Teleoperated robotic arm movement using electromyography signal with wearable Myo armband

Abstract

The main purpose of this research is to move the robotic arm (5DoF) in real-time, based on the surface Electromyography (sEMG) signals, as obtained from the wireless Myo gesture armband to distinguish seven hand movements. The sEMG signals are biomedical signals that estimate and record the electrical signals produced in muscles through their contraction and relaxation, representing neuromuscular activities. Therefore, controlling the robotic arm via the muscles of the human arm using sEMG signals is considered to be one of the most significant methods. The wireless Myo gesture armband is used to record sEMG signals from the forearm. In order to analyze these signals, the pattern recognition system is employed, which consists of three main parts: segmentation, feature extraction, and classification. Overlap technique is chosen for segmenting part of the signal. Six time domain features (MAV, WL, RMS, AR, ZC, and SSC) are extracted from each segment. The classifiers (SVM, LDA, and KNN) are employed to enable comparison between them in order to obtain optimum accuracy of the system. The results show that the SVM achieves higher system accuracy at 96.57 %, compared to LDA reaching 96.01 %, and 92.67 % accuracy achieved by KNN.The electrical signal produced through contraction or relaxation of muscles which are ruled by the 3 nervous system are called Electromyography (EMG) signals. This signal depends on the physiological and anatomical characteristic of muscles and is considered to be a complex signal.The surface electromyography (sEMG) are EMG signals that collect the electrical signals of the muscle activity through placing the electrodes on the surface of the skin. Fig. 1 shows the surface electromyography (sEMG) signals that start with the low amplitude, which changes with muscle contraction activity [1].Detection of sEMG signals are useful and improve important methodologies in many applications.Such applications are becoming increasingly in demand, in spheres such as biomedical engineering[2], the robotics arm and automation control systems [3,4].The measurements and precise representations of the sEMG signals depend on the characteristics of the electrodes and their relationship with the skin of the forearm or shoulder, and are affected by the amplifier design, and the transition of the sEMG signals from analogue to digital format [5].A raw sEMG signal has the maximum voltage of (0-2) mV, and a range of frequency approximately between (0-1000) Hz, but the important frequency that contains useful information lies between (20-500) Hz [6]. The sEMG signals can be acquired by positioning surface electrodes on the arm or the shoulder.There are two main types of the electrodes that acquire sEMG signals: needle electrodes (inside the skin) and surface electrodes, with no significant variance between them [7]. There are two types of surface electrodes: wired like Myoware muscle sensor or wireless such as Myo gesture control armband. They differ in features, the most important of which is the sampling rate. All these...

Real-Time EMG Based Pattern Recognition Control for Hand Prostheses: A Review on Existing Methods, Challenges and Future Implementation

“…The studies based on feature extractions proposed across TD, FD and TFD shows the best results using the TD EMG feature. Hudgins [34] proposed the four different time-domain features (MAV, WL, ZC, SSC) [35] for feature extraction from EMG, and it is the most adopted one to date in the field of myoelectric pattern recognition [11]. Willison amplitude (WAMP) [36], Autoregressive (AR) model parameters [37] and time domain-auto regression (TD-AR) are also used to extract feature information.…”

Applying Deep Learning Techniques to Estimate Patterns of Musical Gesture

“…The IMU bracelet weighs 93 grams with an adjustable diameter of 12.5-38.4 cm; none of the eight participants reported that the device caused any significant impediment their optimal performance. The hardware includes eight medical-grade stainless steel EMG sensors which report raw electrical muscle activity in a voltage range of 0-2 mV expressed in oscillations of −1 to 1 (Hassan et al, 2019). Two battery cells are embedded with a capacity of 260 mA/hr and an operating voltage range of 1.7 to 3.3 V. A three-axis gyroscope records angular velocity in degrees of change in radians per second, and a three-axis accelerometer as an estimation of −8 to 8 g (1 g = 9.81 m/s 2 ).…”

EMG Characterization and Processing in Production Engineering

“…Other classification techniques based in ML are used for gestures and movement identification, obtaining better results than other traditional methods [ 59 , 60 , 61 , 62 ], despite presenting some disadvantages such as the lack of transparency in the determination of results [ 12 ].…”

“…Hassan et al [ 62 ] used a Myo bracelet, with eight channels taken from the forearm, to classify seven proposed hand movements. The proposed movements are used to control a robotic arm using inexpensive hardware.…”