Analyzing the robotic behavior in a smart city with deep enforcement and imitation learning using IoRT

Abstract

Smart City aims to develop an environment in which different things goes to different people. The smart city provides a core infrastructure by improving the status of the inhabitants by providing a smart environment by applying Smart Solutions. The Internet of Things (IoT) is a revolutionary concept which finds its way in many applications such as business, industry, healthcare, Transportation, modern Information Technology applications and many more. IoT combined with Artificial Intelligence (AI) can be applied to many day to day applications in superior systems like transportation, robotics, industrial, and automation systems applications. This research focuses on developing a robotic behavior control using the Internet of Robotic Things (IoRT) using deep learning for a Smart City. The IoRT is a promising standard that brings together autonomous robotic systems in the midst of the IoT vision of connected sensors and smart objects pervasively embedded in the day to day environments. Robotic behavioral control models the robot with the essential features to react with the immediate environment via sensory-motor links. Robotic behavioral control has a direct interconnection between the sensors and actuators and controls the functions necessary to move around the environment and carry out necessary tasks. This deep learning solution applied to the robotic behavioral control for robotic application uses two main paradigms: Deep Reinforcement Learning (DRL) and Imitation Learning (IL).DRL merges the concept of deep learning architecture using neural networks and Reinforcement learning algorithms to identify the behavior of the robots.IL focus on imitating human learning or expert demonstration for controlling the robot behavior. The behavior of the robot is monitored in a diner and its performance is estimated to be 92% in realtime