New users of advanced prosthetic devices have to undergo tedious training routines in order for the computer that controls the given prosthesis to understand the wishes of the user. Sensors are used to measure the electrical activity of the muscles use to signal a prosthetic to move, but these signals change drastically depending on the user’s posture and orientation, amount of sweat formed between the skin and the sensors, and even the time of day.
Now researchers from North Carolina State University and the University of North Carolina at Chapel Hill have developed a way of avoiding a lot of this training for prosthetic hands by having the computer adjust its interpretations of muscle activity based on a computer model of the arm and hand.
“When someone loses a hand, their brain is networked as if the hand is still there,” said He (Helen) Huang, professor in the biomedical engineering program at North Carolina State University and the University of North Carolina at Chapel Hill. “So, if someone wants to pick up a glass of water, the brain still sends those signals to the forearm. We use sensors to pick up those signals and then convey that data to a computer, where it is fed into a virtual musculoskeletal model. The model takes the place of the muscles, joints and bones, calculating the movements that would take place if the hand and wrist were still whole. It then conveys that data to the prosthetic wrist and hand, which perform the relevant movements in a coordinated way and in real time – more closely resembling fluid, natural motion.”
Since real anatomy and even biological processes are modeled, the result is natural motion that can be achieved faster than with rote training. While this technology has already demonstrated impressive results, it still requires quite a bit of tuning and trying with real amputees before it becomes commercially available.
Study in IEEE Transactions on Neural Systems and Rehabilitation Engineering: Myoelectric Control Based on A Generic Musculoskeletal Model: Towards A Multi-User Neural-Machine Interface…