When fish swim together, they do not coordinate their movements or communicate with each other, instead it is a natural behavior that forms schools. Now, researchers from the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS) have developed a way for robotic fish to mimic this behavior autonomously.
Researchers suggest that this is the first-time complex 3D collective behaviors have been demonstrated with implicit coordination in underwater robots.
“Robots are often deployed in areas that are inaccessible or dangerous to humans, areas where human intervention might not even be possible,” said Florian Berlinger, a PhD candidate at SEAS. “In these situations, it really benefits you to have a highly autonomous robot swarm that is self-sufficient. By using implicit rules and 3D visual perception, we were able to create a system that has a high degree of autonomy and flexibility underwater where things like GPS and Wi-Fi are not accessible.”
Dubbed Blueswarm, researchers developed a vision-based coordination system for the fish-inspired robotic swarm based on blue light emitting diode (LED) lights. Each underwater robot was equipped with two cameras and three LED lights, and an on-board fish-lens camera detects the LEDs of neighboring Blueswarm robots with a custom algorithm determining their distance, direction and heading.
The robots were able to exhibit complex self-organizing behaviors such as aggregation, dispersion and circle formation, reacting to its neighbors’ locations to position itself to move toward the center if they want to aggregate or do the opposite if they want to disperse. To swim in a circle, researchers programed the fish to follow lights directly in front of them in a clockwise manner.
To test the robots, SEAS researchers simulated a search mission with a red light in the tank. Using the dispersion algorithm, the robots spread out in the tank until one came close enough to the light source to detect it. Upon detection, the robot’s LEDs began to flash, causing the other Blueswarm to aggregate around the signaling robot.
“Our results with Blueswarm represent a significant milestone in the investigation of underwater self-organized collective behaviors,” said Radhika Nagpal, a professor of computer science at SEAS. “Insights from this research will help us develop future miniature underwater swarms that can perform environmental monitoring and search in visually-rich but fragile environments like coral reefs. This research also paves a way to better understand fish schools, by synthetically recreating their behavior.”
The full research can be found in the journal Science Robotics.
