Wednesday, 7 March 2012

Intelligent Helicopters

Scientist at STANFORD have developed an Artificial Intelligence System that enables Robotic Helicopters to teach themselves to fly difficult stunts by watching other helicopters perform the same maneuvers. It can result in development of autonomous helicopter than can perform a complete airshow of complex stunts on its own. It is one of most recent example of latest technology inventions .


This project is directed under Professor Andrew Ng who directed the research of their graduate students- Pieter Abbeel, Adam Coates, Timothy Hunter and Morgan Quigley. The stunts performed by such intelligent helicopters are far more difficult then any other computer controlled helicopters. They have developed various learning algorithms for these Helicopters which helps them to learn by themselves by just observing other expert helicopters.


The experiment was is an important demonstration of Apprenticeship Learning in which robots learn by observing an expert. Stanford's artificial intelligence system learned how to fly by "watching" the four-foot-long helicopters flown by expert radio control pilot Garett Oku.

This advanced helicopter can learn and perform actions such as traveling flips, rolls, loops with pirouettes, stall-turns with pirouettes, a knife-edge, an Immelmann, a slapper, an inverted tail slide and a hurricane, described as a "fast backward funnel."


Previous autonomous helicopters were able to fly stunts by simply replaying the exact finger movements of an expert pilot using the joy sticks on the helicopter's remote controller. But the major problem was that uncontrollable variables such as gusting winds due to which this is not very advance. To solve this problem, the researchers had Oku and other pilots fly entire airshow routines and every movement of the helicopter was recorded.

As Oku repeated a maneuver several times, the trajectory of the helicopter inevitably varied slightly with each flight. At this point, the learning algorithms created by Ng's team were able to discern the ideal trajectory the pilot was seeking. Thus the autonomous helicopter learned to fly the routine better and more consistently.


This advanced and intelligent contains some instrumentation mounted on the helicopter and some on the ground. These instrumentations monitor the position, direction, orientation, velocity, acceleration and spin of the helicopter in several dimensions. A ground-based computer crunches the data, makes quick calculations and beams new flight directions to the helicopter via radio 20 times per second. Some of the important instruments it uses areAccelerometersGyroscopes and Magnetometers.

These advance intelligent helicopters are a new generation of very robust, very reliable helicopter which can fly just as their human counterparts.

No comments:

Post a Comment