A review on EMG-based motor intention prediction of continuous human upper limb motion for human-robot collaboration

By Luzheng Bi, Aberham Genetu Feleke, Cuntai Guan. Biomedical Signal Processing and Control, 2019

360 citations recorded by the source corpus.

Abstract Electromyography (EMG) signal is one of the widely used biological signals for human motor intention prediction, which is an essential element in human-robot collaboration systems. Studies on motor intention prediction from EMG signal have been concentrated on classification and regression models, and there are numerous review and survey papers on classification models. However, to the best of our knowledge, there is no review paper on regression models or continuous motion prediction from EMG signal. Therefore, in this paper, we provide a comprehensive review of EMG-based motor intention prediction of continuous human upper limb motion. This review will cover the models and approaches used in continuous motion estimation, the kinematic motion parameters estimated from EMG signal, and the performance metrics utilized for system validation. From the review, we will provide some insights into future research directions on these subjects. We first review the overall structure and components of EMG-based human-robot collaboration systems. We then discuss the state of arts in continuous motion prediction of the human upper limb. Finally, we conclude the paper with a discussion of the current challenges and future research directions.

Subfields: Biomedical Engineering, Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/2a28de3c4d13c7c2285e540b69c2577e27812638

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Cognitive Neuroscience

Citations in the corpus

Estimation of Knee Movement from Surface EMG Using Random Forest with Principal Component Analysis (2019, background): “These predictions can be broadly categorized as classification and regression models [14].”
Real-Time EMG Based Pattern Recognition Control for Hand Prostheses: A Review on Existing Methods, Challenges and Future Implementation (2019, methodology): “To delineate this, a control algorithm requires parameters such as kinematics and models of joints [13], motion and activities range [11].”
Deep Learning for EMG-based Human-Machine Interaction: A Review (2021, methodology): “Moreover, there are new formats, such as fused time-domain descriptors (fTDD) [74], [75] and Hilbert spacefilling curves [76], which are used for next step processing.”