Prediction-based reactive control strategy for human-robot interactions

In this paper a reactive control strategy intended for human-robot interactions (HRI) is presented. A conventional reactive control scheme is reviewed first. This is followed by the introduction of a new prediction-based reactive control strategy. The new control strategy considers foreseeable dangerous events by predicting human motion using artificial neural networks, based on the previous pattern of the motion. This approach enables a robot to foresee an upcoming danger in order to take preventive actions before the danger is immanent. Experimental results for a CRS-F3 robot manipulator are presented in order to demonstrate and validate the effectiveness of this method.