Author/Authors :
Kastalskiy, Innokentiy National Research Lobachevsky State University of Nizhny Novgorod - Gagarin Ave - Nizhny Novgorod, Russia , Mironov, Vasily National Research Lobachevsky State University of Nizhny Novgorod - Gagarin Ave - Nizhny Novgorod, Russia , Lobov, Sergey National Research Lobachevsky State University of Nizhny Novgorod - Gagarin Ave - Nizhny Novgorod, Russia , Krilova, Nadia National Research Lobachevsky State University of Nizhny Novgorod - Gagarin Ave - Nizhny Novgorod, Russia , Pimashkin, Alexey National Research Lobachevsky State University of Nizhny Novgorod - Gagarin Ave - Nizhny Novgorod, Russia , Kazantsev, Victor National Research Lobachevsky State University of Nizhny Novgorod - Gagarin Ave - Nizhny Novgorod, Russia
Abstract :
A neuromuscular interface (NI) that can be employed to operate external robotic devices (RD), including commercial ones, was
proposed. Multichannel electromyographic (EMG) signal is used in the control loop. Control signal can also be supplemented
with electroencephalography (EEG), limb kinematics, or other modalities. Te multiple electrode approach takes advantage of the
massive resources of the human brain for solving nontrivial tasks, such as movement coordination. Multilayer artifcial neural
network was used for feature classifcation and further to provide command and/or proportional control of three robotic devices.
Te possibility of using biofeedback can compensate for control errors and implement a fundamentally important feature that has
previously limited the development of intelligent exoskeletons, prostheses, and other medical devices. Te control system can be
integrated with wearable electronics. Examples of technical devices under control of the neuromuscular interface (NI) are presented.
