One way that prosthetic limbs that can be controlled (given that they are rigged to move) is through myoelectric sensing, which is the recording of electrical currents created from movement in the arm's muscle. Users will have to flex their arm and nerves in very specific and uncomfortable patterns to get the hand to make just one kind of motion, and it's like learning a whole new language just to get the prosthetic hand to work.
At the University Of Minnesota, strides are being made in order to create AI controlled limbs without the use of myoelectric sensing. "Now Diu Khue Luu and Anh Tuan Nguyen from the University of Minnesota with colleagues, have found a way to do this using an AI decoder that learns the user’s intention based on the nerve signals it senses in the arm. 'We present a neuroprosthetic system to demonstrate that principle by employing an artificial intelligence (AI) agent to translate the amputee’s movement intent,' they say."
How exactly does this AI work? Well for people only missing one hand (let's say left), they hook up a sensor to their left hand, and one to the area on their arm where their right hand should be. They tell the person to try and think about creating hand movements both for their left hand, and for their "ghost or phantom" hand. The AI that they programmed then reads the information from nerves using the sensors, and compares the data from the right and left hand. This is how they record or calibrate the data of movement for that specific person. The sensors are kept on the right hand and once the prosthesis is put on, whenever they try and use their right hand, the AI will detect the specific type of movement from their nerves, compare it to the previous data, and move the prosthesis in the same way.
"The result is a remarkable degree of dexterity. In tests, the subjects successfully achieve the intended action 99.2% of the time with a median reaction time of 0.81 seconds. Crucially, each movement is intuitive with the AI system matching the intended motion. 'The AI agent allows amputees to control prosthetic upper limbs with their thoughts by decoding true motor intent,' say Luu, Nguyen and co."
How can technology improve this experience? With 3D printing. People are already designing their own prosthetic limbs using 3D modeling software like CAD. The fact that people can literally design their own limb is amazing! Creating prostheses' with 3D printing is much cheaper than using metal or other materials. Combining a well designed hand print with the tech from the University of Minnesota would help so many people regain a functioning limb that moves in a comfortable manner.
for NMD 200 (professor Jon Ippolito).
References: https://www.discovermagazine.com/technology/ai-is-revolutionizing-prosthetic-arm-control
Credits:
Created with images by Yakobchuk Olena - "Ginger girl with prosthesis hand having video call on laptop" • Blue Planet Studio - "3D rendering artificial intelligence AI research of robot and cyborg development for future of people living. Digital data mining and machine learning technology design for computer brain." • LIGHTFIELD STUDIOS - "partial view of male architect with prosthetic arm making model of house at table" • primipil - "Disabled man with artificial prosthetic hand close up male hand against gray background" • THINK b - "robot hand" • Andrii Zastrozhnov - "Rehabilitation of disabled in hospital. Prosthetic arm." • primipil - "Young disabled man with artificial prosthetic hand in casual clothes riding bike"