Stanford's 'autonomous' helicopters teach themselves to fly
Scratch another one off the list of "things only humans can do". This is not even a full artificial "intelligence"; it just learns how to compute data and algorithyms to fly a remote control helicopter, beaming instructions by radio signal 20 times a second. However, that doesn't mean it's any less fun, or that there is any less need for people to buy remote control helicopters and fly them for fun! It does mean these things will save lives fighting fires and searching for land mines- in addition to whatever other military and crowd control scenarios are dreamed up that aren't "fit to print".
Computer Science Professor Andrew Ng (center) and his graduate students Pieter Abbeel (left) and Adam Coates have developed an artificial intelligence system that enables these helicopters to perform difficult aerobatic stunts on the their own. The “autonomous” helicopters teach themselves to fly by watching the maneuvers of a radio control helicopter flown by a human pilot.
There is interest in using autonomous helicopters to search for land mines in war-torn areas or to map out the hot spots of California wildfires in real time, allowing firefighters to quickly move toward or away from them. Firefighters now must often act on information that is several hours old, Abbeel said.