Additional Coverage:
Bionic Hands Get a Brain Boost: AI-Powered Prosthetics Promise Easier, More Intuitive Control
Salt Lake City, UT – A groundbreaking new study suggests that the key to unlocking the full potential of bionic hands lies in giving them a bit of artificial intelligence. Researchers at the University of Utah NeuroRobotics Lab have developed a bionic hand that, controlled by an AI program under the guidance of the amputee, offers a remarkable approximation of normal hand dexterity.
Published Tuesday in the journal Nature Communications, the research tackles a significant hurdle in prosthetic design: making these advanced devices feel natural and intuitive to use. “As lifelike as bionic arms are becoming, controlling them is still not easy or intuitive,” explained lead investigator Marshall Trout, a postdoctoral researcher involved in the study. He noted that nearly half of all users abandon their prostheses, often due to poor controls and the high cognitive burden required to operate them.
The challenge stems from the fact that much of our natural hand movement is unconscious. We don’t consciously tell each finger how to grip a coffee mug or a pen; it just happens. However, traditional robotic prosthetic hands demand this precise, deliberate thought for every movement, making simple tasks surprisingly complex.
To bridge this gap, the researchers turned to AI. They trained the AI to respond to proximity and pressure sensors embedded in the bionic hand.
These sensors are incredibly sensitive – the pressure sensors can detect the weight of a cotton ball, while the proximity sensors allow each finger to “see” an object. This enables the AI to automatically form specific, pre-programmed grasping postures, taking the mental load off the user.
Amputees then work in tandem with the AI, sharing control to achieve the desired function. “What we don’t want is the user fighting the machine for control,” Trout stated.
“In contrast, here the machine improved the precision of the user while also making the tasks easier. In essence, the machine augmented their natural control so that they could complete tasks without having to think about them.”
The innovative bionic hand was tested with four volunteers who had amputations between the elbow and the wrist. All participants demonstrated improved grip security and precision, requiring significantly less mental effort to control the prosthesis. They were able to perform a range of everyday tasks, from picking up small objects to raising a cup – a seemingly simple action that actually requires precise pressure control to avoid dropping or crushing the object.
“By adding some artificial intelligence, we were able to offload this aspect of grasping to the prosthesis itself,” said senior researcher Jacob George, a professor of engineering at the University of Utah. “The end result is more intuitive and more dexterous control, which allows simple tasks to be simple again.”
Looking ahead, the team is now exploring even more advanced solutions, including brain implants that could allow amputees to control prosthetics with their minds and even experience a sense of touch through the hand’s pressure sensors. This research marks a significant step towards creating prosthetics that not only mimic the appearance of a natural hand but also its effortless function.