Human divers - and dolphins - could have a reprieve from searching out mines attached to ships' hulls, thanks to a new algorithm from MIT.
In the last few years, Navy scientists have been engineering robots for minesweeping and other underwater missions, but these haven't been accurate enough to reliably find mines that can be just ten centimeters across.
"A mine this small may not sink the vessel or cause loss of life, but if it bends the shaft, or damages the bearing, you still have a big problem," says ssistant mechanical engineering professor Franz Hover.
"The ability to ensure that the bottom of the boat doesn’t have a mine attached to it is really critical to vessel security today."
He and his team have now designed algorithms that, they say, vastly improve robots’ navigation and feature-detecting capabilities, distinguishing mines from structures such as propellers and shafts.
"It’s not enough to just view it from a safe distance," says Hover. "The vehicle has to go in and fly through the propellers and the rudders, trying to sweep everything, usually with short-range sensors that have a limited field of view."
First, the researchers programmed the Hovering Autonomous Underwater Vehicle (HAUV) to approach a ship’s hull from a safe 10-meter distance, swimming in a square around the structure. The vehicle’s sonar camera emits signals that boomerang back as the robot makes its way around the ship; the researchers process the sonar signals into a grainy point cloud. At such a low resolution, Hover says one can clearly make out a ship’s large propeller, though not an iPod-sized mine.
Next, the researchers programmed the robot to swim closer to the ship, navigating around the structure based on a mesh model produced by applying computer-graphics algorithms to the sonar data.
The idea, Hover says, is for the robot to cover every point in the mesh; and with each point spaced 10 centimeters apart, this is narrow enough to detect a small mine.
A common approach in robotic inspection is to have the the robot sweep over the structure in lines, as if it were mowing a lawn. But the researchers came up with a more efficient approach, using optimization algorithms to program the robot to sweep across the structures while taking into account their complicated 3-D shapes.
The team's tested its algorithms in the field, creating underwater models of two vessels: the Curtiss, a 183-meter military support ship in San Diego, and the Seneca, an 82-meter cutter in Boston. It's planning tests this month in Boston Harbor.
"The goal is to be competitive with divers in speed and efficiency, covering every square inch of a ship," says graduate student Brendan Englot. "We think we’re close."