Using Intel's neuromorphic chip, scientists from the National University of Singapore (NUS) have developed
To prove its effectiveness, the team from NUSfirst taught a robot arm equipped with artificial leather to read Braille. The robotic arm then transmitted tactile data and translated it. The accuracy was 92%, the device used 20 times less energy than analogues.
Scientists have created a rubber-like substitute for human tissue
Scientists went even further and combined tactile andvisual data. They trained the hand to classify objects using both artificial skin and a camera. They sent the data to the processor and proved that combining event-based vision and touch using a spiked neural network made the system 10% more accurate than using visual data alone.
They also discovered that the device processedsensor data is 21% faster than the best processor, while consuming 45 times less power. The researchers presented their results in the scientific journal Robotics: Science and Systems.
See also:
— Look at the huge “wall” of hundreds of thousands of galaxies behind the Milky Way
— Comet NEOWISE is visible in Russia. Where to see it, where to look and how to take a photo
— How T cells formed new immunity against COVID-19 and changed statistics