INTELLIGENT TRAFFIC LIGHT CONTROL USING EMBEDDED

SYSTEMS
TOPIC PAGE NO.

1. INTRODUCTION 04
2. WHAT AN EMBEDDED SYSTEM IS? 04
3. CREATING AN EMBEDDED APPLICATION 05
3.1 WRITING THE SOFTWARE PROGRAM 05
3.2 WRITING TOGETHER THE NECESSARY 05
HARDWARE
3.3 TESTING AND DEBUGGING 06
4. APLLICATIONS OF EMBEDDED SYSTEMS 07
1.1 OFFICE SYSTEMS AND MOBILE EQUIPMENT 07
1.2 BUILDING SYSTEM 07

1.3 MANUFACTURING AND PROCESS CONTROL 07

1.4 MEDICAL DIAGNOSTIC, MONITORING AND 07
LIFE SUPPORT
1.5 TRANSPORT 07
1.6 COMMUNICATION 08
1.7 BANKING,FINANCE AND COMMERCIAL 08
1.8 TESTING AND DIAGNOSTIC SYSTEMS 08
2. INTELLIGENT TRAFFIC LIGHT CONTROL USING 08
EMBEDDED SYSTEMS
3. CONCLUSION 11
4. REFERENCES 11

1
2. WHAT AN EMBEDDED SYSTEM IS?

General purpose definition of an Embedded system is that they are

devices used to control, monitor or assist the operation of equipment, machinery
or plant .Any device that includes a programmable computer but is not itself a
general-purpose computer is an embedded system. “Embedded” reflects the fact
that they are integral part of the system. In simple terms, any device using a
Microprocessor for control and automation is an Embedded System. But then how
does an Embedded System differ from a computer? After all both use
Microprocessors. The difference lies in the fact that a computer is a general-
purpose device capable of performing several types of tasks like word processing,
internet-access, gaming etc. On the other hand an Embedded System usually
performs one or few specific tasks e.g. traffic light control, industrial automation
control, video games etc. Accordingly a computer uses a general purpose
Microprocessor like Pentium, Athlon, Duron, PowerPC etc. while an Embedded
System uses a Microprocessor/Micro-controller like 8951, Z80, 8051, 80186, PIC
etc.

Embedded systems are also known as real time systems since they respond
to an input or event and produce the result with in a guaranteed time period. This
time period can be few microseconds to days or months. Real time systems are
defined as those systems in which the correctness of the system depends not only
on the logical result of computation, but also on the time in which the results are
produced. Real time system spans a broad spectrum of complexity from very
simple micro controllers in “Embedded systems” (such as microprocessor
controlling an automobile engine) to highly sophisticated, complex and
distributed systems. Real-time and embedded systems technology is a key
enabling technology for the future in an ever-growing domain of important
applications.

Real time systems as the name suggests are the computer systems, which
are used in the real world in time critical situations. A real time system is a

2
 system, which requires a “timely” response from the computer system to prevent
failures.

3. CREATING AN EMBEDDED APPLICATION:

Creating an embedded application involves three important activities
 Writing the software program.
 Writing together the necessary hardware.
 Testing and Debugging.

3.1 WRITING THE SOFTWARE PROGRAM:

The software for an embedded system can be written in Assembly
Language, C, C++ or Java (usually called “FIRMWARE”) out of which C and
Assembly are the most commonly used. If we are using different processors for
each new application, then Assembly Language is the most suited. In this case we
will not need a compiler since Assembly Language has one-to-one
correspondence with the instruction set of the processor. However if we are using
the same processor and similar hardware configuration for each new application,
it is advisable to create a C compiler for the target system and then use C
language so that coding time in future projects may be minimized. We could also
use a processor specific C compiler available from different vendors instead of
writing our own compiler. Assembly language may still be preferred over C on
account of overall speed of execution.

3.2 WRITING TOGETHER THE NECESSARY HARDWARE:

The coding of Embedded system can be done by anyone with a decent
background in programming. However the hardware writing part needs a
background in electronics and PCB fabrications. This is also the most challenging
part of creating an embedded system.
A system designer has to study the data sheet of a Microprocessor/Micro
controller for pin configurations, operating voltage, input/output current
capabilities, temperature resistance etc and connect it to the system to be

3
controlled .For example, the outputs of a traffic light controller system may be
connected to relays that switch the appropriate traffic lights ON or OFF. The
embedded system may also be connected to some I/O devices(keyboards, control
keys, LCD displays, seven segment displays etc.,) to allow human intervention
into the embedded system.

3.3 TESTING AND DEBUGGING:

This is the most important and time-consuming activity in the
implementation of an embedded system. This is what makes an embedded system
crash proof. Imagine a scenario where your cell phone stops functioning just
because you pressed five keys together and the embedded controller was not
designed to handle such an absurd input. The software as well as hardware needs
to be thoroughly tested for errors in operation by simulating all possible scenarios.
The system may encounter and also those scenarios that the system is unlikely to
encounter. Debugging involves defining a suitable; predefine response to all
possible operation scenarios that may be faced by the embedded system.

4. APPLICATIONS OF EMBEDDED SYSTEMS:

Embedded controllers may be found in the following kinds of systems. The list
does not claim to be exhaustive.

4.1 OFFICE SYSTEMS AND MOBILE EQUIPMENT:

Telephone systems, Faxes, Copiers, Time recording systems, Mobile telephones,

still and video cameras, answering machines, laptops and notebooks, PDAs,
personal organizers, printer, microwave etc.

4.2 BUILDING SYSTEMS:

Backup lighting and generators, Fire control, heating and ventilating systems,
Lifts, elevators, escalators, Security systems, Security cameras, Safes and vaults,
Door locks, air conditioning, CTV systems, sprinkler systems, lighting systems,
building management systems etc.

4.3 MANUFACTURING AND PROCESS CONTROL:

4
Manufacturing plants, Water and sewage systems, Nuclear Power systems, Oil
refineries and related storage facilities, Bottling plants, automated factories,
Simulators, Test equipment used to program, maintain and test control systems,
Energy control systems, Robots.

4.4 MEDICAL DIAGNOSTICS, MONITORING AND LIFE SUPPORT:

Heart defibrillators, Pacemaker monitors, Patient information systems, Patient

monitoring systems, Pharmaceutical control and dispensing systems, for example
infusion pumps, X-ray equipment.

4.5 TRANSPORT:

Airplanes, Trains, Buses, Marine craft, Automobiles, Air traffic control systems,
Signaling systems, Radar systems, Traffic lights, Ticketing systems/machines, Car
parking and other meters.

4.6 COMMUNICATIONS:

Telephone exchanges, Cable systems, Telephone switches, Satellites, Data

switching equipment (X.25, SMDS, Frame relay).

4.7 BANKING, FINANCE AND COMMERCIAL:

Automated teller systems, Credit card systems, Point of sale systems including
scanner/cash systems.

4.8 TESTING AND DIAGNOSTIC SYSTEMS:

Energy metering, environmental monitoring equipment.

5. INTELLIGENT TRAFFIC LIGHT CONTROL USING EMBEDDED

SYSTEMS:

Growing number of road users and the limited resources provided by

current infrastructures lead to ever increasing traveling times. Traffic in a city is
very much affected by traffic light controllers. When waiting for a traffic light, the
driver looses time and the car uses fuel. To make traffic light controllers more

5
intelligent, we exploit the emergence of novel technologies such as
communication networks and sensor networks, as well as the use of more
sophisticated algorithms for setting traffic lights. The Intelligent Traffic Control
System is formed as a network of embedded systems. Intelligent traffic light
control does not only mean that traffic lights are set in order to minimize waiting
times of road users, but also that road users receive information about how to
drive through a city in order to minimize their waiting times. This means that we
are coping with a complex multi-agent system, where communication and
coordination play essential roles. The research has led to a novel system in which
traffic light controllers and the behavior of car drivers are optimized using
machine-learning methods.

The idea of setting a traffic light is as follows. Suppose there are a number
of cars with their destination address standing before a crossing. All vehicles
communicate to the traffic light with their specific place in the queue and their
destination address. Now the traffic light has to decide which option (i.e., which
lanes are to be put on green) is optimal to minimize the long-term average waiting
time until all vehicles have arrived at their destination address. The learning
traffic light controllers solve this problem by estimating how long it would take
for a car to arrive at its destination address (for which the vehicle may need to
pass many different traffic lights) when currently the light would be put on green,
and how long it would take if the light would be put on red. The difference
between the waiting time for red and the waiting time for green is the gain for the
car. Now the traffic light controllers set the lights in such a way to maximize the
average gain of all cars standing before the crossing. To estimate the waiting
times, we use 'reinforcement learning’ which keeps track of the waiting times of
individual cars and uses a smart way to compute the long term average waiting
times using dynamic programming algorithms. One nice feature is that the system
is very fair; it never lets one car wait for a very long time, since then its gain of

6
setting its own light to green becomes very large, and the optimal decision of the
traffic light will set his light to green. Furthermore, since we estimate waiting
times before traffic lights until the destination of the road user has been reached,
the road user can use this information to choose to which next traffic light to go,
thereby improving its driving behavior through a city. We solve the traffic light
control problem by using a distributed multi-agent system, where cooperation and
coordination are done by communication, learning, and voting mechanisms.

Fig 1-Simulator showing the infrastructure, road users, and plots of

average waiting times
A large number of fixed and learning traffic light controllers have already been
tested in the simulator and the resulting average waiting times of cars have been

7
 plotted and compared. The results indicate that the learning controllers can reduce
average waiting times with at least 70% in semi-busy traffic situations, and even
much more when high congestion of the traffic occurs.

7. REFERENCES:
1. http://www.google.com.
2. http://www.howstuffworks.com.
3. http://www.ercim.org/publication/ercim_news/enw53.
4. Embedded Systems in the Real World, Phillip Koopmans. Carnegie Mellon
University.
5. http://www.msnsearch.com