Students at Switzerland's ETH Zurich here have developed a robot which works 30 times faster than the quickest human.
The Institute of Neuroinformatics' "Sensors Group"at the ETH Zurich has used a brain-inspired neural network and camera to develop "Dextra a robotic hand" which essentially reads your mind anticipating your hand gestures to defeat you in the rock-paper-scissors game.
"Dextra sees the world in super slow motion. It is so fast at seeing the symbol you are about to throw that it is able to both determine your next move and execute a winning symbol 30 times faster than the quickest human," ETH Zurich Professor, Tobi Delbruck told PTI.
Conventional robotic or computer systems must continually process frames at a very high rate in order to react quickly. High processing rates in the camera and the computing system sap energy and power.
"The robotic AI computation occurs only when necessary enabling the system to always react quickly, while at the same time, optimizing energy use. It is a digital convolutional neural network (ConvNet) accelerator that determines which symbol the human game player displays," he added.
The professor further explained that NullHop, like the DVS, takes advantage of the sparse data reducing the number of necessary computations by a factor of four.
"By using NullHop and the DVS, the system driving Dextra can react in about 10 milliseconds, about 30 times faster than the quickest human," he added.
(This story has not been edited by Business Standard staff and is auto-generated from a syndicated feed.)