Underwater robots are used in a variety of research projects these days, from mapping the sea floor and Antarctic ice to tracking endangered species. The vehicles are able to stay in the water for long periods of time and go to greater depths than manned vehicles could, so they've been able to gather new and more comprehensive information for scientists.
Right now, these autonomous underwater vehicles (AUVs) are guided by engineers who spend a lot of time writing tedious algorithms and commands to map out specific missions for them and often engineers have to continue to control them from a remote location once the robots are in the water. MIT have set out to create underwater robots that could do a lot of the thinking on their own, even planning the missions themselves.
MIT reports, "Now a new programming approach developed by MIT engineers gives robots more “cognitive” capabilities, enabling humans to specify high-level goals, while a robot performs high-level decision-making to figure out how to achieve these goals.
For example, an engineer may give a robot a list of goal locations to explore, along with any time constraints, as well as physical directions, such as staying a certain distance above the seafloor. Using the system devised by the MIT team, the robot can then plan out a mission, choosing which locations to explore, in what order, within a given timeframe. If an unforeseen event prevents the robot from completing a task, it can choose to drop that task, or reconfigure the hardware to recover from a failure, on the fly."
The idea is that the engineers can now give very simple choices or commands to the AUV system like "go to this or that location and map it out" and the vehicles will be able to choose and execute them on their own.
The scientists tested the system over three weeks in March off the western coast of Australia to see if different types of AUVs could work collaboratively in a marine environment. It turns out, they can. An autonomous glider running on the new system was able to complete a scientific mission all while navigating around other AUVs in the same water. If another vehicle was in an area it needed to explore, it would reshuffle its priorities and complete another area first.
“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 of aeronautics and astronautics at MIT, and principal developer of the mission-planning system. “With this system, we were showing we could safely zigzag all the way around the reef, like an obstacle course.”
In this new system, the researchers see the AUVs working in a hierarchy, a model that is based on the command system aboard the Starship Enterprise from Star Trek -- one robot will act as the captain making the highest level of decisions, while other robots will serve as navigators, engineers or even doctors that repair other robots.
These "cognitive" underwater vehicles will be able to explore even more remote places in the sea since they don't have to stay in constant contact with engineers to operate and their ability to modify their mission on the fly when obstacles arise will be able to produce even better results.