Exactly one year ago I reached out to Professor Dorigo Marco after reading about his research in The Economist in an article titled Artificial intelligence: Riders on the swarm. Marco is a researcher at the Free University of Brussels and is one of the founders of a field that has become known as “swarm intelligence”.
Dr. Dorigo was interested to learn that ants are good at choosing the shortest possible route between a food source and their nest. This is reminiscent of a classic computational conundrum, the travelling-salesman problem. Given a list of cities and their distances apart, the salesman must find the shortest route needed to visit each city once. As the number of cities grows, the problem gets more complicated. A computer trying to solve it will take longer and longer, and suck in more and more processing power. The reason the travelling-salesman problem is so interesting is that many other complex problems, including designing silicon chips and assembling DNA sequences, ultimately come down to a modified version of it…
Dr. Dorigo is now working on something that can act as well as think: robots. A swarm of small, cheap robots can achieve through co-operation the same results as individual big, expensive robots—and with more flexibility and robustness; if one robot goes down, the swarm keeps going.
While Marco replied that he was not yet ready for press, he did finally reach out to me, this month, one year later. “This is to let you know that I have won, together with Mauro Birattari and Rehan O’Grady, the Best Video Award at AAAI,” he write. “As you know, I was the Scientific Coordinator of the project, while Mauro Birattari and Rehan O’Grady (researchers in my group) are the Directors of the video.”
His winning project, “Swarmanoid” is a heterogeneous robot swarm with eye-bots, hand-bots, and foot-bots, which specialize in manipulating objects and climbing, moving on the ground and transporting objects, and flying and observing the environment from above. This video below presents the Swarmanoid project, a 4 year research project coordinated by Marco Dorigo and funded by the Commission of the European Union. In it you’ll watch a small army of flying, climbing and rolling robots who’ve been taught to work together to find and “rescue” a book from a high shelf.
Check it out below, and enjoy the gentle Arcade beats:
But this is a reminder that it’s not about the task of fetching a book, it’s about the technology involved getting robots to solve a problem together. Imagine millions of robots working together, or nanobots that could morph into any shape to solve a problem. It’s collaborative production, crowdsourced intelligence and hive mind at its digital finest.