This search and rescue drone can follow you by your screams, which is not scary at all

“],” filter “: {” nextExceptions “:” img, blockquote, div “,” nextContainsExceptions “:” img, blockquote “}}”>

The most recent member of search and rescue cannot follow you by your fingerprints. He can’t read the route you left in your car. It cannot detect your smell or body heat. Instead, it finds you by following the sound of your screams.

As you may have understood, this new recruit is not a person: it is a drone. Developed by researchers from Fraunhofer FKIE laboratory in Germany, the robotic plane is designed to focus on the sound of people in distress, pinpointing their location with a range of microphones, a built-in computer and a sophisticated artificial intelligence program. If you think this sounds scary, you are not alone. Mashable compared the drone to something Terminator; we will admit that for a lost hiker it may not be as heartwarming as seeing a human. But, like the Terminator, you might end up having to go with it if you want to live.

“In a post-disaster situation [where] every minute is crucial to find victims, we decided to exploit the possibilities offered by drones to quickly fly over large areas, which may be difficult to access or dangerous, ”said Macarena Varela, member of the Fraunhofer FKIE who has recently presented the project at the 180th Meeting of the Acoustical Society of America, said in an email.

When operational, drones will occupy a unique niche in the ecosystem of first responders. For SAR teams racing against the clock to locate a lost or injured hiker, planes are a valuable tool, allowing them to quickly scan large areas for signs of life. But since few or no volunteer teams can afford to operate their own helicopters, rescuers usually have to seek help from law enforcement agencies, National Guard units, or private companies. which causes delays and limited resources. Cheaper drones and ultralight planes help make up some of the difference, but without the expensive and complex thermal cameras and other sensors used by larger craft, they are limited to visual search, making them ineffective in the field. night or on a dense covered ground with trees.

The drone, equipped for research
Photo: Courtesy of Fraunhofer FKIE

Fraunhofer FKIE’s currently developing project aims to get around this problem by capitalizing on a common behavior in desperately lost people. Namely: They cry for help. Starting with a commercial quadcopter (in this case a DJI Matrice M600), the designers added a range of tiny microphones connected to a miniature computer that processes and filters background noise from wind and rotors and calculates the location of the screams. .

To make the drone feasible, the Fraunhofer FKIE team had to resolve several technical issues. One of the most important was to make the system light enough to fly: Varela says that she and her colleagues Wulf-Dieter Wirth and Manfred Okum succeeded in creating an array of microphones capable of localizing sounds in 2016, but the system , built with condenser microphones, was too heavy. for human researchers transport on foot, let alone for a quadcopter. It wasn’t in 2018 that Wirth suggested using microelectromechanical system microphones – ultralight, etched silicone mics often used in phones, laptops, and other electronic devices – which they were able to successfully modify. their invention to the point of being able to install it on a drone. To determine the direction from which a hiker’s cries are coming from, the drone relies on an audio processing technique called beamforming: its microphones (the current iteration of the search and rescue drone uses 32) are arranged in a roughly spherical network called a crow’s nest. , and it processes the signals from each microphone to maximize the matrix’s sensitivity to sounds in particular directions.

The project is not the first attempt to build autonomous search and rescue drones. Researchers from German laboratories NEC Europe are develop a drone that focuses on cell phone signals to locate lost people. In 2017, Lockheed Martin demonstrated a pair of autonomous helicopters capable of locating and recovering a lost hiker in a simulation. (Similar planes are reportedly already in use by the U.S. military, a stark reminder that robots that find people are dual-use.)

While the Fraunhofer FKIE drone is still in development, early trials are promising. When tested in open areas, the drone was able to determine the location of a person within seconds. The team behind the drone – which Varela says is more ethnically and nationally diverse than the field generally is, with colleagues from “almost every continent” – is currently pursuing it as a passionate project thanks to funding from the institute. But with all the interest the drone has generated, they don’t rule out trying to bring it to market in the future.

Before the drone reaches this point, however, there is still work to be done. Researchers are still experimenting with machine learning to improve the drone’s ability to filter out noise and more accurately locate lost people; Varela says they plan to double the number of microphones in the drone’s network. It may take a while before you see Searchinator in action.

“What has helped us is that our group is very positive and always ready to find solutions to challenges instead of focusing on them… If we meet a challenge, for example something breaks, we will find [the] means repairing or replacing it, so that we can continue with our measurement, ”she said. “In other words, a lot of engineering.”

About Geraldine Higgins

Check Also

Generate a Badoo level using a virtual number or learn about each other and complete new ones

Generate a Badoo level using a virtual number or learn about each other and complete …

Leave a Reply

Your email address will not be published. Required fields are marked *