The autonomous control of the Service-Oriented robot arms based on the artificial intelligence object identifying technology

Abstract

With the rapid evolution of Artificial Intelligence (A.I.) technology, traditional image recognition approaches are replaced, because the speed of the detection is too slow and not accurate, especially in robot fields. The sensing abilities are the most important feature with a service robot. The object recognition is one of the sensing abilities, in order to let the service robot can detect the object extremely fast and accurate, the robot use Artificial Intelligence technology, the sensing ability of a robot could be improved significantly. In this study, YOLO object Identification approach is used to enhance the robot sensing to locate a particular object, and then to pick it up. In order to reach this goal, the CNN and deep learning technologies are studied.