3D Robotics

Landing tech could let drones see like pilots

From Wired's Danger Room: "One big difference between Army and Air Force drones is that the Air Force’s robo-lanes can’t land themselves. That’s contributed to a number of Air Force Predators crashing when humans run into problems. But there may be a way of providing autolanding capability without the weight and expense of conventional systems. Computer vision company 2d3 is developing a new system to allow drones to see their way to a safe landing, using their own cameras rather than radio beacons or radar." Read the rest here.
E-mail me when people leave their comments –

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

Join diydrones

Comments

  • Synthetic vision is truly cool! I am thinking of a 3D radar scan (range, azimuth, and elevation) represented as a dynamic 3D wire mesh image. Conventional radar imaging systems do not provide all three coordinate dimensions (there is no elevation angle measurement) but this can be simulated by altimeter/gps readings.
  • This HUD type synthetic view isn't new to Drones...They have had it for sometime in the classified side. Air Force implemented this a few years ago after seeing all the Army Predator's crash over and over again. They want a 100% automated system to avoid the pilots having to manually land or takeoff. Their new proposal calls for MAVs Micros Aerial Vehicles with 100% autonomous capability, so full automatic operation, no pilot interaction. Now MAVs are not predators, but the future will come to a point where these are 100% pilotless vehicles flying in the NAS - National Airspace all day long un-attended..Like Metro trains can today, although I am glad a human still sits in the cockpit just in case manual control is needed to avery disaster like what happened on the metro in Maryland/District of Columbia recently. The technology is there even for fullscale aircraft today, synthetic vision HUDs have been tested by companies such a scaled composite and the computer power is still bulky for private aircraft, but could be implemented easily in commercial.
  • I believe I saw this tech implemented some time ago when searching for image recognition research papers.
    Can't remember the company that did it atm however... mind blank. :(
  • Synthetic vision is the future man!
  • Hmmm; I'm thinking "foggy"!
This reply was deleted.