AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

Chapter 1

Introduction
A fully autonomous vehicle can be defined as a car which is able to perceive its
environment, decide which route to take to its destination, and drive it. In other words we can
say autonomous vehicles are smart cars or robocars which uses a variety of sensors, computer
processors, and data bases such as maps to take over some or all of the functions of driving
from human operators. Cars equipped with this technology will have its own benefits. It will
likely reduce crashes, energy consumption, and considerably pollution. Recently major
OEM’s has announced their plans to begin selling such vehicles in a few years from now.

Figure 1.1: OEM with ready prototyp

DEPT OF EEE NIEIT MYSURU 1

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

Chapter 2

Literature

2.1 Literature Review

Removing a driver from behind the wheel takes away more than just the physical responses.
It also eliminates the complex decision-making that goes into even routine journeys –
choosing whether to swerve into a neighboring lane to avoid a possible obstacle or navigating
ambiguous intersections. The implications of Self-Driving cars are vast and these are covered
in the topic below with associated headings for each concept.

2.2 Innovation

Autonomous Electric Vehicles and driving methods are highly researched and being actively
developed across the globe. R&D [1] in this area in Pakistan allows an entry and
encouragement of advanced technologies in the country and therefore allows for future
contribution in the development and innovation in autonomous driving technologies. The
secondary purpose is optimal traffic management. [2] With increase in population, and
congestion of urban centers, autonomous vehicles working on optimal trajectory planning
algorithms will play their part in optimal traffic management.

2.3 Motivation

Millions of people have lost their lives or have become physically disabled worldwide in past
many years as a consequence of traffic accidents. This has given the motivation to go for an
Autonomous vehicle as almost most of the traffic accidents are caused by human mistakes.
According to statistics, in the next 10 years the number of lives claimed by traffic accidents
each year likely to be double. 1. As per WHO about 1.24 million people die each year as a
result of road traffic crashes. .Road traffic injuries are the leading cause of death among
young people, aged 15-29 years. Half of those dying on the world’s roads are “vulnerable
road users”: pedestrians, cyclists and motorcyclists. Without action, road traffic crashes are
predicted to result in the deaths of around 1.9 million people annually by 2020.

DEPT OF EEE NIEIT MYSURU 2

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

Figure 2.3.1: Road fatalities per capita (fatalities per 100,000 inhabitants per year)

DEPT OF EEE NIEIT MYSURU 3

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

Chapter 3

3.1 Classification of Autonomous Vehicles

There are many OEM’s which has already implemented this into their exiting production
vehicles to come up with a prototype for testing purpose. This includes many renowned
automakers. National Highway Traffic Safety Administration (NHTSA) has classified this
technology into 4 different levels.

Level 1- Function specific Automation: This will include the automation of specific control
functions, such as cruise control, lane guidance and automated parallel parking. Drivers are
fully engaged and responsible for overall vehicle control (hands on the steering wheel and
foot on the pedal at all times).

Level 2- Combined Function Automation: This signifies the automation of multiple and
integrated control functions, such as adaptive cruise control with lane centring. Drivers are
responsible for monitoring the roadway and are expected to be available for control at all
times, but under certain conditions can be disengaged from vehicle operation.

Level 3 -Limited Self-Driving Automation: Drivers can cede all safety-critical functions
under certain conditions and rely on the vehicle to monitor for changes in those conditions
that will require transition back to driver control. Drivers are not expected to constantly
monitor the roadway.

Figure 3.1.1: Timeline for Adoption (Morgan Stanley Research)

DEPT OF EEE NIEIT MYSURU 4

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

Level 4 - Full Self-Driving Automation: Vehicles can perform all driving functions and
monitor roadway conditions for an entire trip, and so may operate with occupants who cannot
drive and without human occupants. However many automakers have started testing there
prototypes but still it’s a long way to go to attain that accuracy and confidence where we can
blindly put our faith on Autonomous vehicles. Google has set a target of 2018 to
commercially launch its autonomous vehicle. Autonomous vehicles will have a long term
impact on the society and it will be radical change on how we commute. But this change from
conventional to autonomous vehicles should be a gradual one so that people will have that
confidence and it can be used at large scale. There is a recent study done by Cisco on
customer confidence on an autonomous vehicle. According to this study half of the world’s
consumer will trust a car which operates without a human driver. Cisco surveyed more than
1500 consumers around ten countries and focused on automobile buying and driving
experience.

Figure 3.1.2: Cisco survey for Autonomous vehicles

DEPT OF EEE NIEIT MYSURU 5

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

Chapter 4

4.1 Objectives of Autonomous Vehicles:

The main objectives of an autonomous vehicle are listed below:

(a) Perception

(b) Motion Planning

(c) Navigation

(d) Behaviour

4.1.1 Perception: It is the ability of the vehicle to understand its immediate environment.
This will help the vehicle to avoid collision between vehicles and also to keep a check on any
kind of obstacles which may come in the vehicle path. Now a days there are many electronic
devices available in the market which can be used for this purpose. LIDAR, RADAR, GPS to
name few. Light Detection and Ranging, or LIDAR, systems determine distance to obstacles
by using laser range finders which emit light beams and calculate the time of flight until a
reflection is returned by objects in the environment. Similarly, Radio detection and ranging,
more commonly known as RADAR is another key sensor for autonomous vehicles. Like
LIDAR, RADAR systems uses signals time of flight to determine the range to objects in the
environment. Unlike LIDAR, RADAR uses radio waves, which give radar systems different
capabilities and limitations.

DEPT OF EEE NIEIT MYSURU 6

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

Figure 4.1.1.1: Perception devices

The other common device used in autonomous vehicle for perception is monovision cameras.
Monovision cameras means they have one source of vision. Monovision cameras are very
simple devices and the video feed is usually used for understanding basic surroundings
typically fixed infrastructure like lane markings, speed limit signs, etc. The hardware itself is
pretty simple and cheap.

Automotive monovision cameras are less sophisticated and have lower pixel density than
cameras on smartphones.

4.1.2 Motion Planning: Motion planning involves performing low level operations towards
achieving high level goal. It’s very complex to plan the path of an autonomous vehicle in a
dynamic environment, especially when the vehicle is required to utilize its full capabilities.
There have been recent advances in computational capabilities both in terms of hardware and
algorithms and communication architectures which can help us in making an error free
autonomous vehicle. Motion planning consist of path variables which are to be controlled to
avoid any kind of mishap. Those path variables are:

(i) Steering (direction): The motion planning should be efficient enough to steer the vehicle
through any type of static or dynamic traffic.

(ii) Speed: Motion planning module should be efficient enough to control the speed of the
vehicle according to the environment. After taking in account above mentioned parameters
autonomous vehicle should be able to play with these parameters and generate local paths

DEPT OF EEE NIEIT MYSURU 7

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

which can be followed. It should also be able to assign costs to paths based on time taken,
fuel consumption, distance from obstacles and other constraints. Once all the available paths
are obtained it should choose the best path on the basis of time, cost, traffic and other various
constraints.

4.1.3 Navigation: Vehicles also use sensor suites for localization, i.e. determining their own
position in the world. The use of global positioning systems (GPS) is essential for
localization. Vehicle GPS systems receive signals from orbiting satellites to triangulate their
global coordinates. These coordinates are cross-referenced with maps of the road network to
enable vehicles to identify their position on roads.

Figure 4.1.3.1: Types of sensors and their location

GPS is typically coupled with inertial navigation systems (INS) which consists of gyroscopes
and accelerometers to continuously calculate position, orientation and velocity of the vehicle
without need for external references.

4.1.4 Behaviour: Once the vehicle has perceived its environment, completed the motion
planning and navigated the route, it’s time to act. So on the basis on all detailed parameters an
autonomous vehicle takes decision. There are many challenges faced by an autonomous
vehicle few of them are listed and discussed.

(i) Lane Analysis: In Vision based lane detection lots of methods have been presented in
recent past. These methods use different lane patterns (dashed or solid), different lane model
(2D or 3D, straight or curved, etc.) and also different techniques (Hough transform. Template

DEPT OF EEE NIEIT MYSURU 8

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

matching, etc.). But till now autonomous vehicles have been only tested at roads which are
well planned and structured. The capabilities of this vehicle on unstructured and unplanned
road is yet to be tested. Figure 6 shows an autonomous vehicle preparing to negotiate a curve
in the road to reach its next destination. The optical image is overlaid with a proposed path of
encircled destination points ( white indicated that the lane marker detection and lane center
estimation are functioning, and black indicates subsequent steps without current estimations),
directional lines of motion to those points, and yellow lane and curb markers.

Figure 4.1.4.1: Lane detection

(ii) Overtaking: Overtaking has always been associated as the main cause of accidents
worldwide. And in an autonomous vehicle the concern becomes more. Safe overtaking can be
defined as vehicle crossing another vehicle safely well aware of vehicle coming from behind
opposite direction. Overtaking in autonomous vehicle is done by developing algorithms. In
this there are electronics devices fitted in the vehicle which work on the logic given in the
algorithm to complete this task. First the source car with the help of sensors detects the
vehicle ahead and estimates the distance between them. With the help of this its estimates its
relative speed. Stereo cameras are used to detect the moving objects which used edge
detection technology. If during overtaking vehicle approaches from opposite the source
vehicle detects and moves the vehicle to safe distance and supersede the decision of
overtaking.

DEPT OF EEE NIEIT MYSURU 9

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

Figure 4.1.4.2: Schematic diagram of overtaking

DEPT OF EEE NIEIT MYSURU 10

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

Chapter 5

5.1 COMPONENTS

 The Lidar system

 GPS

 Radar sensor

 Ultrasonic sensor

 Video cameras

 Central computer

Figure 5.1.1 Components of Autonomous vehicles

5.1.1 THE LIDAR SYSTEM

• The Light Detection and Ranging (LIDAR) which is mounted on the roof of the
vehicle is the most important device in the Autonomous vehicles.

• This laser allows the vehicle to generate a detailed 3D map of its environment.

• The LIDAR consists of an emitter, mirror and receiver.

• The emitter sends out a LASER beam that bounces off a mirror that is rotating along
with the cylindrical housing at 10 revolution per minute.

DEPT OF EEE NIEIT MYSURU 11

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

• After bouncing off objects ,the LASER beam returns to the mirror and is bounced
back towards the receiver . Where it can be interpreted into data.

• The vehicles can then generate a map of its surroundings and use the map to avoid
objects.

5.1.2 GPS

• To obtain macro location- accuracy up to 2-3 meters

• A GPS is used, just like the satellite navigation system in most cars, to get a rough
location of the car, also radar, laser and cameras take over to monitor the world
around the car 360 degrees for more precise location

5.1.3 VIDEO CAMERAS

• Used for near vision.

• A camera mounted near the rear- view mirror/windshield build a real-time 3D images
of the road ahead spotting hazards like pedestrians and animals.

• It is also used to identify road signs, markings and traffic signals.

5.1.4 Radars

• Radars are fitted in the bumpers at front

• The radar chirps between 10 and 11GHz over a 5 millisecond period transmitting the
radar signals from a centrally located antenna cone, two receive cones, separated by
approximately 14 inches, receive the reflected Radar energy.

• Traditional Radar sensors are used to detect dangerous objects in the vehicles path
that are more than 100 meters away.

• Accident prevention systems trigger alerts when they detect something in a cars blind
spot.

DEPT OF EEE NIEIT MYSURU 12

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

5.1.5 ULTRA SONIC SENSORS

• It is used to measure the position of objects very close to the vehicle ,such as cuts and
other vehicles when parking.

• Keep track of the movements of the car and will alert the car about the obstacles in
the rear.

• Cars that offer automatic ‘reverse park Assist ‘technology utilize such sensors to
help navigate that car into tight reverse parking spots.

• These sensors get activated when the cars is engaged in the reverse gear.

• These sensor provide input to a number of different automotive systems including the
anti-lock brake system and electronic stability control.

5.1.6 Central computer

• The software can recognize objects ,people,cars,road marking, signs and traffic lights
and safely navigate around them.

• It works based on machine learning technology.

• Information from all the sensors is analyzed by a central computers, based on the
information received the software takes self-driving decisions such as steering,
accelerate and brakes.

• Programme to interpret the common road signs- predetermine shape and motion
descriptors are programmed into the system to help the car make intelligent decisions.

Eg-if a cyclist gestures that he intends to make a manoeuvre,the driverless car

interprets it correctly and slow down to allow the cyclist to turn.

DEPT OF EEE NIEIT MYSURU 13

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

5.2 Working mechanism

Input devices: from sensors such as LIDAR, GPS Receiver, Laser range finder
From mobile apps online controller from human beings.

Processing: using algorithms/coding.

computers software’s

automobile chip

Output: as a function of mechanical mechanism such as breaking acceleration

turning etc.

5.2.1 How it works?

 Radar sensor dotted around the car monitor the position of vehicles nearby.

 Video cameras detect traffic lights ,read road signs and keep track of other vehicles
while also looking out of for pedestrians and other obstacles.

 Lidar sensor help to detect the edges of roads and identify lane markings by bouncing
pulse of light off the cars surroundings.

DEPT OF EEE NIEIT MYSURU 14

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

 A central computer analyses all of the data from the various sensors to manipulate the
steering acceleration and braking.

Fig 5.2.1 working of autonomous vehicles

5.3 VARIOUS AUTONOMOUS VECHICLES

DEPT OF EEE NIEIT MYSURU 15

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

Fig 5.3 various autonomous vechicles

Chapter 6

6.1 Barriers to Implementation:

Autonomous vehicles comes with lots of benefits such as reduced driver stress, mobility for
non-drivers, increased safety, increased fuel efficiency and reduced pollution to name few.
But still there will be many challenges which will act as barriers in implementation of this
technology. Some of the major challenges are discussed ahead:

(a) Cost: The companies which are testing there autonomous vehicles have paid very hefty
amount in building those vehicles. Google itself has paid around $80,000 for the AV module
which is way out of a normal man’s reach. It is expected once this technology is proven it
may come down to half of the price which is still a very huge amount. In future if the prices
of Autonomous vehicles comes somewhere near to conventional vehicles J.D power recent
survey shows 37% people would definitely or probably but an autonomous vehicle as their
next vehicle.

DEPT OF EEE NIEIT MYSURU 16

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

(b) Technology challenges: However many renowned automakers such Mercedes, BMW,
Audi, Nissan have already announced that they will be ready with a partially autonomous
vehicle (Level 3) but still it is a long way to go as in many countries road conditions are not
up to mark. This technology still needs extensive research and testing to build that confidence
where we can completely rely on these vehicles. According to experts it will still take another
10-15 years

(c) Removal of old cars: The foremost challenge for implementing autonomous car will be
scraping of all the old cars which are not fitted with autonomous module because it cause of
lot of unpredictable outcomes and so will reduce the effectiveness and safety of the
autonomous vehicles. There can be a solution if the older cars can be retrofitted but again itis
going to be a huge task by looking at the no. conventional vehicles plying at the roads. Also if
everyone is ready to put into that much of cost.

(d) Unemployment issue: Although autonomous vehicles have many benefits but the biggest
challenge we foresee is the unemployment issue. The day autonomous technology will be
fully proven there won’t be any need for drivers. So all those people who today earning their
livelihood as professional drivers will no more be able to earn it. The most important
industries which are supposed to be get affected with the introduction of autonomous vehicles
are taxi, trucking and marine freighting.

(e) Security & Privacy concern: In today’s world where everything is getting controlled by
electronics security and privacy concerns is also a biggest issue. So do is the hackers.
Electronic data is not safe today and it’s vulnerable to information abuse. Even an
autonomous vehicle can be utilized by any terrorist outfit to carry out their suicide missions.
Also as these vehicles will be connected through GPS anyone can get the position and it can
be used to any kind of bad purpose.

(f) Standards & Regulation: Government should make standards and laws to streamline the
process of introducing autonomous vehicles into the road. There should be laws where the
concern over privacy and protection and management of this huge private data should be
addressed. Autonomous vehicles should not be used by any terrorist group this should also be
addressed by government.

DEPT OF EEE NIEIT MYSURU 17

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

6.2 BENIFITES

1) Reduce accidents

2) Reduce traffic congestion

3) Reduced CO2 emission

4) Lower fuel consumption

5) More efficient parking

Chapter 7

scope

 In 2012, Bengaluru engineer driven for the test to build India's first driverless car, ie,
Tata Nano Autonomous.
 IIT Kharagpur, Kanpur and Bombay are working on 'autonomous vehicle solutions'
or driverless solutions,  Project and testing their technology
on Mahendra E20 electric cars.

  It can help to reduce a huge accident that occurs in India.

 It can reduce the problems of traffic jam.

DEPT OF EEE NIEIT MYSURU 18

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

Chapter 8

Conclusion:

Autonomous vehicles will benefit the economy through fuel efficiency, the environment
through reduced carbon emissions, society through more togetherness, and the legal system
through a simpler system of liability. However, these ideas revolve around two central aspects
of autonomous vehicles: how they work and how they are kept secure. As technology
advances, the security technology regarding self-driving cars will also continue to grow to
combat hackers, improve the accuracy of internal systems, and prevent accidents.

DEPT OF EEE NIEIT MYSURU 19

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

Chapter 9
Reference:
1. Todd Litman, Autonomous Vehicle Implementation Predictions Implications for Transport
planning,Victoria Transport policy Institute, January 29, 2015.

2. Autonomous Vehicle Technology: A Guide for Policymakers, RAND Corporation, 2014.

3. NHTSA, 14-13, May 30, 2013

(http://www.nhtsa.gov/About+NHTSA/Press+Releases/U.S.
+Department+of+Transportation+Releases+Policy+on+Aut omated+Vehicle+Development).

4. Autonomous car policy report, Carnegie Mellon University, 2014.

5. www.cisco.com 6. www.lloyds.com 7. www.ll.mit.edu/publications/labnotes/automation.

DEPT OF EEE NIEIT MYSURU 20

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

DEPT OF EEE NIEIT MYSURU 21

 AUTONOMOUS VEHICLES: THE FUTURE OF AUTOMOBILES

DEPT OF EEE NIEIT MYSURU 22