Toward Robust, Adaptiveand Reliable Upper-Limb Motion Estimation Using Machine Learning and Deep Learning-A Survey in Myoelectric Control

To develop multi-functionalhuman-machine interfaces that can help disabled people reconstruct lost functions of upper-limbs, machine learning (ML) and deep learning (DL) techniques have been widely implemented to decode human movement intentions from surface electromyography (sEMG) signals. However, due to the high complexity of upper-limb movements and the inherent non-stable characteristics of sEMG, the usability of ML/DL based control schemes is still greatly limited in practical scenarios. To this end, tremendous efforts have been made to improve model robustness, adaptation, and reliability. In this article, we provide a systematic review on recent achievements, mainly from three categories: multi-modal sensing fusion to gain additional information of the user, transfer learning (TL) methods to eliminate domain shift impacts on estimation models, and post-processing approaches to obtain more reliable outcomes. Special attention is given to fusion strategies, deep TL frameworks, and confidence estimation. Research challenges and emerging opportunities, with respect to hardware development, public resources, and decoding strategies, are also analysed to provide perspectives for future developments

Automated summary

This article provides a systematic review of recent achievements in the field of multi-functional human-machine interfaces. By exploring the fusion of multi-modal sensors, transfer learning methods, and post-processing approaches, the aim is to enhance the robustness, adaptability, and reliability of the models. Additionally, research challenges and emerging opportunities in hardware development, public resources, and decoding strategies are analyzed to provide perspectives for future developments.