Real-Time Logistics and Warehouse Integration via Networks of the Future and Dynamic Digital Twins

Warehouse management is becoming increasingly important due to supply and logistics demands. It is the central hub for inventory tracking and logistics operations. Warehouse management is a complicated collection of different operations. Due to this intricacy, errors become unavoidable and firm to visualise. There are many challenges faced in warehouse management such as inaccuracy in inventory, lack of realtime tracing, and coordination. However, the introduction of Industry 4.0 tools including smart sensors, robotics, and Artificial Intelligence (AI) techniques together for precise modelling of Autonomous Mobile Robots (AMR) systems. These technologies can be combined with human operations is necessary to achieve optimal performance and cost-effectiveness. This research presents a novel approach to integrate human-based operations with AMR to generate a realtime digital twin of automated warehouses. A predictive model for process time estimate was created by us using human factors analysis and multivariate multiple regression. In order to guarantee a realistic portrayal of warehouse activities, we also used the A* algorithm to recreate AMR methods. With an emphasis on the critical role that accurate data play in ensuring the validity and efficacy of our analysis, our research seeks to decrease costs while improving operational efficiency. This research will focus on the enhancements in scheduling by simulating the calculated time and automatically scheduling the production line as well as smart logistics management with the assistance of IIoT (Industrial Internet of Things), process modelling, and 5G. The case study will evaluate the performance of pathfinding and grid mapping in Autonomous Guided Vehicles (AGVs) operating in a warehouse to promote efficiency with time and warehouse management.