Driverless cars and Helicopters – A Reality of the Future ?
Professor Sebastian Thrun, director of the Stanford Artificial Intelligence Laboratory, wants to cut the number of cars on planet earth by 50%.
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.
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.
Printable Version
· 
E-mail this to a friend
·
Leave a Comment
·
Permalink ·
(No Ratings Yet)
Loading ...
Top Related posts:
