When most people picture swarms of collaborating robots, they generally think of applications such as search and rescue operations. A new study, however, suggests that such swarms could also be used to help artists put paint to canvas.
Led by Dr. María Santos, a team at the Georgia Institute of Technology recently created an experimental system in which the user starts by indicating which sections of a canvas they wish to be painted in which colors.
This data is relayed to a group of tiny wheeled robots, each one of which is “aware” of its current location both on the canvas, and relative to the other bots. By wirelessly communicating with one another, the devices are thus able to determine which individual robots should paint which areas of the canvas, in order to get the job done as efficiently as possible.
In the current setup, the painting process is simulated by projecting trails of color behind each robot. Ultimately, though, the scientists plan on equipping the bots with cartridges of primary colors of paint, that can be mixed together as needed to deposit paint of the desired color. Color printers (even compact handheld ones) already work on the same principle, except they use toner instead of paint.
Additionally, if a given robot is incapable of producing a certain color on its own, it can collaborate with another member of the swarm. The two robots will proceed to both deposit paint of two different colors on the same part of the canvas, with the mixture of those two colors approximating the one color that was indicated.
“The multi-robot team can be thought of as an ‘active’ brush for the human artist to paint with, where the individual robots (the bristles) move over the canvas according to the color specifications provided by the human,” says Santos.
The research is described in a paper that was recently published in the journal Frontiers in Robotics and AI.