Mind-controlled prosthetics for amputees have been around for years. And they’re amazing. But the functionality they provide is limited. They can be awkward to use and don’t provide fine motor control. And their use was generally confined to those who hadn’t just lost a limb, but who were also paralyzed. That’s because it required a direct interface to the brain, an invasive and risky procedure.
Now engineering researchers at the University of Michicgan have come up with a way to gain better control by using the nerves present in the residual part of an amputee’s limb. This technique takes advantage of:
… faint, latent signals from arm nerves and amplified them to enable real-time, intuitive, finger-level control of a robotic hand.
To achieve this, the researchers developed a way to tame temperamental nerve endings, separate thick nerve bundles into smaller fibers that enable more precise control, and amplify the signals coming through those nerves. The approach involves tiny muscle grafts and machine learning algorithms borrowed from the brain-machine interface field. (Source: University of Michigan)
This is a major breakthrough. Fingers will now work more like fingers, which will enable users to better manipulate objects. Study participants, working in a University research lab:
…were able to pick up blocks with a pincer grasp; move their thumb in a continuous motion, rather than have to choose from two positions; lift
spherically shaped objects; and even play in a version of Rock, Paper, Scissors called Rock, Paper, Pliers.
Beyond being able to play Rock, Paper, Scissors Pliers, there are some more practical uses, like the ability to manipulate a zipper. This new approach enables full rotation of the thumb, as opposed to the limited directional possibilities of earlier approaches.
Here’s what the Michigan researchers did to make all this possible:
They wrapped tiny muscle grafts around the nerve endings in the partici ves new tissue to latch on to. This prevents the growth of nerve masses called neuromas that lead to phantom limb pain. And it gives the nerves a megaphone. The muscle grafts amplify the nerve signals. Two patients had electrodes implanted in their muscle grafts, and the electrodes were able to record these nerve signals and pass them on to a prosthetic hand in real time.
For the user, the manipulation of the prosthetic is done intuitively. They don’t have to think twice, or concentrate hard on the motion they’re trying to achieve. There’s no learning curve. The learning is all done thanks to machine learning algorithms.
This is quite an advancement, and opens up all sorts of new possibilities when it comes to the use of prosthetics. As I’ve said more than once, one of the proudest aspects of being an engineer is the engineering work dedicated to improving lives.
If you’re interested in learning more, you should definitely check out this presentation from the University of Michigan, Thought Into Action, which explores this incredible research.
In the meantime, safe well!