Toward Drift-Resistant Assistive Device Control via sEMG–SMG Fusion

Abstract

Effective assistive robotic technology requires an effective control interface. Optical-flow-based sonomyography (SMG) can provide continuous control signals for such devices, but may drift over time. This work investigates whether surface electromyography (sEMG) can reduce drift by restricting SMG tracking to periods of muscle activation. Although the combined sEMG–SMG signal reduces noise, our naive threshold-based approach does not improve control performance because tissue deformation can occur without measured sEMG activation. These results motivate improved sensor placement and more advanced fusion methods for hybrid biosensing control.

Gavin Sueltz

BS/MS Student, ME

Maria Herrera

BS/MS Student, ME

Vikram Athithan

Undergraduate, ME

Laura A. Hallock

Assistant Professor of Mechanical Engineering

My research interests include robotic assistance and rehabilitation, neuromusculoskeletal sensing, and human–robot control interfaces.