That input data would be routed to a computer to be processed in previous versions of electronic skin.
A group of researchers lead by an Indian national has invented an electronic skin that can learn from “pain” and could aid in the development of a new generation of intelligent robots with human-like sensitivity.
The artificial skin was created by a team from the University of Glasgow using a novel sort of processing system based on asynaptic transistors, which replicate the brain’s neural networks to learn.
That input data would be routed to a computer to be processed in previous versions of electronic skin.
Instead, in the new e-skin, detailed in Science Robotics, a circuit inserted into the skin functions as an artificial synapse, reducing the input to a simple spike of voltage whose frequency fluctuates depending on the amount of pressure applied to the skin, speeding up the reaction process.
The team trained the skin to respond appropriately to simulated pain using the varied output of that voltage spike, which then triggered the robot hand to react.The team was able to make the robot hand recoil from a strong poke in the centre of its palm by setting a threshold of input voltage to elicit a reaction.
“Through this method, we’ve been able to construct an electronic skin capable of distributed learning at the hardware level that doesn’t require messages to be sent back and forth to a central processor before taking action.”Instead, it considerably speeds up the process of responding to touch by reducing the amount of processing required,” stated James Watt School of Engineering Professor Ravinder Dahiya.
“We feel this is a significant step forward in our efforts to develop large-scale neuromorphic printed electronic skin that responds appropriately to stimuli,” he said.
The researchers printed a grid of 168 synaptic transistors manufactured from zinc-oxide nanowires directly onto the surface of a flexible plastic surface to create an electronic skin capable of a computationally efficient, synapse-like response.The synaptic transistor was then attached to a skin sensor located on the palm of a fully articulated, human-shaped robot hand.
When the sensor is contacted, it changes its electrical resistance – a little change corresponds to a light touch, while a bigger change corresponds to a harder touch.This input is intended to resemble how sense neurons function in the human body.
In other words, it learned to walk away from a simulated source of discomfort using an inbuilt information processing system that mimicked the human nervous system’s operation.
Found this article interesting? Follow BG on Facebook, Twitter and Instagram to read more exclusive content we post.
