Internet of Things based Cyber-Physical System framework for Real-Time Operations

Abstract

The paper presents an intelligent cyber-physical system (CPS) framework using object detection for real-time operations in an Internet-of-Things (IoT) connected physical environment. To facilitate real-time object detection, we used a variant of Convolutional Neural Network (CNN) known as Faster R-CNN (R stands for the region proposals). The control action related to the detected object is exchanged with the actuation system using Real-Time Data Exchange (RTDE) protocol. We demonstrate the proposed framework to perform pick-and-place operations as it is a widely performed operation on a production floor using a Universal Robot (UR5) as an actuation system.