- The Washington Times - Wednesday, July 6, 2016

Scientists at the University of Zurich in Switzerland are developing robots that can acquire targets and “prey” on them.

Researchers with the Institute of Neuroinformatics have created hardware that learns from “predator and prey” behavior seen in nature. “Silicon retina” that mimics the human eye aids in the task, which developers say will benefit mankind.

“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 Vice News on Tuesday. “This way, the problem is less like a predator and its prey and more like herding, or a parent and child.”

Most robotics are inefficient at “preying” exercises because the devices are dependent upon normal cameras. Silicon retina, however, contains pixels that “individually and autonomously detect changes in illumination and transmit that information in real time, which results in a steady flow of visual information instead of a series of disjointed images,” the website reported.

A device with the right software, therefore, “learns” how to more efficiently track targets as it repeats a given task.

The work is part of the European Union-funded project VISUALISE, which aims to improve bio-inspired artificial vision technology.

“Robots guided by neural networks can perform extremely well in situations they have learned from through massive training, Diederik Moeys, a PhD student and first author of the work, told Vice News. “But any unknown or new situation can produce the most unexpected — and sometimes hilarious — results.”

LOAD COMMENTS ()

 

Click to Read More

Click to Hide