This paper presents a novel training system called the Augmented Mirror Hand (MIRANDA) for advanced prosthetic devices. MIRANDA utilizes virtual reality technology and electromyographic data to train the control system of the prosthesis. The system includes an experimental environment, a hand reflection module, and an aggregation module to collect and store synchronized data. A machine learning algorithm is then trained on the collected data to predict the expected movements of the arm. The experiment was conducted with 10 healthy volunteers, and the results showed a prediction error of around 7 degrees accuracy with a CNN-based decoder. MIRANDA has the potential to be used in combination with other paradigms to record muscle electrical activity data in amputees and support the learning of controlling advanced bionic prosthetic devices, which can lead to more intuitive prosthetic control. The proposed system can also contribute to improving the economic and social outcomes for amputees by better preparing them for the use of advanced prosthetic devices.
CITATION STYLE
Kovalev, A., Makarova, A., Antonov, M., Chizhov, P., Aksiotis, V., Tsurkan, A., … Ossadtchi, A. (2023). Augmented Mirror Hand (MIRANDA): Advanced Training System for New Generation Prosthesis. In Communications in Computer and Information Science (Vol. 1833 CCIS, pp. 77–83). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-35992-7_11
Mendeley helps you to discover research relevant for your work.