Research from Uppsala University and the Karolinska Institute could pave the way for artificial hands and robots to sense touch like a human hand. Their study has been published in the journal science. This technology can also be used to restore lost functionality to patients after a stroke.
“Our system can determine what kind of object it's facing, just like a blindfolded person, just by feeling it and deciding whether it's a tennis ball or an apple, for example. As such,” says Zibin Zhang, associate professor of electrical engineering. Uppsala University.
He and his colleague Libo Chen conducted the study in close collaboration with researchers from the Division of Signals and Systems at Uppsala University, who provided data processing and machine learning expertise, and from the Division of Neurobiology, Care Sciences and Society. A group of researchers. of Neurogeriatrics at the Karolinska Institutet.
Inspired by neuroscience, they have developed an artificial tactile system that mimics the way the human nervous system responds to touch. The system uses electrical pulses that process tactile information similar to the human nervous system. “With this technology, a prosthetic hand will feel like part of the wearer's body,” Zhang explains.
The prosthetic system has three main components: an electronic skin (e-skin) with sensors that can detect pressure by touch; A set of artificial neurons that convert analog touch signals into electrical pulses. and a processor that processes signals and identifies objects. In theory, it could learn to identify an unlimited number of objects, but the researchers used 22 different objects to grasp and 16 different surfaces to touch in their tests.
“We are also looking at developing the system so that it can also sense pain and heat. It should also be able to sense what the hand is touching, e.g. as, whether it's wood or metal,” says assistant professor Libo Chen. , who led the study.
According to researchers, interactions between humans and robots or artificial hands can be made safer and more natural thanks to tactile feedback. Prosthetics can also be given the ability to handle objects with the same dexterity as a human hand.
“The skin has millions of receptors. Current e-skin technology cannot provide enough receptors, but this technology makes it possible, so we would like to develop artificial skin for the entire robot,” says Chen.
The technology could also be used clinically, for example, to monitor movement disorders caused by Parkinson's disease and Alzheimer's disease, or to restore functionality to patients after a stroke. To help me.
“The technology can be further developed to detect whether a patient is about to fall. This information can then be used to either externally stimulate muscles to prevent falls,” Zhang says. or an assistive device can be used immediately to handle and prevent it”.