Fishing Robot Style

Red Fish, Blue Fish, One Fish, Robot Fish that is how Dr. Seuss is read at MIT.  Unlike land-based robots, MIT’s flexible aquatic craniate is a “soft robot” that is “powered by fluid flowing through flexible channels” mimicking gills.  This self contained power system, requires no recharging or even traditional batteries, so it potentially could swim long distances (as long as you follow Mr. Carp’s sage advice, “Never feed him a lot. Never more than a spot! Or something may happen. You never know what).

“We’re excited about soft robots for a variety of reasons,” Daniela Rus, director of MIT’s Computer Science and Artificial Intelligence Laboratory.

“As robots penetrate the physical world and start interacting with people more and more, it’s much easier to make robots safe if their bodies are so wonderfully soft that there’s no danger if they whack you.”  Some of the robot’s interactions in the human world include bumping into objects. That can be a problem for traditional robots, but not always for soft robots. “In some cases, it is actually advantageous for these robots to bump into the environment, because they can use these points of contact as means of getting to the destination faster,” Rus said.

Designed by MIT graduate student Andrew Marchese, the fish looks simple, but it’s mechanics are hardly so. “Each side of the fish’s tail is bored through with a long, tightly undulating channel. Carbon dioxide released from a canister in the fish’s abdomen causes the channel to inflate, bending the tail in the opposite direction. Each half of the fish tail has just two control parameters: the diameter of the nozzle that releases gas into the channel and the amount of time it’s left open.”

For now, the fish can perform between 20 and 30 escape maneuvers, or directional changes, before it runs out of the carbon dioxide that it relies on to function. Simple one-directional swimming exhausts the supply even faster. “The fish was designed to explore performance capabilities, not long-term operation,” Marchese said. “Next steps for future research are taking that system and building something that’s compromised on performance a little bit but increases longevity.”

As Marchese improves his design, eventually his aquatic life will have to go free like Willy into the ocean entering a new sphere of contained robotics.  By just adding machine learning capabilities, these fish could learn from the live counterparts and create “school like behaviors” to explore the depths of the ocean further and deeper than ever imagined by Jacques Cousteau.

Please note that in the spirit of MIT’s fish, I will be traveling to the white sand beaches of Mexico  for Passover, and will note be posting next week.  Happy Holidays to all!