Through the recent extensive technological advancements in the field of Ubiquitous Computing in general and in the field of Industrial Internet of Things(IIoT) in par, we are observing a breakthrough in the industrial digitalization and automation concepts. It is indeed the foundation of the 4th Industrial Revolution (Industry 4.0), which has become the central area of focus in a broad spectrum of industrial fields, especially in the manufacturing context. The key role of ubiquity enablers is to provide the management systems with fine-grained monitoring and controlling mechanisms while merging the required equipment and computational hardware out of sight in the background. However, the ever-increasing dynamism and complexity in the industrial environments, on the one hand, and demanding mass customization and higher levels of optimization requirements, on the other hand, require an extraordinary sophisticated management process. As a pioneer industrial field, the manufacturing industries engaged already in the digital transformation era and, therefore, are subject to devising more robust and holistic management approaches. As a significant subsystem, in-house logistics (i.e., Intralogistics) in the manufacturing shop-floors denotes one of the most volatile and dynamic environments, which is in urgent demand for viable planning solutions as part of the shift towards full automation. To that end, Automated Guided Vehicles (AGV) have been introduced for accomplishing the material handling operation in the industrial shop-floors. Nevertheless, without a highly reactive and flexible management logic, AGV utilization can only lead to more management burden, which exceeds the capacity of human resources. On the other hand, traditional planning approaches are far incapable of coping with such highly dynamic and time-critical planning and scheduling tasks. This is where one might think of Artificial Intelligence (AI) as a promising approach for automating different operational aspects of the AGV-based Intralogistics environments. Therefore, in this thesis, we aim to develop a practical AI planning approach and integrating that intelligent logic into the ubiquitous computing environment of Intralogistics. To that end, we propose our novel Centralized Intelligent Intralogistics Management System (CIIMS), which incorporates an AI planning service for reaching the automated management objective.