World's Largest Swarm of Miniature Robot Submarines

A fleet of little robot submarines is learning to cooperatively perform tasks underwater

2 min read
World's Largest Swarm of Miniature Robot Submarines
Image: CoCoRo Project

Forty one tiny robot submarines is a lot of tiny robot submarines. It’s so many, in fact, that controlling them individually doesn’t make sense, and the only way to go is to give them levels of swarm intelligence, so that each individual robot can take care of itself while the swarm as a whole completes an objective.

The CoCoRo (Collective Cognitive Robotics) Project, sponsored by the European Commission, has been working with a heterogeneous swarm of autonomous underwater vehicles (AUVs) since 2011, and the most important thing you need to know about these robots is that 20 of them are named Jeff.

Just look at those cute lil’ thrusters on the yellow and white robo-subs (those are called Lily)! Adorable.

But the highlight of the project is Jeff:

That’s a lot of agility for an underwater robot, and Jeffs are powerful too, able to swim upstream against a current of 1 m/s. The Lily robots aren’t quite as burly, so in the swarm, they stay higher in the water to provide a communications link between the Jeff robots, the base station, and the rest of the world.

Each AUV is capable of operating on its own, and small groups share data between themselves, and then the entire swarm makes decisions based on the collective data. The advantages here are the same as with any robot swarm: it’s versatile, adaptable, and very robust to failures of each individual robot. You could lose a handful of Lilys or Jeffs and it would be very sad, but the mission could continue.

The specific swarm behaviors that the robots employ are modeled on swarming experts: namely, fish, birds, social insects, and even slime molds, which is very cool:

A group of Lily robots can achieve a coherent shoaling or flocking configuration by emitting and receiving pulsed light signals. Similar to slime mold or fireflies, such pulsed signals are relayed from one agent to the next, forming signal waves that move through the whole swarm. We use such waves to keep the swarm of Lily robots together as a group, to coordinate the swarm and to move it in a desired direction.

In terms of practical applications, one possible scenario includes underwater search, where Jeff robots spread out to locate a target, signal each other when it’s found, and then call Lily robots over for help communicating with the surface:

We're happy to be able to report that Jeff and Lily have been able to occasionally escape from the laboratory to have adventures in swimming pools, lakes, and rivers. The researchers will be posting new videos over the rest of the year, so we’ll have plenty more of them, and here’s something to look forward to:

[ CoCoRo Project ] via [ RoboHub ]

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

“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.

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

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