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.
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.