A new approach in programming allows engineers to specify high-level goals to autonomous underwater vehicles (AUVs), which in turn perform high-level decision-making to meet those goals.
Called Enterprise, the system's name and design are inspired by the fictional Star Trek starship. Its components take on roles similar to those who would command a ship. One component acts as a captain, making higher-level decisions to plan out the mission, such as where and when to explore. Another component functions as a navigator, planning the route. The third works as a doctor or engineer, diagnosing and repairing problems autonomously.
With these components, engineers give the AUVs a list of goals and parameters, including what areas to explore, time constraints and even more specific things like what distance to maintain from the seafloor.
The AUV then plans out its mission, choosing where to go and how to respond to problems when they arise.
Autonomous in the Sea and in Space
Tested on an autonomous water glider, the robot adapts its mission plan to avoid getting in the way of other vehicles, while still achieving its most important objectives. If another vehicle takes longer than expected to explore a particular area, the glider shifts its priorities, staying in its current location to avoid potential collisions.
“We wanted to show that these vehicles could plan their own missions, and execute, adapt and re-plan them alone, without human support,” says Brian Williams, a professor at MIT and principal developer of the Enterprise system. “With this system, we were showing we could safely zigzag all the way around the reef, like an obstacle course.”
Several classes of AUVs were tested over the course of three weeks, demonstrating their ability to work cooperatively to map the ocean environment. MIT engineers and groups from the Woods Hole Oceanographic Institution, the Australian Center for Field Robotics, the University of Rhode Island and elsewhere were present.
The Enterprise system is similar to one that Williams developed for NASA’s Ames Research Center. Tasked with developing an autonomous system that would enable spacecraft to diagnose and repair problems without human assistance, the system was successfully tested on NASA’s Deep Space 1 probe, which performed an asteroid flyby in 1999.
“That was the first chance to demonstrate goal-directed autonomy in deep space,” Williams says. “This was a chance to do the same thing under the sea.”
The Implications Behind Cognitive Robots
By giving robots control of higher-level decision-making, engineers can be free to think about overall strategy, says Williams.
Such a system could also reduce the size of the operational teams needed on research cruises and could even enable robots to explore more remote areas of the sea, not being dependent on contact with engineers.
“If you look at the ocean right now, we can use Earth-orbiting satellites, but they don’t penetrate much below the surface,” Williams says. “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.”
Williams and his colleagues will present the mission-planning system in June at the International Conference on Automated Planning and Scheduling in Israel.
Source: Jennifer Chu, MIT News