We might as well just give up control over the planet right now.
In recently published research, scientists detail a set of experiments in which robots — real, physical machines — improved themselves through a kind of digital Darwinism. The bots, each drawing from a collective “gene pool,” competed with one another over multiple generations, gradually swapping genetic material in a process akin to sexual reproduction. The research article appeared in the journal Frontiers in Robotics and AI.
While this kind of evolutionary robotics research has been around a while, the new study presents an important step forward in assessing the evolutionary dynamics of physically embodied robots — and it suggests that we’re mashing the fast-forward button on the impending robotic revolution.
Researchers from Vassar College set up an experiment in which 10 small-wheeled robots — all of them a model of the Ana BBot, manufactured by Johuco Ltd. — were issued the same task: to gather beams of light while avoiding certain obstacles. Each bot was also issued its own set of “genes” — a specific pattern of wires connected to pins on a circuit board.
Much more HERE