On-Demand Myoelectric Control Using Wake Gestures to Eliminate False Activations During Activities of Daily Living

TL;DR

This paper introduces a novel on-demand myoelectric control system using wake gestures to significantly reduce false activations during daily activities, enhancing reliability for real-world applications.

Contribution

It proposes and evaluates a wake gesture-based control paradigm that effectively switches modes to prevent false activations in myoelectric systems during ADLs.

Findings

Achieved >99.9% suppression of non-target muscle inputs during ADLs

Successfully demonstrated wake gesture control in tasks like alarm dismissal and robot control

Maintained reliable mode switching with high sensitivity during intentional gestures

Abstract

While myoelectric control has recently become a focus of increased research as a possible flexible hands-free input modality, current control approaches are prone to inadvertent false activations in real-world conditions. In this work, a novel myoelectric control paradigm -- on-demand myoelectric control -- is proposed, designed, and evaluated, to reduce the number of unrelated muscle movements that are incorrectly interpreted as input gestures . By leveraging the concept of wake gestures, users were able to switch between a dedicated control mode and a sleep mode, effectively eliminating inadvertent activations during activities of daily living (ADLs). The feasibility of wake gestures was demonstrated in this work through two online ubiquitous EMG control tasks with varying difficulty levels; dismissing an alarm and controlling a robot. The proposed control scheme was able to appropriately ignore almost all non-targeted muscular inputs during ADLs (>99.9%) while maintaining sufficient sensitivity for reliable mode switching during intentional wake gesture elicitation. These results highlight the potential of wake gestures as a critical step towards enabling ubiquitous myoelectric control-based on-demand input for a wide range of applications.