ATLANTA, May 12 (UPI) -- Engineers at the Georgia Institute of Technology have programmed a fleet of robots to respond to a basic set of commands issued via a tablet device.
A tablet interface represents the floorspace, within which the small, hockey puck-like robots navigate. When the screen is touched, the location glows and a corresponding light appears on the floor. Users can simply touch their finger on the tablet, and the fleet of robots will follow to the corresponding point on the floor.
The robots have been programmed to communicate with each other and navigate their way to the circle of light. Their communication system allows them to evenly occupy the lighted space without bumping into each other. Swiping or dragging a finger across the screen causes the light to do the same. The obedient robots follow.
Touch two places on the tablet simultaneously and two corresponding lights appear. The robots will automatically divide themselves evenly and occupy each light accordingly.
The revelatory part of the technology isn't so much the simplified instruction delivery method -- finger and tablet -- but the programming that allows a swarm of robots to respond en masse to generalized instructions.
"It's not possible for a person to control a thousand or a million robots by individually programming each one where to go," researcher Magnus Egerstedt, a professor in Georgia Tech's School of Electrical and Computer Engineering, said in a press release. "Instead, the operator controls an area that needs to be explored. Then the robots work together to determine the best ways to accomplish the job."
Egerstedt says the technology could be used to send hundreds of small robots into disaster areas to explore dangerous or hard-to-navigate confines, searching for injured victims.
"In the future, farmers could send machines into their fields to inspect the crops," researcher and PhD candidate, Yancy Diaz-Mercado, offered. "Workers on manufacturing floors could direct robots to one side of the warehouse to collect items, then quickly direct them to another area if the need changes."
The engineers recently described their technology in a paper published in IEEE Transactions on Robotics.