Watch SRI's Nimble Microrobots Cooperate to Build Structures

Tiny robot swarms team up to create the future of manufacturing

2 min read
Watch SRI's Nimble Microrobots Cooperate to Build Structures
Photo: SRI International

Over the past year or two, we've seen all kinds of creative robots and robot teams that are learning how to build things. Recently, we've highlighted Harvard's TERMES Project, and we're particular fans of this robot that builds ramps by tossing thousands of toothpicks and glue into a giant random pile.

SRI International has also been developing construction robots, but on a much smaller scale, with swarms of magnetically actuated microrobots that can work together to build macro-scale structures.

Magnetically controlled robots aren't a new idea, but generally, it's difficult to independently control more than one at a time, because any externally generated magnetic field equally affects all of the robots that it comes in contact with.

Photo: SRI International

SRI has solved this problem by driving their robots around on circuit boards (including flexible ones) that can keep the magnetic fields localized. Not only are the robots very finely controllable, but they're fast: a robot that I'm guessing (based on the size of the dime it's next to) is about two millimeters in length travelling at 35 centimeters per second would be analogous to yours truly running at slightly under Mach 1. Impressive.

This robotic micro-factory technology is part of DARPA's Open Manufacturing Program, which seeks to "lower the cost and speed the delivery of high-quality manufactured goods" by "creating a manufacturing framework that captures factory-floor and materials processing variability and integrates probabilistic computational tools, informatics systems and rapid qualification approaches."

SRI's robots fit in due to their ability to autonomously and rapidly assemble very small things (like electronics) as well as relatively large things, like structures. The robots aren't doing anything that isn't already being done by more traditional autonomous systems, but the advantage here is that the microrobots aren't nearly as limited by workspaces (especially if you mount their build surface on a mobile base), are inherently more versatile, and can be assigned to collaborate in giant swarms.

[ SRI ]

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
LightGreen

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