AI in logistics: recognising opportunities – using data
How data from logistics can create added value in AI applications
The logistics industry is constantly evolving – driven in particular by digitalisation, automation and data-based decision-making. Artificial intelligence (AI) is playing an increasingly important role in this, even if the real key to progress lies not in the AI itself, but in the underlying data, as no AI can work effectively without high-quality, structured and contextualised data. ‘This is exactly where our department's research comes in: data-driven is the keyword,’ explains Prof Dr Ralf Elbert, Professor at the Department of Corporate Management and Logistics at TU Darmstadt.
Use of AI in logistics
AI applications are already being used selectively in logistics – for example in route optimisation, demand forecasting and predictive maintenance. Machine learning systems help to recognise patterns in large amounts of data and derive recommendations for action. For example, bottlenecks in the warehouse can be identified at an early stage or delivery processes optimised.
However, AI is not the only topic of the future in . Rather, the focus is on collecting, analysing and using data generated in the logistics process. At the Department of Business Management and Logistics, students learn how to obtain reliable information from data and derive well-founded decisions from it. The ability to link data sources, model processes based on data and integrate digital systems in a meaningful way forms the basis for all other technologies – including AI. logistics studies
Data-based logistics is an ideal field of application for AI
AI offers interesting prospects for logistics, especially for standardisable, data-intensive processes. There is great potential in demand forecasting and sales planning, in production and transport optimisation with their diverse data. However, the ability to capture, interpret and utilise data intelligently remains crucial.