Research on Picking Identification and Positioning System Based on IOT

Abstract

The key and necessary condition for accurate picking are to identify and locate the target fruit accurately. This paper focuses on the development of picking robot, mainly through two aspects: software and hardware. Moreover, it mainly consists of the binocular vision system and the camera calibration model. Based on these two core components, it can complete the function of identification and positioning. The results show that it can accurately locate the target location in the aspect of recognition function. What is more, its error is no more than 8mm, and its picking rate is over 96%. It shows high precision and efficiency, which plays a decisive role in the realization of picking automation.