Researchers from the University of Alberta in Canada have developed a pioneering prosthetic arm that uses AI to respond to the user’s intention.

Called the Bento Arm, the assistive device uses an onboard computer to respond to a combination of muscle signals and electrical activity in the wearer’s upper arm and shoulder to control the elbow and wrist with high degrees of precision and accuracy.

The AI-powered prosthetic uses machine learning to map the wearer’s intent, will, and desire for how the arm will move.

“Robotic limbs are increasingly common, but here the difference is that AI is critical for connecting the person with their robot arm,” explained Patrick Pilarski, the co-lead of the Bionic Limbs for Improved Natural Control (BLINC) Lab at the University of Alberta, an interdisciplinary research group that designs smart prosthetics.

Patrick says that BLINC’s technology is completely open-source, available for use by researchers, companies and hospitals around the world.

“Open-source technology helps people get the right prosthetic technology at the time of prescription, so they get a prosthetic device that suits them best,” added Patrick. “It’s all about improving someone’s ability to do activities in their daily life and community.”

The BLINC Lab and the open-source BLINCdev collaboration are supported by Amii and the Glenrose Hospital Foundation.

In October last year, BLINC’s representative Chris Neilson demonstrated the Bento Arm at Cybathlon 2024.

Cybathlon is a global competition that sees disabled people master everyday tasks with the help of newly developed assistive technologies, such as exoskeletons, powerchairs, prosthetic legs, and brain computer interfaces.

There are eight different disciplines to compete in, where a “pilot” solves a task using assistive technologies that teams from around the world have developed. The aim of Cybathlon is to significantly advance assistive technologies for disabled people.

The Bento Arm won eighth place at Cybathlon 2024 in the arm prosthesis race.

“Chris had to essentially drive the Bento Arm, much like you might drive a race car, telling his arm what to do using signals and movement from his body,” Patrick commented. “Machine learning is a key piece of that relationship.”

Learn more about the Bento Arm in the video below: