We will teach you in 10 minutes
The Swiss have taught a bionic prosthesis to hold objects securely
Vasily Sychev, N+1
Researchers from the Federal Polytechnic School of Lausanne have developed a prototype system that allows a person without a hand to securely hold objects with a bionic prosthesis and control each of his fingers separately. To do this, they have developed a learning algorithm that helps a person control the prosthesis. Details about the work of Swiss developers are published in Nature Machine Intelligence, and it is briefly described in the message of the Polytechnic school.
Some modern bionic prostheses work on the principle of reading myoelectric signals from the surface of the skin of the stump. A person gives mental orders to the lost limb to perform an action, which causes a reaction of the muscles in the stump and the appearance of electrical potentials, which are recorded, interpreted and performed by a bionic prosthesis. Difficulties in managing such a prosthesis lies in a large number of "noises", side electrical potentials recorded on the surface of the skin of the stump, which are not related to the work of muscles during movement.
The algorithm, developed by researchers from the Federal Polytechnic School of Lausanne, was created using a multilayer perceptron, a neural network built on the passage of a signal through several neural layers. This neural network was trained on several volunteers: three people with amputated limbs and seven with whole limbs. In general, neural network training took about 10 minutes for each of the participants.
The multilayer perceptron was trained to recognize an attempt to bend each finger separately, simultaneously the index and middle or ring and little fingers, clenching into a fist, pinch grip and thumb flexion. Based on the results of the training, the generated algorithm controlled the Allegro Hand robotic brush, consisting of a thumb and three ordinary fingers. This brush was installed on an industrial manipulator Kuka IIWA 7. All this construction imitated a bionic prosthetic right hand.
During the experiments, problems were found with the third finger on the robot arm, and it had to be completely turned off. As a result, the robot arm could only operate with a thumb and two ordinary fingers. With the help of a robot arm, volunteers were able to take plastic bottles and perform various actions with them, including pouring their contents into a glass.
2019_SharedControl_Vimeo from Mediacom EPFL on Vimeo.
The developers included a modified object retention algorithm in the robot arm control algorithm – if the bottle taken into the robot arm began to slip, the brush increased the grip force. The reaction to the slip was no more than 400 milliseconds.
Previously , developers from The University of Utah announced the completion of the LUKE prosthetic arm, named after the main character of "Star Wars" Luke Skywalker. They equipped the device with biofeedback. Now the owner of the prosthesis can use electrodes implanted in peripheral nerves and muscles to feel touching objects, vibrations and even pain. In addition, the modification allows the user to control the prosthesis more precisely.
Portal "Eternal youth" http://vechnayamolodost.ru