Unmanned Vehicles (UVs) and the Industry Internet of Things (IoT) are two examples of new technology being incorporated into manufacturing processes during the fourth industrial revolution. IT networks must be machine-compatible to integrate these technologies; this includes addressing problems with connectivity, fog, and cloud-based computing security, lowering latency, and improving data reliability and standard of service. Regarding IoT, AI techniques must handle resource management, network

deployment, and these problems. The significant issues are unstable and high-latency communications between Industrial IoT endpoints and the Cloud. By extending storage and computation to the network’s edge, fog computing offers a valuable tool for merging intricately linked processing systems. Interoperability may be addressed using fog in an IoT gateway and advanced software distributed on the edge. However, as an IoT gateway is essential to processing and delivering data to many systems and platforms, selecting one is critical regarding accuracy and latency. Intelligent IoT monitoring and real-time control based on Integrating Autonomous Robots for Instantaneous Industrial Operations, visual recognition, and cloud/edge computing services are proposed to address these challenges. By deploying Deep Learning (DL) facilities close to customers who want them, latency and processing costs associated with transmitting data through the Cloud may be minimized. The suggested methods enhance platform decision-making and industrial automation system performance by integrating cloud-based services into an operational loop. A smart approach that offers a trade-off between accuracy and latency is suggested to choose the right AI for the situation under observation.