Chapter -1

INTRODUCTION
For the past hundred years innovation with in the automotive sector as brought major
technological advances leading to safer, cleaner and more affordable vehicles. In the decades
of the 21st century the industry appears to be on the cusp of revolutionary change with
potential to dramatically reshape not just the competitive landscape but also the way we
interact with vehicles and indeed. The future design of our road and cities. The revolution
when it comes will be engendering by advent of an autonomous or self-driving car.

Self-driving vehicles have been defined as vehicles in which operation occurs without direct
driver input to control the steering, acceleration and braking according to the national
highway traffic safety administration. In this type of vehicles the driver is not expected to
constantly monitor the roadway while operating in self-driving mode. This definition assumes
that the vehicles will always have a driver however this isn’t essential autonomous
technologies are already able to perform all of the required function for vehicles to move
safely without any one board at all. The wide spread adoption of driverless vehicles may
seem distant vision something we would expect to see in futuristic movie perhaps.

Self-driving cars are mainly depends on the instruction is given by the GPS system. It gives
the clear picture of road. On the road the complete technology solution shall handle even the
most complicated scenarios. If the passenger is incapacitated for any reason and doesn’t take
over in time, the car will bring itself to a safe place to stop. Self-driving cars as a holistic
solution that generates exact positioning and complete 360 (degree) views of the cars
surrounding. This is achieved by a combination of multiple radars, cameras and laser sensors.
A redundant network of computers process the information generating a real time map of
moving and stationary objects in the environment. The cameras have a high dynamic range
and can handle very quick changes in lighting condition example: When entering a tunnel.
Sensor are used to detect are identify the any objections to car on the road. It has technology
to detect the speed board in the highways and it goes on that speed. For this car cloud
services are attached. It connected to the traffic authorities control centres. It has a backup
system facilities as in the aeroplanes that will ensure that autopilot will continue to function
safely also if an element of the system was to become disabled. Modern society faces
extensive future challengers to improve safety and reduce pollution and global co-emissions.
Autonomous can cut fuel consumption by up to 50% in certain situations. Impaired mobility
and congestion can be added to the list of challenges.

1
 Fig: 1.1 working model of autonomous car

 Ultrasonic sensors may be used to measure the position of object very close to the
vehicle, such as curbs and other vehicles when parking
 Signals from the GPS(global positioning system) satellites are combined with reading
from tachometers, altimeters and gyroscope to provide more accurate positioning than
is possible with GPS alone.
 LIDAR (light detecting and ranging) sensors bounces pulses of light off the
surrounding. Then are analysed to identity lane marking and the edges of roads.
 Video cameras detect traffic lights, read road signs, keep track of the position of other
vehicles and look out for pedestrians’ obstacles on the road.
 Radar sensors monitor the position of other vehicles nearby. Such sensors are already
used in adoptive cruise-control systems.
 The information from all of the sensors is analysed by a central computer that
manipulates the steering, accelerator and brakes. Its software must understand the
rules road, both formal and informal.

2
 Chapter -2
COMPONENTS OF AUTOPILOT MODE
Autonomous car or “Self driving car are defined as a motor vehicles that uses a artificial
intelligence, sensor and global positioning system coordinates to drive itself without the
active intervention of a human operator”. When we compare autonomous car and normal car
both are totally different. In the basis of safety manner, comfort, of the people, in the eyes of
pollution and the parts include. Then the components include in the self-driving car are

• Ultrasonic sensors

• Radars

• Cameras

• Laser scanners

• G.P.S. unit

• Cloud based 3-d digital map

along this there is a backup system as in the aeroplanes. Now we discuss one by one, how its
work in the autonomous car.

2.1 ULTRASONIC SENSORS

A sensor is a device that detects and responds to some type of input from the physical
environment. There are many types of sensors are there but we use here ultra-sonic sensors.
Ultrasonic sensors may be used to measure the position of objects very close to the vehicles,
such as curbs and other vehicles and support autonomous drive at low speeds. The sensors are
based on the technology used for current park assist functions enhanced with advanced
signals processing. A typical example of when this technology is useful is for detecting
unexpected situations such as pedestrians or hazards on the road close to the car.

It has four sensors looking backward, four sensors looking forward and four sensors looking
to the sides

3
 Fig: 2.1 Ultrasonic sensors

2.2 RADARS
Radar is an objective detection system that uses radio waves to determine the range, altitude,
direction or speed of objective. In self-driving car 4 surrounded radars are use. It has field of
view greater than 140 degree (Field of view is the area visible through a microscope or
stereoscope. The higher the magnification the small the field view.) It has 3 long range radar
of field view greater than 20 degree of range >150 meter. This four radars behind the front
and rear bumpers cone (on each corner of the car) are able to locate objects in all direction.
By sweeping both left and right, transmitting waves bounces off signs, poles and tunnels, the
monitor a full 360 degree around the car. The two long range radars placed in the rear bumper
of the car ensure a good rewarded field of view. This technology is particularly useful when
changing lanes because it can defect fast moving vehicles approaching from for behind.

4
 Fig: 2.2 Radars

2.3 CAMERAS
Cameras are a device for recording visual images in the forms of photograph film or
video signals. Here we use the trifocal cameras.

Trifocal cameras: In these mainly 3 cameras. The main camera is the popular aril alexia and
two small indie GS2K satellite cameras which creates 3D by combining 3d cine photography.
In addition a trifocal cameras placed behind the upper part of the wind screen is 3 cameras in
one providing a board 140 degree view, a 45 degree view and along range yet narrow 34
degree view for improved depth perception and distant object detection the cameras can spot
suddenly appearing pedestrians other on expected road hazards.

5
 Fig: 2.3 Cameras

2.4 G.P.S. unit and cloud services

G.P.S. means global positioning system. Signals from GPS satellites are combined with
reading from tachometers, 3-degree freedom of altimeters and 3-degree freedom gyroscope to
provide more accurate position than is possible with GPS alone. A tachometer is an
instrument measuring the rotation speed of a shaft or disk as in a motor or other machine. It is
usually display in RPM (revolution per minute). It is used to control the speed of the engine.
By matching the 360 degrees, image created by the altitude of sensors with the wrap image.
The car will get the information about its position in relation to the surroundings. By combing
the information from the sensors and the map self-driving car is able to choose the best
course in real time factoring in variables such as the curvature of the road speed limit,
temporary signs and other traffic.

The cloud service is connected to the traffic authorities control centre. This ensures that the
most up to date traffic information is always available. The control centre operation also
operates also have the ability to tell the drivers to turn off the autonomous drive if necessary.

6
 Fig: 2.4 G.P.S. and cloud services

2.5 Laser scanner

Laser scanning is a versatile tool that can be applied to a multitude of surveying challenges.
High definition 3D Laser Scanning allows for the effective and safe completion of surveys of
inaccessible, complex and irregularly shaped structures. The scanner can identity objects in
front of the car and ensure very high angle resolution. It can also distinguish between objects.
The unique laser sensor has a range of 150 meters for vehicles and covers a 140 degree field
view. This sensors bounce pulse of light off the surrounding. These are analysed to identify
lane markings and the edge of roads.

7
 Fig: 2.5 Laser scanners

2.6 Backup system

In addition of all these system, there is a backup system facilities is present as in the
aeroplanes. It is use full if any one component is not working properly while moving. On that
time it gives a backup system to that component and makes the car moving safely. This is
very essential to the autonomous car. For example: the probability of a brake system failure is
very small but a self-driving vehicles needs a second independent system to brake the vehicle
to a stop as it un likely that the driver will be prepared to press the brake pedal.

8
Fig: 2.6 Backup system

9
 Chapter -3
WORKING PRINCIPLE OF AUTOPILOT MODE

Fig: 3.1 working of self-driving car

3.1 Mapping and localization

Prior to making any navigation decisions, the vehicle must first build a map of its
environment and precisely localize itself within that map. The most frequently used sensors
for map building are laser rangefinders and cameras. A laser rangefinder scans the
environment using swaths of laser beams and calculates the distance to nearby objects by
measuring the time it takes for each laser beam to travel to the object and back. Where
video from camera is ideal for extracting scene colour, an advantage of laser rangefinders is
that depth information is readily available to the vehicle for building a three-dimensional

10
map. Because laser beams diverge as they travel through space, it is difficult to obtain
accurate distance readings greater than 100m away using most state-of-the-art laser
rangefinders, which limits the amount of reliable data that can be captured in the map. The
vehicle filters and discreteness data collected from each sensor and often aggregate the
information to create a comprehensive map, which can then be used for path planning.

For the vehicle to know where it is in relation to other objects in the map, it must use its
GPS, inertial navigation unit, and sensors to precisely localize itself. GPS estimates can be
off by many meters due to signal delays caused by changes in the atmosphere and
reflections off of buildings and surrounding terrain, and inertial navigation units accumulate
position errors overtime. Therefore localization algorithms will often incorporate map or
sensor data previously collected from the same location to reduce uncertainty. As the
vehicle moves, new positional information and sensor data are used to update the vehicle’s
internal map.

3.2 Obstacle Avoidance

A vehicle’s internal map includes the current and predicted location of all static (e.g.
buildings, traffic lights, stop signs) and moving (e.g. other vehicles and pedestrians)
obstacles in its vicinity. Obstacles are categorized depending on how well they match up
with a library of pre-determined shape and motion descriptors. The vehicle uses a
probabilistic model to track the predicted future path of moving objects based on its shape
and prior trajectory. For example, if a two-wheeled object is travelling at 40 mph versus 10
mph, it is most likely a motorcycle and not a bicycle and will get categorized as such by the
vehicle. This process allows the vehicle to make more intelligent decisions when
approaching crosswalks or busy intersections. The previous, current and predicted future
locations of all obstacles in the vehicle’s vicinity are incorporated into its internal map,
which the vehicle then uses to plan its path.

11
3.3 Path Planning

The goal of path planning is to use the information captured in the vehicle’s map to safely
direct the vehicle to its destination while avoiding obstacles and following the rules of the
road. Although manufacturers’ planning algorithms will be different based on their
navigation objectives and sensors used, the following describes a general path planning
algorithm which has been used on military ground vehicles.

This algorithm determines a rough long-range plan for the vehicle to follow while
continuously refining a short-range plan (e.g. change lanes, drive forward 10m, turn right).
It starts from a set of short-range paths that the vehicle would be dynamically capable of
completing given its speed, direction and angular position, and removes all those that would
either cross an obstacle or come too close to the predicted path of a moving one. For
example, a vehicle travelling at 50 mph would not be able to safely complete a right turn 5
meters ahead, therefore that path would be eliminated from the feasible set. Remaining
paths are evaluated based on safety, speed, and any time requirements. Once the best path
has been identified, a set of throttle, brake and steering commands, are passed on to the
vehicle’s on-board processors and actuators. Altogether, this process takes on average
50ms, although it can be longer or shorter depending on the amount of collected data,
available processing power, and complexity of the path planning algorithm. The process of
localization, mapping, obstacle detection, and path planning is repeated until the vehicle
reaches its destination.

3.4 The Road Ahead

Car manufacturers have made significant advances in the past decade towards making self-
driving cars a reality; however, there still remain a number of technological barriers that
manufacturers must overcome before self-driving vehicles are safe enough for road use.
GPS can be unreliable, computer vision systems have limitations to understanding road
scenes, and variable weather conditions can adversely affect the ability of on-board
processors to adequately identify or track moving objects. Self-driving vehicles have also
yet to demonstrate the same capability as human drivers in understanding and navigating
unstructured environments such as construction zones and accident areas.

12
These barriers though are not insurmountable. The amount of road and traffic data available
to these vehicles is increasing, newer range sensors are capturing more data, and the
algorithms for interpreting road scenes are evolving. The transition from human-operated
vehicles to fully self-driving cars will be gradual, with vehicles at first performing only a
subset of driving tasks such as parking and driving in stop-and-go traffic autonomously. As
the technology improves, more driving tasks can be reliably outsourced to the vehicle. This
car move in the road as the speed control board in the high ways as shown in fig.

Fig: 3.2 Scanning of speed control board

13
Fig: 3.3 components

14
 CONCLUSION
By implementing this Autopilot mode technology will surely reduce the occurrences of road
accidents by a considerable value. In the future, the wide acceptance of this technology will
create an “Accident free world”.

15
 REFERENCES
Websites
 http://www.cnet.com/news/a-ride-in-volvos-autonomous-car-how-the-next-step-
in-driver-safety-requires-replacing-the-driver/
 http://www.wired.com/2015/02/volvo-will-test-self-driving-cars-real-customers-
2017/
 http://www.theverge.com/2015/2/23/8091455/volvo-drive-me-self-driving-car-
test-2017
 http://www.SeminarsTopics.com
 https://www.youtube.com/watch?v=SyMGRqh8J2k
 https://www.google.co.in/search?q=volvo+self+driving+cars&biw=1366&bih=6
73&source=lnms&tbm=isch&sa=X&ei=5x5JVZLmOYTMmwW5hYDQAw&sqi
=2&ved=0CAgQ_AUoAw

16