Google self-driving car coming around the corner

May 14, 2014
Google's Lexus RX 450H Self Driving Car is seen parked on Pennsylvania Ave. in Washington, DC, on April 23, 2014

A white Lexus cruised along a road near the Google campus, braking for pedestrians and scooting over in its lane to give bicyclists ample space.

The car eased into a turn lane, waited for a green light and a break in traffic, then continued on its way in the Silicon Valley city of Mountain View.

It even avoided stopping on train tracks.

But there was nobody holding the wheel. What looked like the work of a conscientious driver was a Google car making all the moves—with an AFP reporter in the back seat.

Google used machine learning to teach cars how people drive and, from there, to anticipate what motorists in surrounding traffic are likely to do.

Computer-fast reflexes

"Computers have really good reaction times. They don't get distracted, drowsy, fall asleep, and they don't drive drunk," Google software team lead Dmitri Dolgov told reporters getting an intimate look at prototypes at the Computer History Museum.

"They don't need to stop messing with the radio to see what is happening, or even take time to move a foot from the gas pedal to the brake."

The bustling street crowd paid little heed to the self-driving car, which sported a whirling gadget on top about the size and shape of a large coffee can.

The roof-top device used radar and lasers to track everything around it.

A camera peeking out from the Lexus front grill watched what was ahead.

Data is processed by onboard computers programmed to simulate what a careful driver would do, but at super-human speeds. And, naturally, the Google autonomous car was connected to the Internet.

A "Googler" from the technology titan's test driving team had a laptop computer that showed what the car "saw"—everything from cyclists and traffic signals to orange cones and painted lines in the street.

Google's Lexus RX 450H Self Driving Car, seen parked on Pennsylvania Ave. in Washington, DC, on April 23, 2014

Another Googler was in the driver's seat, ready to take over in the unlikely chance a human was needed to make a driving decision.

A red button could be hit to grab control from the computer. A tap of the brake would do the same.

Real driving a drag

Development of the self-driving car began five years ago, part of a special project headed by Google co-founder Sergey Brin.

"If you are in a car commercial, that is driving we enjoy," said project director Chris Urmson.

"If you are commuting to work, that is not fun."

This video is not supported by your browser at this time.

While most people have cars that boast seating for four or more people and that can achieve racing speeds, statistics show that much road time is clocked by solo drivers going closer to 30 miles (48 kilometers) per hour.

Google cars navigate using detailed digital maps showing what streets are supposed to look like, then concentrate processing power on assessing real-world variables such as traffic.

The cars can't drive places where Google hasn't mapped roadways down to implied speed limits, elevations of traffic signals, and curb heights, according to mapping team lead Andrew Chatham.

"It tells the car what the world looks like empty, then the job of the software is to figure out what is going on," Chatham said.

Google's Lexus RX 450H Self Driving Car, seen parked on Pennsylvania Ave. in Washington, DC, on April 23, 2014

Have no fear

Prototype Google cars have driven more than 100,000 miles on public roads, always with someone ready to take the wheel.

There have been two accidents while cars were on auto-pilot. Both times, vehicles were rear-ended while stopped at , according to Urmson.

"We are at the point where we are really convinced we have cracked this and can make it work," Urmson said of self-driving cars being trusted on roads.

Urmson sidestepped predicting when Google self-driving cars might hit the market, but said he is determined to make it happen by the time his six-year-old son reaches driving age.

Brin has publicly stated the even more ambitious goal of having the cars ready less than four years from now.

A panel of urban development and transportation specialists that took part in the event billed the self-driving car as a quantum leap in safety that could prevent many of the approximately 33,000 roadway deaths in the US each year.

Instead of owning cars, people could summon them when needed and be chauffeured places while they text, chat on phones, put on make-up or do other distracting tasks some motorists attempt while driving.

"This is not a science project, this is reality," said former General Motors vice president Larry Burns.

"It is something you need to embrace; there is nothing to fear."

Explore further: Google: Driverless cars are mastering city streets (Update)

add to favorites email to friend print save as pdf

Related Stories

With human behind wheel, Google's self-driving car crashes

Aug 07, 2011

Google Inc.'s quest to popularize cars that drive themselves seemed to hit a roadblock Friday when news emerged that one of the automated vehicles was in an accident. But in an ironic twist, the company is saying that the ...

Sweden joins race for self-driving cars

Dec 02, 2013

A hundred self-driving Volvo cars will roll onto public roads in and around the Swedish city of Gothenburg in 2017, the Chinese-owned car maker said Monday.

Recommended for you

Cadillac CT6 will get streaming video mirror

3 hours ago

Cadillac said Thursday it will add high resolution streaming video to the function of a rearview mirror, so that the driver's vision and safety can be enhanced. The technology will debut on the 2016 Cadillac ...

Poll: Americans skeptical of commercial drones (Update)

Dec 19, 2014

Americans broadly back tight regulations on commercial drone operators, according to a new Associated Press-GfK poll, as concerns about privacy and safety override the potential benefits of the heralded drone ...

Cheaper, more powerful VR system for engineers

Dec 17, 2014

It's like a scene from a gamer's wildest dreams: 12 high-definition, 55-inch 3D televisions all connected to a computer capable of supporting high-end, graphics-intensive gaming.

Nokia HERE prepares maps for autonomous cars

Dec 17, 2014

Autonomous cars will need a new kind of map, a crucial element that until now has been given a back seat to the more popularly discussed issues of sensors and legal questions. Senior Writer Greg Miller in ...

Dutch launch 'intelligent bicycle' that warns of danger

Dec 15, 2014

The Netherlands on Monday launched its first-ever "intelligent bicycle", fitted with an array of electronic devices to help bring down the high accident rate among elderly cyclists in the bicycle-mad country.

User comments : 3

Adjust slider to filter visible comments by rank

Display comments: newest first

alfie_null
5 / 5 (3) May 14, 2014
I wonder what Google's plans are for making this technology available to end users? Will they work with car manufacturers? Do it themselves? I'm also curious as to the expected cost.
indio007
3.9 / 5 (7) May 14, 2014
This is the gov't worse nightmare.
Do you realize how much revenue is made in the business of the "incompetent driver"?.
Do you know how many people get arrested due to a traffic stop?
This will crumble the DMV.
It's already been ruled by the courts that traffic laws can not be force the purpose of making revenue only safety and the general welfare..
Computerized cars are going to remove safety and general welfare as an excuse to rob us.
Zera
2 / 5 (3) May 14, 2014
My prediction is this will form part of "Visual" recognition, coupling to "Auditory", obviously "Tactile" (i.e. keyboards), package that we the public will see within the next 5-10 years. Google is quite obviously building hard a.i. with potential for semi-soft balancing act between those specific expressions of machine learning.

Homes will form part of networks, with cars/balloons/satellites/etc, forming part of the moving network to mesh those fuzzy to reach spots.

The relationship humanity has with machines has already re-defined humanity rapidly over the last 100 years, see that timeframe start to shrink.

2nd prediction - in the next 4 years get ready for "google assistant" the phone/computer software code that remembers everything about you, learns from your emails and phone calls, knows the quickest way, physically trains you, diets you, loves you ;) , suggests music for you, and that's as far as i will go tonight.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.