Press "Enter" to skip to content

Algorithm that can ‘see’ intention could lead to improved prostheses

Researchers at the University of Illinois at Chicago have developed a mathematical algorithm that can “see” a user’s intention for movement, even if the movement is interrupted. The algorithm could lead to the development of “smart” prostheses for people with stroke or disabilities that can inhibit movement, according to a university press release.

“Say you are reaching for a piece of paper, and your hand is bumped mid-reach — your eyes take time to adjust; your nerves take time to process what has happened; your brain takes time to process what has happened and even more time to get a new signal to your hand,” Justin Horowitz, a University of Illinois at Chicago graduate student research assistant and first author of the study, stated in the release. “So, when something unexpected happens, the signal going to your hand cannot change for at least a tenth of a second — if it changes at all.”

To test this concept, Horowitz examined people who reached for an object on a virtual desk, but had their hand pushed in the wrong direction. He then developed an advanced mathematical algorithm that determined a person’s intent by analyzing his or her actions. The algorithm can predict the way the person wants to move and can be incorporated into systems of artificial intelligence.

The results of the study are published online in PLOS ONE.

Horowitz noted the algorithm could help “smart” prostheses interpret the intentions of stroke patients, who can unintentionally corrupt their own actions due to muscle spasms or tremors.

“We call it a psychic robot,” Horowitz stated. “If you know how someone is moving and what the disturbance is, you can tell the underlying intent — which means we could use this algorithm to design machines that could correct the course of a swerving car or help a stroke patient with spasticity.”

Reference:

Horowitz J, et al. PLOS ONE. 2015;doi: 10.1371/journal.pone.0137289.

Disclosure: Horowitz reports the study is supported by National Institute of Neurological Disorders and Stroke grant NS053606.

Be First to Comment

Leave a Reply

Your email address will not be published.