ISSN (Online) 2394-6849

International Journal of Engineering Research in Electronics and Communication

Engineering (IJERECE)
Vol 5, Issue 4, April 2018

Prototype of Autonomous Car Using Raspberry Pi

[1]
Tiple Anjali Hemant, [2] Tiple Hemant P, [3] Gurav Sagar Hanumant
[1][2][3]
Department of ENTC, S.S.P.M’s COE Kankavli, India.

Abstract: - In the modern era, the vehicles are focused to be automated to give human driver relaxed driving. In the field of
automobile various aspect has been considered which makes vehicle automated. In this paper, considering the different features
and the cost, on a small scale a three-wheel vehicular robotic prototype has been designed that will follow the lane and avoid
obstacles. Autonomous cars are a developing technology which may prove to be the next big evolution in personal transportation.
This report begins by describing the landscape and key players in the self-driving car market. Current capabilities, as well as
limitation and opportunities of key enabling technologies, are reviewed, along with a discussion on the impact of such advances on
society and the environment. Most impact, including reduced traffic and parking congestion, independent mobility for poor
people, increased safety, and energy conservation and pollution reductions will only be significant when autonomous vehicles
become common and affordable to common people. Raspberry Pi is the central processor of our Autonomous car. Various images
are captured by the camera module, on this images various Image processing techniques are used to achieve Artificial Intelligence.

Index Terms— Artificial Intelligence, Camera Module, Image Processing, Raspberry Pi.

II. METHODOLOGY
I. INTRODUCTION
A. Block diagram
Automated vehicles are technological development in the Here is simple block diagram of prototype of autonomous
field of automobiles. Now a days, due to inconvenience car which describe the actual structure of project and
of public transportation peoples are using their private command flow between the various sub-systems. As
vehicles. Due to such a large number of vehicles, the shown in figure, there are two sub-system. That are
traffic problem has been occurred. To resolve this traffic Image processing sub-system and obstacle detection sub-
problem, traffic rules are designed. But disobey of such system. Camera attached to image processing sub-system
traffic rules causes accidents. And maximum accidents which capture the image and provide system. System
will be occurred due to human error. To reduce these extracts the data from the image and generates the
accidents and to improve safety transportation we require command about turn. Mainly image processing is used
Autonomous Vehicle. Autonomous drive technology is here to detect the road lane. Generated commands are
one of the most important innovation in the automative forward to obstacle detection subsystem. Obstacle
industry. If we will able to implement this technology detection sub-system is detect the obstacle in front of car
and have total control over it, then it can result in large and also calculate the distance between the obstacle and
benefits for both individuals & society. Members of the car. And if sufficient distance is available to move car
IEEE predicts that in 2040, Autonomous cars will consist forward the command from Raspberry pi is forwarded to
of up to 75% of the cars on the roads. Tens of millions of motor driver else this command are rejected.
people have lost their lives or have become disabled
worldwide in the last 10 years as a consequence of traffic
accidents, the purpose of this project is to create a safe
self-driving car that could help millions of people each
year. Almost all the traffic accidents are caused by
human mistakes. Unfortunately, according to statistic, in
the next 10 years the number of lives lost each year will
likely be doubled. To avoid such problems we are
moving towards Autonomous Car.

39
 ISSN (Online) 2394-6849

International Journal of Engineering Research in Electronics and Communication

Engineering (IJERECE)
Vol 5, Issue 4, April 2018

B. Component Description 2. Software Description

1. Hardware Description Raspbian OS:-
Raspberry pi:- Of all the operating systems Arch, Risc OS, Plan 9 or
Raspberry pi small size computer which having its Raspbian available for Raspberry Pi, Raspbian comes out
Raspbian OS. It’s able to do multiple function on top as being the most user-friendly, best-looking, has
simultaneously. It has 1.2 Ghz quad core ARM cortex A- the best range of default software’s and optimized for the
53 and RAM 1 GB.[1] It required power upto to 5V, 2.5 Raspberry Pi hardware [8]. Raspbian is a free operating
amp which is negligible with respect to PC.[1] system based on Debian (LINUX), which is available for
free from the Raspberry Pi website [8].
Python:-
Python is a widely used general-purpose, high-level
programming language [7,9, 10]. Its syntax allows the
programmers to express concepts in fewer lines of code
when compared with other languages like C, C++or java
[9, 10].
GPIO Python Library:-
The RPi.GPIO Python library allows you to easily
configure and read-write the input/output pins on the Pi’s
GPIO header within a Python script [7, 9]. This package
is not shipped along with Raspbian.
OPEN CV:-
It (Open Source Computer Vision) is a library of
Pi-camera:- programming functions mainly aimed at real-time
Camera used in this project having 8MP resolution with computer vision. It has over 2500optimized algorithms,
fixed lens. It is capable to capture picture 3280x2464 including both a set of classical algorithms and the state
pixel size. [2] of the art algorithms in Computer Vision, which can be
used for image processing, detection and face
recognition, object identification, classification actions,
traces, and other functions [10]. This library allows these
features be implemented on computers with relative ease,
provide a simple computer vision infrastructure to
prototype quickly sophisticated applications [9, 10]. The
library is used extensively by companies like Google,
Yahoo, Microsoft, Intel, IBM, Sony, Honda, Toyota, and
startups area as Applied Minds, Video Surf . It is also
used by many research groups and government [10]. It is
based on C++ but wrappers are available in python as
well. In our project is used to detect the roads and guide
the car on unknown roads [10].
Ultrasonic Module:-
To measure distance purpose ultrasonic module is Arduino Language:-
commonly used because it not affected by environmental The Arduino IDE supports the languages C and C++
distraction.[3] The module used here having working using special rules of code structuring. The Arduino IDE
frequency of 40 Hz and capable to measure from 10 cm supplies a software library from the Wiring project,
to 400 cm.[4] This module have measuring angle of 15 which provides many common input and output
degree.[4] procedures.
Ardiuno board:-
Ardiuno is a single board microcontroller kit for building C. Flow Chart
digital devices and interactive objects in the physical and 1. Image processing sub-system algorithm
digital world. It allow to program in C language. It has
internal analog to digital convertor.

40
 ISSN (Online) 2394-6849

International Journal of Engineering Research in Electronics and Communication

Engineering (IJERECE)
Vol 5, Issue 4, April 2018
dark pixel are calculated respectively. This number
decides the command for the car.
After the image analysis the image, raspberry pi generate
the command as described above in block diagram. These
generated commands are forwarded to arduino board
through GPIO pin. For forwarding this command
following table is referred.
COMMAND GPIO pin 1 GPIO pin 2

STOP LOW LOW

FORWARD HIGH HIGH

LEFT HIGH LOW

RIGHT LOW HIGH

2. Obstacle detection sub-system algorithm

Here in this algorithm Lane detection is done in region of

interest only as described below. Region given in red
mark is our region of interest and the columns are helpful
to decide the position of lane and also decision of turn is
also carried out on the basis of this. Consider the given
box is the picture capture by the camera.

III. RESULT

A. Image processing sub-system result

It is important to detect the LANE from the image of
road. And check their position in the form of pixel co-
ordinates for the decision of turn. Following picture
Numbers of white pixel in each block with respect to shows the image captured by the camera.

41
 ISSN (Online) 2394-6849

International Journal of Engineering Research in Electronics and Communication

Engineering (IJERECE)
Vol 5, Issue 4, April 2018

To perform the LANE detection operation it is important

to convert image into gray scale as follow. After
detection of lane, image look like below picture. That is
lane in image marked is total white due to thresholding of
image. The white pixels from the region of interest are
considered only. Count of this image will give the
position of lane on the road. The region of interest is slide
vertically with respect to speed of car.
Result if distance greater than 10 cm
B. Obstacle detection sub-system result
The distance between two objects is provide by
IV. CONCLUSION AND FUTURE WORK
Ultrasonic module. Arduino’s serial communication
gives us result about the distance and also gives stop
A. Conclusion
command to the vehicle as shown in figure below. Here
Driverless car revolution which aims at the development
are the screenshots of serial mode of arduino and distance
of autonomous vehicles for easy transportation without a
display in cm. There are two cases.
driver. For the economy, society and individual business
this autonomous technology has brought many broad
Result if distance less that 10 cm
implications. In this paper, a method is determined for
marked road edges are explained in detail relying upon
OpenCV. Cars that drive themselves will improve road
safety, fuel efficiency, increase productivity and
accessibility; the driverless car technology helps to
minimize loss of control by improving vehicle’s stability
as they are designed to minimize accidents by addressing
one of the main causes of collisions: Driving error,
distraction and drowsiness. The algorithm mention in this
paper has been successfully implemented in prototype of
Autonomous car.

B. Future work
The work could be enhanced by improving the algorithm
by adding advanced machine learning to it. Using
advanced algorithm we can improve Image processing
algorithms. Multi layered processors can be used for fast
processing. The present obstacle detection algorithm just
detects the obstacle and stops, but in future it can be
improved by the avoiding the obstacle, and go through
another way using advanced obstacle detection
algorithm.

42
 ISSN (Online) 2394-6849

International Journal of Engineering Research in Electronics and Communication

Engineering (IJERECE)
Vol 5, Issue 4, April 2018

REFERENCES

[1] Raspberry pi 3 b model data sheet [Online],

available at http://docs-
europe.electrocomponents.com/webdocs/14ba/0900766b
814ba5fd.pdf

[2] Pi camera module datasheet [Online], available

at http://docs-
europe.electrocomponents.com/webdocs/127d/0900766b
8127db0a.pdf

[3] Johann Borenstein & Yoram Koren, Obstacle

Avoidance with Ultrasonic Sensors, IEEE JOURNAL OF
ROBOTICS AND AUTOMATION, VOL. 4, NO. 2,
APRIL I988, pp. 213-218

[4] Ultrasonic module Hc- sr04 model datasheet

[Online], available at
http://www.micropik.com/PDF/HCSR04.pdf

[5] Li, M., Zhao, C., Hou, Y. & Ren, M. , A New

Lane Line Segmentation and Detection Method based on
Inverse Perspective Mapping, International Journal of
Digital Content Technology and its Applications.
Volume 5, Number 4, April 2011, pp. 230-236

[6] Design and Implementation of Autonomous Car

using Raspberry Pi International Journal of Computer
Applications (0975 – 8887) Volume 113 – No. 9, March
2015

[7] Stewart Watkiss, Design and build a Raspberry

Pi robot [Online], available at:
http://www.penguintutor.com/electronics/robot/rubyrobot
-detailedguide.pdf

[8] David Hayward, Raspberry Pi operating

systems: 5 reviewed and rated [Online], available at:
http://www.in.techradar.com/news/software/

[9] Matt Richardson, Shawn Wallace, Getting

Started with Raspberry Pi, 2nd Edition, Published by
Maker Media, Inc., USA, 2014. Book ISBN: 978-1-457-
18612-7

[10] Gary Bradski, Adrian Kaehler, Learning

OpenCV: Computer Vision with the OpenCV Library,
"O'Reilly Media, Inc.". Copyright.September 2008, 1st
Edition, Book ISBN: 978-0-596-51613-0

43