Stanford's autonomous helicopters teach themselves how to fly

Stanford computer scientists 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. The result is an autonomous helicopter than can perform a complete airshow of complex tricks on its own.

Much more in the full article here.

Views: 297

Comment by Scott James on September 2, 2008 at 3:41am
It's amazing what you can get out of a Basic Stamp these days! :)
Comment by Nullified on September 2, 2008 at 4:58am
Very impressive! Although I don't think they used a Basic Stamp for this, but they did mention that some of the calculations were done on the ground and commands transmitted wirelessly at 20Hz to the helicopter.
Comment by ionut on September 2, 2008 at 1:04pm
Nice.I presume the morons that pay tuition there support all these big boys toys :)

3D Robotics
Comment by Chris Anderson on September 2, 2008 at 1:35pm
Not quite. It's DARPA funded. Papers and more here.
Comment by Scott James on September 2, 2008 at 11:17pm
The Basic stamp comment was a joke! ;-)
Comment by Nullified on September 3, 2008 at 8:40am
Ok, fair enough :) It would be even more impressive (and funny) if they did actually use Basic stamps...
Comment by ionut on September 3, 2008 at 8:47am
I curious if anybody here will try something similar.Did they just used the prerecorded transmiter comands and create a statistical model ,or they also include the onboard sensors(gyro,GPS) ?
Comment by Howard Gordon on September 3, 2008 at 11:07am
They are using onboard inertial sensors. The news stories are somewhat misleading in describing the training process as "watching". There's no vision system component - it's all done by capturing the experienced operator's commands and correlating this with feedback from onboard sensors for each specific maneuver. I'm not minimizing the accomplishment - they have tackled a very complicated control problem with impressive results. However, it is unclear how far along in complete dynamic control, e.g. plotting a flight path using a 3D simulation model and feeding that directly into vehicle control, though certainly that has to be the ultimate goal.


You need to be a member of DIY Drones to add comments!

Join DIY Drones


Season Two of the Trust Time Trial (T3) Contest 
A list of all T3 contests is here. The current round, the Vertical Horizontal one, is here

© 2019   Created by Chris Anderson.   Powered by

Badges  |  Report an Issue  |  Terms of Service