Programming underwater robots can be a tedious task. Engineers have to break down missions into small, simple tasks, and then write scripts for each low-level command. Now a new approach, developed by researchers at MIT, will enable the robots to figure out more on their own.
In the new paradigm, the robot would plan the mission based on some basic information provided by the engineer, such as the mission’s goal, time limit, and any physical constraints. If a problem occurs during the mission, the robot can opt to skip that part of the mission or try another approach.
Several kinds of AUVs, including an autonomous underwater glider, were tested using the novel system in Australia last March. Using the system, the glider changed its mission plan to avoid getting in the way of other vehicles, while still achieving its most important scientific objectives. When another robot was taking longer than expected in a particular area, the glider would reschedule its work in that area and move on to another part of its mission.
“We wanted to show that these vehicles could plan their own missions, and execute, adapt, and re-plan them alone, without human support,” Brian Williams, principal developer of the mission-planning system, said in a release. “With this system, we were showing we could safely zigzag all the way around the reef, like an obstacle course.”
Williams believes his system, called Enterprise, will free up engineers to think about overall strategy. It could also enable the exploration of more remote areas, given that the robots wouldn’t have to be in continuous contact with humans.“If you look at the ocean right now, we can use Earth-orbiting satellites, but they don’t penetrate much below the surface,” Williams said. “You could send sea vessels which send one autonomous vehicle, but that doesn’t show you a lot. This technology can offer a whole new way to observe the ocean, which is exciting.”