Researchers at the University of Utah used artificial intelligence to make a commercial TASKA Prosthetics hand act more like a natural hand. They fitted custom fingertips that measured pressure and included optical proximity sensors sensitive enough to detect an effectively weightless cotton ball landing on a finger.
The team trained a neural network on the proximity data so each finger moved to the right distance for a stable grasp. Each finger has its own sensor and can "see" what is in front of it, so the digits work in parallel to form a secure hold on different objects. To avoid the user and machine fighting over control, the researchers developed a bioinspired shared-control system that balances human and AI input.
The study, led by Jacob A. George and Marshall Trout, appears in Nature Communications. The system was tested with four participants whose amputations were between the elbow and wrist. Participants completed fine motor tasks like picking up small objects and drinking from a plastic cup. The team plans to combine these sensors and intelligent control with implanted neural interfaces. Funding came from the National Institutes of Health and the National Science Foundation.
Difficult words
- artificial intelligence — computer systems that learn and make decisions
- fingertip — end part of a finger used to touchfingertips
- sensor — device that detects and measures changessensors
- neural network — computer model that learns from data
- shared-control — method dividing control between human and machine
- amputation — loss of a limb by surgical removalamputations
- neural interface — device connecting nerves to electronic systemsneural interfaces
Tip: hover, focus or tap highlighted words in the article to see quick definitions while you read or listen.
Discussion questions
- How would having fingertips with tiny sensors change everyday tasks for a prosthetic user?
- What are possible advantages and disadvantages of a shared-control system between a person and AI?
- Would you feel comfortable using a device with implanted neural interfaces? Why or why not?
Related articles
People learn to use robotic leg prostheses but misjudge their gait
A four-day study found that people who practised with a robotic lower‑limb prosthesis improved their walking but misjudged their own movement. Researchers say better visual feedback could help users calibrate their body image and gait.
Ecuador teams build tech to fight election disinformation
A revived Hacks Hackers chapter in Ecuador held a February conference and a hackathon to tackle electoral disinformation. Three winning teams — Goddard, VeritasAI and PillMind — received prizes, mentoring and support to develop prototypes.
Dopamine helps lock in new skills during sleep
A study from the University of Michigan finds that dopamine neurons become active during NREM sleep soon after a person learns a movement. Their activity, together with sleep spindles, strengthens motor memories and improves skills after sleep.
Jamaica seeks cheaper energy after high electricity bills
After Hurricane Beryl many Jamaicans said their electricity bills rose sharply. Regulators recommended lower payments for some customers, and the government is studying solar and ocean renewables, though experts warn projects need large funding and protection from storms.