3D Robotics

Cool on multiple levels. (Insert obligatory "This is how Skynet becomes self-aware!" joke). From hackaday:

 

3689418227?profile=original

Swarm robotics is really starting to produce some interesting results. This image is from the video embedded after the break that show a group of five robots creating a landing platform for a quadrotor helicopter. The four that actually make up the platform are not in contact with each other, but instead following commands from the leader. We’re impressed by the helicopter’s ability to target and land on the moving platform. Takeoff appears to be another issue, as the platform bots stop moving until the quadcopter is airborne again.

These robots are part of a Graduate project at Georgia Tech. [Ted Macdonald] has been working along with others to implement an organizational algorithm that guides the swarm. The method requires that the robots have an overview of the location of all others in the swarm. This is done with high-speed cameras like we’ve seen in other robotic control projects. But that doesn’t discourage us. If you already have a flying robot as part of the swarm, you might as well add a few more to serve as the eyes in the sky.

E-mail me when people leave their comments –

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

Join diydrones

Comments

  • 3D Robotics
    Ita: That's true for the front-facing camera, but not the down-facing camera. So in this case, the object recognition and tracking had to be done on a ground computer.
  • The AR.drone does onboard feature tracking and optical flow, which is most of the hard work needed to track a unique beacon. They may very well be doing some work on a ground computer, but it could possibly be done autonomously as well, which is really cool.

    (BTW - the AR.drone video stream is compressed, which means it's fairly hard to get quality feature info from it at the same level as the original uncompressed frames)

  • Developer

    Yeah it looks like they are also using Vicon camera system.. There seems to be bright red lights on roof level according some reflections on the glass pads. But really neat looking. A bit more computing power and few extra C-code lines and we have movable cities.

     

    We have come far in last 2 years so I wonder where we are after next 10 :)

  • 3D Robotics

    Chase, I presume it's object recognition/tracking done by a ground computer. It's not hard with the AR.Drone, which sends a video stream from its downward facing camera and is controlled via wifi. (Despite it's name, it's not an autonomous quad--it's all controlled via wifi)

  • How do they get the Quad-Copter to track the drone?

     

    We are working with some students at Georgia Tech and I was wondering if it is the same guys.

  • So cute! If a practical charging solution could be developed for a multirotor helicopter and its roving landing pad(s), it would greatly increase the scope of possible mission profiles for autonomous helicopters. Heck, forget land-based platforms... imagine a lighter-than-air airship that could support a swarm of quads in the air for long periods.

This reply was deleted.