U.S. Navy Tests Robot Boat Swarm to Overwhelm Enemies

A swarm of autonomous boats could escort larger ships in the future

3 min read
U.S. Navy Tests Robot Boat Swarm to Overwhelm Enemies
Image: U.S. Navy

A fleet of U.S. Navy boats approached an enemy vessel like sharks circling their prey. The scene might not seem so remarkable compared to any of the Navy's usual patrol activities, but in this case, part of an exercise conducted by the U.S. Office of Naval Research (ONR), the boats operated without any direct human control: they acted as a robot boat swarm.

The tests on Virginia's James River this past summer represented the first large-scale military demonstration of a swarm of autonomous boats designed to overwhelm enemies. This capability points to a future where the U.S. Navy and other militaries may deploy underwater, surface, and flying robotic vehicles to defend themselves or attack a hostile force.

"What's new about the James River test was having five USVs [unmanned surface vessels] operating together with no humans on board," said Robert Brizzolara, an ONR program manager.

In the test, five robot boats practiced an escort mission that involved protecting a main ship against possible attackers. To command the boats, the Navy use a system called the Control Architecture for Robotic Agent Command and Sensing (CARACaS). The system not only steered the autonomous boats but also coordinated its actions with other vehicles—a larger group of manned and remotely-controlled vessels.

Brizzolara said the CARACaS system evolved from hardware and software originally used in NASA's Mars rover program starting 11 years ago. Each robot boat transmits its radar views to the others so the group shares the same situational awareness. They're also continually computing their own paths to navigate around obstacles and act in a cooperatively manner.

Navy researchers installed the system on regular 7-foot and 11-foot boats and put them through a series of exercises designed to test behaviors such as escort and swarming attack. The boats escorted a manned Navy ship before breaking off to encircle a vessel acting as a possible intruder. The five autonomous boats then formed a protective line between the intruder and the ship they were protecting.

Photo: John F. Williams/U.S. Navy
An unmanned boat operates autonomously during an Office of Naval Research demonstration of swarm boat technology on the James River in Newport News, Va.

Such robotic swarm technology could transform modern warfare for the U.S. Navy and the rest of the U.S. military by reducing the risk to human personnel. Smart robots and drones that don't require close supervision could also act as a "force multiplier" consisting of relatively cheap and disposable forces—engaging more enemy targets and presenting more targets for enemies to worry about.

"Numbers may once again matter in warfare in a way they have not since World War II, when the U.S. and its allies overwhelmed the Axis powers through greater mass," wrote Paul Scharre, a fellow at the Center for a New American Security, a military research institution in Washington, D.C., in an upcoming report titled "Robotics on the Battlefield Part II: The Coming Swarm."

"Qualitative superiority will still be important, but may not be sufficient alone to guarantee victory," Scharre wrote. "Uninhabited systems in particular have the potential to bring mass back to the fight in a significant way by enabling the development of swarms of low-cost platforms."

The Navy does not have a firm timeline for when such robot swarms could become operational. For now, ONR researchers hope to improve the autonomous system in terms of its ability to "see" its surroundings using different sensing technologies. They also want to improve how the boats navigate autonomously around obstacles, even in the most unexpected situations that human programmers haven't envisioned. But the decision to have such robot boats open fire upon enemy targets will still rest with human sailors.

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