The team trained a model that would allow any number of robots to work together to move a long rod around two obstacles and through a narrow door in computer simulations.
“We made it a little more difficult on ourselves. We want to accomplish the task with as little communication as possible among the robots,” lead author Andrew Barth said.
Neither robot directed the other and they did not share their strategy in advance to complete the task.
They used an AI technique called genetic fuzzy logic: an intelligent control technique that mimics human reasoning by replacing a simple binary classification (yes, no) with degrees of right or wrong. These genetic algorithms modify individual solutions to learn from past results to optimise performance over time.
“Ultimately, we want to expand this to 10 or more robots working cooperatively on a project,” Barth said. “If you want to build a gigantic habitat in space, say, you’ll need a lot of robots working together...