Loihi Artificial Skin Detects Touch 1,000 Times Faster Than the Human Nervous System

A photo of the Loihi neuromorphic chip.
A photo of the Loihi neuromorphic chip. Intel

Researchers from the National University of Singapore (NUS) are utilizing the Intel Loihi neuromorphic chip to develop artificial skin. The skin detects touch 1,000 times faster than the human nervous system, and it could help improve robotic automation in medicine, manufacturing, and the service industry.

The NUS team presented its research at the Robotics: Science and Systems conference earlier this week. They detailed how robotics hands fitted with the artificial skin system can read Braille with 92% accuracy, all while using 20 times less power than a traditional processor.

Intel modeled its Loihi chip on the human brain, so its architecture is significantly different from typical Von Neumann processors. It may not stand in for your computer’s CPU or GPU, but the Loihi chip is a stellar development for AI and robotics, which requires speed, precision, and energy-efficiency. According to the NUS research team, its artificial skin system processes sensory data 21% faster than leading GPU hardware, all while using 45 times less power. (Hey, maybe we could use this system with VR.)

We’re still in the early chapters of robotics and artificial intelligence. As time goes on, products like the Boston Dynamics Spot will only get cheaper, more common, and more complex. Prepare yourself for a strange future!

Source: National University of Singapore via Engadget

Andrew Heinzman Andrew Heinzman
Andrew is a writer for Review Geek and its sister site, How-To Geek. Like a jack-of-all-trades, he handles the writing and image editing for a mess of tech news articles, daily deals, product reviews, and complicated explainers. Read Full Bio »

The above article may contain affiliate links, which help support Review Geek.


Our Readers' Favorite Products This Week







PlayStation 5 Digital Edition
83 people were interested in this!














Show More