Other related sites

Page last updated at 11:54 GMT, Thursday, 10 September 2009 12:54 UK

Cutting traffic with driverless cars

By Ian Hardy
Reporter, BBC Click

Name almost any Californian big time tech company - such as Google, Yahoo or Sun - and the chances are good that its roots are in Stanford University in Silicon Valley.

A driverless car
The cars have no human driver and no remote control system - everything from sensors to navigation is handled by an on board computer

Every year Stanford admits about 15,000 students - just over half are postgraduates - and some of the brightest minds in the world.

A few will become household names in a decade or less. And it all comes down to the professors who challenge, push, question and encourage new ideas.

For all its cutting edge technology, Stanford University is also steeped in history.

It opened in 1891 and the grounds were designed by Frederick Law Olmsted - the same man who planned New York's Central Park.

But despite that long history, many of the academics and researchers at the University have their eyes set firmly on the future.

Driverless cars

For instance, Professor Sebastian Thrun, director of the Stanford Artificial Intelligence Laboratory, wants to cut the number of cars on planet earth by 50%.

Professor Sebastian Thrun
Professor Thrun is a leader in the field of driverless cars

He said: "Today we have about 600 million cars worldwide. It turns out almost every car is parked at any point in time.

"It's a huge waste of money and resources to do so - we use cars about 3% of the time.

"Just imagine in the future you pull up your smart phone and you say, (using GPS) I need a car now. And around the corner comes your car."

Professor Thrun is a leader in the field of driverless cars and has built two robotic vehicles called Stanley and Junior.

The cars have no human driver and no remote control system - everything from sensors to navigation is handled by an onboard computer.

They were both entered into the DARPA Grand Challenge - a race for autonomous vehicles. Stanley won in 2004 and Junior took second place in 2007.

But the ultimate goal is to create a world where self-aware vehicles can drive passengers around without hitting pedestrians or bumping into other vehicles.

"To be able to understand the environment as deep as humans do is the holy grail of artificial intelligence.

"It's a huge amount of work to make computers understand what is the behaviour of the two people on the right, both waiting at an intersection - will they walk or not? It is a really hard question."

Perfect missions

The next step is a self-piloted aircraft. Researchers at Stanford are trying to programme helicopters to fly perfect missions every time including loops.

Scientist with small helicopter
Researchers are looking to develop an aircraft that doesn't need a pilot

Imagine, for example, a search and rescue chopper that can descend into a narrow canyon countless times without its rotors ever touching the edges.

Andrew Ng, an associate professor in the Computer Science Department, said it would be very difficult to write software to make a helicopter carry out stunts in the air.

Instead, researchers asked an expert human pilot to demonstrate the stunts. The computer learned from the demonstrations how to fly by itself.

It is called apprenticeship learning - the computer figures out what the human pilot is trying to do and then uses algorithms to correct or perfect the manoeuvre.

The software is also able to take into account random events like updraughts.

Professor Ng said: "The accelerometers of the helicopter will feel the force of the wind pushing the helicopter aside and what the helicopter has learned to do is how to adjust the controls to move itself back onto the desired flight path."



Print Sponsor


RELATED INTERNET LINKS
The BBC is not responsible for the content of external internet sites


FEATURES, VIEWS, ANALYSIS
Has China's housing bubble burst?
How the world's oldest clove tree defied an empire
Why Royal Ballet principal Sergei Polunin quit

BBC navigation

BBC © 2013 The BBC is not responsible for the content of external sites. Read more.

This page is best viewed in an up-to-date web browser with style sheets (CSS) enabled. While you will be able to view the content of this page in your current browser, you will not be able to get the full visual experience. Please consider upgrading your browser software or enabling style sheets (CSS) if you are able to do so.

Americas Africa Europe Middle East South Asia Asia Pacific