Roboticists often look to the living world for guidance on locomotion. There are countless robots designed to move like animals: some run like cheetahs, others slither like snakes, and a few even fly like insects.
Michael Milford thinks roboticists should consider a two-pronged, biomimetic approach to navigation, too. Specifically, Milford thinks combining an algorithm that mimics the brain of a human, with an algorithm for the eyes of a rat could drastically improve robotic navigation. As chief investigator of the Australian Research Council Center of Excellence in Robotic Vision, Milford intends to do just that.
“This is a very Frankenstein type of project. It’s putting two halves of a thing together,” Milford says in a press release. “A rodent’s spatial memory is strong but has very poor vision, while humans can easily recognize where they are because of eyesight.”
Sophisticated models of both systems already exist, he says. But they still need to be combined. “We’ve got all the ground work there but plugging them altogether is the massive challenge we have,” he says.