A of led by an Indian-born engineer in the UK has created an that can sense ‘pain’, which they say could help create a new of intelligent robots with human sensitivities. Professor Ravinder Dahiya, from the James Watt School of Engineering at the University of Glasgow, said the discovery marks a real step towards creating large-scale neuromorphic printed electronic skins that respond appropriately to stimuli.

His team at the university has developed an artificial skin based on a novel processing system of synaptic transistors that mimics the brain’s neural pathways for learning. Robotic hands using smart skin are said to exhibit an extraordinary ability to learn to respond to external stimuli.

“We learn early in life to appropriately respond to unexpected stimuli such as pain to prevent us from harming ourselves again. Of course, the development of this new electronic skin didn’t really involve causing pain as we know it — it’s just A shorthand way of explaining the process of learning from external stimuli,” Dahiya explained.

“Through this process, we were able to create an electronic skin capable of distributed learning at the hardware level, which does not require sending messages back and forth to the central processor before taking action. Instead, it greatly speeds up the process by reducing the required the amount of computation to respond to the touch process,” he said.

In a new paper, “Electronic skin based on printed synaptic transistors lets robots feel and learn,” published Wednesday in the journal Science Robotics, researchers at the University of Scotland describe how they built their prototype computational electronic skin, and How it improves the current state of touch-sensitive robotics.

See also  NASA released the "Aremis Agreement", the basic principles of the "International Convention on the Exploration of the Moon"

The development of the electronic skin is described as the latest breakthrough in flexible, stretchable printed surfaces by the Bendable Electronics and Sensing Technologies (BEST) group at the University of Glasgow.

Fengyuan Liu, a member of the BEST team and co-author of the paper, added: “In the future, this research could the basis for more advanced electronic skins, enabling robots to explore and interact with the world in new ways, or to create that can approach human touch sensitivity. prosthetics.” For decades, scientists have been working to create artificial skin that feels tactile. A widely explored approach is to distribute an array of contact or sensors on the surface of the electronic skin to allow it to detect when it comes into contact with an object.

The data from the sensors is then sent to a computer for processing and interpretation. Sensors often generate large amounts of data that can take to process and respond properly, introducing delays that reduce the potential effectiveness of skins for real-world tasks.

The University of Glasgow team’s new electronic skin draws inspiration from how the human peripheral nervous system interprets signals from the skin to eliminate latency and consumption.

Once the human skin receives the input, the peripheral nervous system starts processing it at the point of contact, reducing it to just the important information before sending it to the brain. The reduction in sensory data allows efficient use of the communication channels needed to send the data to the brain, which then responds almost immediately, allowing the body to respond appropriately.

See also  Comet SW3's Spectacular Meteor Shower Tau Herculids Could Happen Next Week: How To Watch It And Other Details

To build a computationally efficient, synaptic-like electronic skin, the researchers printed a grid of 168 synaptic transistors made of zinc oxide nanowires directly onto the surface of a flexible plastic surface. They then connected synaptic transistors with skin sensors that reside on the palm of the fully articulated humanoid robot.

When the sensor is touched, it records a change in its resistance – changes correspond to light touches, while heavier touches produce larger changes in resistance. The input is designed to mimic how sensory neurons work in the human body.