Researchers design drones that can hunt down humans based on their screams

A team of German researchers have designed a system to help drones find humans by listening to their screams.

Though the technology sounds like a Black Mirror episode, researchers actually intend their designs to be used for good, locating people trapped by collapsed buildings or natural disasters.

In a disaster scenario, finding a victim quickly can be the most important factor for survival – while unmanned aerial vehicles (UAV), or drones, can get to people trapped quickly, they often don’t have the same sensitivity to hearing or seeing humans that other humans do.

But experts in aerial acoustics at German research institute Franhofer FKIE think they have developed a method for drones to accurately find humans just as well as we can.

‘We have a lot of experience in filtering noise, such as wind noise, extremely loud helicopter noise, ground vehicles noise, and more,’ Fraunhofer FKIE’s research fellow Macarena Varela said.

‘We use different types of filters to be able to reduce noise, and we use diverse detection procedures to extract the signals of interest, such as impulsive sounds or screams.’

Researchers have not discussed the technology being used for any nefarious purposes, such as on the battlefield – but that doesn’t mean people won’t use the technology for evil at some point.

Last year, a UN report detailed that a drone had autonomously attacked humans for the first time.

To view this video please enable JavaScript, and consider upgrading to a webbrowser thatsupports HTML5video

Presenting his team’s work at the annual Meeting of the Acoustical Society of America, Varela said his team had had highly accurate tests so far.

‘We have already successfully detected and angularly located impulsive sounds very precisely near distances with the presence of drone noise,’ Varela said.

‘We will be testing the system on a flying drone to measure impulsive sounds, such as screams, and process the data with different methods to also estimate the geographical positions of the sounds.’

The novel technique uses a ‘Crow’s Nest Array’ of microphones, along with advanced ‘beamforming’ processing techniques.

While the team has had good results so far, Varela has said that environmental noises can play a part in the effectiveness of the microphones.

Researchers have also designed drones that can find targets via smell.

SNIFFDRONE, a project from the Institute of Bioengineering of Catalonia, was designed to help assess the efficacy of waste management plants, while a University of Washington team designed a smelling-drone that uses moth antenna to detect smells with a high degree of accuracy.

Source: Read Full Article