British researchers have created an electronic skin that can feel “pain”.
They believe this will help create a new generation of intelligent robots with human-like sensitivity and the ability to learn from painful mistakes.
A team of engineers from the University of Glasgow have developed an artificial skin for learning using a new type of processing system based on “synaptic transistors” that mirror neural pathways in the brain.
Robotic hands using smart skins have an excellent ability to learn to respond to external stimuli.
The researchers will explain how they prototyped an electronic computing skin (e-skin) and how it enhances the cutting edge of touch-sensitive robotics.
Scientists have been working for decades to create touch-sensitive artificial skin.
One of the most studied methods consists of extending a series of contact or pressure sensors on the surface of the electronic skin to detect contact with an object.
The data received from the sensor is sent to the computer for processing and interpretation.
Sensors often generate large amounts of data that take a long time to process and respond properly, which can cause delays and reduce the potential effect of skin on actual work.
A new form of grass-go-team electronic skin stimulates how the human peripheral nervous system responds to signals from the skin to eliminate incubation and energy expenditure.
As soon as human skin receives input, the peripheral nervous system begins processing it at the point of contact, paring it down to important information before sending it to the brain.
This reduction in sensory data allows efficient use of the communication channels necessary to send data to the brain. The brain responds almost instantly, allowing the body to respond appropriately.
To create computationally efficient synaptic electronic skins, the researchers printed a grid of 168 synaptic transistors made from zinc oxide nanowires directly onto the surface of a flexible plastic surface.
Next, we connected the synaptic transistor to a skin sensor in the heart of a fully articulated human-shaped robot.
Touch the sensor to detect changes in electrical resistance. Small changes correspond to light touches and strong touches produce large changes in resistance.
This input is designed to mimic the work of sensory neurons in the human body.
In the first generation electronic masks, this input data was sent to the computer for processing. Instead, an integrated circuit in the skin acts as an artificial synapse, reducing the input to a simple voltage spike. Its frequency changes with the level of pressure applied to the skin, accelerating the reaction process.
This group used the alternating output of this voltage spike to teach the skin to respond appropriately to the simulated pain elicited by the robot’s hand reaction.
By setting the input voltage limit that triggers the reaction, the team was able to remove the robot arm from the sharp edge at the center of the wrist.
In other words, it learned to steer clear of simulated sources of discomfort through the onboard information processing process that mirrors the workings of the human nervous system.
The development of the electronic skin is the latest achievement in flexible and elastic printing from the Flexible Electronics and Sensing Technologies (BEST) team led by Professor Ravinder Dahia of the University of Glasgow.
Professor Dahia, a spokesman for the Faculty of Engineering at James Watt University, said:
Of course, the development of this new form of electronic skin did not include actual pain as we know it, it is a shorthand way of explaining the learning process from external stimuli.
“Through this process, we were able to create an electronic skin that could distribute learning at the hardware level without having to send a message before it could be executed on the CPU.
Instead, it significantly speeds up the touch response process by reducing the number of calculations required.
“We believe this is a real step forward in our work to create a large neuromorphic-printed electronic skin that can respond appropriately to stimuli.”
Fengyuan Liu, a member of the BEST group and co-author of the paper, said: “In the future, this research could be the basis for a more advanced electronic skin that will allow robots to explore and communicate in new ways around the world. Reaching levels of Tactile sensitivity close to humans. Construction of artificial limbs that can be made.”
A paper by the team titled “Printed Synapse Transistor-Based Electronic Skin for Robots to Feel and Learn” was published in Science Robotics.
This study was funded by the Engineering and Physical Sciences Research Council (EPSRC).
Source: Metro
I have worked in the news industry for over 10 years. I have a vast amount of experience in covering health news. I am also an author at News Bulletin 247. I am highly experienced and knowledgeable in this field. I am a hard worker and always deliver quality work. I am a reliable source of information and always provide accurate information.
