Prediction of interaction force using EMG for characteristic evaluation of touch and push motions

Prediction of interaction force between human and contacting environment has always been an important issue for such as robot control and clinical treatment. Although force/torque sensors can provide direct and precise measurement results, in many cases it is inconvenient to attach these sensors on the environment surface or on human beings. The purpose of this paper is to propose a prediction method for interaction force between human and contacting environment, using only electromyographic (EMG) signals. The motions are touch motion and push motion of upper extremity. Seven muscles of the upper limb were selected to record EMG signals. The predict function were derived from two muscle-skeleton models implemented for touch motion and push motion, respectively. The Bayesian linear regression (BLR) algorithm was implemented for parameters calibration. In order to avoid complex model for dynamic movement, a neural network classifier was used to recognize the force exerting motions. The proposed method was applied in a remote interaction force evaluation experiment. The “Phantom Premium” haptic device is used to represent the predicted force in the remote site. The experimental results show that the proposed method can provide acceptable prediction results with root-mean-square (RMS) error below 2.20 N.