EMG-Based Control of a 5 DOF Robotic Manipulator

Gowtham, S.; Krishna, K.M. Adithya; Srinivas, T. Arun; Raj, R. G. Pranav; Joshuva, A.

doi:10.1109/wispnet48689.2020.9198439

Cited by 13 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The person is in a resting position in this illustration, and [35]. Similarly, controlled motion of a five DOF robotic arm using electromyogram signals and control of a four DOF robotic arm using EEG signals have been achieved [36,37]. The proposed system achieves six DOF of the prototype arm using real-time EEG signals.…”

Section: Resultsmentioning

confidence: 99%

Spectral Analysis and Validation of Parietal Signals for Different Arm Movements

Ganesan¹,

Juliet²,

Joshi³

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Brain signal analysis plays a significant role in attaining data related to motor activities. The parietal region of the brain plays a vital role in muscular movements. This approach aims to demonstrate a unique technique to identify an ideal region of the human brain that generates signals responsible for muscular movements; perform statistical analysis to provide an absolute characterization of the signal and validate the obtained results using a prototype arm. This can enhance the practical implementation of these frequency extractions for future neuro-prosthetic applications and the characterization of neurological diseases like Parkinson's disease (PD). To play out this handling method, electroencephalogram (EEG) signals are gained while the subject is performing different wrist and elbow movements. Then, the frontal brain signals and just the parietal signals are separated from the obtained EEG signal by utilizing a band pass filter. Then, feature extraction is carried out using Fast Fourier Transform (FFT). Subsequently, the extraction process is done by Daubechies (db4) and Haar wavelet (db1) in MATLAB and classified using the Levenberg-Marquardt Algorithm. The results of the frequency changes that occurred during various wrist movements in the parietal region are compared with the frequency changes that occurred in frontal EEG signals. This proposed algorithm also uses the deep learning pattern analysis network to evaluate the matching sequence for each action that takes place. Maximum accuracy of 97.2% and maximum error range of 0.6684% are achieved during the analysis. Results of this research confirm that the Levenberg-Marquardt algorithm, along with the newly developed deep learning hybrid PatternNet, provides a more accurate range of frequency changes than any other classifier used in previous works of literature. Based on the analysis, the peak-to-peak value is used to define the threshold for the prototype arm, which performs all the intended degrees of freedom (DOF), verifying the results. These results would aid the specialists in their decision-making by facilitating the analysis and interpretation of brain signals in the field of neuroscience, specifically in tremor analysis in PD.

show abstract

Section: Resultsmentioning

confidence: 99%

Spectral Analysis and Validation of Parietal Signals for Different Arm Movements

Ganesan¹,

Juliet²,

Joshi³

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

show abstract

“…The problem of robotic control in harmful environments has led to the development of different approaches over the past decades. In [9], this problem is addressed by using electromyogram (EMG) signals recorded from the muscles of the elbow. The proposed applications were assisting elderly people, supporting people with physical disabilities, or teleoperation in hazardous sites.…”

Section: Related Workmentioning

confidence: 99%

User-oriented Natural Human-Robot Control with Thin-Plate Splines and LRCN

Lima,

Amaral,

Nascimento-Jr

et al. 2021

Preprint

View full text Add to dashboard Cite

We propose a real-time vision-based teleoperation approach for robotic arms that employs a single depth-based camera, exempting the user from the need for any wearable devices. By employing a natural user interface, this novel approach leverages the conventional fine-tuning control, turning it into a direct body pose capture process. The proposed approach is comprised of two main parts. The first is a nonlinear customizable pose mapping based on Thin-Plate Splines (TPS), to directly transfer human body motion to robotic arm motion in a nonlinear fashion, thus allowing matching dissimilar bodies with different workspace shapes and kinematic constraints. The second is a Deep Neural Network hand-state classifier based on Long-term Recurrent Convolutional Networks (LRCN) that exploits the temporal coherence of the acquired depth data. We validate, evaluate and compare our approach through both classical cross-validation experiments of the proposed hand state classifier; and user studies over a set of practical experiments involving variants of pick-and-place and manufacturing tasks. Results revealed that LRCN networks outperform single image Convolutional Neural Networks; and that users' learning curves were steep, thus allowing the successful completion of the proposed tasks. When compared to a previous approach, the TPS approach revealed no increase in task complexity and similar times of completion, while providing more precise operation in regions closer to workspace boundaries.

show abstract

“…It has been seen in the reviewed literature that different control methods were used to control the exoskeleton robot arm. In the literature studies, it is seen that ready-made robot arms are used and controlled only with EMG signals or only with position and acceleration sensors [19][20][21][22][23][24][25][26][27]. In some recent studies in the literature, it is seen that only PID controllers [28][29][30][31] control robot arms.…”

Section: Introductionmentioning

confidence: 99%

Implementation and Comparison of Wearable Exoskeleton Arm Design with Fuzzy Logic and Machine Learning Control

Ersin,

Yaz

2024

Journal of Sensors

View full text Add to dashboard Cite

In this study, a wearable exoskeleton arm was designed and controlled with different control methods to help people with muscle disorders in their arms and support treatment. The developed robot arm was transferred to Simulink software with the Simmechanics application. Two electromyography (EMG) muscle sensors and the ADXL335 position and acceleration sensors attach to the human arm’s biceps and triceps muscle areas. As the human moved the arm, data were obtained from the EMG muscle sensors and the ADXL335 position and acceleration sensor. The received data were first trained with the fuzzy logic algorithm. The same data were then trained with machine learning algorithms in Simulink software. It has been determined that the best result is the quadratic support vector machine (SVM) algorithm. The fuzzy logic algorithm trained with the PID controller block and the received sensor data have been added to the degrees of freedom regions that will enable rotation in the block diagram of the previously exported system. Later, the fuzzy logic block was removed and the machine learning algorithm, the quadratic SVM algorithm, was added. The designed system was operated with two different control systems, and the control algorithm closest to the human arm movement was determined. In addition, each part of the system, whose design was prepared, was removed and assembled separately with a 3D printer. ESP32 microcontroller development board was used to control the system, and it was run in real-time with EMG muscle sensors and position sensors.

show abstract

EMG-Based Control of a 5 DOF Robotic Manipulator

Cited by 13 publications

References 8 publications

Spectral Analysis and Validation of Parietal Signals for Different Arm Movements

Spectral Analysis and Validation of Parietal Signals for Different Arm Movements

User-oriented Natural Human-Robot Control with Thin-Plate Splines and LRCN

Implementation and Comparison of Wearable Exoskeleton Arm Design with Fuzzy Logic and Machine Learning Control

Contact Info

Product

Resources

About