Autonomous Vehicle an overview

Journal of Advanced Engineering Research
ISSN: 2393-8447
Volume 2, Issue X, 2015, pp.XX-XX
Research Article 1 www.jaeronline.com
Autonomous Vehicle an Overview
Surya Kandhaswamy.T1, *, Shafeequr Rahman S.I, Dr. P Gopal3
1Department of Automobile Engineering, Anna University BIT Campus, Tiruchirappalli 620024, India.
2Department of Automobile Engineering, Anna University BIT Campus, Tiruchirappalli 620024, India.
3Asst.Prof, Department of Automobile Engineering, Anna University BIT Campus, Tiruchirappalli 620024, India.
*Corresponding author email: suryatks@gmail.com Tel. :+91 8903417955
ABSTRACT
The next big unsettling innovation in the field of automobile is predicted to be Autonomous Driving. The future being
predominantly technology driven is supposed to revolutionize the art of driving and transportation.To efficiently
comprehend the progress of study in autonomous driving in the recent past around the world, it is vital to conduct an
overall review. This will help to identify the progress in different fields in which autonomous driving has evolved as well
as to identify its shortcomings.
Keywords - Autonomous,Driverless, Robotic, Self-driving, Environmental impacts.
1. Introduction
Fully autonomous driving in real urban settings has
remained an important but elusive goal. Many
noteworthy attempts have been made, and several
important milestones have been reached in the recent
past.This paper presents a review of recent autonomous
drivable cars.
Marlon G. Boarnet [1], a specialist in transportation
and urban growth at the University of Southern
California quotes that “Approximately every two
generations, we rebuild the transportation infrastructure
in our cities in ways that shape the vitality of
neighborhoods; the settlement patterns in our cities and
countryside; and oureconomy, society and culture” & as
many consider, autonomous driving cars are this new big
revolution everyone is keen about. Leading not only to
great ecological benefits such as the enhancement of fuel
efficiency [2,3] , through the optimization of
highways[2,3,4,5,6] ,platoon driving that would save to
20-30% fuel consume [7]and the reduction of required
cars to only 15% of the current amount needed[1], but
also leading to societal aspects such as decline on the
accident and death tolls considered as the eight highest
death cause worldwide in 2013 (World Health
Organization, 2013), enormous productivity increases
while travelling, stress reduction among drivers, and the
reduction of parking space to up to ¼ of the current
capacity.[8]
All the benefits and technological difficulties do not
come without a certain amount of challenges, snags and
required variations in current systems,for it to work. By
now several States in the USA have devised laws
allowing autonomous cars testing on their roads. The
National Highway Traffic Safety Administration in the
United States (2013) provides an authorized self-driving
car classification dividing into
a) No-Automation (Level 0)
b) Function-specific Automation (Level 1)
c) Combined Function Automation (Level 2)
d) Limited Self-Driving Automation (Level 3)
e) Full Self-Driving Automation (Level 4).
The Europeans have also started altering the Vienna
Convention on Road Traffic and the Geneva Convention
on Road Traffic [9]in order to be equipped to acclimate
this new technology, but legal issues and doubt still
remain as one of the main uncertainties of the debate.
Some of the main problems in the field of
autonomous driving found throughout the literature and
the web are; assessment and standard set for critical
event control, how to deal with the requirement for a
‘driver’ if such a need arises,ownership and maintenance
[10], civil and criminal liability, corporate manslaughter
[11], insurance, data protection and privacy issues and
other contingency planning[12].
Having a deeper view at the history of Autonomous
Driving, as explained in the IEEE Spectrum [1] in Figure
1 it can be perceived that the technological expansion
and main milestones of the autonomous driving field
started already a few decades ago. Leading to a huge
analysis of some semi-autonomous features,
improvement of present technologies and understanding
on the future difficulties while focusing in the near future
in the connected car.
The main concern for all semi-autonomous features in
the literature is that humans are poor monitors of
automation [13] meaning that driving performance
naturally declines as automation increases,leading to big
safety concerns while being “out of the loop” in case of
necessary reaction [5,6,14], situation that is impending
until the technology is fully automated.

Surya Kandhaswamy T et al., / Journal of Advanced Engineering Research, 2015, x (x), xxx-xxx
Figure 1: Sixty-five years of automotive baby steps [1]
2.Vision-Based Intelligent Vehicle
Research Worldwide
Vision-based vehicle detection for driver assistance has
received significant consideration over the last 15 years.
There are at least three major reasons for the sudden
budding of research in this field: 1) the startling losses
both in human lives and finance caused by vehicle
accidents, 2) the availability of feasible technologies
accumulated within the last 30 years of computer vision
research, and 3) the exponential growth in processor
speeds have paved the way for running time.
The early lane detection was primarily built on a
pattern matching technique,while the obstacle detection
was abridged to the determination of the free-space in
front of the vehicle using the stereo image pairs without
3D reconstruction.
The first research struggles on developing intelligent
vehicles were centered in Japan in the 1970s, significant
research activities have been triggered by prototype
vehicles manufactured in Europe in the late-1980s and
early-1990s. MITI, Nissan, and Fujitsu pioneered the
research in this area by joining forces in the project
“Personal Vehicle System”.
In March 2004, the whole world was stimulated by
the “grand challenge” organized by The US Defense
Advanced Research Projects Agency (DARPA). In this
competition,15 fully autonomous vehicles attempted to
independently navigate a 250-mile (400 km) desert
course within a fixed time period, all with no human
intervention whatsoever—no driver, no remote-control,
just pure computer-processing and navigation
horsepower, competing for a 1 million cash prize.
Although, even the best vehicle (i.e., “Red Team” from
Carnegie Mellon)made only sevenmiles,it was a very big
step towardsbuilding autonomous vehicles in the future.
2.1. Past Initiatives Taken in Japan
In Japan, industry, government, and academia have
cooperatively undertaken various initiatives to create
automated driving technologies.This chapterintroduces
two projects demonstrative of these efforts: Advanced
Cruise Assist Highway Systems (AHS: 1994–2010) and
Energy ITS (Development of Energy-saving ITS
Technologies; 2008–2012)
2.1.1. Advanced Cruise AssistHighway Systems
The Advanced Cruise Assist Highway Systems (AHS)
are systems aims to link roads and vehicles by providing
drivers with real-time data, thereby
improving the safety of vehicle travel and increasing
traffic volume, while eventually aiming for the
achievement of automated driving.
In 1994, the former Public Works Research Institute
(now National Institute for Land and Infrastructure
Management) started development and testing of the
systems. In 1996, magnetic markers were installed at
intervals of 2 m in the center of traffic lanes and a test of
automated driving was carried out on a public road: the
continuous operation of a platoon of 11 vehicles for
about 11 km at a top speed of
80 km/h. [16]
2.2. Energy ITS Project
The Energy ITS Project is a project undertaken with the
participation of 15 organizations from industry,
academia, and the public sector under the leadership
of New Energy and Industrial Technology Development
Organization (NEDO) and subsidized by the Ministry of
Economy, Trade and Industry for a five year
research period extending from 2008 until 2012. The
project has constructed an experimental system
consisting ofmillimeter wave radar, laser radar, cameras,
and steering control systems etc. intended to be used to
achieve very safe and reliable platooning that can be
performed on expressways. It also included
research and development of prototype vehicles which
have achieved platoon formation functions,lane-keeping
control functions, inter-vehicle distance control
functions, and so on. At the end of 2010, a test in which
3 large trucks traveled 10 m apart in a platoon
for a distance of80 km was successfully carried out.And
at the end of 2012, 4 large and small trucks successfully
performed a test platoon traveling at intervals of 4 m.
2.3. History ofAutomated Driving in the United
States
For ground transportation, the vision comprised what
about 15–20 years later became reality with the U.S.
Interstate Systemand also some automated vehicle
control, which was described as radio controls to
maintain proper distance between vehicles—basically
what became reality as adaptive cruise control about 60
years after the fair. In the book“Magic Motorways”,that
Geddes published in 1940, he explained in more detail,
how many of the systems that were used already in
aircraft at that time, could help automobiles to stay in the
lane and keep proper distance.
2.3.1. Automated Highway Systems
Automated Highway Systems also became a very
important research topic at the Ohio State University,
when in the 1960s much work was pursued in that field.
The work, significantly funded by the U.S. Federal
Highway Administration, started with automated
steering, braking, and acceleration control for vehicles
and went on for about 20 years. The basic concept was
similar to the one that GM and RCA had worked on, that
means magnetic sensors in the front and rear of the car,

picking up magnetic signals from wires in the road
surface. Especially during the 1970s, much work was
done at Ohio State University in platooning vehicles on
such automated highways, until federal funding ceased
in the early 1980s. Also during the 1960s and
1970s, Bendix, which later merged with several other
corporations such as Raytheon and Allied Signal, worked
on similar concepts that aimed for automated vehicles by
using cables in the road surface and radio
communication.
In 1986, California Partners for Advanced Transit and
Highways (PATH) was formed, a collaborative of
academia, public and private sectors, which was
administered by the Institute of Transportation Studies
(ITS) at the University of California at Berkeley in
collaboration with the California Department of
Transportation (Caltrans). In its mission to increase
highway capacity and safety, PATH put from
the beginning a strong focus on highway automation
(besides highway electrification, another primary
research direction for the program).
In 1991, U.S. Congress directed the U.S. Department
of Transportation (U.S. DOT) with the “Intermodal
Surface Transportation Efficiency Act” (ISTEA) to
“develop an automated highway and vehicle prototype
from which future fully automated intelligent vehicle-
highway systems can be developed by 1997”.
Thereafter, the U.S. Federal Highway Administration
(FHWA) formed the National
Automated Highway System Consortium (NAHSC).
NAHSC was a consortium of a number of technology
and construction companies, transit organizations, as
well as universities, with General Motors and FHWA
heading the collaboration and the California PATH
collaborative being a core member. In 1994 the
consortiumaimed to deploy automated highway systems
between 2002 and 2010 with demonstrations
of prototypes in the second half of the 1990s. The most
significant demonstration project was conducted in 1997
on Interstate-15 outside San Diego, when about
20 vehicles (cars, trucks, busses) platooned with close
following distance and lateral control showing gains in
energy and traffic efficiency through automated control
and still allow for other vehicles to merge in and out of
the platoon.The longitudinal control of the vehicles was
performed through radar sensing on each vehicle as well
as vehicle-to-vehicle communication so that the vehicles
could be kept at a proper distance. In order to keep the
vehicles in the lane, lateral control used magnets.
2.3.2. Automated Vehicles and Public
Competitions
In 1995, Carnegie Mellon University demonstrated in a
4,500 km drive from Pittsburgh to Los Angeles,that they
were able to accomplish 98.2 % automated
lateral control on that journey with camera and laser
vision systems together with a neural network control
concept. The demonstration, which was dubbed
“No Hands Across America” [17]
In 2003, the U.S. Defense Advanced Research
Projects Agency (DARPA) decided to use a prize budget,
which had been authorized by U.S. Congress earlier, to
respond to a Congressional mandate from 2001
formulated as “It shall be a goal of the Armed
Forces to achieve the fielding of unmanned, remotely
controlled technology such that…by 2015, one-third of
the operational ground combat vehicles are unmanned”.
[19,20]
2.3.3. The Role ofSilicon Valley
After and probably through the Grand and Urban
Challenge competitions, one of the worldwide leading
centers for automated driving research evolved in Silicon
Valley. With Stanford University being one of the most
successful participants in the Challenges (first in 2005,
second after Carnegie Mellon University in 2007), many
automotive companies, most notably from Germany and
Japan,came to the university to collaborate on automated
vehicle research. In addition, Velodyne, a technology
company in the area, became a major supplier of LIDAR
systems for many research vehicles.
By the summer of 2012, with Google becoming a
major player in automated vehicle development, global
research and development activities got accelerated and
virtually all major vehicle manufacturer as well as major
suppliers in the industry started or grew their efforts in
the field, often seeking collaboration with Silicon Valley
academic and industry partners. This movement also
attracted the legislators’ attention,
sparking initiatives to regulate testing, operation, and
sales of such vehicles.
2.3.4. Definition and Standardization Activities
As many terms had been used to describe automated
vehicles, with “autonomous”, “driverless”, “robotic”,
and “self-driving” being some of them, different
initiatives came underway in the early 2010s to define
different levels of automation and respective systems.
SAE International organized the On-Road Automated
Vehicle Standards Committee, which for instance had
established standards for adaptive cruise control (ACC)
and other driver assistance systems.
In 2012 the committee issued Taxonomy and
Definitions for Terms Related to On-Road Autonomous
Vehicles that set forth six descriptive levels of
automation that defined which
part of the driving task the human would perform and
which the automated system would take over.
A year later, with the 2013 Policy on Automated
Vehicle Development, NHTSA proposed a similar but
not identical set of descriptive levels for vehicle
automation, which consisted of five levels. The primary
difference between SAE’s and NHTSA’s definitions was
that SAE distinguished in its highest levels
between automation of all or some driving modes, which
NHTSA combined into one category. However, both
proposed the term“automated” to describe vehicle
systems that take a driving task over from the driver at
least in part.
2.4. Research and Innovation for Automated

Driving in Germany and Europe
With striking demonstrations and successful field tests,
vehicle manufacturers in Germany and Europe recently
drew public attention to their research and innovation
activities in highly automated and autonomous driving.
In summer 2013 Daimler mastered the 100 km-long
route from Mannheim to Pforzheim with a Mercedes-
Benz S 500 prototype car equipped with production-
based technologies for autonomous driving. It was the
same route where Bertha Benz had set out on the first
long-distance automobile journey 125 years ago. [21,22]
Researchers at BMW are currently testing
applications for autonomous driving in a prototype
BMW 5 vehicle on highways between Munich and
Nuremberg, giving a spectacular presentation of their
achievements at the CES 2014 in Las Vegas in early
2014. The vehicle comprises radars, laser scanners,
cameras and ultrasound sensors which are all
unobtrusively incorporated in the car’s body.[23]
2.4.1. Product Developments
Driver assistance systems have greatly advanced in
recent years: their two most relevant functionalities for
highly automated driving, adaptive cruise control and
lane departure warning, are commonplace in high-end
automobiles today.
In an adaptive cruise control(ACC) system,the driver
selects the desired speed and sets the distance to be
maintained to the vehicle ahead. This gap can be set
at several distances,adapting to the driving situation and
individual driving style.
Standard ACC can be activated from speeds ofaround
30 km/h (20 mph) upwards and can support the driver,
primarily on interurban journeys and on highways or
motorways.
An ACC Stop and Go systemmaintains a set distance
to the receding vehicle even at very low speeds and can
decelerate to a complete standstill. When the vehicle in
front accelerates within a few seconds,the ACC vehicle
follows automatically.
Such system can support the driver in congested
traffic at speeds below30 km/h. ACC and ACC for Stop-
and-Go are provided e.g. by Bosch and Continental.
BMW, e.g., is offering a ACC for stop and go situations
for its series 5 and up vehicles.
2.4.2. Communication Standards
Automated cars heavily rely on the data connection to
other cars and to the infrastructure which cannot be
developed without common technical requirements
regarding, for example, frequencies used or data
management. The European Commission’s Action plan
for the deployment of ITS in Europe thus aimed
at the development of harmonized standards for ITS
implementation, in particular regarding cooperative
systems. Following a mandate by the European
Commission, ETSI and CEN/ISO finalized a first
standardization package which was announced recently.
2.4.3. Future Development Paths
From a technological point of view, automated vehicles
represent the evolution of today’s driver assistance
systems. It starts with the systematic combination of
lateral and longitudinal control, and is further supported
by C2X communication and environment perception. A
networking with driver information and drive systems
is gradually advancing the concept toward its goal.
From 2016, partially automated systems may
therefore be assisting drivers by combining lateral and
longitudinal control in “stop and go” situations on the
freeway at low speeds of up to 30 km/h. But this initial
step toward automated driving does not relieve drivers
of their responsibility to constantly pay attention to what
is happening on the road. As well as covering higher
speeds above 30 km/h on the freeway, highly
automated driving will allow drivers to use the time they
would spend driving on other activities. With both levels
of automated driving, however, the driver must
be able to regain control of the vehicle at all times.
Fully automated road vehicles that require neither
supervision nor takeover of control by a driver will be
the most advanced system. It would have a significant
impact on our mobility behavior, road safety and traffic
efficiency in interurban (motorway/freeway) and urban
applications as it could lead to radically new solutions
such as robot taxis.[24,25]
3.Societal and Environmental Impacts
3.1. Ethics and Automated Vehicles
Vehicle automation has progressed rapidly this
millennium, mirroring improvements in machine
learning, sensing,and processing.Media coverage often
focuses on the anticipated safety benefits from
automation, as computers are expected to be more
attentive, precise, and predictable than human drivers.
Mentioned less often are the novel problems from
automated vehicle crash. The first problem is
liability, as it is currently unclear who would be at fault
if a vehicle crashed while self-driving. The second
problem is the ability of an automated vehicle to make
ethically-complex decisions when driving, particularly
prior to a crash.
To ensure its own safety, an automated vehicle must
continually assess risk: the risk of traveling a certain
speed on a certain curve, of crossing the centerline to
pass a cyclist, of side-swiping an adjacent vehicle to
avoid a runaway truck closing in from behind. The
vehicle (or the programmer in advance)must decide how
much risk to accept for itself and for the adjacent
vehicles. If the risk is deemed acceptable, it must decide
how to apportion this risk among affected parties. These
are ethical questions that,due to time constraints during
a crash, must be decided by the vehicle autonomously.
3.2. Fatalities and Injuries from Accidents
The ongoing carnage from U.S. road accidents—33,561
fatalities in 2012, 2.4 million people injured, and billions
of dollars in medical costs and property damage —could
be reduced by as much as 80 % through road vehicle
automation. New vehicles are now available with a

growing array of automated driver assistance
technologies, such as adaptive cruise control and lane
keeping, to reduce driver errors leading to accidents.
These technology applications are the precursors to a
future of self-driving cars with and without a driver in
the vehicle.
3.3 Congested Roadways
Traffic congestion wastes time and fuel, damaging the
economy and the environment. Urban pollution and
greenhouse gas emissions increase dramatically in
stop-and-go traffic. The estimated cost of traffic
congestion is $121 billion annually, not counting the
costs ofthe adverse health consequences oftraffic related
vehicle pollution.
Information processing and wireless communications
capabilities, collectively called telematics, can make
travel safer and more efficient by providing real-time,
hands-free information to drivers. Telematics today can
calculate the most efficient travel route, provide hints on
how to avoid traffic, assure that an emergency response
comes quickly, identify and reserve the nearest available
parking space, and provide increasingly sophisticated
and detailed information on desired destinations.The era
of big data and wireless communication for drivers and
their cars is creating what some call the “mobility
internet”.
3.4 Reduction ofCriteria Pollutants
There are six criteria emissions—particulate matter,
ozone, sulfur dioxide, nitrogen dioxide, carbon
monoxide, and lead—which are regulated under the
Clean Air Act. Although catalytic convertors and more
efficient engines have reduced these emissions, research
now shows that tailpipe emissions are killing more
people than carcrashes,as noted earlier. Electric vehicles
have no tailpipe emissions,
and the electric power generating plants that provide
EAVs (Electric Autonomous Vehicles) their electricity
are increasingly clean or are located far from urban areas.
4. Conclusion
This paper has reviewed the growth of autonomous
driving in different parts of the world. One of the most
important aspects of this paper is the parallel
consideration of technological advancements in several
hotspots around the world. It also signifies the
contribution of different educationalinstitution in testing
and analysis. The main goal of this paper is to raise
awareness about the potential of autonomous vehicles
which may lead to increased benefits and thoughts about
certain shortcomings and the countermeasures that can
be applied to overcome them.
Acknowledgements
This work was supported by the Mr. Vinoth The authors
are grateful to him.
Reference
[1] Ross, P. E., 2014. Robot, you can drive my car;
Autonomous driving will push humans into the
passenger seat. IEEE SPECTRUM , 51(6), pp. 60-90.
[2] Payre, W., Cestac, J. & Delhomme, P., 2014.
Intention to use a fully automated car; Attitudes and a
priori acceptability. Transportation Research Part F:
Traffic Psychology and Behaviour, Band 27, Part B, pp.
252-263.
[3] Luettel, T., Himmelsbach, M. & Wuensche, H.-J.,
2012. Autonomous Ground Vehicles—Concepts and a
Path to the Future. PROCEEDINGS OF THE IEEE , 100
(Special Issue: SI ), pp. 1831-1839.
[4] Le Vine, S., Zolfaghari, A. & Polak, J., 2015.
Autonomous cars; The tension between occupant
experience and intersection capacity. Transportation
Research Part C, Band 52, pp. 1-14.
[5] Hamish Jamson, A., Merat, N., Carsten, O. M. & Lai,
F. C., 2013. Behavioural changes in drivers experiencing
highly-automated vehicle control in varying traffic
conditions.Transportation Research Part C, Band 30, pp.
116-125.
[6] Merat, N. et al., 2014. Transition to manual; Driver
behaviour when resuming control from a highly
automated vehicle. Transportation Research Part F:
Traffic Psychology and Behaviour, Band 27 Part B , pp.
274-282.
[7] Ross, P. E., 2014. Robot, you can drive my car;
Autonomous driving will push humans into the
passenger seat. IEEE SPECTRUM , 51(6), pp. 60-90.
[8] Alessandrini, A., Campagna, A., Delle Site, A. &
Filippi, F., 2015. Automated Vehicles and the
Rethinking of Mobility and Cities. Transportation
Research Procedia, Band 5, pp. 145-160.
[9] Reuters, 2014. Reuters. [Online] Available at:
http://www.reuters.com/article/2014/05/19/us-daimler-
autonomous-driving-idUSKBN0DZ0UV20140519
[Zugriff am 30 April 2015].
[10]Teare, I., 2014. Technology Law Update. [Online]
Available at: http://www.technology-law-
blog.co.uk/2014/12/driverless-cars-the-top-10-legal-
issues.html [Zugriff am 30 April 2015].

[11] Browning, J. G., 2014. Emerging Technology and
Its Impact on Automotive Litigation. Defense Counsel
Journal, 81(1), pp. 83-90.
[12] Khan, A. M., Bacchus,A. & Erwin, S., 2012. Policy
challenges of increasing automation in driving. IATSS
Research, 35(2), p. 79–89.
[13] Bainbridge, L., 1983. Ironies of Automation.
Automatica, 19(6), p. 775–779.
[14] Weyer, J., Fink, R. D. & Adelt, F., 2015. Human–
machine cooperation in smart cars. An empirical
investigation of the loss-of-control thesis. Safety
Science, Band 72, pp. 199-208.
[15] Lecture Notes in Mobility
Gereon Meyer, Berlin, Germany.
[16] Auto-pilot System Council
http://www.mlit.go.jp/road/ir/ircouncil/autopilot/index.h
tml
[17] No hands across America.
http://www.cs.cmu.edu/afs/cs/usr/tjochem/www/nhaa/n
haa_home_page.html
[18] The National Automated Highway System
Consortium, ITS America, Fact Sheet, October
23, 1995. http://ntl.bts.gov/lib/jpodocs/pressrel/594.pdf
[19] Defense Advanced Research Projects Agency
(2006) Report to congress—DARPA prize
authority—fiscal year 2005 report in accordance with
10 U.S.C. § 2374a
[20] DARPA (2013) Robotics challenge trials 2013.
http://www.theroboticschallenge.org
[21]Press Release, Daimler, 10 Sept 2013
[22]Die Zeit, 21 Apr 2013
[23] Press Release, SARTRE project, 28 May 2012
[24]. Urban mobility advanced platform (Movie),
Renault, 2013
[25]. Reilhac P (2013) Intuitive driving, Presentation at
17th Int. Forum on Advanced
Microsystems for Automotive Applications, Berlin, 17
June 2013
[26]. Becker J (2013) Toward fully automated driving,
Presentation at TRB Second Workshop on
Road Vehicle Automation, Stanford, 17 Jul 2013
[27]. Press Release, Continental, 18 Dec 2012

Autonomous Vehicle an overview

More Related Content

What's hot (20)

Viewers also liked (20)

Similar to Autonomous Vehicle an overview (20)

Recently uploaded (20)

Autonomous Vehicle an overview