Top Banner
06/06/22 1 Traffic Light Control Hoàng Hải Lưu Như Hòa Department of Automatic Control Hanoi University of Technology
27
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Traffic Light Control

04/08/23 1

Traffic Light Control

Hoàng Hải

Lưu Như Hòa

Department of Automatic Control

Hanoi University of Technology

Page 2: Traffic Light Control

04/08/23 2

Overview

Improving safety Minimizing travel time Increasing the capacity

of infrastructures

The problem of transport system is an optimal problem control Main Goals are:

Page 3: Traffic Light Control

04/08/23 3

Outline

Section 1: How traffic can be modeled ? Section 2: What a traffic light control system

contain ? Section 3: New approaches to traffic light

control !!!

Page 4: Traffic Light Control

04/08/23 4

Modeling and Controlling Traffic

Section 1

Page 5: Traffic Light Control

04/08/23 Modeling and Controlling Traffic 5

Modeling and Controlling Traffic

Macroscopic scale: Similar to models of fluid dynamics

PDE

Microscopic scale: each vehicle is considered as an individual

ODE

How traffic can be modeled ?

Page 6: Traffic Light Control

04/08/23 Modeling and Controlling Traffic 6

Macroscopic models

Macroscopic models based on fluid dynamics model

Relation between: traffic flux, traffic density and velocity.

Page 7: Traffic Light Control

04/08/23 Modeling and Controlling Traffic 7

Macroscopic models

Page 8: Traffic Light Control

04/08/23 Modeling and Controlling Traffic 8

Microscopic models

Microscopic models focus on vehicles (position and velocity )

Cellular automaton (CA): discrete model Road Δx Time steps Δt Nagel-Schreckenberg

model

Stephen WolframCreator of CA

Page 9: Traffic Light Control

04/08/23 Modeling and Controlling Traffic 9

Microscopic models

Road Cell

111 110 101 100 011 010 001 000

1 0 1 1 1 0 0 0

Rule 10 2184 10111000If next state is available Then Move forwardsElse Stop

current pattern

new state for center cell

Page 10: Traffic Light Control

04/08/23 Modeling and Controlling Traffic 10

Microscopic models

Self-caused slowdown:

Stable "stop-waves“

Two stable states

Page 11: Traffic Light Control

04/08/23 11

Traffic Light Control System

Section 2

Page 12: Traffic Light Control

04/08/23 Traffic Light Control System 12

Traffic Light Control System

No obvious optimal solution

In practice most traffic lights are controlled by fixed-cycle controllers

Fixed controllers need manual changes to adapted specific situation

Page 13: Traffic Light Control

04/08/23 Traffic Light Control System 13

Driver Detector - Camera

Identification image Expensive Complex Traffic System

Page 14: Traffic Light Control

04/08/23 14

Page 15: Traffic Light Control

04/08/23 Traffic Light Control System 15

Driver Detector - Loop Detector

•Measure Inductive•Most popular•Cheap

Page 16: Traffic Light Control

04/08/23 Traffic Light Control System 16

Traffic Light Control System

Distributed System A set of intersections A set of connection

(roads) Traffic lights regulating Traffic lights are co-

operation

Page 17: Traffic Light Control

04/08/23 Traffic Light Control System 17

Traffic Control and Command Centre

In Thailand

Page 18: Traffic Light Control

04/08/23 Traffic Light Control System 18

Green Waves

Offset of cycle can be adjusted to create green waves.

Page 19: Traffic Light Control

04/08/23 19

Control Algorithms

Section 3

Page 20: Traffic Light Control

04/08/23 Control Algorithms 20

Expert Systems

uses a set of given rules to decide upon the next action (change some of the control parameters)

Findler,Stapp,1992 describe a network of roads connected by traffic light-based expert systems

improve performance but much computation

Can Machines Think?

Page 21: Traffic Light Control

04/08/23 Control Algorithms 21

Evolutionary Algorithms

Taaleetal,1998 using evolutionary algorithms to evolve a traffic light controller for a single intersection

Result: Generates green times for next

switching schedule. Minimization of total delay /

number of stops. Better results (3 – 5%) / higher

flexibility than with traditional controllers.

Dynamic optimization, depending on actual traffic (measured by control loops).

Page 22: Traffic Light Control

04/08/23 Control Algorithms 22

Fuzzy Logic

Passed through 31% more cars

Average waiting time shorter by 5%

Performance also measure 72% higher.

In comparison with a human expert the fuzzy controller passed through 14% more cars with 14% shorter waiting time and 36% higher performance index

Page 23: Traffic Light Control

04/08/23 Control Algorithms 23

Reinforcement Learning

how an agent take actions in an environment to maximize long-term reward

Thorpe used it for the traffic-light problem

Page 24: Traffic Light Control

04/08/23 Control Algorithms 24

Intelligent Agents

Page 25: Traffic Light Control

04/08/23 25

Conclusion

Modeling Macroscopic Model Microscopic Model

Traffic Control System Traffic light control in a junction Co-operation in traffic control system

Control Algorithms

Page 26: Traffic Light Control

04/08/23 26

References

http://en.wikipedia.org [Wiering,2004],Intelligent Traffic Light Control [Tan Kok Khiang,1997] Intelligent Traffic

Lights Control by Fuzzy Logic

Page 27: Traffic Light Control

04/08/23 27

Thank you for your attention!