vehicle following distance, electronic device and storage medium | |
| CN111524345A (en) | Induction control method for multi-objective optimization under constraint of real-time queuing length of vehicle | |
| CN108806285B (en) | Intersection signal adjusting method and device based on array radar | |
| CN113506442B (en) | Urban road network traffic signal lamp control method based on expected income estimation | |
| CN109859465B (en) | Automatic driving longitudinal control parameter adjusting system based on traffic flow dynamic characteristics | |
| DE102017004033A1 (en) | Method for generating a driving behavior in autonomous vehicles | |
| CN113870584A (en) | Game theory-based traffic intersection passing method and system |
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 |