A review of the key technologies for sEMG-based human-robot interaction systems. (September 2020)

• Record Type: Journal Article
• Authors: Li, Kexiang; Zhang, Jianhua; Wang, Lingfeng; Zhang, Minglu; Li, Jiayi; Bao, Shancheng
• Is Part Of: Biomedical signal processing and control. Volume 62(2020)
• Publication Date: 2020-09
• Subjects: Surface electromyography (sEMG) -- Human-robot interaction system (HRIS) -- sEMG pattern recognition -- Multisource information fusion; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2020.102074
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: As physiological signals that are closely related to human motion, surface electromyography (sEMG) signals have been widely used in human-robot interaction systems (HRISs). Some reviews on myoelectric control systems have focused on signal processing, feature extraction and pattern recognition methods. However, to the best of our knowledge, there is no review paper on the comprehensive description of HRISs based on sEMG. Therefore, in this paper, we present a detailed review of the key technologies related to the use of sEMG signals in HRISs. First, the advantages and difficulties of using sEMG signals in HRISs are summarized, and some typical applications are introduced. Second, the research status and existing problems are discussed for four key technologies related to sEMG-based HRISs: signal preprocessing and feature extraction, human motion intention recognition, robustness enhancement for sEMG pattern recognition, and multisource information fusion based on sEMG. Finally, we discuss the bottlenecks hindering the application of sEMG-based HRISs and present prospects for this currently active research area.