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

2024-03-19

IEEE/RJS International Conference on Intelligent RObots and Systems

AI Summary

To address two key challenges in electromyography (EMG)-based hand movement intention decoding for stroke rehabilitation—poor cross-subject/cross-session generalization and severe scarcity of labeled data—this paper pioneers a meta-learning formulation for hand motion intent recognition and proposes MetaEMG, a lightweight meta-learning framework. MetaEMG integrates model-agnostic meta-learning (MAML) with a compact neural architecture, enabling rapid personalization using fewer than 50 labeled samples from a single session and only 1–3 fine-tuning iterations. Evaluated on clinical EMG data from five stroke patients, MetaEMG significantly improves intention classification accuracy under few-shot conditions. This work establishes a novel paradigm for adaptive, low-label-cost intent decoding in rehabilitation robotics.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Machine Learning: Learning with Manifolds
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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 metalearning 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.

Problem

• Fast adaptation for robotic hand orthosis intent inference
• Reducing data collection burden for stroke rehabilitation devices
• Improving EMG-based control accuracy across sessions and subjects

Innovation

• Meta-learning approach for fast adaptation
• Reduces data collection burden with meta-learning
• Improves accuracy with small dataset fine-tuning