The idea is that interactive artificial intelligence will help prosthetics better recognize human intentions, recognize their surroundings, and continue to grow and improve over time.
It𠏋all in mind: Mind-controlled prosthetics
The technology behind prostheses for the upper extremities has made great leaps and bounds over the past decades. Using surface electromyography, skin electrodes on the rest of the arm can detect the slightest muscle movements. These biological signals can be converted and transmitted to the prosthesis in the form of electrical impulses.
Advertisement
The wearer controls his prosthetic hand using a stump. Methods derived from pattern recognition and interactive machine learning also allow people to teach their prostheses about their individual needs when making gestures or movements.
Currently, advanced robotic prostheses are still suboptimal in terms of comfort, function and control, which is why many amputees still prefer cosmetic prostheses. simply no additional functionality.
The researchers specifically focused on how to improve control of both the prosthetic and real upper limbs. The focus is on what is known as intent detection. They are continuing to record and analyze human biosignals, and are designing innovative machine learning algorithms to detect individual movement patterns.
Previous studies performed on people with and without physical disabilities were used to confirm their results. Furthermore, the autonomy is shared between the human and the robot for the purpose of checking the safety of the results.
Researchers are exploiting the potential offered by intent detection to control assistive and rehabilitation robotics. This includes wearable robots such as prosthetics and exoskeletons, but also robotic arms and simulators using virtual reality.
Source: Eurekalert
