Information Systems facilitate monitoring and planning of transportation and logistics resources. By doing so, they ultimately help to reduce costs, traffic congestion, and CO2 emission.
This is achieved by providing a networked infrastructure in which data is collected from logistics and transportation resources, such as the current location of trucks, or the current picking times of orders in a warehouse. Other relevant data service providers, such as weather service providers, can be included in this infrastructure.
From the data that is collected in this manner, information is created, using novel techniques from the area of data science. Such information includes predictions of travel times or waiting times for future transportation or picking orders. It also includes visualizations of the way in which supply chain processes are executed, and how this execution possibly deviates from how the processes were intended, as well as the effects that these deviations may have on key performance indicators.
With that information, planning can be improved using techniques from artificial intelligence. For example, if we can predict better at which time containers will be released at the Port of Rotterdam, we can use that information to transport more containers with cheaper and more environmentally friendly modes of transportation, such as trains or barges.
Against this background, we work on the following techniques:
- Architectures for information sharing
- Data-driven demand prediction
- Data driven prediction of travel times, service times, and arrival times
- Integrating data-driven predictions and shared information in transport planning
- AI-driven techniques for improving transport planning