Artificial Intelligence And Prosthetics Join Forces To Create New Generation Bionic Hand
Friday, July 13, 2018
A team of scientists from Imperial College London and the University of Göttingen have teamed up to create a ‘next generation’ bionic hand. This bionic hand is special because it uses artificial intelligence to improve its functionality.
The work carried out by the team and published in Science Robotics, shows that with the help of machine learning, fluid motion of prosthetics can be achieved. At the moment, movement of prosthetics is controlled by motors that are stimulated with external signals from surrounding muscles in the amputee. In the new bionic hand, however, the patient’s intentions are interpreted by a human-machine interface which then sends signals to the prosthetic. Senior author of the paper Professor Dario Farina from Imperial College’s Department of Bioengineering says, ‘When designing bionic limbs, our main goal is to let patients control them as naturally as though they were their biological limbs . This new technology takes us a step closer to achieving this.’
The bionic hand relies on eight electrodes to pick up weak electrical signals from the stump of the amputee which then sends signals to a miniature computer in the prosthetic. The machine learning algorithm in the computer interprets the signals and provides the set of instructions needed for the bionic hand to move in the way the patient wants. Not only can it move in the way the patient wants, but the speed of the movement can also be controlled which provides a more natural feeling. Farina says, ‘The new bionic hand is not only more natural, but it is also superior in terms of functionality in daily tasks than what’s currently available to patients.’ Check out the short video below of the comparison of conventional bionic hands and a machine learning bionic hand.
Farina says, ‘Following this clinical study, we hope to have this available on the market for patients within three years.’ Before the bionic hand was tested, there was an initial training phase where the patient could train the machine learning algorithm to interpret their own electronic signals. In future prototypes, the aim is to get rid of this initial training phase. On top of this, the team would like to have the bionic hand receive signals from the patient via wireless technology and have greater control over the individual movement of the fingers. This could be the ‘next generation’ of prosthetics and the future is looking very bright. Watch this space.