[go: up one dir, main page]

CN112258856B - Method for establishing regional traffic signal data drive control model - Google Patents

Method for establishing regional traffic signal data drive control model Download PDF

Info

Publication number
CN112258856B
CN112258856B CN202010798058.0A CN202010798058A CN112258856B CN 112258856 B CN112258856 B CN 112258856B CN 202010798058 A CN202010798058 A CN 202010798058A CN 112258856 B CN112258856 B CN 112258856B
Authority
CN
China
Prior art keywords
intersection
area
period
model
traffic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010798058.0A
Other languages
Chinese (zh)
Other versions
CN112258856A (en
Inventor
张海波
王力
吉鸿海
潘彦斌
李丹阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
North China University of Technology
Original Assignee
North China University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by North China University of Technology filed Critical North China University of Technology
Priority to CN202010798058.0A priority Critical patent/CN112258856B/en
Publication of CN112258856A publication Critical patent/CN112258856A/en
Application granted granted Critical
Publication of CN112258856B publication Critical patent/CN112258856B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/07—Controlling traffic signals
    • 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
    • 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
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/07—Controlling traffic signals
    • G08G1/081—Plural intersections under common control

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Traffic Control Systems (AREA)

Abstract

本发明涉及一种区域交通信号数据驱动控制模型建立方法，本发明以浮动车数据(典型的移动检测数据源)为基础，通过估计方法获取交叉口流量参数，基于存储‑转发建模方法构建周期车辆数估计模型，调整对交叉口绿灯时间的约束条件，引入时变控制信号周期C(k)，进而得到全新的绿灯时间约束条件，从而避免浪费绿灯时间，此时考虑打破定周期的约束条件，从而保证空间占有率始终满足xi(k+1)≥0，建立的区域交通信号控制模型可同时描述交叉口的欠饱和、临界饱和和过饱和三种交通状态形式，并提出了基于多智能体网络的以空间占有率均衡为目标的区域交通信号数据驱动控制模型。

Figure 202010798058

The present invention relates to a method for establishing a regional traffic signal data-driven control model. The present invention is based on floating vehicle data (a typical mobile detection data source), obtains intersection flow parameters through an estimation method, and constructs a cycle based on a store-and-forward modeling method. The vehicle number estimation model adjusts the constraints on the green light time at the intersection, introduces a time-varying control signal period C(k), and then obtains a new green light time constraint, so as to avoid wasting green light time, and consider breaking the constraints of the fixed period at this time. , so as to ensure that the space occupancy rate always satisfies x i (k+1) ≥ 0. The established regional traffic signal control model can simultaneously describe the three traffic state forms of undersaturation, critical saturation and oversaturation at the intersection. A data-driven control model of regional traffic signals for a network of agents targeting spatial occupancy balance.

Figure 202010798058

Description

Method for establishing regional traffic signal data drive control model
Technical Field
The invention relates to the technical field of intelligent traffic signal control, in particular to a regional traffic signal data drive control model establishing method.
Background
With the development of social economy and urban traffic, the quantity of automobile reserves in cities in China is increased rapidly. At present, the road construction capacity of most cities is far behind the growth rate of motor vehicles, and the contradiction between the road construction capacity and the motor vehicles is mainly reflected in increasingly serious road traffic jam. Therefore, under the limited road space resources, the improvement of the road utilization rate and the travel efficiency by the intelligent traffic control method is an important task which must be considered by urban traffic managers.
With the continuous development of the ITS (ITS) technology, various advanced traffic detection devices are applied in a large range, great changes are brought to urban road traffic control, various high-precision and large-range detection data enable a traditional control algorithm based on a traffic flow model to be improved, the traditional traffic signal control model and control System using a fixed detector as a detection means cannot meet the control requirements of novel mobile traffic information acquisition modes such as a floating car and a mobile phone, the problems of difficult deployment, high fault rate, poor detection precision, high maintenance cost and the like and the problems of low occupancy rate of a mobile detection method are solved, and new problems and challenges are brought to urban traffic control. With the rapid development of the GPS technology, the floating car has been widely used in the traffic field as a new data acquisition mode. A traffic prediction model is established by means of GPS floating car data, so that real-time road traffic information can be obtained.
The main reason of the phenomenon is that the three major factors of people, vehicles and roads which determine the control strategy are not in a complete linear relationship, the three major factors are in a strong coupling relationship which is mutually related, and the behaviors of people are difficult to predict, so that the control models constructed aiming at the vehicles and the roads have errors with the reality.
Disclosure of Invention
Considering that urban regional traffic signal control is a complex control problem and comprises a series of practical problems of high modeling cost, high dynamic modeling difficulty, poor coordination control effect, low network expansibility and the like, the design of the urban regional traffic data driving control method based on floating car data has important theoretical and practical significance on the basis of the floating car data. In urban traffic, adding additional infrastructure to accommodate the increased number of vehicles is expensive and unsustainable due to limited road resources. A more socially feasible option is to optimize traffic signal timing in a data-driven manner. As urban traffic systems are more and more complex, establishing an accurate road network and even an intersection mechanical model is a difficult or impossible problem due to high-order, strong nonlinearity, non-stationarity and complex structure. In addition, it becomes easier to obtain traffic data regarding vehicle number, queue, occupancy, and traffic, collecting large amounts of online/offline data from secondary heterogeneous traffic sensors (e.g., inductive loop detectors, microwave detectors, video surveillance) on a daily basis. Therefore, the spatiotemporal relationship between traffic data should be considered when executing a data-driven intelligent traffic control system.
The data-driven control method applies relevant theories and methods based on data to the research of the traffic system, analyzes and understands rules and control modes of the traffic system through off-line and on-line data generated by the traffic system under the conditions that the internal mechanism of the traffic system cannot be completely acquired and an accurate traffic flow dynamics model is difficult to establish, designs a control method and makes a control strategy according to the rules, and plays an important role in relieving traffic jam.
With the rapid development of intelligent vehicles and internet traffic and communication technologies, the scale, quality, accuracy, instantaneity and the like of mobile detection data are greatly improved. The signal control method is based on floating car data (typical mobile detection data source), intersection flow parameters are obtained through an estimation method, a periodic vehicle number estimation model is built based on a store-forward modeling method, and a regional traffic signal data driving control model which is based on a multi-agent network and aims at space occupancy balance is provided.
In the traditional analysis of a store-and-forward model, generally, only the traffic signal timing problem in the oversaturated traffic state is considered, more green light time is allocated to a certain direction and a certain period of an undersaturated intersection, and the problem of green light time waste, namely the idle discharge phenomenon, exists; in fact, at this time, the traffic capacity can be guaranteed only by allocating less green light time. However, most traffic signal controls are periodic control, and the constraint of the maximum and minimum green time of the phase is also required to be met, so the adjustable range of the green time in the traditional signal control is limited, and the control problems of three traffic states of undersaturation, critical saturation and oversaturation cannot be perfectly compatible.
In order to solve the problem, in the establishment of a store-and-forward model, constraint conditions for green time of an intersection are adjusted, a time-varying control signal cycle C (k) is introduced, and a brand-new green time constraint condition is obtained, so that green time waste is avoided, the constraint conditions for breaking a fixed cycle are considered, and space occupation is guaranteedThe rate always satisfies xiAnd (k +1) is not less than 0, and the established regional traffic signal control model can describe three traffic state forms of undersaturation, critical saturation and supersaturation at the intersection at the same time, so that the applicability is stronger.
The technical scheme adopted by the invention is as follows:
the method comprises the following steps:
(1) creating a component-positive system model
Figure GDA0003388641810000031
Wherein x ism(k) The value is more than or equal to 0, m is 1, …, and N represents the state of the component system element m at the time k; a ismnM ≠ n denotes the state quantity transfer proportionality coefficient of the component system element m to the component system element n in the sampling period T > 0; i ism(k) Not less than 0 and Om(k) More than or equal to 0 respectively represents the input and the output of the component system element m in the sampling period;
describing the component system model into a vector form:
x(k+1)＝Ax(k)+I(k)
in the formula: x (k) ═ x1(k),…,xN(k)]T∈RNIs a system state vector;
I(k)＝[I1(k),…,IN(k)]T∈RNinputting for the outside of the system; a is an element of RN×NIs a system state matrix and has
Figure GDA0003388641810000032
Assuming that the current state quantity of any component is greater than or equal to the total quantity of state transitions in the sampling period, diagonal elements of the state matrix A are all non-negative, and the column sum satisfies:
Figure GDA0003388641810000033
(2) establishing multi-intersection variable-period multidirectional space occupancy model
Based on a positive system model, as shown in fig. 1, the multi-intersection variable-period multi-directional space occupancy balance control in a traffic area is implemented, and then a mathematical model is as follows:
lm,i(k+1)＝lm,i(k)+Cm(k)qm,i(k)-Sm,igm,i(k)
wherein M is 1, …, and M represents the M-th intersection of the area; the i is 1, …, N represents the ith direction of the intersection, and the N is 4, which represents that the intersection has 4 directions; cm(k) The kth control signal period of the mth intersection of the area is represented and is a variable period; lm,i(k) The number of queued vehicles in the kth period in the ith direction of the mth intersection of the area is shown; sm,iRepresenting the saturation flow rate of the m-th intersection in the i-th direction of the area; gm,i(k) Indicating the green time of the kth period of the mth intersection in the area in the ith direction; wherein q ism,i(k) The vehicle arrival rate of the ith cycle in the ith direction of the mth intersection of the area satisfies the following relation:
Figure GDA0003388641810000034
the green time and the control signal period of each direction of the mth intersection in the area meet the following constraint conditions:
Figure GDA0003388641810000041
wherein, tm,LRepresenting the total loss time of the mth intersection of the area;
defining the space occupancy of a certain direction of the mth intersection of the area as the ratio of the number of queued vehicles in the direction to the length of the road section of the mth intersection, and as follows:
Figure GDA0003388641810000042
wherein x ism,i(k) Represents the m-th of the areaSpace occupancy rate of k cycle in i direction of intersection, lm,i,maxThe length of a road section in the ith direction of the mth intersection of the area is represented;
the variable-period multidirectional space occupancy model of the mth intersection of the traffic area can be expressed in the following form:
Figure GDA0003388641810000043
the saturation of the ith cycle of the mth intersection in the area in the ith direction is defined as follows:
Figure GDA0003388641810000044
defining the green light time constraint and the control signal period constraint of the kth period in the ith direction of the mth intersection of the area as follows:
Figure GDA0003388641810000045
Figure GDA0003388641810000046
the traffic area multi-intersection variable-period multi-direction space occupancy model considering the green light time constraint is as follows:
Figure GDA0003388641810000047
drawings
FIG. 1 is a schematic diagram of the component model.
Detailed Description
The method comprises the following steps:
the method comprises the following steps: establishing a positive system model
Traffic control systems have the distinct feature that the traffic state is non-negative, with the initial non-negative stateSpace and traffic states are always kept non-negative in the evolution process, such as the number of vehicles in a road section, queuing length, traffic flow density, occupancy and the like, and a system with the properties is called a positive system. The positive system model component model is a very simplified model. The network traffic flow evolution is modeled by a component system, the network supersaturation characteristic with any control structure can be described, the non-negativity constraint of the system state is ensured by the self property of the system, the network traffic flow input is given, a network has a unique stable balance point by a non-negative matrix theory, a balance point analysis calculation formula is given, and the quantitative relation between the network steady state and the input is established. Therefore, a network steady-state signal control law is provided, and the control law is a state feedback control law when the intersection is green[129]. A system with n ≧ 2 comprest systems is shown in FIG. 1, where xm(k) The value is more than or equal to 0, m is 1, …, and N represents the state of the component system element m at the time k; a ismnM ≠ n denotes the state quantity transfer proportionality coefficient of the component system element m to the component system element n in the sampling period T > 0; i ism(k) Not less than 0 and Om(k) And the value is more than or equal to 0, which respectively represents the input and the output of the Compartment system element m in the sampling period. Thus, the state of the component system element m satisfies the following conservation equation:
Figure GDA0003388641810000051
further, the above equation is written in vector form:
x(k+1)＝Ax(k)+I(k)
in the formula: x (k) ═ x1(k),…,xN(k)]T∈RNIs a system state vector;
I(k)＝[I1(k),…,IN(k)]T∈RNinputting for the outside of the system; a is an element of RN×NIs a system state matrix and has
Figure GDA0003388641810000052
Suppose any component shouldAnd if the front state quantity is more than or equal to the total quantity of state transition in the sampling period, the diagonal elements of the state matrix A are all non-negative, and the column sum satisfies:
Figure GDA0003388641810000053
thus, the state matrix A is a non-negative matrix, so that the component system is a type of positive system, and the matrix A is referred to as the component matrix.
Step two: establishing multi-intersection variable-period multidirectional space occupancy model
Based on a positive system model, as shown in fig. 1, the multi-intersection variable-period multi-directional space occupancy balance control in a traffic area is implemented, and then a mathematical model is as follows:
lm,i(k+1)＝lm,i(k)+Cm(k)qm,i(k)-Sm,igm,i(k)
wherein M is 1, …, and M represents the M-th intersection of the area; the i is 1, …, N represents the ith direction of the intersection, and the N is 4, which represents that the intersection has 4 directions; cm(k) The kth control signal period of the mth intersection of the area is represented and is a variable period; lm,i(k) Represents the kth period ([ (k-1) C (k), kC (k) at the ith direction of the mth intersection of the area]In-time period) number of queued vehicles (veh); sm,iIndicating the saturation flow rate (veh/s) in the ith direction at the mth intersection of the zone; gm,i(k) And (3) indicating the green time(s) of the kth period in the ith direction of the mth intersection of the area.
Wherein q ism,i(k) The vehicle arrival rate of the ith cycle in the ith direction of the mth intersection in the area is usually related to the number of vehicles in each direction of adjacent intersections, and according to the vehicle conservation law, the following relationship is satisfied:
Figure GDA0003388641810000061
the green time and the control signal period of each direction of the mth intersection in the area meet the following constraint conditions:
Figure GDA0003388641810000062
wherein, tm,LRepresenting the total loss time for the mth intersection of the area.
The space occupancy rate of a certain direction at the m-th intersection of the area is defined as the ratio of the number of vehicles in line in the direction to the length of the road section (vehicle storage capacity), and the form is as follows:
Figure GDA0003388641810000063
wherein x ism,i(k) Represents the space occupancy rate, l, of the kth period in the ith direction of the mth intersection of the aream,i,maxIndicating the link length (vehicle storage capacity) in the ith direction at the mth intersection of the area (veh).
The variable-period multidirectional space occupancy model of the mth intersection of the traffic area can be expressed in the following form:
Figure GDA0003388641810000064
the saturation of the ith cycle of the mth intersection in the area in the ith direction is defined as follows:
Figure GDA0003388641810000065
the index is mainly used for judging three traffic states of undersaturation, critical saturation and supersaturation.
Defining the green light time constraint and the control signal period constraint of the kth period in the ith direction of the mth intersection of the area as follows:
Figure GDA0003388641810000071
Figure GDA0003388641810000072
the traffic area multi-intersection variable-period multi-direction space occupancy model considering the green light time constraint is as follows:
Figure GDA0003388641810000073
at the moment, the multi-intersection multi-direction constrained space occupancy model in the traffic area can describe three traffic state forms of undersaturation, critical saturation and supersaturation at the intersection at the same time.

Claims (1)

1.一种区域交通信号数据驱动控制模型建立方法，其特征在于，1. a method for establishing a regional traffic signal data-driven control model, characterized in that, (1)建立Compartment-正系统模型(1) Establish a Compartment-positive system model
Figure FDA0003388641800000011
Figure FDA0003388641800000011
 其中，xm(k)≥0,m＝1,…,N表示Compartment系统元素m在k时刻的状态；amn,m≠n表示Compartment系统元素m到Compartment系统元素n在采样周期T＞0内的状态量转移比例系数；Im(k)≥0与Om(k)≥0分别表示Compartment系统元素m在采样周期内的输入与输出；Among them, x m (k)≥0, m=1,...,N represents the state of the Compartment system element m at time k; a mn , m≠n represents the Compartment system element m to the Compartment system element n in the sampling period T>0 The proportional coefficient of state quantity transition in ; I m (k) ≥ 0 and O m (k) ≥ 0 respectively represent the input and output of the element m of the Compartment system in the sampling period; 将所述Compartment系统模型描述成向量形式：Describe the Compartment system model in vector form: x(k+1)＝Ax(k)+I(k)x(k+1)=Ax(k)+I(k) 式中：x(k)＝[x1(k),…,xN(k)]T∈RN为系统状态向量；In the formula: x(k)＝[x 1 (k),…,x N (k)] T ∈R N is the system state vector; I(k)＝[I1(k),…,IN(k)]T∈RN为系统外部输入；A∈RN×N为系统状态矩阵，且有I(k)=[I 1 (k),...,I N (k)] T ∈R N is the external input of the system; A∈R N ×N is the system state matrix, and there are
Figure FDA0003388641800000012
Figure FDA0003388641800000012
 假定任意Compartment当前状态量大于等于采样周期内状态转移总量，则状态矩阵A对角线元素均为非负，且列和满足：
Figure FDA0003388641800000013
Assuming that the current state of any Compartment is greater than or equal to the total amount of state transitions in the sampling period, the diagonal elements of the state matrix A are all non-negative, and the column sum satisfies:
Figure FDA0003388641800000013
 (2)建立多交叉口变周期多方向空间占有率模型(2) Establish a multi-intersection variable-period multi-directional spatial occupancy model 在正系统模型的基础上，一个交通区域内多交叉口变周期多方向空间占有率均衡控制，则其数学模型如下：On the basis of the positive system model, the multi-intersection variable-period multi-directional spatial occupancy control in a traffic area is balanced, and the mathematical model is as follows: lm,i(k+1)＝lm,i(k)+Cm(k)qm,i(k)-Sm,igm,i(k)l m,i (k+1)=l m,i (k)+C m (k)q m,i (k)-S m,i g m,i (k) 其中，m＝1,…,M表示该区域第m个交叉口；i＝1,…,N表示该交叉口第i个方向，N＝4表示该交叉口有4个方向；Cm(k)表示该区域第m个交叉口第k个控制信号周期，为可变周期；lm,i(k)表示该区域第m个交叉口第i方向第k个周期的排队车辆数；Sm,i表示该区域第m个交叉口第i方向的饱和流率；gm,i(k)表示该区域第m个交叉口第i方向第k个周期的绿灯时间；其中qm,i(k)表示该区域第m个交叉口第i方向第k个周期的车辆到达率，其满足如下关系：Among them, m=1,...,M represents the m-th intersection in the area; i=1,...,N represents the i-th direction of the intersection, and N=4 means that the intersection has 4 directions; C m (k ) represents the k-th control signal period of the m-th intersection in this area, which is a variable period; lm ,i (k) represents the number of queued vehicles in the k-th period of the i-th direction of the m-th intersection in this area; S m ,i represents the saturated flow rate in the i-th direction of the m-th intersection in this area; g m,i (k) represents the green light time of the k-th cycle in the i-th direction of the m-th intersection in this area; where q m,i ( k) represents the vehicle arrival rate of the k-th cycle in the i-th direction of the m-th intersection in this area, which satisfies the following relationship:
Figure FDA0003388641800000021
Figure FDA0003388641800000021
 该区域第m个交叉口各方向绿灯时间与控制信号周期满足如下约束条件：The green light time and control signal period in each direction of the m-th intersection in this area satisfy the following constraints:
Figure FDA0003388641800000022
Figure FDA0003388641800000022
 其中，tm,L表示该区域第m个交叉口的总损失时间；Among them, t m, L represents the total lost time of the m-th intersection in this area; 定义该区域第m个交叉口某一方向的空间占有率为该方向排队车辆数与其路段长度之比，如下：Define the space occupancy rate of the m-th intersection in a certain direction as the ratio of the number of queued vehicles in this direction to the length of the road section, as follows:
Figure FDA0003388641800000023
Figure FDA0003388641800000023
 其中，xm,i(k)表示该区域第m个交叉口第i方向第k个周期的空间占有率，lm,i,max表示该区域第m个交叉口第i方向的路段长度；Among them, x m,i (k) represents the space occupancy rate of the k-th cycle in the i-th direction of the m-th intersection in this area, and lm ,i,max represents the length of the road segment in the i-th direction of the m-th intersection in this area; 交通区域第m个交叉口变周期多方向空间占有率模型可表述成如下形式：The variable-period multi-directional spatial occupancy model of the m-th intersection in the traffic area can be expressed as follows:
Figure FDA0003388641800000024
Figure FDA0003388641800000024
 该区域第m个交叉口第i方向第k个周期的饱和度定义如下：The saturation of the k-th period in the i-th direction of the m-th intersection in this area is defined as follows:
Figure FDA0003388641800000025
Figure FDA0003388641800000025
 定义该区域第m个交叉口第i方向第k个周期的绿灯时间约束和控制信号周期约束分别为：Define the green light time constraint and the control signal cycle constraint of the k-th cycle in the i-th direction of the m-th intersection in this area as:
Figure FDA0003388641800000026
Figure FDA0003388641800000026
 考虑带有绿灯时间约束的交通区域多交叉口变周期多方向空间占有率模型如下：Considering the multi-intersection variable-period multi-direction space occupancy model in the traffic area with the constraint of green light time is as follows:
Figure FDA0003388641800000027
Figure FDA0003388641800000027
CN202010798058.0A 2020-08-10 2020-08-10 Method for establishing regional traffic signal data drive control model Active CN112258856B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010798058.0A CN112258856B (en) 2020-08-10 2020-08-10 Method for establishing regional traffic signal data drive control model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010798058.0A CN112258856B (en) 2020-08-10 2020-08-10 Method for establishing regional traffic signal data drive control model

Publications (2)

Publication Number Publication Date
CN112258856A CN112258856A (en) 2021-01-22
CN112258856B true CN112258856B (en) 2022-01-18

Family

ID=74224479

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010798058.0A Active CN112258856B (en) 2020-08-10 2020-08-10 Method for establishing regional traffic signal data drive control model

Country Status (1)

Country Link
CN (1) CN112258856B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113192318B (en) * 2021-01-29 2022-09-02 安徽科力信息产业有限责任公司 Data drive control regional traffic signal dynamic optimization method and system
CN113380044B (en) * 2021-08-12 2022-01-07 深圳市城市交通规划设计研究中心股份有限公司 Overflow control signal optimization method and device and storage medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107680391A (en) * 2017-09-28 2018-02-09 长沙理工大学 Two pattern fuzzy control methods of crossroad access stream
CN109767632A (en) * 2019-03-02 2019-05-17 太原理工大学 A Traffic Signal Hybrid Control Method Based on Iterative Learning and Model Predictive Control

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6617981B2 (en) * 2001-06-06 2003-09-09 John Basinger Traffic control method for multiple intersections
US7663505B2 (en) * 2003-12-24 2010-02-16 Publicover Mark W Traffic management device and system
US20140309878A1 (en) * 2013-04-15 2014-10-16 Flextronics Ap, Llc Providing gesture control of associated vehicle functions across vehicle zones
US9830813B2 (en) * 2013-06-18 2017-11-28 Carnegie Mellon University, A Pennsylvania Non-Profit Corporation Smart and scalable urban signal networks: methods and systems for adaptive traffic signal control
ITBA20150017A1 (en) * 2015-03-05 2016-09-05 Virgilio Savino INTELLIGENT SAFETY AND AID SYSTEM FOR VEHICLES IN GENERAL
JP6500517B2 (en) * 2015-03-10 2019-04-17 住友電気工業株式会社 Roadside communication device, data relay method, central device, computer program, and data processing method
CN105185130B (en) * 2015-09-30 2017-07-07 公安部交通管理科学研究所 A kind of signal coordinating control method between intersection under variable period
CN105225502A (en) * 2015-11-02 2016-01-06 招商局重庆交通科研设计院有限公司 A kind of intersection signal control method based on multiple agent
CN107591011B (en) * 2017-10-31 2020-09-22 吉林大学 Adaptive control method for intersection traffic signal considering supply-side constraints
US11498386B2 (en) * 2018-05-31 2022-11-15 Harley-Davidson Motor Company Group, LLC Multi-zone climate control system for a vehicle
CN109559506B (en) * 2018-11-07 2020-10-02 北京城市系统工程研究中心 Method for predicting delay time of intermittent traffic flow of urban road in rainfall weather
CN109841068B (en) * 2019-03-28 2021-03-19 广东振业优控科技股份有限公司 Traffic signal control method based on traffic flow conflict point occupancy rate at intersection center

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107680391A (en) * 2017-09-28 2018-02-09 长沙理工大学 Two pattern fuzzy control methods of crossroad access stream
CN109767632A (en) * 2019-03-02 2019-05-17 太原理工大学 A Traffic Signal Hybrid Control Method Based on Iterative Learning and Model Predictive Control

Also Published As

Publication number Publication date
CN112258856A (en) 2021-01-22

Similar Documents

Publication Publication Date Title
CN112258856B (en) Method for establishing regional traffic signal data drive control model
Egea et al. Assessment of reward functions for reinforcement learning traffic signal control under real-world limitations
Zhang et al. Travel time prediction of urban public transportation based on detection of single routes
Zheng et al. A novel approach to coordinating green wave system with adaptation evolutionary strategy
Pham et al. Distributed stochastic MPC traffic signal control for urban networks
Chen et al. Traffic signal optimization control method based on adaptive weighted averaged double deep Q network
Li et al. Distributed edge signal control for cooperating pre-planned connected automated vehicle path and signal timing at edge computing-enabled intersections
Qiao et al. Traffic signal control using a cooperative EWMA-based multi-agent reinforcement learning
JP3509906B2 (en) Road traffic signal control optimization device and road traffic flow control system using the same
Klingbeil et al. Centralized model‐predictive cooperative and adaptive cruise control of automated vehicle platoons in urban traffic environments
CN119475738B (en) Micro-micro integrated micro three-dimensional simulation method and system for composite traffic network
CN115963840A (en) Intelligent vehicle formation control method based on deep reinforcement learning under communication topology switching
Hou et al. Multi-agent deep reinforcement learning with traffic flow for traffic signal control
Rimoldi et al. Urban traffic congestion control: a DeePC change
CN112133109A (en) Method for establishing single-cross-port multidirectional space occupancy balance control model
Li et al. Elevating adaptive traffic signal control in semi‐autonomous traffic dynamics by using connected and automated vehicles as probes
Hao et al. Developing an adaptive strategy for connected eco-driving under uncertain traffic and signal conditions
Han et al. Congestion control of vehicle traffic networks by learning structural and temporal patterns
CN113380073B (en) Asynchronous filtering estimation method of flow management system based on event trigger mechanism
Wei et al. Multi-Agent Deep Reinforcement Learning for Distributed and Autonomous Platoon Coordination via Speed-regulation over Large-scale Transportation Networks
Zhou et al. Transit Signal Priority Strategy With Heterogeneous Graph-Based Deep Reinforcement Learning for Autonomous Public Transit Vehicles
Huang et al. Adaptive Distributed Training for Multi-Agent Reinforcement Learning in Multi-Objective Traffic Signal Control
Huang et al. An intelligent computational approach of signal control in urban rail transit for vehicular communication
Jing et al. Intelligent traffic assignment method of urban traffic network based on deep reinforcement learning
Wang et al. Real-time network-level traffic signal control: An explicit multiagent coordination method

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
OL01 Intention to license declared
OL01 Intention to license declared