IOP Conference Series: Materials Science and Engineering

PAPER • OPEN ACCESS

Design of Autonomous Vehicle Control using IoT

To cite this article: A Manjunathan et al 2021 IOP Conf. Ser.: Mater. Sci. Eng. 1055 012008

View the article online for updates and enhancements.

This content was downloaded from IP address 178.173.224.86 on 19/02/2021 at 12:49

IVC RAISE 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 1055 (2021) 012008 doi:10.1088/1757-899X/1055/1/012008

Design of Autonomous Vehicle Control using IoT

A Manjunathan1*, A Suresh Kumar2 , S Udhayanan3, C Thirumarai Selvi4 and Albert

Alexander Stonier5

1
Department of Electronics and Communication Engineering, K.Ramakrishnan
College of technology, Trichy, Tamilnadu, India
2
Kongunadu College of Engineering and Technology, Trichy, Tamilnadu, India
3
Sri Bharathi Engineering College for Women, Pudukottai, Tamilnadu, India
4
Sri Krishna College of Engineering and Technology, Coimbatore, Tamilnadu, India
5
Department of Electrical and Electronics Engineering, Kongu Engineering College,
Perundurai 638 060, Tamilnadu, India

*E mail ID: [email protected]

Abstract: A Prototype autonomous vehicle system is explained in this paper. A car has
been driven using internet with more secured. There are three types of detection like
Traffic light detection, Obstacle detection and Lane detection. It is most important
features of this project. The main purpose of this concept is to reduce accident and
human life. The important component are used a Raspberry Pi, a Picamera, a Web
interface and Internet modem. It is based on Computer vision algorithm. Raspberry Pi
is most important one to construct. The video has been pick and passed through
internet. It has low cost and very efficient project.
Keywords-Raspberry Pi, Camera, Internet of Things, Open CV, Computer Vision, IR
Sensor.

1. Introduction
With growth of technology, human life likes automation. Automated car is latest trend in our
environment. It was recognized by people. It has most secured and drive safe during journey. Now
days, road accidents are increased by human. The drivers can distracted and drowsy during driving the
car. Drunken drive is the most important reason for road accident. The car was driven by using
computer vision algorithm [1-3]. It uses sensor to detect the obstacle and reduce the accident. The
project is based on Internet of Things.
In 1920, vehicle automation research has conducted and the first trial was conducted in 1950. The first
autonomous car has been invented in Carnegie Mellon University. After the invention, many company
worked on implementing autonomous vehicle [4-9]. Cities like Belgium, France, Italy and UK are

Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution
of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
Published under licence by IOP Publishing Ltd 1
IVC RAISE 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 1055 (2021) 012008 doi:10.1088/1757-899X/1055/1/012008

interested in driverless car. The countries like Germany, Netherland, Spain are testing robotic car in
traffic.
The Google driving car algorithm was developed by Stanford University Professor [10-12].
Automation car of Google was most popular. Design of Google car was navigation purpose. There are
different types of sensor are used to design the automation car. In 2020, the driverless car will be
introduced [13-15]. It is fully operated through internet. There is no human needed to operate the car.
It can drive itself. The above details are only developed in real time project.
But our project is fully based on prototype method. Prototype is the step by step process and finally
reaches the real time work shown in Figure 1. It is one of the stages of automated car. This vehicle has
six levels. The level 0 is not automation. The level 5 is fully automation and level 3 is fully conditional
automation. Based on this level, the car can be driven safely. This method will become very popular
within few years. It is very safe for environment since it reduces the rate of accidents. The Google car
has been followed the rules and regulation of the land detection. The camera detects while driving the
autonomous car.
Using image processing detection has been avoided. In traffic light detection, image processing is
mainly used. Using sensor to identify the color and compare the color on the image processing data
base and finally detect the traffic light. In this prototype method the car has completed these three
detection after the car has been stopped automatically.

Figure 1. Automatic Car model

2. Existing method
Taking into account, the automation in vehicles one must be always aware of the various kinds of
processes in it. The main idea is to collect the data from the real world and inform the status of the
vehicle and path of motion in personalized computers or smart phones. The invention of Engine
Control Unit (ECU) to serve many parameters of car and have a control over them. They also improve
the engine efficiency and reduction of fuel usage and an overall reduction in expenses incurred.
The features enable the user to take decisions regarding the data captured using different sensor
devices. Automation on home and as well as, vehicle automation pave ways to an integrated cloud
controlled environment.

2
IVC RAISE 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 1055 (2021) 012008 doi:10.1088/1757-899X/1055/1/012008

Figure 2: Process steps in Existing method

The existing IOT based vehicle automation systems are used mainly to have access of different
parameters associated with the vehicle during loco-motion shown in Figure 2. A variety of parameters
such as speed, temperature, humidity, distance and car locking are generally monitored.
3. Proposed method


Figure 3 Block diagram of proposed model

The proposed method indicates the use of vehicle autonomy and creating a computerized path
detection which requires an active internet connection. By using a web browser the car is controlled.
The system shown in Figure 3 makes use of raspberry pi, a camera module, a motor and a driver
circuit. The raspberry pi is used in streaming the video in the internet. It is a single board processing
unit which has a very powerful processing unit with serial camera interface. The camera is generally
used with this system to comparatively record the live motion of the vehicle along its route.

3
IVC RAISE 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 1055 (2021) 012008 doi:10.1088/1757-899X/1055/1/012008

A powerful web server application like apache is generally installed on the raspberry pi to various
web page by using scripting language. An additional sensor is included in the system which is mostly
of ultrasonic or infrared sensor as the prototype is featured to work on low range on work. The
wireless sensor acquires the obstruction that is prevailing along the path of movement of the vehicle
and sends the information to the raspberry module. Based upon the information received by the
raspberry pi it takes the corresponding action and turns the vehicle in prescribed direction. A Dc motor
of 100RPM (Revolutions per minute) is usually used to have proper control over the wheels.


Figure 4: Raspberry Pi module
Latest model of the third generation Raspberry Pi is shown in Figure 4. Raspberry Pi is a single board
to perform many applications. Using this module we can transfer the digital parameters to cloud
storage through internet. The saved data so obtain find a use for monitoring purpose and analyzing the
information.

Figure 5: Automated car

4.Conclusion
In the rapid pace of urban development ,the need for drivers is a challenging task and so, In the
upcoming years, the autonomous driverless car shown in Figure 5 are set to be become a rapid
advancement in the field of automobile engineering. The presence of internet controlled automobiles
in the urban world ensures faster compatibility and better user connectivity. However, the security and
maintenance of inter computer communication is always a surmountable risk.
References
[1] Levinson J, Askeland J, Becker J, Dolson J, Held D, Kammel S, Kolter J.Z, Langer.D, Pink.O,
Pratt et al V., 2011 Towards fully autonomous driving: Systems and algorithms Intelligent
Vehicles Symposium (IV) IEEE, pp. 163-168.
[2] Gurjashan Singh Pannu,Thapar University, Patiala Mohammad Dawud Ansari Jamia Millia
Islamia, New Delhi, Pritha Gupta, Netaji Subhas Institute of Technology, New Delhi March
2015 Design and Implementation of Autonomous Car using Raspberry Pi International
Journal of Computer Applications (0975-8887) Volume 113 – No. 9

4
IVC RAISE 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 1055 (2021) 012008 doi:10.1088/1757-899X/1055/1/012008

[3] Hordur K, Heidarsson and Gaurav S, Skhatme 2011 Obstacle Detection and Avoidance for an
Autonomous Surface Vehicle using a Profiling Sonar IEEE May 9-13.
[4] Bhuvaneshwari C, Manjunathan A 2019 Advanced gesture recognition system using long-term
recurrent convolution network Proc. ICONEEEA, pp. 1-8.
[5] Johann Bornstein& Yoram Koren, 1988, “Obstacle Avoidance with Ultrasonic Sensors”, IEEE
Journal on Robotics and Automation, vol. 4, no. 2, pp. 213- 218.
[6] Manjunathan A, Bhuvaneshwari C 2020 Designing of smart shoe Materials Today: Proceedings
21, 500-503.
[7] Yue Wanga, Eam Khwanga Teoha & Dinggang Shenb 2004 Lane detection and tracking using B-
Snake Image and Vision Computing 22.
[8] Joel C. McCall & Mohan M.Trivedi 2006 Video-Based Lane Estimation and Tracking for Driver
Assistance: Survey, System, and Evaluation, IEEE Transactions on Intelligent Transportation
Systems vol. 7, no. 1, pp.20-37.
[9] Bruce Moulton, Gauri Pradhan, Zenon Chaczko Voice Operated Guidance Systems for Vision
Impaired People: Investigating a User-Centered Open Source Model”.
[10] Clarus Concept of Operations 2005 Publication No” FHWA-JPO-05-072, Federal Highway
Administration (FHWA).
[11] Martin P, Rouchon P, and Rudolph J 2004 Invariant tracking ESAIM: Control, Optimisation and
Calculus of Variations, vol. 10, no. 1, pp. 1–13.
[12] Urmson C, Anhalt J, Bagnell D, Baker C, et al., 2008 Autonomous driving in urban
environments: Boss and the urban challenge, Journal of Field Robotics, vol. 25, pp. 425–466.
[13] Ruyi Jiang, Reinhard Klette, Shigang Wang and Tobi Vaudrey 2009 Low-level Image Processing
for Lane Detection and Tracking, Proceedings of ArtsIT 2009, LNICST Vol. 30, pp. 190-197.
[14] Yong Zhou, Rong Xu, Xianofeng Hu and Qingtai Ye 2006 A Robust Lane Detection and
Tracking Method Based on Computer Vision, Measurement Science and Technology, Vol. 17,
736-745.
[15] Mohammad Osiur Rahman, Fouzia Asharf Mousumi, Edgar Scavino, Aini Hussain and Hassan
Basri 2009 Real Time Road Sign Recognition System Using Artificial Neural Networks for
Bengali Textual Information Box, European Journal of Scientific Research, Vol. 25, No. 3, pp.
478-487.