
AUTOMATED CAR BRAKING SYSTEM USING FUZZY LOGIC CONTROLLER
ABSTRACT
This paper deals with a Fuzzy Logic Controller (FLC) for an automated car
braking system. The response of the system will be simulated by using Fuzzy Logic
Toolbox in MATLAB and PID controller. The purpose of this controller is to brake a
car when the car approaches for an obstacle at a specific range. For this, the Fuzzy
Logic Controller is design using the Fuzzy Logic Toolbox in MATLAB. The system
uses four rules and three membership function. The two parameters such as distance
and speed will be observed for both controllers and the ability to attenuate
disturbance will be simulated. Output of the controller will determine the force of the
car brake. Base on the simulation, it can be concluded that the response of Fuzzy
Logic Controller is better than PID. However, PID controller can be used to
constitute a reference for the performance of the fuzzy logic controller.
INTRODUCTION
1.1 Fuzzy Logic Controller (FLC)
Fuzzy logic was formulated by Lotfi Zadeh of the University of California at
Berkeley in the mid1960s, based on earlier work in the area of fuzzy set theory.
Zadeh also formulated the notion of fuzzy control that allows a small set of 'intuitive
rules' to be used in order to control the operation of electronic devices. In the 1980s
fuzzy control became a huge industry in Japan and other countries where it was
integrated into home appliances such as vacuum cleaners, microwave ovens and
video cameras. Such appliances could adapt automatically to different conditions; for
instance, a vacuum cleaner would apply more suction to an especially dirty area. One
of the benefits of fuzzy control is that it can be easily implemented on a standard
computer.
Fuzzy controllers appear in consumer products such as washing machines,
video cameras, cars. As for in industry, for controlling cement kilns, underground
trains, and robots. A fuzzy controller is an automatic controller, a selfacting or selfregulating
mechanism that controls an object in accordance with a desired behavior.
The object can be, for instance, a robot set to follow a certain path. A fuzzy
controller acts or regulates by means of rules in a more or less natural language,
based on the distinguishing feature: fuzzy logic. The rules are invented by plant
operators or design engineers, and fuzzy control is thus a branch of intelligent
control.
2
1.2 Proportional Integral Derivative (PID) Controller
A proportionalintegralderivative controller (PID controller) is a generic
control loop feedback mechanism widely used in industrial control systems. A PID
controller attempts to correct the error between a measured process variable and a
desired set point by calculating and then outputting a corrective action that can adjust
the process accordingly.
The PID controller calculation (algorithm) involves three separate
parameters; the Proportional, the Integral and Derivative values. The Proportional
value determines the reaction to the current error, the Integral determines the reaction
based on the sum of recent errors and the Derivative determines the reaction to the
rate at which the error has been changing. The weighted sum of these three actions is
used to adjust the process via a control element such as the position of a control
valve or the power supply of a heating element.
1.3 Car Braking System
Braking system is the most important system in a car. If the brakes fail, the
result can be disastrous. The brakes are in essence energy conversion devices, which
convert the kinetic energy of the vehicle into thermal energy.
In this project, a car brake system will be controlled by the Fuzzy Logic
Controller (FLC) and the Proportional Integral Derivative (PID) controller. The
purpose of the automated car braking system is to develop an automated control
system that would maintain a safe driving distance from obstacles while in traffic.
The system will successfully detect an obstacle ahead at a specific range and create a
way for the system to avoid collision by braking the car. By that, it will results in a
more enjoyable and less stressful drive. The system will be developed in fuzzy logic
toolbox available in MATLAB and will be simulated to see the performance of the
car braking system.
3
1.4 Problem Statement
The increasing rate of road accident had been increasing nowadays. At
present, there are four deaths per 10,000 vehicles. In many such cases, the cause of
the accident is driver distraction and failure to react in time. Generally, a car brake
system operated manually as the driver push the brake pedal. Therefore, to overcome
this problem, an automated car braking system will be implemented to avoid such
accident.
1.5 Objectives
The objectives of this project are:
I. To develop a Fuzzy Logic Controller and Proportional Integral
Derivative Controller using MATLAB for an automated vehicle due to
an obstacle.
II. To evaluate and analyze the performance of the systems.
1.6 Scope of Project
This project is to design a Fuzzy Logic Controller and Proportional Integral
Derivative Controller that can be use to control a car brake automatically. Thus, the
scopes that need to be considered in this project are:
I. Car brake
The car brake will be controlled by the fuzzy logic controller from the
MATLAB toolbox and PID controller designed according to the range
detected to the obstacle ahead by reducing the speed from the
specified speed desired.
4
II. Range
The range targeted for the obstacle to be detected is 25m from the car.
Therefore, the car will be brake and stop before it hit the obstacle.
III. Obstacle
Obstacles in this project refer to any objects including cars, human or
animal those were ahead the car. The obstacles will give input to the
controller to brake the car.
1.7 Literature Review
1.7.1 Car Braking Issues
Traffic congestion is a worldwide problem. This problem is mainly due to
human driving which involves reaction times, delays, and judgement errors that may
affect traffic flow and cause accidents. [1] In many such cases, the cause of the
accident is driver distraction and failure to react in time. Advanced system of
auxiliary functions has been develop to help avoid such accident and minimize the
effects of collision should one occur. This is done by reducing the total stopping
distance. [2] By that means, the car brake itself should have a good software system
to assist a driver along the road.
Electronic brake control system has been making the car safer for the past 25
years. In recent years, braking developments have led to significantly greater driving
safety. [3] For the past few years, there are many car brake development that uses
the involvement of the electronic roles such as the Intelligent Cruise Control (ICC),
Antilock Braking Systems (ABS), Traction Control System (TCS) and the
Sensotronic Brake Control (SBC).
Many studies in this field depend upon a precise mathematical model of the
vehicle. In fact, behaviors of the drivers are mostly based on the experience, not the
5
exact mathematic computation. The model of vehicle is highly nonlinear function; it
is difficult to find the precise model. Therefore, fuzzy logic systems have been
designed by many researchers for automated driving controller since fuzzy system
emulates the performance of a skilled human operator in the linguistic tulles that do
not need use a mathematic model. [1]
Ordinary cruise control systems for passenger cars are becoming less and
less meaningful because of the increasing traffic density rarely make it possible to
drive at a preselected speed. However, in order to achieve high customer acceptance
an intelligent cruise control system has to perform similarly to an experienced
human driver. Therefore, it is necessary to adjust the following distance and the
control dynamics according to the individual driverâ€™s needs. Applying fuzzy logic to
intelligent cruise control seems to be an appropriate way to achieve this human
behavior, because driverâ€™s experience can be transformed easily into rules. [4]
1.7.2 Fuzzy Logic Toolbox
Fuzzy logic imitates the logic of human thought, which is much less rigid
than the calculations computer generally perform. [5] Intelligent control strategies
mostly involve a large number of inputs. Most of the inputs are relevant for some
specific condition. Using fuzzy logic, this input is only considered in the relevant
rule. This keep the complex system transparent.[6] Whereby using fuzzy logic, the
concept will be much easily to understand as it was based on natural language.
The objective of using fuzzy logic has been to make the computer think like
people. Fuzzy logic can deal with the vagueness intrinsic to human thinking and
natural language and recognize its nature is different from randomness. Using fuzzy
logic algorithm could enable machines to understand and respond to vague human
concept such as hot, cold, large, small, etc. It also could provide a relative simple
approach to reach definite conclusion from imprecise information. [7]
6
Fuzzy logic is very adequate to built qualitative models of many kind of
system without an extensive knowledge of their mathematical models. The use of
fuzzy controllers allows achieving a human like vehicle operation. [8]
There are two general types of fuzzy expert system:
I. Fuzzy control
II. Fuzzy reasoning
Although both make use of fuzzy sets, they differ qualitatively in
methodology. [9] Fuzzy control comprises the steps of sense, preprocess, fuzzify,
evaluate, activate, aggregate, defuzzify and act. However, difficulty occurs with the
using of fuzzy logic system. Usually it is difficult to determine the membership
function and fuzzy logic rules. Many cycles of trailanderror are required to achieve
the desired performance. [1]
The fuzzy logic toolbox is a collection of function built on the MATLAB
numeric computing environment. It provides tools for us to create and edit fuzzy
interference system with the framework of MATLAB or integrate the fuzzy system
into simulation with simulink. The fuzzy logic toolbox for use with MATLAB is a
tool for solving problems with fuzzy logic. It is a fascinating area of research because
it does a good job of trading off between significant and precision. [10]
Although it is possible to use Fuzzy Logic Toolbox by working strictly from
the command line, in general it is much easier to build a system graphically. [10]
There are five primary GUI tools for building, editing, and observing fuzzy inference
systems in Fuzzy Logic Toolbox:
I. Fuzzy Inference System (FIS) Editor
II. Membership Function Editor
III. Rule Editor
IV. Rule Viewer
V. Surface Viewer 
