Don’t worry — the end goal isn’t actually predatory in nature. Rather, scientists say, they’re just trying to get robots to navigate their surroundings more accurately and efficiently, perhaps by finding a mark and following it around.
“Following [in large groups of self-driving cars or drones] is the obvious application, but one could imagine future luggage or shopping carts that follow you,” Tobi Delbruck, a professor at the Institute of Neuroinformatics, told Motherboard via email. “This way, the problem is less like a predator and its prey and more like herding, or a parent and child.”
But regardless of what you call it, the concept behind the new technology is decidedly, well, animalistic. The robot’s hardware is modeled after animal behavior, and depends largely on a silicon retina that behaves much like the human eye to quickly process visual data. A normal camera wouldn’t suffice in this situation because a slower frame rate doesn’t allow for the robot to see an actual movement path, especially if its “prey” (or whatever) is moving quickly.
The data obtained by way of the retina is then processed using a deep learning neural network that becomes “smarter” the more it’s used. Because in both the wild and in the lab, practice makes perfect.
So watch out, world. You may soon be followed around by robots who are watching you, quite literally, like a hawk. But whether or not that’s actually a bad thing has yet to be determined.
Editors' Recommendations
- Boston Dynamics’ Spot robot shows off its grabbing skills in new video
- The future of military training? Target practice on running, shrieking robots
- MIT learns to make robots less clumsy by putting cameras in their fingers
- Sphero’s new mini robot kits hone your STEM and soccer skills
- Astro the dog-inspired quadruped robot can sit, lie down, and… learn?