Meta-Learning for Fast Adaptation in Intent Inferral on a Robotic Hand Orthosis for Stroke

TL;DR

This paper introduces MetaEMG, a meta-learning method that enables rapid adaptation of neural networks for intent inference in stroke patients using EMG signals, reducing data collection efforts.

Contribution

It is the first to formulate intent inferral for stroke patients as a meta-learning problem and demonstrates fast adaptation with minimal data and fine-tuning.

Findings

MetaEMG improves intent inferral accuracy with small datasets.

Fast adaptation achieved with few fine-tuning epochs.

First application of meta-learning to stroke intent inference.

Abstract

We propose MetaEMG, a meta-learning approach for fast adaptation in intent inferral on a robotic hand orthosis for stroke. One key challenge in machine learning for assistive and rehabilitative robotics with disabled-bodied subjects is the difficulty of collecting labeled training data. Muscle tone and spasticity often vary significantly among stroke subjects, and hand function can even change across different use sessions of the device for the same subject. We investigate the use of meta-learning to mitigate the burden of data collection needed to adapt high-capacity neural networks to a new session or subject. Our experiments on real clinical data collected from five stroke subjects show that MetaEMG can improve the intent inferral accuracy with a small session- or subject-specific dataset and very few fine-tuning epochs. To the best of our knowledge, we are the first to formulate intent inferral on stroke subjects as a meta-learning problem and demonstrate fast adaptation to a new session or subject for controlling a robotic hand orthosis with EMG signals.