Movement control of robot in real time using EMG signal

Abstract

The Electromyogram signals or EMG signals are generated whenever there is any muscular activity. These signals can be detected easily over the surface of the body. The surface EMG signal detected from voluntarily activated muscles can be used as a control signal for functional neuromuscular electrical stimulation. Muscle signal (EMG) based switching systems may be an option for people who retain some ability to contract certain muscles but may not be able to operate a mechanical switch. This may be because the particular muscle that can be contracted is not suitable for operating a switch or because the muscle contraction is not strong enough to operate the switch. A proper positioning of the recording electrodes in relation to the stimulation electrodes, and a proper processing of the recorded signals is required to reduce the stimulus artifact and the non-voluntary contribution. As these signals are generated whenever there is any muscular activity, so, we can recognize any muscular activity made by the human by measuring the amplitude of the signal. Based on decision made upon the amplitude of the EMG signal we can take many decisions or we can make machine of our interest. In this paper we have made a real time machine which can classify the muscle activity between two actions: relaxed position and contracted position. The prototype hardware has been tested and verified for the working in real time.