KLM as new partner in the AI & Mobility Lab ✈️

In 2023, KLM transported approximately 30 million passengers. A significant portion of these passengers transfer at Schiphol Airport. It is expected that these numbers will continue to grow in the coming years. For successful and punctual flight operations, many pieces of the puzzle need to fall into place. The planning of this puzzle is becoming increasingly complex, for example, due to uncertainties about the weather, absenteeism, and equipment malfunctions.

‍

Associate Professor Marjan van den Akker of the AI & Mobility Lab explains: "Executing a flight requires a lot: of course, an aircraft, cabin crew, and a pilot, but also various ground activities such as catering, ground staff, and loading and unloading luggage. This means that if a flight is delayed or an aircraft is unavailable, other processes are also disrupted, such as baggage handling or passengers and crew missing their connections. Artificial intelligence can help alleviate such disruptions quickly and effectively."

‍

Most data-driven airline
‍

"At KLM, we are strongly focused on innovation, and this commitment is underscored by this collaboration," says Bob Tulleken, Vice President of Operational Decision Support at KLM. "We aim to become the most data-driven airline in the world, and this collaboration with the University of Utrecht illustrates our determination to remain at the forefront of a challenging industry. By using AI, we can build more robust and adaptable aviation operations."

‍

With its expertise in algorithm optimization and experience in aviation, transportation, and logistics, the University of Utrecht is ideally suited to address these issues together with KLM, Van den Akker confirms. "The knowledge of our researchers aligns seamlessly with the needs of KLM. Within the AI Labs, we can also exchange knowledge and experience in artificial intelligence with other partners. For example, the NS (Dutch Railways) faces similar challenges to KLM."

‍

"The expertise of our researchers and the desires of KLM complement each other perfectly.

- Marjan van den Akker, Associate Professor

‍

Two PhD candidates are currently researching under the guidance of Van den Akker how KLM can use smart technologies to make last-minute adjustments to the planning. "At KLM, they are currently still using separate fleet and crew management models. This means that each department has its own planners who only look at the fleet, or only at the crew, and how to shift them. However, as the fleet and crew come under increasing pressure and disruptions occur more frequently, better decisions can be made by jointly optimizing for fleet and crew."

‍

For this purpose, one of the PhD candidates, Philip de Bruin, is currently developing an algorithm that can quickly calculate whether you can adjust pilots and airplanes, or - if that is not possible - can see which flights are best delayed or canceled with minimal impact on passengers and crew. This integrated approach provides the opportunity to recover more efficiently from disruptions, says Van den Akker.

‍

Ground processes
The second PhD candidate, Lisanne Heuseveldt, is developing an algorithm that looks at ground processes, particularly baggage handling and passenger boarding. Van den Akker: "Here too, you want to be able to quickly adjust your planning if an aircraft arrives too late or too early. We are currently doing this for loading and unloading luggage and we also want to do it more in conjunction with other aspects, so we are looking at both baggage handlers and the boarding process. Based on various considerations that the algorithm takes into account, you can then decide which flight has priority."

‍

In addition to KLM, Utrecht University in the AI & Mobility Lab also collaborates with NS, Prorail, Qbuzz, and other organizations in the field of mobility and public transport.

‍

More about the lab