Autonomous Mobile Inspection of Process Parameters using Reinforcement Learning in Industrial IoT Environment

Due to their error-prone and time-consuming nature, conventional manual inspection techniques are inadequate in the Industrial Internet of Things (IIoT) environment. This paper presents an approach to resolve these challenges by applying Reinforcement Learning (RL) for autonomous mobile inspection of the industrial process parameters. Our system optimizes the navigation and inspection strategies of mobile robots in industrial settings with the Deep Deterministic Policy Gradient (DDPG) algorithm. The mobile robot is equipped with sensors to inspect parameters and support decisions on where the most important inspections need to be conducted. Our method provides improved navigation efficiency, avoid human interventions, and increases overall productivity. This paper highlights the potential of RL to revolutionize industrial inspections while ensuring optimal performance and safety. Simulation results show the validation of the proposed approach concerning autonomous navigation in the industrial environment, reaching target locations, and successful inspection of the industrial parameters. video of the test cases demonstrating the system can be found in this link: [https://youtu.be/XG2ivEbs5jc]