Google's Driverless Car report

Google Driverless Car
Dept. of ISE 2014-2015 Page 1
CHAPTER 1
INTRODUCTION
The system combines information gathered from Google street view with artificial
intelligence software that combines input from video camera inside the car, a LIDAR sensor on the
top of the vehicle, RADAR sensors on the front of the vehicle and a position sensor attached to one
of the rear wheel that helps to locate the car position on the map. At the same time some hardware
components are used in the car these are APPIANIX PCS, VELODYNE, SWITCH, TOPCON,
REAR MONITOR, COMPUTER, ROUTER, FAN, INVERTER and BATTERY along with some
software program is installed in it. By all the components combined together to operate the car
without the DRIVER. i.e., the car drives itself only.
Figure 1.1 Driverless Car
1.1 Overview
The overview of this project is to implement a driverless car is an autonomous vehicle that
can drive itself from one point to another without assistance from a driver. One of the main
impetuses behind the call for driverless cars is safety. An autonomous vehicle is fundamentally

defined as a passenger vehicle. An autonomous vehicle is also referred to as an autopilot, driverless
car, auto-drive car, or automated guided vehicle (AGV). Most prototypes that have been built so far
performed automatic steering that were based on sensing the painted lines in the road or magnetic
monorails embedded in the road.
1.2 Purpose
Purpose of the current work is to study and analyze the driverless car technology. This
mobility is usually taken for granted by most people and they realize that transportation forms the
basis of our civilization. The need for a more efficient, balanced and safer transportation system is
obvious. This need can be best met by the implementation of autonomous transportation systems.
1.3 Scope
Current work focuses on how to use the Future Car Technology That's On the Road Today. In
the future, automated system will help to avoid accidents and reduce congestion. The future vehicles
will be capable of determining the best route and warn each other about the conditions ahead. Many
companies and institutions working together in countless projects in order to implement the
intelligent vehicles and transportation networks of the future.

CHAPTER 2
LITERATURE SURVEY
A driverless car is an autonomous vehicle that can drive itself from one point to another
without assistance from a driver. Some believe that autonomous vehicles have the potential to
transform the transportation industry while virtually eliminating accidents and cleaning up the environment.
According to urban designer and futurist Michael E. Arth, driverless electricvehicles—in
conjunction with the increased use of virtual reality for work, travel, and pleasure— could reduce the
world's 800,000,000 vehicles to a fraction of that number within a few decades.
Arth claims that this would be possible if almost all private cars requiring drivers, which are
not in use and parked 90% of the time, would be traded for public self-driving taxis that would be in
near constant use.
This would also allow for getting the appropriate vehicle for the particular need —a bus could
come for a group of people, a limousine could come for a special night out, and a
Segway could come for a short trip down the street for one person. Children could be chauffeured in
supervised safety, DUIs would no longer exist, and 41,000 lives could be save death year in the U.S.
alone.
Driverless passenger car programs include the 800 million EC EUREKA Prometheus Project
on autonomous vehicles (1987-1995), the 2getthere passenger vehicles (using the FROG-navigation
technology) from the Netherlands, the ARGO research project from Italy, and the DARPA Grand
Challenge from the USA. For then wider application of artificial intelligence to automobiles smart
cars. Most autonomous vehicle projects made use of stock cars and modified them adding “smart”
hardware to create automated cars.
The advantage of using stock cars is the ease of obtaining the car through sponsors. The
stocks cars help convey the message autonomous vehicles are not science fiction anymore and these
systems can be implemented on normal cars.
“Google’s Driverless Car Draws Political Power: Internet Giant Hones Its Lobbying Skills in State
Capitols; Giving Test Drives to Lawmakers”, WSJ, 12 October 2012:
Overall, Google spent nearly $9 million in the first half of 2012 lobbying in Washington for a
wide variety of issues, including speaking to U.S. Department of Transportation officials and

lawmakers about autonomous vehicle technology, according to federal records, nearing the $9.68
million it spent on lobbying in all of 2011. It is unclear how much Google has spent in total on
lobbying state officials; the company doesn’t disclose such data.
In most states, autonomous vehicles are neither prohibited nor permitted-a key reason why
Google’s fleet of autonomous cars secretly drove more than 100,000 miles on the road before the
company announced the initiative in fall 2010. Last month, Mr. Brin said he expects self-driving cars
to be publicly available within five years.
In January 2011, Mr. Goldwater approached Ms. Dondero Loop and the Nevada assembly
transportation committee about proposing a bill to direct the state’s department of motor vehicles to
draft regulations around the self-driving vehicles. “We’re not saying, ‘Put this on the road,’” he said
he told the lawmakers. “We’re saying, ‘This is legitimate technology,’ and we’re letting the DMV
test it and certify it.” Following the Nevada bill’s passage, legislators from other states began
showing interest in similar legislation. So Google repeated its original recipe and added an extra
ingredient: giving lawmakers the chance to ride in one of its about a dozen self-driving cars…In
California, an autonomous-vehicle bill became law last month despite opposition from the Alliance
of Automobile Manufacturers, which includes 12 top auto makers such as GM, BMW and Toyota.
The group had approved of the Florida bill. Dan Gage, a spokesman for the group, said the California
legislation would allow companies and individuals to modify existing vehicles with self-driving
technology that could be faulty, and that auto makers wouldn’t be legally protected from resulting
lawsuits.
“They’re not all Google, and they could convert our vehicles in a manner not intended,”
Mr. Gage said. But Google helped push the bill through after spending about $140,000 over the past
year to lobby legislators and California agencies, according to public records.
As with California’s recently enacted law, Cheh’s [Washington D.C.] bill requires that a
licensed driver be present in the driver’s seat of these vehicles. While seemingly inconsequential, this
effectively outlaws one of the more promising functions of autonomous vehicle technology: allowing
disabled people to enjoy the personal mobility that most people take for granted. Google highlighted
this benefit when one of its driverless cars drove a legally blind man to a Taco Bell. Bizarrely,
Cheh’s bill also requires that autonomous vehicles operate only on alternative fuels.
While the Google Self-Driving Car may manifest itself as an eco-conscious Prius, self-
driving vehicle technology has nothing to do with hybrids, plug-in electrics or vehicles fueled with

natural gas. The technology does not depend on vehicle make or model, but Cheh is seeking to
mandate as much. That could delay the technology’s widespread adoption for no good
reason…Another flaw in Cheh’s bill is that it would impose a special tax on drivers of autonomous
vehicles. Instead of paying fuel taxes, “Owners of autonomous vehicles shall pay a vehicle-miles
travelled (VMT) fee of 1.875 cents per mile.” Administrative details aside, a VMT tax would require
drivers to install a recording device to be periodically audited by the government. There may be good
reasons to replace fuel taxes with VMT fees, but greatly restricting the use of a potentially
revolutionary new technology by singling it out for a new tax system would be a mistake.
The State of Nevada has adopted one policy approach to dealing with these technical and policy
issues. At the urging of Google, a new Nevada law directs the Nevada Department of Motor Vehicles
(NDMV) to issue regulations for the testing and possible licensing of autonomous vehicles and for
licensing the owners/drivers of these vehicles. There is also a similar law being proposed in
California with details not covered by Nevada AB 511. This paper evaluates the strengths and
weaknesses of the Nevada and California approaches
Another problem posed by the non-computer world is that human drivers frequently bend the rules
by rolling through stop signs and driving above speed limits. How does a polite and law-abiding
robot vehicle act in these situations? To solve this problem, the Google Car can be programmed for
different driving personalities, mirroring the current conditions. On one end, it would be cautious,
being more likely to yield to another car and strictly following the laws on the road. At the other end
of the spectrum, the robocar would be aggressive, where it is more likely to go first at the stop sign.
When going through a four-way intersection, for example, it yields to other vehicles based on road
rules; but if other cars don’t reciprocate, it advances a bit to show to the other drivers its intention.
However, there is a time period between a problem being diagnosed and the car being fixed. In
theory, one would disable the vehicle remotely and only start it back up when the problem is fixed.
However in reality, this would be extremely disruptive to a person’s life as they would have to tow
their vehicle to the nearest mechanic or autonomous vehicle equivalent to solve the issue. Google has
not developed the technology to approach this problem, instead relying on the human driver to take
control of the vehicle if there is ever a problem in their test vehicles this can create particularly tricky
situations such as deciding whether the police should have the right to pull over autonomous
vehicles, a question yet to be answered. Even the chief counsel of the National Highway Traffic
Safety Administration admits that the federal government does not have enough information to
determine how to regulate driverless technologies.

CHAPTER 3
HISTORY
The Sebastian Thrun was invented the Google driverless car. He was director of the Stanford
Artificial Intelligence laboratory. Sebastian friends were killed in car accident, so that he decided
there should not be any accidents on the road by car. By that decision only the Google Driverless car
was invented.
Figure 1.1 Sebastian Thrun
”Our goal is to help prevent traffic accidents, free up people’s time and reduce carbon
emission by fundamentally changing car use”-Sebastian Thrun. The Google Driverless car was tested
in the year 2010; Google has tested several vehicles equipped with the system, driving 1,609
kilometers (1,000 mi) without any human intervention, in addition to 225,308 kilometers (140,000
mi) with occasional human intervention. Google expects that the increased accuracy of its automated
driving system could help reduce the number of traffic-related injuries and deaths, while using
energy and space on roadways more efficiently. It was introduced in oct-2010 and it becomes legal
in Nevada at June 2011, August 2012- Accident.
The project team has equipped a test fleet of at least eight vehicles.. The car has traversed
San Francisco's Lombard Street, famed for its steep hairpin turns and through city traffic. The
vehicles have driven over the Golden Gate Bridge and on the Pacific Coast Highway, and have
circled Lake Tahoe. The system drives at the speed limit it has stored on its maps and maintains its
distance from other vehicles using its system of sensors. The system provides an override that allows
a human driver to take control of the car by stepping on the brake or turning the wheel, similar to
cruise control systems already in cars.

CHAPTER 4
COMPONENTS
4.1 LIDAR SENSOR
Figure 4.1 Lidar sensor
The LIDAR (Light detection and Ranging) sensor is a scanner. It will rotate in the circle. It is
fixed on the top of the car. In the scanner contains the 64 lasers that are send surroundings of the car
through the air. These the laser is hits objects around the car and again comes back to it. By these
known How far that objects are from the car and also it calculates the time to reach that object. These
are can see in monitor in a 3D object with the map. The monitor is fixed in front seat. “The heart of
the system generates a detailed 3D map of environment (velodyne 64- beam laser). The map
accessed from the GPRS connection.
Figure 4.1 Road

For example , that a person was crossing the road, the LIDAR sensor will reorganized by
sending the lasers in to the air as waves and waves are disturbed these it identify as some object was
crossing and by these the car will be slow down.
4.2 RADAR SENSOR
Figure 4.2 Radar Sensor
The three RADAR sensors were fixed in front of the bumper and one in the rear bumper.
These will measures the distance to various obstacles and allow the system to reduce the speed of the
car. The back side of sensor will locates the position of the car on the map.
Figure 4.2 Front and Back side of the road
For example, when the car was travelling on the road then RADAR sensor was projected on
road from front and back side of the car.
4.3 VIDEO CAMERA
The video camera was fixed near the rear view mirror. That will detect traffic lights and any
moving objects front of the car. For example if any vehicle or traffic detected then the car will be
slow down automatically, these all will be done by the artificial intelligence software only.

Figure 4.3 Video Camera
By that the computer will recognize moving obstacles like pedestrians and bicyclists. Its position on
the map. The position of the car can be seen on the monitor.
4.4 POSITION ESTIMATOR
Figure 4.4 Position Estimator
A sensor mounted on the left rear wheel. By these sensor only measures small movements made
by the car and helps to accurately locate its position on the map. The position of the car can be seen
on the monitor.

CHAPTER 5
WORKING
5.1 How does it Work…?
The “driver” sets a destination. The car’s software calculates a route and starts the car on its
way. A rotating, roof-mounted LIDAR (Light Detection and Ranging - a technology similar to radar)
sensor monitors a 60-meter range around the car and creates a dynamic 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 3-D map. Radar systems in the front and rear bumpers calculate distances to obstacles.
Artificial intelligence (AI) software in the car is connected to all the sensors and has input
from Google Street View and video cameras inside the car.
t their self-driving cars approved by the DMV.
-driving cars.
iver is suddenly needed.
Figure 5.1 Working

CHAPTER 6
ADVANTAGES & DISADVANTAGES
6.1 APPLICATIONS
 The greater precision of an automatic system could improve traffic flow.
 It would eliminate accidents caused by driver error.
 Increasing roadway capacity by reducing the distances between cars.
 The current location of vehicle can be determined using global positioning system (G.P.S).
 Dramatically increases highway capacity and reduce or eliminate traffic jams.
 Time will be saved in the traffic.
 The car itself park at the parking area.
 No license will be needed for driver because it is self-driver.
6.2 LIMITATIONS
 If the vehicle is using internet which is have less security then from the hackers point of view
in some cases the vehicle can be switched off on the road(in rare cases).
 Hackers can change the rout which is plotted in the system (in rare cases).
 In case of failure of main sensor and backup sensors the vehicle can create a chance of
accident.
 The cost of car is high.
 By coming Google driverless car into the market so many taxi drivers can lose their jobs.

CHAPTER 7
PREDICTIONS ABOUT THE FUTURE OF DRIVERLESS
CAR
In a few short decades, new automotive technology might eliminate the need for drivers to
wait at red lights. It may eliminate the need for steering wheels. It may even eliminate the need for
drivers to carry licenses. Those are some of the bold predictions coming from members of the
Institute of Electrical and Electronics Engineers, which predicts that 3 of 4 cars on the road will be
driverless by 2040.
"Over the next 28 years, use of more automated technologies will spark a snowball effect of
acceptance and driverless vehicles will dominate the road," says Jeffrey Miller, an IEEE member and
associate professor at the University of Alaska Anchorage.
He notes that such technologies are already seeping into the mainstream market, including
parallel parking assist, automatic braking and even the seemingly antiquated cruise control.

Handing over the entire scope of driving duties is another matter, but already, programs such
as Google's driverless car have completed 300,000 miles of accident-free driving and California,
Nevada and Florida have passed laws that allow autonomous vehicles on their roads.
Other predictions about the future of driverless cars from the IEEE:
No drivers' licenses will be needed. Since people of all ages and abilities can use these
vehicles, no specific driver certifications are needed. "People do not need a license to sit on a train or
bus," said Dr. Azim Eskandarian, director of the Center for Intelligent Systems Research. " ... So
there will not be any special requirements for drivers or occupants to use the vehicle as a form of
transportation."
Car-sharing programs will become more main stream. They'll take you to your destination
and then be readied for another occupant. "Since cars today are parked for more than 90 percent of
their lifetime, shred car services will promote more continuous movement, garner more efficient
operation and use less gas," said Dr. Alberto Broggi, IEEE senior member.
Infrastructure won't be prohibitive. Existing roads can already handle the advent of
autonomous vehicles. No major overhaul is needed. Broggi directed a project in 2010 that led two
driverless cars to complete an 8,000-mile trip between Italy and Shanghai.
Say farewell to red lights and stop signs. Once cars are driverless, intersections will be
equipped with sensors, cameras and radar that controls traffic flow. That will not only end collisions,
but promote fuel-efficient flow of traffic.
High-Occupancy Vehicle lanes might be replaced by Driverless Car lanes, which would not
only promote autonomous travel, but help driverless cars travel both more safely and faster, reaching
speeds of perhaps 100 mph by 2040.

CHAPTER 8
CONCLUSION
It is so useful for the humans when driving the car. By the Google driverless car can avoid
the accidents on the roads and can reduce the traffic time at the traffic signals, can prevent the
drinking driving on the roads. The car itself can driver at night times also. At the same time so many
taxi drivers can lose their jobs.
The driver less car’s technologies improves vehicles stability helps to minimize loss of control.
Driver less cars are designed to minimize accidents by addressing the main causes of collisions:
 Driving error
 Distraction
 Drowsiness

CHAPTER 9
REFERENCES
 [1] Chea, T. California governor signs driverless cars bill [Internet]. The Associated Press; 2012 Sep 26 [cited
2013 Feb 2]. Available from:http://news.yahoo.com/california-governor-signs-driverless-cars-bill-225332278–
finance.html
 [2] United States Department of Energy. 2005 Compare Side by Side: Fuel Economy [Internet]. Environmental
Protection Agency; 2005 [cited 2013 March 2]. Available
from: http://www.fueleconomy.gov/feg/Find.do?action=sbs&id=20934
 [3] United States Department of Energy. 2013 Most and Least Efficient Cars [Internet]. Environmental
Protection Agency; 2013 April 11 [cited 2013 March 1]. Available
from: http://www.fueleconomy.gov/feg/best/bestworstNF.shtml
 [4] Newman, G. A Future Filled with Driverless Cars [Internet]. Insurance Journal; 2013 Feb 11 [cited 2013
Mar 2]. Available from:http://www.insurancejournal.com/magazines/features/2013/02/11/280151.htm
 [5] Odest Jenkins. 2013. March 26.
 [6] Bertam, M., Jenkins, O., & Littman, M. Interviewed by Peseri, Alexandra. 2013. April 11.
 [7] Use patterns among early adopters of adaptive cruise
control.http://www.ncbi.nlm.nih.gov/pubmed/23156618
 [8] Marcus, G. Moral Machines [Internet]. The New Yorker; 2012 Nov 27[cited 2013 April 15] 2012 Nov 27.
Available from:http://www.newyorker.com/online/blogs/newsdesk/2012/11/google-driverless-car-morality.html
 [9] Wikipedia. Ernst Dickmanns [Internet]. Wikipedia; 2013 Mar 13 [cited 2013 April 11]. Available
from: http://en.wikipedia.org/wiki/Ernst_Dickmanns
 [10] Mariacher, E. 3 driverless cars trends in 2012 [Internet]. Blogger; 2013. Jan 2 [cited 2013 April 13].
Available from: http://driverless-cars.blogspot.com/2013/01/3-driverless-cars-trends-in-
2012.html#.UWoAenCrJ0o

Google's Driverless Car report

Recommandé

Recommandé

Contenu connexe

Tendances

Tendances (20)

En vedette

En vedette (6)

Similaire à Google's Driverless Car report

Similaire à Google's Driverless Car report (20)

Plus de Manasa Chowdary

Plus de Manasa Chowdary (7)

Dernier

Dernier (20)

Google's Driverless Car report