3D Robotics

Voice controlled heli UAV

From BotJunkie:

"This little helicopter is able to understand you when you tell it what to do. No pushing buttons, no using special commands, you just tell it where you want it to go and (eventually) it goes. Of course, I’m sure it required a bit of work to define where “door” and “elevator” and “window” are, but it’s a much more intuitive way to control a UAV that works when your hands are full, when you’re stressed (think military), or simply when you have no idea now to control a UAV.

I don’t have much in the way of other details on this project, besides the fact that it probably comes from the Robust Robotics Group at MIT, and possibly from someone who lives in this dorm. How do I know? Well, one of the research goals of the RRG is “to build social robots that can quickly learn what people want without being annoying or intrusive,” and this video is on the same YouTube channel. ‘Nuff said.

[ MIT Robust Robotics Group ]"

E-mail me when people leave their comments –

You need to be a member of diydrones to add comments!

Join diydrones


  • Here's a tech paper on it http://tkollar.csail.mit.edu/TK/Publications/kollar10.pdf

    Although this level of sophistication is probably too much for the typical hobbyist, I'll bet it wouldn't be that difficult to get a groundstation to interpret much simpler commands (e.g. "left", stop" "climb" etc) to command a telemetry equipped UAV

    - Roy
  • I think a premade voice processor was used. You can see the iphone showing the text, so it seems it does all the processing a transmits it to the copter.

    How do they do the map thing in the lower right corner?
  • Very nice... It looks to me like a very nice combination of several different technologies like voice recognition, natural language processing, navigation in 3d environment, indoor positioning and autonomous flight. The commands given to the machine are simple navigation commands, like goto to known location, or relative movements. The flight plan is "basically" a sequential processing of those multiple commands.

    So i would say it works like this:
    -The speech recognition translates the voice input into text.
    -the natural language processing system translates the text into a flight plan.
    -the 3d navigation system defines the optimal path
    - the quad starts to execute the flight plan, adjustments are made to the flight plan to avoid moving obstacles like people until the drone reaches its targeted location.

    easy, right? no not at all... great work!
  • "fly to the kitchen and bring me a sandwich"
  • Not that impressive really. Just connecting two technologies and the end result is a lot of latency when compared with a joystick/tx or even keyboard. For what they are aiming for maybe that is ok though...
  • Sort of going out of his way to get iPhone points. Shouldn't there be a microphone on the aircraft with him talking to the aircraft?
  • Thanks for the link Chris! Flight arena and quadrotor autonomous triple flips at 1300deg/s are impressive, other project are very interesting, too.
  • I wish they had robot quadrotor projects back when I was living in that dorm...
  • Nice vide Chris !
    Nice videos Bosak !, amazing !
  • T3
    Not exactly related but close:
    I have seen a music-controlled research quadcopter at a polytechnic institute at Zurich.
    It was oscillating in sync with music from typical mp3 player fed to the machine.
This reply was deleted.