|
Stanford
University researchers have been experimenting with designing a
robotic radio-controlled model helicopter that can fly autonomously,
as described in this LiveScience posting — which has a link
to video of the helicopter in flight. The
researchers' approach is to use an artificial intelligence technique
called "apprenticeship learning," in which the prototype
automated control system first "watches" an expert human operator
fly the helicopter through various aerobatic maneuvers, while it
compares the control inputs to the resulting motions of the aircraft.
A number of accelerometers, gyroscopes, and magnetometers help the
control system monitor helicopter position and acceleration in three
dimensions.
The researchers have published a paper that discusses the control issues addressed.
What do you think? Would
such apprenticeship learning have application in factory automation?
The preceding article is a "sneak peek" from Data Acquisition, a newsletter from GlobalSpec. To stay up-to-date and informed on industry trends, products, and technologies, subscribe to Data Acquisition today.
|