autoevolution
 

U.S. Army Researchers Develop Stealth Communication Technique for Robot Teams

The image of a battlefield where drones and robots are the main players is no longer just a scene from a movie, but a pretty accurate representation of future military conflicts. In fact, the U.S. Army is not only developing robots for future operations, but is also working on robot teams and how they can collaborate efficiently.
Robots could have goal conflicts when operating in the same area. 1 photo
Photo: U.S. Army
Apparently, communication between military robots is already good, if they are able to freely talk to one another. But if they can’t communicate directly, whether because radio signals are affected by clutter or because the nature of the mission requires them to remain hidden, then that’s a potential issue.

This is what Army researcher Dr. Bradley Woosley had in mind when he joined other researchers from the U.S. Army Combat Capabilities Development Command (DEVCOM), the Army Research Laboratory and the University of Nebraska, in trying to find a solution for indirect communication between robots within the same team.

During a mission, if several robots intended to operate in the same area and weren’t able to communicate with each other, there would be a risk of some of them performing the same task. In order to avoid that, they should be able to find out, indirectly, who is doing what.

The technique developed by the team of researchers, called “α-shape”, allows robots to communicate the task they are about to do to only one of them, who would be able to remember this information and “respond” whenever some other member of the team asks about the same task.

By integrating a geometric approximation with an intelligent search algorithm, this technique allows robots to search in the communication network, find goal conflicts and store them. And this is possible even when some members of the team become disconnected from the network.

The α-shape solution proved to be a fast way to prevent duplicated tasks within a robot team, even in scenarios where there are communication loses.

So far, it has been tested on Clearpath Jackal Robots, as well as simulated robots in various scenarios. The next step for the team of researchers is developing the robots’ ability to predict each other’s behavior.

If you liked the article, please follow us:  Google News icon Google News Youtube Instagram X (Twitter)
press release
About the author: Otilia Drăgan
Otilia Drăgan profile photo

Otilia believes that if it’s eco, green, or groundbreaking, people should know about it (especially if it's got wheels or wings). Working in online media for over five years, she's gained a deeper perspective on how people everywhere can inspire each other.
Full profile

 

Would you like AUTOEVOLUTION to send you notifications?

You will only receive our top stories