artificial intelligence

Why would fish follow a robot?

NYU (US)—Forget artificial intelligence. How about artificial leadership? A mechanical engineer at New York University is combining smart materials and mathematics to build robots that lead schooling fish.

Someday, Maurizio Porfiri, assistant professor of mechanical engineering at NYU’s Polytechnic Institute, hopes the robots could lead fish away from the turbines of power plants. They also could potentially lead flocking birds to new wintering grounds if their forests have been destroyed, or even herd humans to safety when a fire breaks out.

First, however, engineers must uncover the mechanics of leadership for each of these life forms.

Porfiri chose to start with the bait fish swimming in his tanks because their information-sharing is particularly rich: They make their decision on whether to school based upon what they see and the flow that they feel, which can be studied using fluid dynamics.

Fish leaders, according to published report and to Porfiri’s observations, beat their tails faster, mill about, and accelerate to gain attention, gather a school, and lead it.

Using a shallow, donut-shaped tank and cameras, researchers began a mathematical journey into fish schooling in one-dimensional environments. They recently reported their results from this study in the Journal of the Royal Society Interface.

Meanwhile, they built silent, remotely controlled, fish-like robotic swimmers that fit in the palm of a hand. These first robots can “swim” along a plane; the next step is to create robots that can dive and surface.

Since fish of different sizes and species school together, Porfiri correctly hypothesized that they would not only accept a robotic peer that was larger than themselves but also welcome it as a group leader.

To engage live shoal mates, Porfiri wanted to give the robot other fish qualities.  Foremost, it would have to swim silently, and its locomotion would have to closely match that of live fish. To achieve these goals, he employed ionic polymers that swell and shrink in response to electrical stimulation from a battery, propelling the robot.

Such biomimetic and innovative propulsion systems also motivated Porfiri’s recent research on energy harvesting in aquatic environments using ionic polymers. This research will produce underwater microsensors that can scavenge untapped energy from little eddies and small vibrations.

In addition, the robotic fish technology is helping him develop new artificial muscles that will operate without batteries, powered remotely by electromagnetic waves.

Meanwhile, the fish modeling continues as the team explores the effect of the species’ numerosity, or perception of numbers, on schooling behavior. (Fish intuitively count three or four objects around them, as opposed to about ten for humans.)

The researchers study their formation, intelligence, computing capacity and the ways they avoid predators for clues to other living creatures. Their research will also find application in autonomous vehicle teams, including submarines, airplanes, and ground vehicles.

More news from NYU-Poly:

Related Articles