Forgot your password?
typodupeerror
AI United Kingdom Build Technology

Intelligent Autonomous Flying Robots Learn and Map Environment As They Fly 37

Posted by timothy
from the learning-as-they-go dept.
An anonymous reader writes with this story about a machine-learning project out of the UK's University of Sheffield: Using simple drones the researchers have created automatic-control software that enables the "flying robot" to learn about its surroundings using a camera and an array of sensors. The robot starts with no information about its environment and the objects within it. But by overlaying different frames from the camera and selecting key reference points within the scene, it builds up a 3D map of the world around it. Other sensors pick up barometric and ultrasonic data, which give the robot additional clues about its environment. All this information is fed into autopilot software to allow the robot to navigate safely, but also to learn about the objects nearby and navigate to specific items.
This discussion has been archived. No new comments can be posted.

Intelligent Autonomous Flying Robots Learn and Map Environment As They Fly

Comments Filter:
  • by Anonymous Coward

    It would be nice if these were fed back in real time to a remote monitor. Maybe a 21st century canary in a coal mine? Applications for search and rescue, scouting real time optimal traffic routes for police / fire / paramedics.

  • Cool project, but the article/video is short on detail. I'd like to know more about the way this robot is actually learning. Is it a neural network? How does it know an oscilloscope is an oscilloscope? Does it use binocular vision to recognize distance? Ultrasound? Both? What type of computing hardware is on board? For that matter, what type of quadracoptor is this? And more importantly where can I get one?

    • by Anonymous Coward

      So the robot starts with no information about its environment and the objects within it. By overlaying different frames from the camera and selecting key reference points within the scene, it builds up the 3D map of the world around it. Barometric and ultrasonic sensors give the robot additional clues about its environment. All this information is fed into autopilot software to allow the robot to navigate safely, but also to learn about the objects nearby and navigate to specific items.

      Instead of a neural n

  • by Anonymous Coward

    Carnegie Mellon folks developed the SLAMM algorithm (and variants of if) some years back to do live mapping on their quadrotors. It has been used by almost everybody who is doing autonomous flying robots. It is hard not to say that anyone was not influenced by that work. Some of their work had laser scanners that would map the surroundings and identify walls -- building out a maze of sorts as it explored. Heck on seeedstudio.com you can pickup a (LIDAR) 360 2D laser scanner and algorithm to build your own.

    N

  • SLAM? (Score:5, Informative)

    by Animats (122034) on Sunday June 29, 2014 @02:28AM (#47343543) Homepage

    Doing this is called Simultaneous Localization and Mapping, or SLAM. There's been enormous progress in that in the last decade. The basic idea is to take a large number of images of the same scene, possibly with inacccurate data about where they were taken, and build up a 3D model. It sort of works most of the time. Some algorithms do well indoors, especially where there are lots of strong edges and corners. Those are easy features to lock onto. Outdoors is tougher, although outdoors you can usually use GPS. It's a basic capabiilty robots need.

    The video is frustrating. There's no comparison with previous work. Is this an advance, or did they just use known algorithms. [openslam.org]

    • by Anonymous Coward

      If I can expand on what you said: specifically using a large collection of photographs to generate a 3D model is known as "Structure From Motion"(SFM) or Photogrammetry. It's a popular thing to do with aerial photos taken by drone/UAS for GIS data gathering and there were a number of applications for that purpose, although many of the free online ones have been commercialized last I went looking. Catch123 is one such product from Autodesk, although if you want more control over the pipeline then doing it yo

    • by fenris60 (925596)
      For me the interesting part is integrating SLAM with the object recognition and building semantics on top of that. Can you use the relatively powerful situation calculus to give the robot objectives? They seems to suggest this might be the case. For anyone with a Kinect and a fair bit of patience, you can try out an RGBDSlam algorithm for yourself (http://wiki.ros.org/rgbdslam).
  • by mentil (1748130) on Sunday June 29, 2014 @02:33AM (#47343553)

    They tend to bump into the same walls repeatedly before learning they're there and proceeding to bump into the adjacent wall.

  • The more intelligent and autonomous my flying robots are, the better, I say ... hey, what are you ... Gahhhhhhhhh!!!
  • by citizenr (871508) on Sunday June 29, 2014 @08:58AM (#47344133) Homepage

    They are using PTAM package from Uni of Oxford
    http://www.robots.ox.ac.uk/~gk... [ox.ac.uk]

    Whats more they are using off the shelf ardrone-PTAM package

    https://github.com/nymanjens/a... [github.com]

    and replicating something done TWO YEARS AGO by Jens Nyman (from Belgian uni)

    https://www.youtube.com/watch?... [youtube.com]

    so W T F

    • I guess this shouldn't have made its way to /., this is an internal news publication and they don't claim having made any breaktrough technological advance by doing this neither. See this as an internal publication to publicize what is done at Sheffield University to undergraduate students.
  • You want to get skynet? Cause this is how you get skynet.
  • Not too easily purposed to warfare and domination of other peoples. Just what we need more of.

    • by dywolf (2673597)

      Its just the evolution of terrain following radar.
      No one here remembers the F111 family, capable of flying on autopilot through canyons at penetration speed, wingtips just feet from the walls?

"We learn from history that we learn nothing from history." -- George Bernard Shaw

Working...