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
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.
Brothers build magnetic system to remove arsenic
Arsenic in Indian groundwater causes serious health problems. Two brothers from Bihar developed METAL, a chemical-free magnetic way to clean water and built the MARU unit; their startup Navmarg has treated over 300,000 litres and plans sensors and AI.
