User independent hand motion recognition for robot arm manipulation

다국어 초록 (Multilingual Abstract)

In the present work, tele-manipulation of robot arm and gripper is experimentally performed using inertia measurement unit (IMU) and electromyogram (EMG)-based human motion recognition. The movement of robot arm and motion of robot gripper is determined based on the measured IMU and EMG data, respectively. To overcome user dependence which is one of main disadvantage of EMG-based motion recognition, reference voluntary contraction method-based normalization of measured EMG data is carried out. Training and test data of EMG are obtained from experiments for four kinds of hand motion of four experimental participants. After extraction of feature vectors, artificial neural network is applied for the EMGbased hand motion recognition. Even when training data and test data are obtained from different participants, it is confirmed that classification accuracy can be greatly improved through the proposed simple normalization method. Finally, a real-time tele-manipulation of 6-degree-offreedom robot arm is demonstrated successfully by adopting the proposed user independent human motion recognition method.

참고문헌 (Reference)

1 S. Tadokoro, "The world robot summit disaster robotics categoryachievements of the 2018 preliminary competition" 33 : 286-293, 2019

2 M. Tavakoli, "Robust hand gesture recognition with a double channel surface EMG wearable armband and SVM classifier" 46 : 121-130, 2018

3 G. Jang, "Robotic index finger prosthesis using stackable double 4-BAR mechanisms" 23 : 318-325, 2013

4 Smart Systems KIT, "Robot Arm Tele-manipulation Using Unnomalized EMG"

5 Smart Systems KIT, "Robot Arm Tele-manipulation Using Nomarlized EMG"

6 T. Wang, "Remote-controlled vascular interventional surgery robot" 6 : 194-201, 2010

7 L. Zhang, "Real-time and user-independent feature classification of forearm using EMG signals" 27 : 101-107, 2019

8 P. Geethanjali, "Myoelectric control of prosthetic hands : stateof-the-art review" 9 : 247-255, 2016

9 M. A. Hussein, "Motion control of robot body by using kinect sensor" 8 : 1384-1388, 2014

10 I. B. Abdallad, "Kinect-based sliding mode control for lynxmotion robotic arm" 2016

11 "Intuitive"

12 W. Geng, "Gesture recognition by instantaneous surface EMG images" 6 : 36571-, 2016

13 E. P. Doheny, "Effect of elbow joint angle on force-EMG relationships in human elbow flexor and extensor muscles" 18 : 760-770, 2008

14 P. K. Artemiadis, "EMG-based control of a robot arm using low-dimensional embeddings" 26 : 393-398, 2010

15 V. G. T. Francesco, "Decoding of individuated finger movements using surface electromyography" 56 : 1427-1434, 2009

16 T. Matsubara, "Bilinear modeling of EMG signals to extract userindependent features for multiuse myoelectric interface" 60 : 2205-2213, 2013

17 K. Englehart, "A wavelet based continuous classification scheme for multifunction myoelectric control" 48 : 302-311, 2001

18 L. Bi, "A review on EMG-based motor intention prediction of continuous human upper limb motion for human-robot collaboration" 51 : 113-127, 2019

19 J. -U. Chu, "A real-time EMG pattern recognition system based on linear-nonlinear feature projection for a multifunction myoelectric hand" 53 : 2232-2239, 2006

20 C. Fleischer, "A human-exoskeleton interface utilizing electromyography" 24 : 872-882, 2008