From Unstable Contacts to Stable Control: A Deep Learning Paradigm for HD-sEMG in Neurorobotics

TL;DR

This paper introduces a deep learning model that enhances the robustness of high-density surface electromyography (HD-sEMG) interfaces for neurorobotics, effectively handling unstable skin contact and electrode disconnections.

Contribution

It presents a novel 3D Dilated Efficient CapsNet architecture trained with augmented data to improve resilience against electrode dropout in HD-sEMG systems.

Findings

Model maintains high performance despite electrode dropout.

Conventional models' performance degrades with dropout, but our approach recovers it.

Proposed method enhances reliability of wearable neurorobotic interfaces.

Abstract

In the past decade, there has been significant advancement in designing wearable neural interfaces for controlling neurorobotic systems, particularly bionic limbs. These interfaces function by decoding signals captured non-invasively from the skin's surface. Portable high-density surface electromyography (HD-sEMG) modules combined with deep learning decoding have attracted interest by achieving excellent gesture prediction and myoelectric control of prosthetic systems and neurorobots. However, factors like pixel-shape electrode size and unstable skin contact make HD-sEMG susceptible to pixel electrode drops. The sparse electrode-skin disconnections rooted in issues such as low adhesion, sweating, hair blockage, and skin stretch challenge the reliability and scalability of these modules as the perception unit for neurorobotic systems. This paper proposes a novel deep-learning model providing resiliency for HD-sEMG modules, which can be used in the wearable interfaces of neurorobots. The proposed 3D Dilated Efficient CapsNet model trains on an augmented input space to computationally `force' the network to learn channel dropout variations and thus learn robustness to channel dropout. The proposed framework maintained high performance under a sensor dropout reliability study conducted. Results show conventional models' performance significantly degrades with dropout and is recovered using the proposed architecture and the training paradigm.