University of Glasgow experts develop smart skin to provide robots human-like sensitivity

In a bid to create a new generation of smart robots with human-like sensitivity, a team of researchers from University of Glasgow has developed what y call computational electronic skin (e-skin). This is basically a prototype of an artificial skin that uses a new type of processing system. In ir official report, experts ted that this system is based on "synaptic transistors, which mimic brain’s neural pathways" that enable robot to learn to feel pain. 

University of Glasgow even shared a video explaining mechanism of artificial e-skin. tably, robot hand in explainer video showed a remarkable ability to learn to react to external stimuli.

idea of touch-sensitive artificial skin

So far, scientists have spent decades working on development of touch-sensitive artificial skin for robots and most widely-explored method is spreading an array of contact or pressure sensors across skin's surface. When se sensors come in contact with an object, y send data to a computer that processes information and n responds. While it definitely sounds smart, this method causes a delay in response which ultimately reduces skin's effectiveness in real-world tasks. 

To overcome this limitation, Glasgow team drew inspiration from how human peripheral nervous system interprets signals from skin in order to eliminate latency and power consumption. This is because when our skin is exposed to a stimulus, our peripheral nervous system begins processing it at point of contact, reducing it to only vital information before it is sent to brain. Scientists say that this idea of 'localised learning' reduces amount of sensory data. With a limited amount of data, re is an efficient use of communication channels and thus our brain receives sensation of touch immediately.

w since idea was in hand,  Bendable Electronics and Sensing Techlogies (BEST) Group, led by Professor Ravinder Dahiya needed to work on a model that mimics way sensory neurons work in human body. experts printed a grid of 168 synaptic transistors made from zinc-oxide nawires directly onto surface of a flexible plastic surface. n, y connected synaptic transistor with skin sensor present over palm of a fully-articulated, human-shaped robot hand. w, when  robotic hand was touched (like in video) it responded by drawing its hand backward. robot's reaction was also based on intensity of stimuli; harder touch, harder response. 

"We believe that this is a real step forward in our work towards creating large-scale neuromorphic printed electronic skin capable of responding appropriately to stimuli", Professor Dahiya said in a statement.