ReFIT Algorithm Will Lead To Mind Controlled Robotic Limbs
When a paralyzed person thinks of moving a limb, the part of the brain in charge of that movement still produces some activity. Researchers from Stanford University have worked out ReFIT or Recalibrated Feedback Intention-Trained Kalman filter algorithm. It utilizes this brain activity with a silicon chip implanted into the brain of the subject and records action potentials, before sending the data back to a computer. The frequency with which the nerve impulses are produced provides the computer with information on the direction and speed of the user’s desired movement. The Stanford team claims this innovative algorithm suitable for brain-implantable prosthetic systems (neuroprosthetics); it increases the effectiveness of mind-controlled computer cursor movement to a degree that approaches the speed, accuracy and natural movement of a real arm. During the tests conducted on rhesus monkeys, they were using the ReFIT algorithm to mentally direct a mouse cursor to an onscreen dot, and then hold it for half a second. The reults showed that ReFIT performed far better than previous algorithms, and enabled the monkeys to reach their target twice as quickly as before (75-85 percent of the speed of real arms). The FDA has recently approved clinical human trials of ReFIT, so in future it might become the basis for the creation of mind controlled robotic limbs.