How’s this for a fishy AI story? Researchers at Florida Atlantic University’s engineering school have won an $800,000 grant from the National Science Foundation (NSF) to create a school of bio-robotic fish.
The underwater project — which combines undulating propulsion with software-programmable, multi-function wireless sensing and communications — is being helmed by FAU’s Center for Connected Autonomy and AI (CA-AI) and the SeaTech Institute. And it is likely to redefine how sensitive underwater ecosystems such as sea grass, mangrove forests, kelp forests and coral reefs are studied and protected via swarms of underwater drones.
Scientists intend to use the research to explore remote aquatic environments that have been unsafe or hard for human divers or other engineered systems to reach.
“One of the key motivations for developing a school of bio-inspired fish is to survey sensitive littoral areas, such as coral reefs, which are crucial for the health of both ocean ecosystems and coastal communities,” said Oscar Curet, principal investigator and an associate professor in the FAU Department of Ocean and Mechanical Engineering.
“Our overarching goal is to integrate ocean robotics and networking technology with environmental enhancement and community collaboration to monitor and protect coastal habitats,” Curet said. “This includes rapidly detecting and documenting hazardous conditions like elevated acidification and temperature fluctuations, as well as tracking changes in ecological diversity, coral health, and coastal erosion.”
The initiative, called “Development of a School of Robotic Fish for Research and Training on AI Biomimetics and Multi-modal Communications,” leverages artificial intelligence (AI), bio-inspired robotics, and advanced underwater communication systems.
“Our overarching goal is to integrate robotics, AI and environmental enhancement to safeguard critical marine ecosystems,” Curet said.
Submerged drones date to the 1950s and the development of the Autonomous Underwater Vehicle (AUV). The University of Washington designed the first AUV, named Special Purpose Underwater Research Vehicle, to gather oceanographic data in Arctic waters. By the 1980s, Remotely Operated Vehicle (ROV) technology was added to AUV capabilities, and in the 1990s there was a shift to longer-term underwater exploration with solar-powered AUVs.
AUVs graduated from research-based applications to industrial and commercial uses in the early 2000s. Since the 2010s, military applications resurfaced for AUVs, highlighted by the successful launch of unmanned surface vehicles by Ukraine in the Black Sea in 2022
Fast forward to today. Unlike drones on land and in the air, most underwater swarms have had difficulties organizing beyond the ocean’s surface. FAU’s project approached the challenge by looking at nature, and studied how fish move without a leader. They came up with the idea of a school of robo-fish that exploited hydrodynamic interactions with their peers and the water environment to minimize energy consumption while enhancing maneuvering.
To that end, researchers are creating a multi-agent system of three underwater vessels equipped with advanced communication systems that use light and sound to communicate underwater. A buoy on the ocean’s surface acts as a command center and internet gateway, capable of gathering data and remotely communicating with underwater robots.
As explained by FAU researchers: The deployable bio-inspired robotic fish use “undulating fin propulsion and feature integrated multi-modal acoustic/optical underwater communication and positioning systems; a programmable research platform that can establish mobile underwater wireless networks and evaluate AI/machine learning applications for underwater mobility; and a surface buoy capable of collecting and sharing information with remote operators in real-time.”
The project aims to train undergraduate and graduate students studying the ocean and engineering with skills in ocean IoT, connected autonomy and AI.
