Fuzzy Inference Enabled Deep Reinforcement Learning-Based Traffic Light Control for Intelligent Transportation System

2020 ◽  
pp. 1-10
Author(s):  
Neetesh Kumar ◽  
Syed Shameerur Rahman ◽  
Navin Dhakad
Keyword(s):  
Reinforcement Learning ◽  
Intelligent Transportation System ◽  
Fuzzy Inference ◽  
Intelligent Transportation ◽  
Transportation System ◽  
Light Control ◽  
Traffic Light ◽  
Traffic Light Control

The Application of Polling in Intelligent Transportation System

2014 ◽  
Vol 602-605 ◽  
pp. 853-856
Author(s):  
Meng Yao Wang ◽  
Hong Wei Ding ◽  
Qian Lin Liu ◽  
Zhi Jun Yang
Keyword(s):  
Intelligent Control ◽  
Intelligent Transportation System ◽  
Arrival Rate ◽  
Intelligent Transportation ◽  
Polling System ◽  
Light Control ◽  
Traffic Light ◽  
Traffic Jams ◽  
Traffic Light Control ◽  
The Relationship

This paper presents a new use of polling system[1]in the intelligent traffic light control system[2]. vehicle arrival rate is measured in this system.Through the relationship between arrival rate and waiting time in polling system, achieved an technology that different arrival rate correspond to different length of time[3]of traffic light.With the intelligent control, we can well solve the problem of traffic jams during different periods.

scholarly journals An Edge Based Multi-Agent Auto Communication Method for Traffic Light Control

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4291 ◽  
Author(s):  
Qiang Wu ◽  
Jianqing Wu ◽  
Jun Shen ◽  
Binbin Yong ◽  
Qingguo Zhou
Keyword(s):  
Reinforcement Learning ◽  
Control Method ◽  
Communication Protocol ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Light Control ◽  
Traffic Light ◽  
Traffic Light Control ◽  
Multi Agent

With smart city infrastructures growing, the Internet of Things (IoT) has been widely used in the intelligent transportation systems (ITS). The traditional adaptive traffic signal control method based on reinforcement learning (RL) has expanded from one intersection to multiple intersections. In this paper, we propose a multi-agent auto communication (MAAC) algorithm, which is an innovative adaptive global traffic light control method based on multi-agent reinforcement learning (MARL) and an auto communication protocol in edge computing architecture. The MAAC algorithm combines multi-agent auto communication protocol with MARL, allowing an agent to communicate the learned strategies with others for achieving global optimization in traffic signal control. In addition, we present a practicable edge computing architecture for industrial deployment on IoT, considering the limitations of the capabilities of network transmission bandwidth. We demonstrate that our algorithm outperforms other methods over 17% in experiments in a real traffic simulation environment.

scholarly journals Implementation of Fuzzy Mamdani Method for Traffic Lights Smart City in Rangkasbitung, Lebak Regency, Banten Province (Case Study of the Traffic Light T-junction, Cibadak, By Pas Sukarno Hatta Street)

KOMTEKINFO ◽  
2020 ◽  
Vol 7 (3) ◽  
pp. 176-185
Author(s):  
Dentik Karyaningsih ◽  
Robby Rizky
Keyword(s):  
Fuzzy Logic ◽  
Control System ◽  
Traffic Congestion ◽  
Fuzzy Logic Controller ◽  
Fuzzy Inference ◽  
Light Control ◽  
Traffic Light ◽  
Traffic Lights ◽  
Traffic Jams ◽  
Traffic Light Control

Traffic jams are a common sight that can be seen in almost all major cities in Indonesia. One of them is in Rangkasbitung City, Lebak Regency. This happens because the number of vehicles continues to increase. The traffic light control system implemented in Indonesia is a static preset time because the time of each phase is predetermined. This type of control system is still not effective in overcoming traffic congestion, especially at certain peak traffic jams. By using the Mamdani fuzzy logic system, it is possible to implement the human mindset into a system. Some rules can be set out in the fuzzy logic controller. The purpose of this study is to design a traffic light control system using fuzzy inference that regulates traffic based on its density. The data used are observations made at the research site. The conclusion of this study is to explain that the fuzzy mamdani method can solve existing problems in traffic congestion in Rangkasbitung City, Lebak Regency, Banten Province

Optimalisasi Lampu Lalu Lintas dengan Fuzzy Logic

2013 ◽  
Vol 5 (2) ◽  
pp. 58-62 ◽  
Author(s):  
Adhitya Yoga Yudanto ◽  
Marvin Apriyadi ◽  
Kevin Sanjaya
Keyword(s):  
Fuzzy Logic ◽  
Control System ◽  
Fuzzy Inference ◽  
System Control ◽  
Light Control ◽  
Traffic Light ◽  
Inference System ◽  
Traffic Lights ◽  
The Road ◽  
Traffic Light Control

The traffic lights problem is already commonly found in large cities. The traffic lights are supposed to control the flow of the road, but sometimes causes a congestion. This happens because the distribution of the time are all the same for all lines, without seeing the condition of the density of each lane. There’s one effort that can be done to overcome this problem, is to create a traffic light control system. With this system, the congestion that occurs around the traffic lights can be reduced. This system is using fuzzy logic. Fuzzy logic is one of computer science that studies about the value of truth that worth a lot. For example, a air conditioning system control subway Sendai in Japan. As for making a traffic light control system, the author using Fuzzy Inference System (FIS) that already exist in the application of MATLAB R2013a with Mamdani method. Index Terms —fuzzy logic, traffic lights, MATLAB.

Sign in / Sign up

Export Citation Format

Share Document