Your Finger on a Tablet Can Control Entire Swarms of Robots

Need to control a lot of robots? This tablet interface makes it easy

2 min read
Your Finger on a Tablet Can Control Entire Swarms of Robots
Image: Georgia Tech

As robots get smaller, cheaper, and more capable, it often makes sense to rely on swarms of little bots instead of one big one, and as swarms grow in size and complexity, intuitive methods of real-time control become critical. Georgia Tech’s GRITS Lab has developed a way to dynamically control large swarms of robots using just a tablet and a finger (or two).

“It’s not possible for a person to control a thousand or a million robots by individually programming each one where to go,” said Magnus Egerstedt, Schlumberger Professor in Georgia Tech’s School of Electrical and Computer Engineering. “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.” 

While robots are usually pretty good at determining efficient ways of completing tasks, they’re far less good at adapting to change and figuring out which tasks need to be done, especially if they need to change priorities on the fly. This is where the humans come in: with Georgia Tech’s system, a novice user can assign goals just by poking at a tablet, and a swarm of robots will coordinate with each other to achieve those goals.

The scenario that this system was designed for is the obligatory disaster search-and-rescue mission, where you have a large amount of rugged terrain that needs to be covered optimally. Robots are good at doing things optimally, and they have no trouble cooperating to search an area. Meanwhile, a human can identify areas of interest, and set those areas as goals for the robot swarm. Once a new goal is assigned, the robots redeploy themselves based on an algorithm that guarantees optimal coverage, without the human having to get any more involved. Here’s that part of the system in action:

The latest research works very much like this, except you have a human dynamically selecting the areas that the robots should care about most.

This sort of control can also come in very useful in commercial contexts, according to the researchers:

“In the future, farmers could send machines into their fields to inspect the crops,” said Georgia Tech Ph.D. candidate Yancy Diaz-Mercado. “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.”

Cleaning robots, surveillance robots, delivery drones…  Really, any multi-robot system that needs to adaptively cover an area could benefit from an interface like this, and it works even if (especially if) you have no experience with robots, and no idea what you’re doing. And that’s what makes it so cool.

[ GRITS Lab ]

The Conversation (0)

How the U.S. Army Is Turning Robots Into Team Players

Engineers battle the limits of deep learning for battlefield bots

11 min read
Robot with threads near a fallen branch

RoMan, the Army Research Laboratory's robotic manipulator, considers the best way to grasp and move a tree branch at the Adelphi Laboratory Center, in Maryland.

Evan Ackerman

This article is part of our special report on AI, “The Great AI Reckoning.

"I should probably not be standing this close," I think to myself, as the robot slowly approaches a large tree branch on the floor in front of me. It's not the size of the branch that makes me nervous—it's that the robot is operating autonomously, and that while I know what it's supposed to do, I'm not entirely sure what it will do. If everything works the way the roboticists at the U.S. Army Research Laboratory (ARL) in Adelphi, Md., expect, the robot will identify the branch, grasp it, and drag it out of the way. These folks know what they're doing, but I've spent enough time around robots that I take a small step backwards anyway.

The robot, named RoMan, for Robotic Manipulator, is about the size of a large lawn mower, with a tracked base that helps it handle most kinds of terrain. At the front, it has a squat torso equipped with cameras and depth sensors, as well as a pair of arms that were harvested from a prototype disaster-response robot originally developed at NASA's Jet Propulsion Laboratory for a DARPA robotics competition. RoMan's job today is roadway clearing, a multistep task that ARL wants the robot to complete as autonomously as possible. Instead of instructing the robot to grasp specific objects in specific ways and move them to specific places, the operators tell RoMan to "go clear a path." It's then up to the robot to make all the decisions necessary to achieve that objective.

Keep Reading ↓ Show less