Uppsala University and Karolinska Institutet researchers have made a breakthrough that could lead to prosthetic hands and robots with the ability to feel touch like a human hand. Published in the journal Science, their study also suggests potential for restoring lost functionality to stroke patients. “Our system can determine what type of object it encounters as fast asfrom the Signals and Systems Division at Uppsala University, who provided data processing and machine learning expertise, and a group of researchers from the Department of Neurobiology, Care Sciences and Society, Division of Neurogeriatrics at Karolinska Institutet.
Using ideas from neuroscience, they have created an artificial sense of touch that allows a person to distinguish between objects just by touching them, such as determining whether an object is a tennis ball or an apple,” explains Zhibin Zhang, a docent at the Department of Electrical Engineering at Uppsala University.
Together with his colleague Libo Chen, they conducted the research with the help of experts in data processing and machine learning. Their artificial tactile system was inspired by neuroscience and developed in collaboration with researchers from Karolinska Institutet.The technology is a system that mimics the human nervous system’s response to touch, using electrical pulses to process tactile information. According to Zhang, this allows a prosthetic hand to feel like a natural part of the body. The artificial system consists of an electronic skin with touch sensors, artificial neurons that convert touch signals into electrical pulses, and a processor that identifies objects. In theory, it can learn to recognize an infinite number of objects.The researchers have used 22 different objects for grasping and 16 different surfaces for touching in their tests. Assistant Professor Libo Chen, who led the study, mentioned that they are also working on developing the system to feel pain and heat, as well as to distinguish the material of the hand’s touch, such as wood or metal. The researchers believe that tactile feedback can make interactions between humans and robots or prosthetic hands safer and more natural, and that prostheses can be given the ability to handle objects with the same dexterity as a human hand.”The skin is equipped with a large number of receptors. Current e-skin technology is not able to provide a sufficient number of receptors, but this new technology has the potential to change that, allowing us to create artificial skin for an entire robot,” explains Chen.
This technology could also have medical applications, such as monitoring movement impairments caused by Parkinson’s disease and Alzheimer’s disease, or aiding patients in regaining lost functionality after a stroke.
“The technology could be further developed to detect when a patient is at risk of falling. This information could then be used to either externally stimulate a muscle to prevent the fall, or prompt an assistive device to take action,” explains Chen.Zhang emphasizes, “The spike timing-based coding in neuromimetic tactile system enables dynamic object classification, which can take over and prevent it.
