KUKA Real-Time Control through Angle Estimation of Wrist from sEMG with Support Vector Regression

In this paper, a wrist joint angle estimation model based on support vector regression(SVR) is established, which is optimized by combining the cuckoo algorithm with the steepest descent method. The sEMG signals were sampled from two forearm muscles. In order to shorten the model train time and improve the accuracy of the estimation model, a new technique combining cuckoo algorithm with the steepest descent optimization method is proposed to find the bestc and bestg of SVR in a short time. Experiments on a subject showed, the proposed method shows a good performance in both accuracy and timeliness. Then, in order to verify the estimation effectiveness and practicality of sEMG, the estimation angle was used to control a KUKA robot in real time, and obtaining a good experimental result. The method discussed in this paper can provide a valuable reference for the sEMG based control for rehabilitation robot systems.

[1]  Feng Zhang,et al.  sEMG-based continuous estimation of joint angles of human legs by using BP neural network , 2012, Neurocomputing.

[2]  Dario Farina,et al.  Intuitive, Online, Simultaneous, and Proportional Myoelectric Control Over Two Degrees-of-Freedom in Upper Limb Amputees , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[3]  Parvin Mousavi,et al.  Joint angle-based EMG amplitude calibration , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  Zengguang Hou,et al.  Estimation of Lower Limb Periodic Motions from sEMG Using Least Squares Support Vector Regression , 2014, Neural Processing Letters.

[5]  H. Kawasaki,et al.  Estimation of finger joint angles from sEMG using a recurrent neural network with time-delayed input vectors , 2009, 2009 IEEE International Conference on Rehabilitation Robotics.

[6]  Dapeng Li,et al.  Artificial Neural Network Prediction of Angle Based on Surface Electromyography , 2011, 2011 International Conference on Control, Automation and Systems Engineering (CASE).

[7]  Arthur F T Mak,et al.  Feasibility of using EMG driven neuromusculoskeletal model for prediction of dynamic movement of the elbow. , 2005, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[8]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[9]  Caihua Xiong,et al.  Simultaneous and Continuous Estimation of Shoulder and Elbow Kinematics from Surface EMG Signals , 2017, Frontiers in neuroscience.