These 3D printed fishing boats can swarm and school

Researchers have created a smart school of robotic fish that swarm and swim like real ones, offering promising insights into how developers can improve decentralized autonomous operations for other gadgets such as autonomous vehicles and robotic space explorers. Also, they are quite cute smelly.

These seven 3D printed robots, or Bluebots, can synchronize their movements for group swimming, or Blueswarm, without any external control, according to a study published in Robotic science this month from the John A. Paulson School of Engineering and Applied Sciences at Harvard and the Wyss Institute for Biologically Inspired Engineering.

Equipped with two wide-angle eye cameras, each robot navigates its tank following the LED lights of its companions. Based on the signals they observe, each robot reacts accordingly using a built-in Raspberry Pi computer and a custom algorithm to measure distance, direction, and heading.

“Each Bluebot reacts implicitly to the positions of its neighbors”, explains Florian Berlinger, doctoral student at SEAS and Wyss and first author of the research document, according to Press release. “So if we want the robots to aggregate, then each Bluebot will calculate the position of each of its neighbors and move towards the center. If we want the robots to disperse, the Bluebots do the opposite. If we want them to swim like a school in a circle, they are programmed to follow the lights directly in front of them clockwise.

Previous robotic swarms could navigate two-dimensional spaces, but operating in three-dimensional spaces like air or water has proven difficult. The goal of this research was to create a swarm of robotic fish that could move in a synchronized fashion without the need for WiFi or GPS and without the participation of their human handlers.

“Robots are often deployed in areas that are inaccessible or dangerous to humans, areas where human intervention might not even be possible,” Berlinger said. “In these situations, it is really beneficial for you to have a swarm of highly autonomous and self-sufficient robots.”

This is why these robots can interpret where their companions are based solely on visual cues. In one test, the researchers sent them on a mock search mission to find and surround a red light displayed on the tank. The robots first dispersed using their scattering algorithm. Once one saw the light and approached it, his own LEDs began to flash to signal his companions to change their lens to flash the light.

And the ability to teach robots to cooperate more effectively has enormous potential beyond these little robotic fishes, no matter how cute they are. As Wiring He says if this kind of implicit coordination can be applied to autonomous vehicles, it could help them avoid collisions. This research also has the potential for companies like Amazon implementing robots in their warehouses to work alongside their human colleagues.

“It’s more fantasy than reality right now, but think about going to Mars, if Elon Musk and all the other rich people really want to make it,” Berlinger said at the exit. Before SpaceX can begin transporting humans to the Red Planet, they will need shelters installed there.. “We would then have to send teams of robots in advance. And on Mars, there is no way to control the robots, because there is too much latency for a signal to pass from here to Mars. So they really need a lot of autonomy.