Harvard has created a swarm of robots that is capable of learning

Totally ignoring Asimov’s laws of robotics, a team of computer scientists at Harvard University have crafted a swarm of over one thousand diabolical robots, programmed only for evil. Despite the fact that each of the Kilobots is only about the size of a quarter, their great numbers and advanced coordination allows them to operate without any human interaction, save for issuing the initial command. Once they’ve been given the word, these robots won’t stop until they’ve carried out their inventors’ sinister plans to draw complex shapes on a flat surface.

Harvard University scientists have devised a swarm of 1,024 tiny robots that can work together without any guiding central intelligence. Like a mechanical flash mob, these robots can assemble themselves into five-pointed stars, letters of the alphabet and other complex designs. The researchers at Harvard’s Wyss Institute for Biologically Inspired Engineering in Cambridge, Mass., reported their work Thursday in Science. “No one had really built a swarm of this size before, where everyone works together to achieve a goal,” said robotics researcher Michael Rubenstein, who led the project. While still experimental, such armadas of self-organizing robots one day may aid in oil spill cleanups, deep-sea ventures, military surveillance and planetary exploration. Swarm scientists are inspired by nature’s team players—social insects like bees, ants and termites; schools of fish; and flocks of birds. These creatures collaborate in vast numbers to perform complicated tasks, even though no single individual is actually in charge. “The beauty of biological systems is that they are elegantly simple and yet, in large numbers, accomplish the seemingly impossible,” said Harvard computer scientist Radhika Nagpal.

Read full article