See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/279917067

Intelligent Traffic Light Control System for Isolated Intersection Using Fuzzy
Logic

Conference Paper · April 2013

DOI: 10.13140/RG.2.1.4854.6406

CITATIONS READS
13 4,249

3 authors, including:

Javed Alam Dr. Manoj Kumar Pandey

Quant lase lab Abu Dhabi UAE Amrapali Group of Institutes
9 PUBLICATIONS 95 CITATIONS 19 PUBLICATIONS 116 CITATIONS

SEE PROFILE SEE PROFILE

All content following this page was uploaded by Javed Alam on 09 July 2015.

The user has requested enhancement of the downloaded file.

 Conference on Advances in Communication and Control Systems 2013 (CAC2S 2013)

Intellegent Traffic Light Control System for Isolated Intersection Using Fuzzy Logic

JAVED ALAM
Assistant Professor, Deptt of MCA
Dehradun Institute of Technology, Dehradun, UK (INDIA)
[email protected]

Prof.(Dr.) M. K. PANDEY
Director Computer Science & Applications
AIMCA, Haldwani UK (INDIA)
[email protected]

HUSAIN AHMED
Assistant Professor, Deptt of EE
Dehradun Institute of Technology, Dehradun, UK (INDIA)
[email protected]

Abstract

Traffic is the major problem which every country faces because of the increase in number of vehicles throughout the world,
particularly in large urban areas. Therefore the need arises for simulating and optimizing traffic control algorithms to better
accommodate this increasing demand. Fuzzy optimization deals with finding the values of input parameters of a complex
simulated system which result in desired output. Traditional techniques may require an enormous amount of simulation runs to
evaluate the system. Describes, design and implementation of an intelligent traffic lights control system based on fuzzy logic
technology. Software has been developed in MATLAB to simulate the situation of an isolated traffic junction based on fuzzy
logic. Simulation results show that the fuzzy logic controller has better performance and is more cost effective than fixed time
controller. Moreover, Fuzzy optimization is more flexible than Traditional techniques.

Keyword: Simulation, Fuzzy logic, Intelligent Traffic lights control System, Arrival, Queue and Extension time.

1. Introduction measures of overcoming such a problem. Many solutions

The monitoring and control of Road traffic is becoming were proposed to solve the traffic jam. Most
a major problem in many countries. The increasing conventional traffic surveillance systems use intrusive
number of vehicles and the lower phase of highways sensors, including inductive loop detectors, micro-loop
developments have led to traffic congestion problem. probes, and pneumatic road tubes. However, these
There are many factors that lead to traffic congestion sensors disrupt traffic during installation and repair,
such as the density of vehicles on the roads, human which leads to a high cost installation and maintenance.
habits, social behavior, and traffic light system. One In addition, over the ground sensors like videos, radars,
major factor is due to the traffic lights system that and ultrasonic were used. These systems are also high
controls the traffic at junction. Traffic policeman are cost and their accuracy depends on environment
deployed at traffic intersection everyday in order to condition [1].
overcome these congestion during peak hour, thus one of
the roots of the problem is due to ineffective traffic lights Conventional methods for traffic signal control
controllers. With effective control the intersection, it is based precise models fail to deal efficiently with the
believed that the overall capacity and performance of complex and varying traffic situations. They are modeled
urban traffic network could be resolve. With the ever based on the preset cycle time to change the signal
increasing number of vehicles on the road, the without any analysis of traffic situation. Due to fixed
Monitoring authorities have to find new ways or cycle time, such systems do not consider that which

© 2013. The authors - Published by Atlantis Press 209

intersection has more load of traffic, so should kept intersection using fuzzy logic technology which has the
green more or should terminate earlier then complete capability of mimicking human intelligence for
cycle time. In case of intersections, conventional control controlling traffic lights. Software based on MATLAB
systems only consider waiting time of signals on has been developed to simulate an isolated traffic
different directions but not the vehicle directions. Such junction. The control of the traffic lights using both
situations can be seen in various areas of Dehradun like conventional fixed-time and fuzzy logic controllers can
Darshanlal-chowk where traffic flow varies in different be simulated in the software. Analysis on the traffic
hours and heavy traffic flows in morning and evening lights simulation such as waiting time, density, cost, etc.
timings because of large number of offices on that route. can also be made using the software. The software can
Also, in different intersections, traffic flow abruptly also be used as an exercise for undergraduate and
changes in schools timings then other daily hours. Preset graduate students to understand the concept of fuzzy
Cycle Time Controllers fail in such scenarios because logic and its application to a real environment. The rules
they could not get complete information of vehicles and membership functions of the fuzzy logic controller
earlier. Also, sometimes situation arises, when some VIP can be selected and changed and their outputs can be
movement is there, the traffic flow has to divert and compared in terms of several different representations.
control different intersections. In such situations,
efficiency of human decision-making is unprecedented Fuzzy logic technology allows the implementation of
efficiency of human because decision- real-life rules similar to the way humans would think. In
making objectives are unclear [1]. Traffic Control System, humans would think in the
following way to control traffic situation at a certain
Fuzzy based controllers are proved to be well junction: “if the traffic is heavier on the north or south
manager of traffic system in such scenarios. Fuzzy lanes and the traffic on the west or east lanes is less, then
controllers have the ability to take decision even with the traffic lights should stay green longer for the north
incomplete information. More and more sophisticated and south lanes”. Such rules can now be easily
controllers are being developed for traffic control [2, accommodated in the fuzzy logic controller. In this
3,4,5,6 and 7]. These algorithms are continually consideration, we can say that it is replaceable to Traffic
improving the safety and efficiency by reducing the Police Officers. Fuzzy Logic works glowing when traffic
waiting delay of vehicles on signals. This increases the flow in different directions is highly uneven as compared
tempo of travel and thus makes signals more effective to Pretimed Controller. The beauty of fuzzy logic is that
and traffic flow smooth. The key motivation towards it allows fuzzy terms and conditions such as “short”,
Fuzzy Logic in traffic signal control is the existence of “Medium”, and “long” to be quantized and understood
uncertainties in signal control. Decisions are taken based by the computer [8, 11].
on imprecise information and the effect of evaluation is
not well known [7].
2. Literature review
Lin Zhang and Honglong Li developed Fuzzy Traffic In this section, we discuss different research work in the
Controller for Oversaturated Intersections [7]. They field of traffic control system. In other words this section
designed an algorithm to control over-saturated concentrates on the use of fuzzy logic for traffic control.
intersections of two-way streets with left turning The first attempt made to design Fuzzy Traffic
movements. Jee-Hyong Lee and Hyung Lee-Kwang also Controller was in 70s by Pappis and Mamdani [2]. After
designed a Fuzzy Control Model. The goal of controller that Niittymaki, Kikuchi, Chui and other researchers [4]
is to decrease the average time delay in the whole traffic developed different algorithms and logic controllers to
network. They assumed that special establishments normalize traffic flow. Kelsey and Bisset also designed a
named right-turning lane in the intersection allow right- simulator for signal controlling of an isolated
turning traffic flow to pass the intersection without intersection with one lane. Same work was also done by
disturbing the other traffic flows at the same intersection. Niittymaki and Pursula [5]. They observed that Fuzzy
Under this assumption, right-turning traffic flow is out of Controller reduces the vehicle delay when traffic volume
the consideration of fuzzy control [8]. was heavy. Niittymaki and Kikuchi developed Fuzzy
based algorithm for pedestrians, crossing the road.
In this paper we discuss the implementation of an
intelligent traffic lights control system for isolated Nakatsuyama, Nagahashi, and Nishizuka [6] applied

210
fuzzy logic to control two adjacent intersections on an relative graded membership and so are the functions of
arterial with one-way movements. Fuzzy control rules mentation and cognitive processes. The utility of fuzzy
were developed to determine whether to extend or sets lies in their ability to model uncertain or ambiguous
terminate the green signal for the downstream data. Applications of fuzzy logic occur in three primary
intersection based on the upstream traffic. Chui was the categories: consumer products, industrial/commercial
first who uses Fuzzy Logic to control traffic in multiple systems and decision support systems [1].
intersections [4]. In this attempt, only two way streets
are evaluated without considering any turnings.
4. Description of the proposed fuzzy traffic light
In recent years, Lin Zhang and Honglong Li [7] also control system
worked on designing Fuzzy Traffic Controller for The first traffic management systems used in Germany
Oversaturated intersections. Jee-Hyong Lee and Hyung was implemented on roads with frequent accidents
Lee-Kwang [8] presented direction-varying traffic signal caused by fog or icy road conditions. Later, these
control but assume that right turn traffic flow do not systems were extended to detect and control traffic to
disturb any other traffic flows in an intersection. increase the traffic capacity. These traffic control
systems use several detection stations along the road.
I.N.Askerzade (Askerbeyli), Mustafa Mahmood [3] These stations employ magnetic sensors for traffic
discuss a paper entitled “Control the Extension Time of detection, as well as weather stations transmitting
Traffic Light in Single Junction by Using Fuzzy Logic” environmental data from road surface and the air layer
In this paper discuss the implementation of an intelligent near the ground. A central traffic control computer
traffic lights control system using fuzzy logic technology collects the data transmitted from the section stations. A
which has the capability of mimicking human control strategy derives an adequate speed limit for every
intelligence for controlling traffic lights. Software based section. The control objectives are:
on MATLAB has been developed to simulate an isolated • Keep traffic flowing in case of peak traffic
traffic junction. Fuzzy logic technology allows the • Slow down traffic at the inflow to congestion
implementation of real-life rules similar to the way • Warn for bad weather conditions such as fog or
humans would think. For example, humans would think ice
in the following way to control traffic situation at a
certain junction: if the traffic is heavier on the north or Along the road of such an “intelligent” highway,
south lanes and the traffic on the west or east lanes is alterable road signs posted on traffic sign gantries
less, then the traffic lights should stay green longer for display speed limits for each lane and display non
the north and south lanes. Such rules can now be easily regular events such as road work, warnings for traffic
accommodated in the fuzzy logic controller. back-ups, breakdowns, an accident, or dangerous
weather conditions [1]. Fuzzy logic traffic lights control
is an alternative to conventional traffic lights control
3. Fuzzy logic which can be used for a wider array of traffic patterns at
The Fuzzy Logic tool was introduced in 1965, also by an intersection. A fuzzy logic controlled traffic light uses
Lotfi Zadeh, and is a mathematical tool for dealing with sensors that count cars instead of proximity sensors
uncertainty. It offers to a soft computing partnership the which only indicate the presence of cars. This provides
important concept of computing with words. It provides the controller with traffic densities in the lanes and
a technique to deal with imprecision and information allows a better assessment of changing traffic patterns.
granularity. The fuzzy theory provides a mechanism for As the traffic distributions fluctuate, the fuzzy controller
representing linguistic constructs such as “many,” “low,” can change the signal light accordingly.
“medium,” “often,” “few.” In general, the fuzzy logic
provides an inference structure that enables appropriate The general structure of a fuzzy intelligent traffic
human reasoning capabilities. On the contrary, the lights control system is illustrated as in Figure-1. There
traditional binary set theory describes crisp events, are two electromagnetic sensors placed on the road for
events that either do or do not occur. It uses probability each lane. The first sensor behind each traffic light
theory to explain if an event will occur, measuring the counts the number of cars passing the traffic lights, and
chance with which a given event is expected to occur. the second sensor which is located behind the first sensor
The theory of fuzzy logic is based upon the notion of counts the number of cars coming to the intersection at

211
distance S from the lights. The number of cars between versa;
the traffic lights is determined by the difference of the
reading between the two sensors. This is in contrast to • no right and left turns are considered in this
conventional control systems which place a proximity system;
sensor at the front of each traffic light and can only sense
the presence of a car waiting at the junction, not the • the fuzzy logic controller will observe the
number of cars waiting at the traffic. The distance density of the north and south traffic as one side
between the two sensors S, is determined accordingly and the west and east traffic as another side;
following the traffic flow pattern at that particular • the East-West lane is assumed as the main
intersection. The fuzzy logic controller is responsible for approach;
controlling the length of the green time according to the The flow diagram of a fuzzy logic controller is shown in
traffic conditions. The state machine controls the figure 3.
sequence of states that the fuzzy traffic controller should
cycle through. There is one state for each phase of the
traffic light. There is one default state which takes place
when no incoming traffic is detected. This default state
corresponds to the green time for a specific approach,
usually to the main approach. In the sequence of states, a
state can be skipped if there is no vehicle queues for the
corresponding approach.

Figure 2: Structure of Fuzzy logic Controller

A fuzzy logic controller was designed for an

isolated 4-lane traffic intersection: east, west, north and
south as shown in Figure 1. In the traffic lights controller
two fuzzy input variables are chosen: the quantity of the
traffic on the arrival side (Arrival) and the quantity of
Figure 1: General Structure of fuzzy light control system
traffic on the queuing side (Queue).
In this research, the main goals of fuzzy logic in the
traffic signal control, and a matter of fact, also in traffic If the north and south side is green then this would
signal control in general, are as follows- be the arrival side while the west and east side would be
considered as the queuing side, and vice-versa. The
• Improving of traffic safety in the intersection. output fuzzy variable would be the extension time
• Maximizing the capacity of the intersection. needed for the green light on the arrival side (Extension).
• Minimizing the delays. Thus based on the current traffic conditions the fuzzy
• Clarifying the traffic environment. rules can be formulated so that the output of the fuzzy
• Influencing the route choices. controller will extend or not the current green light time.
If there is no extension of the current green time, the
state of the traffic lights will immediately change to
5. Methodology another state, allowing the traffic from the alternate
In the development of the intelligent traffic lights control phase to flow.
system the following assumptions are made:

• The junction is an isolated four-way junction 6. Fuzzy parameters and their membership
with traffic coming from the north, west, south functions design
and east directions; For the traffic lights control, there are five membership
functions for each of the input and there are four output
• when traffic from the east and west moves, fuzzy variable of the system. Table 1 shows the fuzzy
traffic from the north and south stops, and vice- input variables of Arrival, Queue and output variable

212
Extension of the system. The fuzzy rule uses in intelligent traffic light control
system shown in the figure 7.

Table 1: Fuzzy Variables form for Intelligent traffic light

control system

Figure 7: Fuzzy rule decided the length of extension time

Figure 3: Queue membership

8. Inference engine and defuzzification

In the fuzzy logic controller once the appropriate rules
are fired, the degree of membership of the output fuzzy
variable i.e., Extension time, is determined by encoding
Figure 4: Arrival membership the antecedent fuzzy subsets, in this case Arrival and
Queue. In the traffic lights fuzzy control system, the
max-min implication technique is used. Using this
technique, the final output membership function for each
rule is the fuzzy set assigned to that output by clipping
the degree of truth values of the membership functions
Figure 5: Extension time membership of the associated antecedents. Once the membership
degree of each output fuzzy variable is determined, all of
the rules that are being fired are then combined and the
actual crisp output is obtained through defuzzification.
There are several of defuzzification methods; here we
use the center of gravity defuzzification technique.
Figure 6: The whole design structure

7. Fuzzy rule set

The inference mechanism in the fuzzy logic controller
resembles that of the human reasoning process. This is
where fuzzy logic technology is associated with artificial Table 2: Fuzzy rules matrix form for the intelligent traffic
lights control System
intelligence. Humans unconsciously use rules in
implementing their actions. For example, a traffic 9. Simulation result
policeman manning a junction say, one from the north After the intelligent traffic light control system was
and one from the west; he would use his expert opinion carefully designed, we test the system and discuss the
in controlling the traffic more or less in the following impact of the input variables on the output variable. The
way: simulation we show the effect of the two inputs to
IF traffic from the north of the city is HEAVY AND resulted extension time.. This system shows the slow
traffic from the west is LESS THEN allow movement of growing in the time that will added to the cycle which
traffic from the north LONGER make the traffic situation more stable. The simulation

213
implemented in three stages. In each stage we test one of controllers due to its flexibility. The flexibility involves
the inputs with other input and discuss their effect on the the number of vehicles sensed at the incoming junction
output extension. and the extension of the green time. In the fixed time
controller, being an open loop system the green time is
not extended whatever the density of car at the junction.
In addition to the fuzzy variables as mentioned, the fuzzy
controller also has an advantage of performing according
to linguistics rules in the manner of how a human would
use. In this paper a basic intelligent traffic light control
system for isolated intersections using fuzzy logic was
developed.

In the intelligent traffic light control system, the

extension time is not a fixed value. They are all fuzzy
variables such as zero, short, medium and large. The
numbers of cars sensed at the input of the fuzzy
controller are also converted into fuzzy values, such as
very short, short, medium, large and very large. In
Table 3: Extension time at different values of input variables addition to the fuzzy variables as mentioned, the fuzzy
arrival and queue side controller also has an advantage of performing according
to linguistic rules in the manner of how a human would
use. The reasoning method in the fuzzy controller is also
similar to that of the policeman handling the traffic flow
at a typical junction.

It can be observed from the results that the intelligent

traffic light control system provides better performance
in terms of total waiting time as well as total moving
time. Less waiting time will not only reduce the fuel
Figure 8: Input variables Arrival, Queue Vs output variable consumption but also reduce air and noise pollution. It
Extension- time
also shows that it can reduce the traffic congestion and
avoids the time being wasted by a green light on an
As shown in figure 8 as well as in Table 3 with empty road.
the different inputs, the extension time (z-axis) is small
when the density of arrival (y-axis) is small and the 11. References
[1] Javed Alam and Dr. M.K. Pandey “Development of
density of the queue side (x-axis) is also small. Unlike
Traffic Light Control System for Emergency Vehicle
the other method, here the external time grows slowly its
Using Fuzzy Logic” International Conference on
being large only when the arrival side density is very
Artificial Intelligence and Soft Computing, IIT- BHU
short to large values and the queue side density is very
Varanasi, India 7-9 December-2012.
shot value. In other words, the external time grows
[2] Pappis, C. P., and E. H. Mamdani. “A Fuzzy Logic
slowly its being large only when the arrival side density
Controller for a Traffic Junction”. IEEE Transactions
increases and the queue side density is constant. On the
on Systems, Man, and Cybernetics, Vol. SMC-7, No.
other hand if arrival side density being constant and the
10, October 1977, pp. 707-717.
queue side density increases then extension time goes to
[3] I.N.Askerzade (Askerbeyli), Mustafa Mahmood
medium to short. This is an important difference
“Control the Extension Time of Traffic Light in Single
between other methods.
Junction by Using Fuzzy Logic” International Journal
of Electrical & Computer Sciences IJECS-IJENS
10. Conclusion Vol:10 No:02 in 2010.
[4] Chiu, S. “Adaptive Traffic Signal Control Using Fuzzy
The fuzzy logic traffic lights controller performed better
Logic”. Proceedings of the IEEE Intelligent Vehicles
than the fixed time controller or even vehicle actuated

214
 Symposium, 1992, pp. 98-107.
[5] Niittymaki, J., and M. Pursula. “Signal Control Using
Fuzzy Logic. Fuzzy Sets and Systems”, Vol. 116, 2000,
pp. 11-22.
[6] Nakatsuyama, M., H. Nagahashi, and N. Nishizuka.
“Fuzzy Logic Phase Controller for Traffic Junctions in
the One-Way Arterial Road”. Proceedings of the IFAC
Ninth Triennial World Congress, 1984, pp. 2865-2870.
[7] Li, H., P. D. Prevedouros, and L. Zhang. “Signal
Control for Oversaturated Intersections Using Fuzzy
Logic” Submitted for consideration for presentation at
the 2005 Annual Meeting of the TRB and publication
in the Transportation Research Record.
[8] Hong Wei, Wang Yong, Mu Xuanqin and Wu Yan. “A
cooperative fuzzy control method for traffic Lights”.
2001 IEEE Intelligent Transportation Systems
Conference Proceedings - Oakland (CA), USA -
August 25-29, 2001.
[9] Yi Hu, CQU, Peter Thomas, Member, IEEE, and
Russel J. Stonier, Member, IEEE. “Traffic Signal
Control using Fuzzy Logic and Evolutionary
Algorithms”. 2007 – IEEE.
[10] J Niittymaki, R Nevala, E Turunen. “Fuzzy Traffic
Signal Control and a New Inference Method! Maximal
Fuzzy Similarity - Fuzzy Sets and Systems”, 2003 -
iasi.rm.cnr.it
[11] Marco Wiering, Jelle van Veenen, Jilles Vreeken, Arne
Koopman. “Intelligent Traffic Light Control”. Institute
of information and computing sciences, Utrecht
university technical report UU-CS-2004-029.

215

View publication stats