Modeling-Based EMG Signal (MBES) Classifier for Robotic Remote-Control Purposes

Abstract

The fast-growing human–robot collaboration predicts that a human operator could command a robot without mechanical interface if effective communication channels are established. In noisy, vibrating and light sensitive environments, some sensors for detecting the human intention could find critical issues to be adopted. On the contrary, biological signals, as electromyographic (EMG) signals, seem to be more effective. In order to command a laboratory collaborative robot powered by McKibben pneumatic muscles, promising actuators for human–robot collaboration due to their inherent compliance and safety features have been researched, a novel modeling-based electromyographic signal (MBES) classifier has been developed. It is based on one EMG sensor, a Myotrac one, an Arduino Uno and a proper code, developed in the Matlab environment, that performs the EMG signal recognition. The classifier can recognize the EMG signals generated by three hand-finger movements, regardless of the amplitude and time duration of the signal and the muscular effort, relying on three mathematical models: exponential, fractional and Gaussian. These mathematical models have been selected so that they are the best fitting with the EMG signal curves. Each of them can be assigned a consent signal for performing the wanted pick-and-place task by the robot. An experimental activity was carried out to test and achieve the best performance of the classifier. The validated classifier was applied for controlling three pressure levels of a McKibben-type pneumatic muscle. Encouraging results suggest that the developed classifier can be a valid command interface for robotic purposes.