Meta's new wristband
Meta researchers unveiled Wednesday a wristband prototype that translates electrical muscle signals into computer commands, allowing users to control devices through subtle hand gestures without physical contact. The technology, detailed in a research paper published in the journal Nature, represents a major advancement in accessibility technology for people with motor disabilities
The sEMG-RD (surface electromyography research device) can interpret handwriting motions traced in the air at 20.9 words per minute, move cursors with wrist turns, and open applications through finger pinches. Unlike previous iterations that required individual calibration, this prototype works immediately across diverse users through neural networks trained on data from thousands of participants
The wristband employs 16 gold-plated sensors arranged around the wrist to capture electrical signals at 2kHz sampling rates, detecting muscle contractions even when movements are barely perceptible. According to researchers led by Thomas Reardon, Meta's director of neuromotor interfaces, and Patrick Kaifosh, research science director at Reality Labs, the device can sense intended actions before physical movement occurs.
The technology streams signals wirelessly over Bluetooth, processing them in real-time without requiring line-of-sight cameras or invasive procedures
Meta is collaborating with Carnegie Mellon University to test the wristband with people who have spinal cord injuries. Douglas Weber, a professor in Carnegie Mellon's Department of Mechanical Engineering, noted that even individuals with complete hand paralysis exhibit muscle activity that the device can interpret.
The technology offers a less invasive alternative to brain-computer interfaces like Neuralink while providing stronger signals than EEG-based headsets. the wristband operates at higher frequencies than EEG systems, making it more practical for immediate deployment