Download full-text PDF Join for free Login

Technical Report PDF Available

Project Report on the Prototype of

an Automated Self Driving Vehicle
January 2021
DOI:10.13140/RG.2.2.28281.08809
Affiliation: Bangladesh University of Engineering and
Technology

Authors:

Yasir Fatha Abed

University of Minnesota Twin Cities

H M Ashiqul M Islam
Bangladesh University of Engineering and …

Anowarul Azim
Bangladesh University of Engineering and …

Md. Abeed Hasan

Show all 5 authors

Abstract

In this project a simple self driving car is designed

and implemented. The concept of the project was
inspired by the recent surge in automated car
industry. The designed car was capable of detecting
the road signals and taking the right turn
accordingly. To implement the whole system, the
body of the car was connected to the analyzer
computer via Wi-Fi where the computer can analyze
the feed video frame by frame. In a real car the
analyzer computer can be simply mounted on
board. The whole system was capable of taking
right decision with excellent accuracy.

Discover the world's research

25+ million members
160+ million publication pages
2.3+ billion citations

Join for free

Advertisement

Chat w/ Online
Experts 24/7

A Technician Will Answer Your

Questions in Minutes. Chat Now.

JustAnswer

Public Full-text 1

Content uploaded by Yasir Fatha Abed

Author content
Content may be subject to copyright.

Bangladesh University of Engineering and

Technology

Course : EEE 318 – Control Systems Laboratory

Project Report on Automated Self Driving Vehicle

Submitted to Submitted By

Dr. Pran Kanai Saha Name Student ID

Professor, Department of Electrical Abeed Hasan 1506022
and Electronic Engineering Yasir Fatha Abed 1506023
Ashiqul Islam 1506024
Tonushree Dutta 1506025
Anowarul Azim 1506026
Ajanta Saha
Lecturer, Department of Electrical
and Electronic Engineering

Acknowledgement
This project was done for the coursework of EEE 318 conducted
by the Department of Electrical and Electronic Engineering,
Bangladesh University of Engineering & Technology. We would
like to express our gratitude to our honorable teachers, Dr Pran
Kanai Saha (Professor, Dept. of Electrical and Electronic
Engineering, BUET) & Ajanta Saha (Lecturer, Dept. of Electrical
and Electronic Engineering, BUET) for their advices and
valuable comments regarding our project, which led us to the
completion of the project. We also want to thank our
classmates and seniors who helped us and encouraged us
during the project.

Abstract
In this project a simple self driving car is designed and
implemented. The concept of the project was inspired by the
recent surge in automated car industry. The designed car was
capable of detecting the road signals and taking the right turn
accordingly. To implement the whole system, the body of the
car was connected to the analyzer computer via wifi where the
computer can analyze the feed video frame by frame. In a real
car the analyzer computer can be simply mounted on board.
The whole system was capable of taking right decision with
excellent accuracy.

Index

Topic Page
Acknowledgement 2
Abstract 3
Chapter 1: Introduction 5
1.1: Introduction to Self Driving Car 5
1.2: Problem Statement 5
Chapter 2: Necessary Components 6
2.1: Arduino Uno 6
2.2: Esp 8266 (NodeMCU V0.9) 6
2.3: Motor Driver L298 7
2.4: DC motor 7
2.5: Camera 8
2.6: Traffic Light 8
2.7: Chassis 8
Chapter 3: Process Implementation 9
3.1: Flowchart of Implementation 9
3.1.1: Getting Data from Camera: 10
3.1.2: Sending data to image processor
via TCP server. 10
3.1.3: Recognizing Feed Data from
Database by Image Processing 10
3.1.4: Sending Instructions to the
Prototype. 11

Chapter 4: Final assembly of the

Prototype 12
Chapter 5: Area of Improvements 12
Conclusion 13

Chapter 1: Introduction
1.1 Introduction to Self-Driving car:

A self-driving car can analyze surrounding without any human interactions and
take decisions accordingly without any human interactions. A number of sensors
are combined and are used to identify the pathway and road signal from the
surroundings. An autonomous car is has reduced costs due to less wastage of
fuel, increased safety, increased mobility, increased customer satisfaction and
that’s why it has more advantage than traditional cars. The biggest benefit of
using a self-driving car is significantly fewer traffic accidents. More than 90% of all
accidents are caused by some degree of human error, including distraction,
impaired driving, or poor decision making. With self-driving cars making decisions
and communicating with one another, the number of accidents should reduce.

1.2 Problem Statement:

In this project a low cost prototype of self driving car is proposed and
implemented. The car will have a camera on board and with the feed video the
analyzer computer can detect traffic signal (turn right , turn left , stop) and give
correct decisions to the car.

Chapter 2: Necessary Components

2.1 Arduino Uno:

The Arduino Uno is an open-source microcontroller board based on the

Microchip ATmega328P microcontroller and developed by Arduino.cc.
The board is equipped with sets of digital and analog input/output pins
that may be interfaced to various expansion boards and other circuits.

Arduino Uno Board

2.2 ESP 8266 (Nodemcu V0.9)

The ESP8266 is a low-cost Wi-Fi microchip, with a full TCP/IP stack and
microcontroller capability, produced by Espressif Systems in Shanghai,
China. The chip first came to the attention of Western makers in August
2014 with the ESP-01 module, made by a third-party manufacturer Ai-
Thinker.

Nodemcu Board V0.9

6

2.3 Motor Driver L298

L298 Motor Driver Module is a high power motor driver

module for driving DC and Stepper Motors. This module
consists of an L298 motor driver IC and a 78M05 5V
regulator. L298 Module can control up to 4 DC motors, or 2 DC
motors with directional and speed control.

L298 Motor Driver

2.4 DC Motor

A DC motor is any of a class of rotary electrical motors that

converts direct current electrical energy into mechanical
energy. The most common types rely on the forces produced
by magnetic fields. Nearly all types of DC motors have some
internal mechanism, either electromechanical or electronic,
to periodically change the direction of current in part of the
motor. Two 5V DC motors are used in this project.

5V DC Motor
7

2.5 Camera

An onboard camera was used to feed live video of the pathway to

the analyzer pc via wifi

2.6 Traffic Signs

Three different traffic signs were used as sample traffic signals.

turn right stop turn left

2.7 Chassis for any robot (LFR/Obstacle Avoider)

A hard chassis for any line follower robot or obstacle avoider

robot can be used for the prototype.

Chapter 3: Process of Implementation

3.1 Flowchart of Implementation

Getting Data from camera

Sending data to image

processor via TCP server

Recognizing Data from

database by image
processing

Sending proper instruction

to prototype vehicle via
TCP server

Executing the instruction

Received via
TCP Server

3.1.1 Getting Data from Camera:

For sending feed data a mobile camera and an app ( Commercially

known as DroidCam ) which sends feed data to the desired TCP
server is used.

3.1.2 Sending data to image processor via TCP server

A wifi module (esp 8266 – nodemcu v0.9) for creating a tcp server,
which worked as a communication channel between image
processor and the prototype car.

3.1.3 Recognizing Feed Data from Database by Image

Processing:

Traffic Sign Detection: To determine the traffic sign from the real
time video, the feed video is divided into some frames differing 30
milisecond. As the number of sign to be detected is small enough
(only 3 - stop , turn left and turn right) , a somewhat simpler
approach – correlation is taken. This task can be divided into
several subtasks as follows.

1) Acquiring Training Image: Around 10 image of each sign,

extracted the sub rectangle containing the sign from the image,
and saved the image matrix as matlab file. Each image was
resized as 600x600 pixels.

2) Dividing the Real Time Video: An image after every 30

milisecond apart is taken and worked with the frame to detect
the traffic sign.

3) Detecting Circular Objects from an Image: The circle Hough

Transform is used to detect circles in the frame. The circle Hough
Transform (CHT) is a basic technique used in Digital Image
Processing, for detecting circular objects in a digital image. The

10

circle Hough Transform (CHT) is a feature extraction

technique for detecting circles. It is a specialization of
Hough Transform. The purpose of the technique is to find
circles in imperfect image inputs. The circle candidates are
produced by “voting” in the Hough parameter space and
then select the local maxima in a so-called accumulator
matrix. This technique is implemented in matlab function
imfindcircles that we used.

4) Correlation: Then we correlate the extracted circle with each

sign. Thresholds were chosen to detect each type of sign
through trial and error.

The matlab codes for the project can be found here.

3.1.4 Sending Instructions to the Prototype

The action for the recognized signal is then sent to the

prototype via tcp server. The Arduino uno was used to drive
the dc motors according to the actions.

11

Chapter 4: Final Assembly of the

Prototype
The prototype was assembled in simple LFR making
procedure and the following car was made.

The prototype car in the test field

Chapter 5: Area of Improvements

The prototype was assembled in simple LFR making
procedure and the following car was made. A good
number of improvements can be made to the prototype
according the field of use. Instead of a separate
computer, on board raspberry pi can be used for image
processing. There is a small number of instructions for
the prototype. The instructions can be increased and
machine learning algorithm can be implemented for
further self sustaining improvements.

12

Conclusion
In this project a simple prototype of a self driving car is
demonstrated. The prototype car can recognize three
separate signals – turn left, turn right and stop with great
accuracy and take decision accordingly. The prototype
can be further improved by including more signals and
using ML approach.

13

Citations (0) References (0)

ResearchGate has not been able to resolve any

citations for this publication.

Recommended publications Discover more

Conference Paper

Enhancement in Optical and Electrical

Properties of Si and GaAs Solar Cells Using
Metal-oxide Anti-r...
June 2021

Tonushree Dutta · Anowarul Azim · Md.

Tawsif Rahman Chowdhury

Read more

Article Full-text available

Automatisiertes Fahren
July 2018 · TATuP Zeitschrift für
Technikfolgenabschätzung in Theorie und Praxis

Torsten Fleischer · Jens Schippl

Dieses TATuP-Thema präsentiert erste Perspektiven,

Indiziensammlungen und Diskussionsbeiträge zum
Themenfeld des automatisierten Fahrens, das seit
einigen Jahren ein wichtiger Gegenstand der
Mobilitätsforschung geworden ist. Auch wenn in der
Öffentlichkeit weiterhin verbreitet Skepsis hinsichtlich
der technischen und organisatorischen Reife herrscht,
dominiert in der Fachwelt die Erwartung, dass ...
[Show full abstract]

View full-text

Conference Paper

Distributed EDCA bursting: improving cluster-

based communication in IVC
July 2016

Michele Segata · Davide Goss · Renato

A. Lo Cigno

Cluster-based communication is a staple topic in

vehicular networks. Clustering communication nodes
promise to reduce channel contention, enable building
backbones and might improve spatial reuse. In this
paper we propose a seemingly simple, yet unexplored
idea: extending 802.11 frame bursting MAC access to
multiple stations aggregated into a cluster. The focus
of the paper is thus not building a ... [Show full
abstract]

Read more

Article

Technologies for highly automated driving on

highways
June 2012 · ATZ worldwide

Nico Kaempchen · Michael Aeberhard ·

Michael Ardelt · Sebastian Rauch

Read more

Company

About us

News

Careers

Support

Help Center

Business solutions

Advertising

Recruiting

© 2008-2024 ResearchGate GmbH. All rights

reserved. Advertisement

Terms · Privacy · Copyright · Imprint · Consent

preferences
Are you recruiting experts in
physics?