Schools of fish exhibit complex, synchronized behaviors that help them find food, migrate, and avoid predators. No fish or team of fish will coordinate these movements, nor will the fish communicate with each other as to what to do next. Rather, these collective behaviors result from what is known as implicit coordination – individual fish make decisions based on what their neighbors are doing.
This type of decentralized, autonomous self-organization and coordination has long fascinated scientists, especially in the field of robotics.
Now, a team of researchers from the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS) and the Wyss Institute for Biological Inspired Engineering have developed fish-inspired robots that can synchronize their movements like a real school of fish without such external control. It is the first time that researchers have demonstrated complex 3D behaviors with implicit coordination in underwater robots.
"Robots are often used in areas that are inaccessible or dangerous for humans, in which human intervention may not be possible," said Florian Berlinger, PhD student at SEAS and Wyss and first author of the paper. "In these situations, it is really beneficial to have a highly autonomous swarm of robots 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 like GPS and WiFi are not accessible. "
The research is published in Science robotics.
The fish-inspired swarm of robots, called the Blueswarm, was created in the laboratory of Radhika Nagpal, Fred Kavli Professor of Computer Science at SEAS and associate faculty member at the Wyss Institute. Nagpal's laboratory is a pioneer in self-organizing systems, from the 1000-robot-kilobot swarm to the termite-inspired robot-building crew.
Most previous robot swarms, however, worked in two-dimensional space. Three-dimensional spaces such as air and water pose considerable challenges for perception and movement.
To overcome these challenges, the researchers developed a vision-based coordination system based on blue LED lights in their fish robots. Each underwater robot, called a bluebot, is equipped with two cameras and three LED lights. The built-in fish lens cameras detect the LEDs on neighboring bluebots and use a custom algorithm to determine their distance, direction and direction. Based on the simple generation and detection of LED light, the researchers showed that the blueswarm can exhibit complex self-organized behaviors, including aggregation, dispersion, and circular formation.
"Every Bluebot reacts implicitly to the positions of its neighbors," said Berlinger. "So if we want the robots to aggregate, each bluebot calculates the position of each of its neighbors and moves towards the center. If we want the robots to disperse, the bluebots do the opposite. If we want them that way swim like. " As a school in a circle, they are programmed to follow the lights right in front of them in a clockwise direction. "
The researchers also simulated a simple search mission with a red light in the tank. With the help of the dispersion algorithm, the bluebots spread over the tank until you get close enough to the light source to see it. As soon as the robot detects the light, its LEDs start flashing, which triggers the aggregation algorithm in the rest of the school. From there all bluebots gather around the signal robot.
"Our results with Blueswarm are an important milestone in the investigation of self-organized collective behavior underwater," said Nagpal. "Findings from this research will help us develop future miniature underwater schools that can perform environmental monitoring and searching in visually rich but fragile environments such as coral reefs. This research also paves a way to better understand schools of fish by using their Reproduce behavior synthetically. "
The research was led by Dr. Melvin Gauci, a former Wyss Technology Development Fellow, co-authored. It was supported in part by the Office of Naval Research, the Wyss Institute for Biological Inspired Engineering, and an Amazon AWS Research Award.