University of Utah engineers give bionic hand a 'Mind of Its Own' with AI

Engineers from the University of Utah have given a bionic hand a mind of its own.

Marshall Trout, a post-doctoral researcher, noted that a significant number of amputees (estimated between 20% and 50%) eventually stop using their bionic hands, partly because operating them requires excessive cognitive effort.

“We have robotic arms that are out there that are capable of recreating all of the different motions of the human hand,” said Professor Jacob George, director of the Utah Neurorobotics Lab.

He added, “But our ability to intuitively control those in a dexterous way is really difficult.”

Trout, under the supervision of George, modified a commercially available hand with optical and touch sensors and artificial intelligence. As the hand approaches an object, the fingers automatically move towards it, stopping just at the point of making contact.

Using electrical signals from the wearer’s muscles, the AI provides a “cognitive assist” to the amputee by controlling the strength of the prosthetic hand’s grasp.

“It’s just helping shape the hand. And then the user can just think about, you know, how much force they want to apply without having to get into the nuances of like ‘Where do I want the hand positioned?’” George stated.

“It’s the human who’s doing all the intention, and the AI is operating behind the scenes to make them a little bit more seamless with their technology.”

Trout said that using the system built by University of Utah engineers, patients were able to manipulate objects with more agility and fewer errors.

Sam Matagi, who lost both hands in a power line accident while working as a lineman, was one of the amputees who tested the system.

Matagi described the feeling as having an assistant, like a phone managing his schedule and other tasks, but likened it more specifically to having “a crane operator inside your arm.”

George believes that the newly developed system could be available on the market in the next five years, and he expects that sensors and AI will become mainstream in prosthetics in the next five to ten years.