Advertisement
Australia markets closed
  • ALL ORDS

    7,937.50
    -0.40 (-0.01%)
     
  • ASX 200

    7,683.00
    -0.50 (-0.01%)
     
  • AUD/USD

    0.6494
    +0.0005 (+0.08%)
     
  • OIL

    82.82
    -0.54 (-0.65%)
     
  • GOLD

    2,332.90
    -9.20 (-0.39%)
     
  • Bitcoin AUD

    98,884.76
    -3,869.89 (-3.77%)
     
  • CMC Crypto 200

    1,398.30
    -25.80 (-1.81%)
     
  • AUD/EUR

    0.6071
    +0.0015 (+0.24%)
     
  • AUD/NZD

    1.0949
    +0.0018 (+0.17%)
     
  • NZX 50

    11,946.43
    +143.15 (+1.21%)
     
  • NASDAQ

    17,479.71
    +8.24 (+0.05%)
     
  • FTSE

    8,040.38
    -4.43 (-0.06%)
     
  • Dow Jones

    38,433.71
    -69.98 (-0.18%)
     
  • DAX

    18,088.70
    -48.95 (-0.27%)
     
  • Hang Seng

    17,201.27
    +372.34 (+2.21%)
     
  • NIKKEI 225

    38,460.08
    +907.92 (+2.42%)
     

This drone tracks human screams (to save lives)

It’s here to help, we think.

Fraunhofer FKIE Institute

A team of researchers from Germany’s Fraunhofer FKIE institute has created a drone that can locate screaming humans. While it sounds like the stuff of dystopian fiction, it’s actually something they set out to create to make it easier for first responders to find survivors following a natural disaster.

“(Drones) can cover a larger area in a shorter period of time than rescuers or trained dogs on the ground,” Macarena Varela, one of the lead engineers on the project, told The Washington Post. “If there’s a collapsed building, it can alert and assist rescuers. It can go places they can’t fly to or get to themselves.”

To create their drone, the researchers first recorded themselves screaming, tapping and producing other sounds that someone in need of help might make. They then used those recordings to train an artificial intelligence algorithm and tweaked the software to filter out ambient sounds like the hum of the drone’s rotors. Outside of software and UAV, the rest of the system isn’t that complicated. The team used the type of microphones you might find on your smartphone, mainly because they wanted to keep the drone light and agile.

ADVERTISEMENT

Varela told The Post the Fraunhofer FKIE team conducted several successful open field tests in which their drone managed to estimate someone’s location “within a few seconds” of picking up the sounds they were making. As a next step, the researchers plan to add a higher frequency microphone to a prototype to make it better at detecting sounds at farther away distances.

This isn’t the first time we’ve seen scientists think of using sound to augment a drone’s capabilities. Last year, a team of researchers from Purdue University developed a system that allowed a UAV to navigate using four microphones and a speaker. By the sounds of it, something could come of this latest project. The Fraunhofer FKIE team told The Post they were approached by several organizations that wanted to partner with them.