Bridging Human-Robot Co-Adaptation via Biofeedback for Continuous Myoelectric Control
Open Access
- 3 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (12) , 8573-8580
Abstract
This letter proposes a novel human-robot co-adaptation framework for robust and accurate user intent recognition, specifically in the context of automatic control in assistance robots such as neural prosthetics and rehabilitation devices empowered by electrophysiological signals. Our goal is to incorporate user adaptability early in the training phase to facilitate both machine recognition and user adaptability, rather than relying solely on brute-force machine learning methods. The proposed framework is featured by applying biofeedback-based user adaptive behavior into model training, while the machine can adapt to those changes through online learning. Specifically, this study focuses on the recognition of two-degree-of-freedom simultaneous and continuous wrist movement intentions based on surface electromyogram (sEMG) array signals, and the performance is tested on twelve able-bodied subjects. The co-adaptive evaluation experiment demonstrates the robust control of this method by introducing sEMG electrode displacement as perturbations. Experimental results show that this method improves the completion time of centre-out tasks by 13% compared to conventional methods (Cohen's d=0.637), and debias 86% of the effect of electrode shift perturbations. This study provides insights into the potential for incorporating human adaptability into machine intelligence to improve user intent recognition and automatic robot control.Keywords
Funding Information
- CEC-Tencent Robotics X Rhinoceros Bird Special Research Program Project
- National Natural Science Foundation of China (92148205, 62173089, 61673105, 62003169)
This publication has 26 references indexed in Scilit:
- Model and experiments to optimize co-adaptation in a simplified myoelectric control systemJournal of Neural Engineering, 2018
- Interface Prostheses With Classifier-Feedback-Based User TrainingIEEE Transactions on Biomedical Engineering, 2016
- EMG Biofeedback for online predictive control of grasping force in a myoelectric prosthesisJournal of NeuroEngineering and Rehabilitation, 2015
- User adaptation in long-term, open-loop myoelectric training: implications for EMG pattern recognition in prosthesis controlJournal of Neural Engineering, 2015
- Concurrent Adaptation of Human and Machine Improves Simultaneous and Proportional Myoelectric ControlIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2015
- Characterization of a Benchmark Database for Myoelectric Movement ClassificationIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2014
- The Extraction of Neural Information from the Surface EMG for the Control of Upper-Limb Prostheses: Emerging Avenues and ChallengesIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2014
- Intuitive, Online, Simultaneous, and Proportional Myoelectric Control Over Two Degrees-of-Freedom in Upper Limb AmputeesIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2013
- A high-performance neural prosthesis enabled by control algorithm designNature Neuroscience, 2012
- Simultaneous and Proportional Estimation of Hand Kinematics From EMG During Mirrored Movements at Multiple Degrees-of-FreedomIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2011