Autonomous Quadrotor Flight Based On Google's Project Tango

Now here we go! Project Tango and UPenn whats not to like. Its always interesting to note that the Asctec machines are in nearly every cutting edge video. I always call that out because they are such nice people that just carry on in a confused market.

Parrot scored with the product placement there ;-)

Views: 1548

Comment by Thomas Robinson on May 23, 2014 at 12:24am

This is insane! For those that aren't familiar with Project Tango, here is a video on YouTube: https://www.youtube.com/watch?v=Qe10ExwzCqk

Comment by Jack Crossfire on May 23, 2014 at 3:07am

Let's see it facing a blank wall.  At least it wasn't called called project "Kinect in a phone".


Moderator
Comment by Gary Mortimer on May 23, 2014 at 3:26am

It is a little more than that is it not Jack?? A better Kinect maybe

Comment by Sergios Zafeiropoulos on May 23, 2014 at 7:23am
I think they are just using its internal sensors gyros etc and not the camera . Anyway with its capabilities it would make excellent indoors autonomous navigation
Comment by Cliff-E on May 24, 2014 at 12:48pm

Looks like a mix of color thresholding and camera calibration techniques to obtain positioning (hence the specific objects in the camera's view)--that seems to be the rage in research nowadays (vision based techniques different from SLAM).

Comment by Kresi on May 26, 2014 at 5:14am

btw, I was following Johnny Lee for six years now. Here you can see, how it all begun before tango: http://johnnylee.net/projects/wii/

@Gary Mortimer : can you write a little more about your experience with Asctec machines?


MR60
Comment by Hugues on May 26, 2014 at 10:44pm

The Asctec drone are described in details on their web site. What I find amazing is the AUW of 2.2kg for a V shape octo carrying max 1kg of payload: that means an octo weighing 1kg !! Impressive flight wind resistance results from such little weight (two times what APM can do).

They also developed two interesting AP features we do not have on APM copter: ability to keep position and orientation whatever the local magnetic field is (APM is very weak on this and causes lots of FlyAway's by loosing sense of direction) and sensors data deviation analysis (safety feature that warns the pilot as soon as a sensor's data deviates too much from a baseline). 

Maybe things to take in pixhawk fc future releases to improve safety?

Comment

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

Join DIY Drones

© 2019   Created by Chris Anderson.   Powered by

Badges  |  Report an Issue  |  Terms of Service