Robotic helicopters teach themselves

Stanford University Professor Andrew Ng, who led the project, said the achievement is an important demonstration of apprenticeship learning, in which robots use an artificial intelligence system to learn by observing an expert, rather than by having software engineers write instructions.

Stanford's artificial intelligence system learned how to fly by watching a four-foot-long helicopter flown by expert radio control pilot Garett Oku.

While it might seem an autonomous helicopter could fly stunts by simply replaying the exact finger movements of an expert pilot using joy sticks on a remote controller, Ng said that's not possible due to many uncontrollable variables such as gusting winds.

So the researchers had Oku and other pilots fly entire air show routines while every movement of the helicopter was recorded. As each maneuver was repeated, the helicopter's trajectory inevitably varied slightly with each flight. But the learning algorithms created by Ng's team were able to discern the ideal trajectory the pilot was seeking.

Ng said there is interest in using autonomous helicopters for such duties as searching for land mines or mapping wildfire hot spots in real time.

(UPI)

Russian spacecraft landed on moon hours before Americans

Mitchell Johnson - Baseball\'s loss and cricket\'s gain

Recession-hit Gujarat auto part makers hope for budget concessions

Punter gets rare 20p worth 7K pounds in change for pint!

UK binmen refuse to empty bins three inches out of exact position!

British immigration officials pass Pak visas in just 11 minutes

Here\'s how Oprah, Miley, Britney, Paris, Macca, \'died\' in hoax reports