Professional Documents
Culture Documents
Seminar report on
Submitted by
(BE18F02F014)
Prof. M. S. Harne
(2020-2021)
1
CERTIFICATE
This is to certify that the Seminar report entitled “Artificial Intelligence Based on Autonomous
Car”, which is being submitted herewith for the complete fulfillment of the ‘Degree of Bachelor
of Technology’ in ‘Mechanical Engineering’ of Government College of Engineering,
Aurangabad affiliated to Dr. Babasaheb Ambedkar Marathwada University, Aurangabad. This is
the result of the Original Research Work and Contribution by ‘Saurabh Sunil Chindhe ’ under
my supervision and guidance. The work embodied in this thesis has not formed earlier for the
basis of the award of any degree or compatible certificate or similar title of this for any other
diploma/examining body or university to the best of knowledge and belief.
Dr. P. B. Murnal
Principal
Government College of Engineering,
Aurangabad
2
ACKNOWLEDGEMENT
This seminar work has been carried out to meet the academic requirements of
Government College of Engineering, Aurangabad for the completion of Seminar in Bachelor of
technology in Mechanical Engineering. I would like to put on record, my appreciation and
gratitude to all who have rendered their support and input. Without them, it would not have
been possible for me to shape this study.
Finally I would like to thank my parents and all my family members, friends for love,
encouragement and support from their hearts. I dedicate all our success to each one of them.
3
Abstract
Artificial Intelligence (AI) is revolutionizing the modern society. In the automotive industry,
researchers and developers are actively pushing deep learning based approaches for autonomous
driving. However, before a neural network finds its way into series production cars, it has to first
undergo strict assessment concerning functional safety. This paper will cover the conversion of
normal conventional cars into the autonomous car (Driverless car), problems associated with it,
objectives, requirements and the expected outcome of this step. It will also cover the standards
and give the critical comparison between conventional and driverless cars.
This AI based car will cause a huge change in people’s life, we will research and analyze the
various impacts on society, legal and ethical challenges, and importantly environmental
constraints. The modern era, the vehicles are focused to be automated to give human driver
relaxed driving. In the field of automobile various aspects have been considered which makes a
vehicle automated. Google, the biggest network has started working on the self-driving cars
since 2010 and still developing new changes to give a whole new level to the automated
vehicles. In this paper we have focused on two applications of an automated car, one in which
two vehicles have same destination and one knows the route, where other don't. The following
vehicle will follow the target (i.e. Front) vehicle automatically. The other application is
automated driving during the heavy traffic jam, hence relaxing driver from continuously pushing
brake, accelerator or clutch.
The idea described in this paper has been taken from the Google car, defining the one aspect here
under consideration is making the destination dynamic. This can be done by a vehicle
automatically following the destination of another vehicle. Since taking intelligent decisions in
the traffic is also an issue for the automated vehicle so this aspect has been also under
consideration in this
4
CHAPTER INDEX
1 Introduction 7
2 History 8
3 Levels of autonomy in self-driving cars 9
4 Philosophy of Autonomous Cars 10
1. Cost
2. Infrastructure
3. Replacing Conventional Cars
4. Security Concerns
8 Autonomous Vehicle Market Outlook - 2026 19-20
9 The pros and cons of self-driving cars 21-22
12 References 25-26
5
FIGURE INDEX
1 Automation levels in 9
driverless cars
2 Perception devices 10
5 Expected release of 18
Autonomous cars
6
Introduction
As the World is progressing, scientists and researchers are struggling to take the human life in
more comfort zone. People around the World are now quite much enthusiastic about the launch
of autonomous cars. The specialty of this car is its ability to perceive its environment using the
modern form of AI, and take decisions without the assistance of any driver. A self-driving car
(sometimes called an autonomous car or driverless car) is a vehicle that uses a combination of
sensors, cameras, radar and artificial intelligence (AI) to travel between destinations without a
human operator. To qualify as fully autonomous, a vehicle must be able to navigate without
human intervention to a predetermined destination over roads that have not been adapted for its
use.
On a technical basis, this car is designed based on the various areas of engineering which
includes electrical, mechanical, computer sciences and control engineering etc. Major
progression in the autonomous car has started when the Mercedes Benz has launched the vision
guided the car in 1980 after this invention it has started a huge focus on the areas of GPS system,
radar etc. This has also resulted in the development of the adaptive steer control, power steering
and other things that are involved in the humanitarian assistance as well. And now the research is
going on to introduce the World with the driverless car which could be much safer, efficient and
reliable for the users.
Road accidents are one of the major cause of death, as according+ to report by Deshpande et al
that nearly 3000 people died daily because of road accidents, among which half of them are not
in the car, other than that it has also been reported that if some safety measures are not taken this
will grow up to 2.4 million a year making the 5th largest cause of death in the World . This
number can be greatly reduced by putting autonomous cars into action which are far more
reliable and react swiftly than humans. It will also cause reduction in the traffic congestion, as
the efficiency of autonomous car makes it reliable in a way of keeping very small gaps between
vehicles, and its outstanding management of speed and time. Following the navigation track
without considering any other distraction makes it friendlier than the conventional cars operated
by drivers.
7
HISTORY
The invention of the real autonomous car goes back to 1926 when the radio the control car was
introduced by the Houdini radio control in NYC. It had an antenna which was responsible for
transmitting the signal and controlled by another car following it, and a motor connected to the
antenna was responsible for car operation. This concept was improved by the scientists of
Nebraska in 1958, when they laid circuit down under the highways which were a source of
detection for the autonomous car about the availability of other car and even guide it for steering
control, acceleration and break.
8
Levels of autonomy in self-driving cars
The U.S. National Highway Traffic Safety Administration (NHTSA) lays out six levels of
automation, beginning with Level 0, where humans do the driving, through driver
assistance technologies up to fully autonomous cars. Here are the five levels that follow Level 0
automation:
Level 1: An advanced driver assistance system (ADAS) aid the human driver with steering,
braking or accelerating, though not simultaneously. An ADAS includes rearview cameras and
features like a vibrating seat warning to alert drivers when they drift out of the traveling lane.
Level 2: An ADAS that can steer and either brake or accelerate simultaneously while the driver
remains fully aware behind the wheel and continues to act as the driver.
Level 3: An automated driving system (ADS) can perform all driving tasks under certain
circumstances, such as parking the car. In these circumstances, the human driver must be ready
to retake control and is still required to be the main driver of the vehicle.
Level 4: An ADS can perform all driving tasks and monitor the driving environment in certain
circumstances. In those circumstances, the ADS is reliable enough that the human driver needn't
pay attention.
Level 5: The vehicle's ADS acts as a virtual chauffeur and does all the driving in all
circumstances. The human occupants are passengers and are never expected to drive the vehicle.
Automation levels in
driverless cars
9
Philosophy of Autonomous Cars
The prime reason for adopting this technology of driverless car goes to the several
functionalities that are not achievable by the humans itself. Perception devices Another major
functionality of driverless car is its capability of planning the ultimate motion which makes it far
more accurate. It might be complex, but recent advances in this fields have resulted in some
algorithms which have dramatically enhanced its ability. Managing the speed and steering of
autonomous cars are a very important factor for the perfection of motion planning. These cars
also use Global positioning system GPS to determine its location along with the inertial
navigation system (INS), for keeping the position in the continuous record and the position as
well, and for that purpose it utilises the gyroscopes and accelerometers.
Perception devices
One of the major concern of these cars to adopt the safer procedure to perform overtaking safely,
so for that reason there are number of different sensors and stereo cameras where they detect the
car ahead and the distance, linked it to the speed of the car itself and by performing other
perception through sensors it carries out the position to pass the other car.
10
Key Physical Components of Autonomous Vehicles
•Cameras – Provide real-time obstacle detection to facilitate lane departure and track roadway
•LIDAR – Measures distance by illuminating target with pulsed laser light and measuring
reflected pulses with sensors to create 3-D map of area.
•GPS – Triangulates position of car using satellites. Current GPS technology is limited to a
certain distance. Advanced GPS is in development.
11
Self-Driving Car Features
Adaptive Cruise Control
Adaptive cruise control can adjust your vehicle’s speed based on the speed of cars on the road in
front you. In many cases, it can even set and maintain a desired following distance. And while
some adaptive cruise control systems require vehicles to be traveling at a certain speed before
they’ll kick in, the best systems can bring a car to a complete stop and get it started again once
traffic in front begins moving.
12
Automatic Parking
Automatic parking is the latest exciting self-driving feature to find its way into a wide range of
vehicles.
Autopilot
Tesla’s Autopilot system is possibly the most advanced autonomous system on the market today.
While many automakers are focusing on making sure vehicles remain in their lanes (lane-keep
assist), avoid collisions (forward-collision braking) or slow down and speed up based on traffic
(adaptive cruise control), Tesla has put together every piece of the puzzle in the best and most
useful way possible
Lane-Keep Assist
More and more automakers are rolling out lane-keep assist, a new feature that builds on lane-
departure warning systems in older models.
Sign Recognition
If you don’t know about road-sign recognition, you might be surprised to learn it exists — but
it’s available and surprisingly helpful. Road-sign recognition is a tool that automatically views
signs on the side of the road and relays that information to the driver.
Hands-free steering
Centers the car without the driver's hands on the wheel. The driver is still required to pay
attention.
Adaptive cruise control
(ACC) down to a stop automatically maintains a selectable distance between the driver's car
and the car in front.
Lane-centering steering
Intervenes when the driver crosses lane markings by automatically nudging the vehicle
toward the opposite lane marking
13
Working of Self-driving cars
AI technologies power self-driving car systems. Developers of self-driving cars use vast amounts
of data from image recognition systems, along with machine learning and neural networks, to
build systems that can drive autonomously.The neural networks identify patterns in the data,
which is fed to the machine learning algorithms. That data includes images from cameras on self-
driving cars from which the neural network learns to identify traffic lights, trees, curbs,
pedestrians, street signs and other parts of any given driving environment.
For example, Google's self-driving car project, called Waymo, uses a mix of sensors, Lidar (light
detection and ranging -- a technology similar to radar) and cameras and combines all of the data
those systems generate to identify everything around the vehicle and predict what those objects
might do next. This happens in fractions of a second. Maturity is important for these systems.
The more the system drives, the more data it can incorporate into its deep learning algorithms,
enabling it to make more nuanced driving choices.
14
The following outlines how Google Waymo vehicles work:
The driver (or passenger) sets a destination. The car's software calculates a route.
A rotating, roof-mounted Lidar sensor monitors a 60-meter range around the car and creates
a dynamic three-dimensional (3D) map of the car's current environment.
A sensor on the left rear wheel monitors sideways movement to detect the car's position
relative to the 3D map.
Radar systems in the front and rear bumpers calculate distances to obstacles.
AI software in the car is connected to all the sensors and collects input from Google Street
View and video cameras inside the car.
The AI simulates human perceptual and decision-making processes using deep learning and
controls actions in driver control systems, such as steering and brakes.
The car's software consults Google Maps for advance notice of things like landmarks, traffic
signs and lights.
15
Uses
Autonomous street-sweeping vehicles are also being produced in China's Hunan province,
meeting the Level 4 requirements for independently navigating a familiar environment with
limited novel situations.
Projections from manufacturers vary on when Level 4 and 5 vehicles will be widely
available. Ford and Volvo both project a 2021 release of a Level 4 vehicle for public
consumption. Tesla CEO Elon Musk, being a pioneer of both self-driving and electric cars,
has claimed that his company will have Level 5 vehicles ready as early as 2020. A successful
Level 5 car must be able to react to novel driving situations as well or better than a human
can.
16
Challenges involved with Autonomous Cars
Following are some of the major issues associated with the driverless cars.
Cost
Various cars manufacturers had to spend a huge amount of money for designing these
autonomous vehicles. The example Google can be considered where they are paying around
$80,000 for one of their AV model, which is totally unaffordable by the ordinary company or
the person. According to the future predictions, it is estimated that this price will come down
to the half, which is still more to be afforded. According to the recent survey done by the JD
power, which concluded that in the future 37% of the people will choose autonomous car as
their next vehicle
Infrastructure
Although many big companies like BMW, Audi, Nissan etc has done a commitment to
introduce driverless car, the infrastructure like roads is not up to date to that level where
these cars could be compromised to launch. According to one report, it will take another 10-
15 years to develop a certain type of infrastructure. Companies are really focussing to invest
such a big amount with something in return .
Replacing Conventional Cars
This is one of the biggest challenges which is being faced by the experts, replacing old
conventional car would be required to increase the efficiency of the autonomous cars. If the
old cars are left over under the same platform then this may lead to unpredictable results for
the autonomous car and compromises the security during its interaction with the other cars.
Security Concerns
Security and privacy are always being the biggest issue associated with the electronic
system. Autonomous cars are based on the AI system, where it also requires a source of
Internet for managing and information exchange, and this is the compromise medium which
can be abused by the hackers. The second major concern is the involvement of terrorist
activity where this platform of the driverless car can give a favourable place where they can
17
perform their suicide mission. And as these car is depending on GPS system, so anyone can
get itself into it to use it for the bad purpose.
Expected release of
Autonomous cars
18
Autonomous Vehicle Market Outlook - 2026
The global autonomous vehicle market size is projected to be valued at $54.23 billion in 2019,
and is projected to garner $556.67 billion by 2026, registering a CAGR of 39.47% from 2019 to
2026. Autonomous vehicle also known as self-driving vehicles uses artificial intelligence (AI)
software, light detection & ranging (LiDAR), and RADAR sensing technology, which is further
used to monitor a 60-meter range around the car and to form an active 3D map of the current
environment. The vehicle is designed to travel between destinations without a human operator.
19
Global Autonomous Vehicle
Market.2
20
The pros and cons of self-driving cars
Pros of Driverless/Fully Autonomous Cars
No Human Error
Computers take away the possibility of human error and distractions whilst driving. That
motorbike you didn’t spot? The car’s computer did.
21
Cons of Driverless/Fully Autonomous Cars
Hacking potential
Increasingly connected vehicles means they are more vulnerable to the threat of hackers, who
may be able to take over control of the cars. Equally, there are privacy concerns in the car being
tracked and knowing your frequent destinations, i.e. your home.
Accidents
Whilst on average accidents may be reduced, some accidents may be worse than if caused by
human error. An error in the car computer’s coding after an update for example could lead to
glitches and potential accidents that could have been prevented by a human.
22
Self-driving car safety and challenges
Autonomous cars must learn to identify countless objects in the vehicle's path, from branches
and litter to animals and people. Other challenges on the road are tunnels that interfere with the
Global Positioning System (GPS), construction projects that cause lane changes or complex
decisions, like where to stop to allow emergency vehicles to pass.
The systems need to make instantaneous decisions on when to slow down, swerve or continue
acceleration normally. This is a continuing challenge for developers, and there are reports of self-
driving cars hesitating and swerving unnecessarily when objects are detected in or near the
roadways.
This problem was evident in a fatal accident in March 2018, which involved an autonomous car
operated by Uber. The company reported that the vehicle's software identified a pedestrian but
deemed it a false positive and failed to swerve to avoid hitting her. This crash caused Toyota to
temporarily cease its testing of self-driving cars on public roads, but its testing will continue
elsewhere. The Toyota Research Institute is constructing a test facility on a 60-acre site in
Michigan to further develop automated vehicle technology.
With crashes also comes the question of liability, and lawmakers have yet to define who is liable
when an autonomous car is involved in an accident. There are also serious concerns that the
software used to operate autonomous vehicles can be hacked, and automotive companies are
working to address cybersecurity risks.
Carmakers are subject to Federal Motor Vehicle Safety Standards (FMVSS), and NHTSA
reported that more work must be done for vehicles to meet those standards.
In China, carmakers and regulators are adopting a different strategy to meet standards and make
self-driving cars an everyday reality. The Chinese government is beginning to redesign urban
landscapes, policy and infrastructure to make the environment more self-driving car-friendly.
This includes writing rules about how humans move around and recruiting mobile network
operators to take on a portion of the processing required to give self-driving vehicles the data
they need to navigate. "National Test Roads" would be implemented. The autocratic nature of the
Chinese government makes this possible, which bypasses the litigious democracy that tests are
funneled through in America.
23
Conclusion
The transition from self-driving cars with varying levels of autonomy to fully autonomous
vehicles is yet to be made. However, modern AI technologies and machine learning development
are making rapid leaps forward in this direction, and that is what’s driving the industry forward.
The vision-guided autonomous car developed by the Mercedes Benz gave a new dimension to
this technology and opened doors for the research work. According to Official report, there will
be quite a large number of autonomous cars that will be launched by 2020, which will be partial
as well the fully autonomous. And by 2035 most of the car around will be autonomous according
to the predictions. Top automotive brands such as General Motors, Ford, and Tesla are in the
final stages of testing their driverless vehicles which means we are on the verge of seeing a
revolutionary change in the way we commute.
This technology is still at its beginning, it might take a while for people to develop a trust for this
technology and adopt it. A number of security threats and concerns are on the way, but it won’t
last forever
24
References
[[1] Deshpande, Pawan. "Road Safety and Accident Prevention in India: A review." Int J Adv
Engg Tech/Vol. V/Issue II/April- June 64 (2014): 68.
2 Cranswick, Marc. Pontiac Firebird: The Auto-Biography. Veloce Publishing Ltd, IEEE
2013.
6Lowrie, James W., Mark Thomas, Keith Gremban, and Matthew Turk. "The autonomous land
vehicle (ALV) preliminary road-following demonstration." In1985 Cambridge Symposium, pp.
336-350. International Society for Optics and Photonics, 1985.
8Broggi, Alberto, Massimo Bertozzi, and Alessandra Fascioli. "Architectural issues on vision-
based automatic vehicle guidance: the experience of the ARGO project." IEEE Real-Time
Imaging 6, no. 4 (2000): 313-324.
25
9Shladover, Steven E. "Lane assist systems for bus rapid transit, Volume I:Technology
Assessment." Publication RTA 65A0160, US Department of Transportation, Washington, DC
(2007).
10Panayotova, Tzveta. "People Movers: Systems and case studies." University of Florida
(2003): 9. [11]Andréasson, Ingmar. "Innovative transit systems." Survey of current devel, IEEE
++(2001).
13Los Angeles Times. (2014, May 28). Look, Ma, no hands: Google to test 200 selfdriving
cars. Available at: http://www.latimes.com/business/autos/la-figooglecar-20140529-story.html
14 Cisco. (2013). Cisco customer experience research, Automotive industry, Global data
26
ACKNOWLEDGEMENT
Any achievement, be it scholastic or other, does not depend solely on the individual
efforts but on the guidance, encouragement and cooperation of intellectuals, elders and friends. A
number of personalities, in their own capacities have helped me in carrying out this seminar
work. I would like to take this opportunity to thank them all.
First of all, I would like to express my hearty gratitude to Dr.P.B. Murnal, Principal,
and Government College of Engineering, Aurangabad for giving me this opportunity to
enrich our knowledge.
Last but not the least, I wish to thank my parents for financing my studies in this college as
well as for constantly encouraging us to learn and providing us this opportunity.
(BE18F02F014)
27