The workshop will explore, identify and develop technological solutions based on artificial intelligence, digital twins, uncrewed and robotic technologies, quantum and HPC/cloud computing, with a specific focus on the digital transformation of the logistics, material handling and warehousing services managed by Leonardo Logistics.
Digital logistics network
The research unit develops methods for the real-time management, processing and conversion of big data from multiple sources and the application of artificial intelligence in the freight transport logistics sector, providing tools to support decision-making processes and simulation scenarios. These research activities involve the dynamic mapping and digitisation of the supply chain and logistics network, dynamic transport optimisation using advanced artificial intelligence and digital twin functionalities, forecasting, and the integration of the Track & Trace shipment service and external data sources.
The research unit studies innovative warehouse management methods and models using artificial intelligence, digital twins and intelligent autonomous systems. In particular, these activities focus on the modelling of virtual warehouses using digital twin tools; the application and specific integration of AI-based robotic systems; the development of intelligent, autonomous technologies to support handling procedures and inventory management; packaging optimisation models, through the introduction of automated systems, and optimisation models for a highly complex and integrated network of warehouses.
Advanced materials forecasting
The research unit develops forecasting models to support the procurement of materials. These techniques are based on artificial neural networks that are able to process adaptive scenarios of the trends in both internal and external factors (e.g. production schedules, technological innovations, contractual conditions with the various players in the supply chain, trends in the relevant stock market indices, contingent market forces, supplier reliability, and other elements of risk, etc.). These models allow for the development of a forward demand plan for materials that are not subject to deterministic demand (e.g. auxiliary production materials, consumables, chemicals and mechanical linkage components). This research also includes creating an environment for simulating ‘what-if’ scenarios that take into consideration the fluctuations between all of the variables that could influence the evaluation model of the expected results (e.g. predicted service level, economic assets tied up in stocks, supply chain lead times, etc.).