Scientists at the Massachusetts Institute of Technology (MIT) have developed a new system for underwater robots that have cognitive abilities for monitoring underwater species, their habitats and other underwater missions.

The robots with cognitive abilities can make high-level decisions for achieving mission goals. Brian Williams, a professor of astronautics and aeronautics at MIT, who helped design the system, named it Enterprise.

Scientists explain that deploying an autonomous underwater vehicle (AUV) requires engineers to write scripts and low-level commands for directing a robot to achieve mission goals. MIT engineers have developed a system that enables humans to specify high-level goals for AUVs, and the cognitive capabilities of the robots help in achieving such high-level goals.

With the help of the new system, robots can devise a plan for the mission, select locations for exploring and work within timeframes. In case of an unforeseen event, the robot can also make a decision to abort a task.

Scientists have tested the system on several AUVs on the western coast of Australia and found that the robots demonstrated the ability to adapt to the mission and at the same time avoided collision with other robots.

"We wanted to show that these vehicles could plan their own missions, and execute, adapt, and re-plan them alone, without human support," said Williams. "With this system, we were showing we could safely zigzag all the way around the reef, like an obstacle course."

Williams revealed that, while developing the system, the engineers took inspiration from Star Trek. Like the hierarchical crew that is managed in Star Trek, the Enterprise system also has a number of decision-making levels.

One part of the Enterprise system is called "captain," which makes high-level decisions related to the entire mission. Another part of the system works like a navigator that plans out a route for achieving the mission goals. The Enterprise system also has a component that works like an engineer or a doctor, which repairs and diagnoses problems autonomously.

Williams has also worked with NASA's Ames Research Center. The space agency has similar systems in place for some of its spacecraft.

The scientists suggest that giving high-level decision making capabilities to robots has many advantages. Such systems can free engineers as robots establish their own mission plans. The system can also reduce the team that manages robotic operations.

Photo: Marion Doss | Flickr