AI-Enabled Soft Sensing Array for Simultaneous Detection of Muscle Deformation and Mechanomyography for Metaverse Somatosensory Interaction.
Adv Sci (Weinh)
; 11(16): e2305025, 2024 Apr.
Article
em En
| MEDLINE
| ID: mdl-38376001
ABSTRACT
Motion recognition (MR)-based somatosensory interaction technology, which interprets user movements as input instructions, presents a natural approach for promoting human-computer interaction, a critical element for advancing metaverse applications. Herein, this work introduces a non-intrusive muscle-sensing wearable device, that in conjunction with machine learning, enables motion-control-based somatosensory interaction with metaverse avatars. To facilitate MR, the proposed device simultaneously detects muscle mechanical activities, including dynamic muscle shape changes and vibrational mechanomyogram signals, utilizing a flexible 16-channel pressure sensor array (weighing ≈0.38 g). Leveraging the rich information from multiple channels, a recognition accuracy of ≈96.06% is achieved by classifying ten lower-limb motions executed by ten human subjects. In addition, this work demonstrates the practical application of muscle-sensing-based somatosensory interaction, using the proposed wearable device, for enabling the real-time control of avatars in a virtual space. This study provides an alternative approach to traditional rigid inertial measurement units and electromyography-based methods for achieving accurate human motion capture, which can further broaden the applications of motion-interactive wearable devices for the coming metaverse age.
Palavras-chave
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Músculo Esquelético
/
Dispositivos Eletrônicos Vestíveis
Idioma:
En
Ano de publicação:
2024
Tipo de documento:
Article