The operation of control centers in local public transport (LPT) is highly complex. Disruptions, delays, or technical failures must be assessed and coordinated in real time—often under considerable time pressure and with direct implications for passengers, operational safety, and service quality. At the same time, it is important to make good use of large amounts of operational and sensor data in order to stabilize control center operations without placing additional strain on employees.
The following practical example addresses precisely this area of tension. It was developed as part of the"KARL Competence Center"research project, in which the CyberForum is involved as a consortium partner. The project partners init, Lavrio.solutions, the Karlsruhe University of Applied Sciences and the FZI Research Center for Information Technology.
motivation
In the control center of a transport company, dispatchers monitor buses and trains using control center software, keeping an eye on the entire public transport system of a city or region. If there are any disruptions (e.g., due to an accident), blocked tracks, or delayed vehicles, the dispatchers step in to minimize the impact on passenger service. To do this, dispatchers trigger so-called dispatch measures in the control center software. These measures include diversions, U-turns, or smaller measures such as waiting for a delayed vehicle to allow passengers to change to another line without missing their connection.
In the event of a disruption, dispatchers must react quickly and take many factors into account at the same time. This exposes them to a great deal of stress, and the complexity of many situations also requires a wealth of experience.
objective
The goal of the use case led by INIT is to evaluate data on previous dispatching measures using artificial intelligence (AI) methods and, based on this, to develop a proposal assistant that supports dispatchers in making difficult decisions. It is particularly important to design the assistant in such a way that it is tailored to the needs of dispatchers and is intuitive to use. Therefore, great importance is attached to the user-friendliness and visualization of the AI-based assistant.
The AI is to be trained in such a way that it takes a variety of relevant factors into account and subsequently suggests scheduling measures that are precisely tailored to the respective situation. This is intended to support dispatchers in their decisions. In addition, the system is to be linked to the control center software in such a way that the dispatching measures are triggered automatically when the dispatchers accept the AI proposal. It is therefore an AI-supported suggestion system that relieves the dispatchers, but at the same time gives them full control over the processes.
approach
The partners are working to support dispatchers in their daily work with the control center software. The control center software is a very complex system and offers dispatchers many options for action in the event of a malfunction. The use case is initially limited to suggesting selected dispatch measures, which are used to develop AI-based algorithms. The starting point is the historical operational data from the control center software, which contains vehicle positions, timetable data, and the respective dispatching measures triggered. The first step is to prepare the existing data and identify any additional data required before evaluating it using suitable AI methods and developing algorithms for the suggestion assistant. To ensure applicability and take all relevant factors into account, surveys will also be conducted with dispatchers at the Karlsruhe tram operator. Based on the Karlsruhe tram data, a prototype will be developed, followed by iterative analysis and further development.
added value
Automated monitoring of buses and trains and the resulting automated generation of recommendations for action regarding scheduling measures support dispatchers in their work and relieve them of stress, especially in the event of disruptions. This allows them to make well-considered decisions that help prevent errors and act more efficiently. The ability to automatically adjust timetable data and (partially) automate other downstream processes, such as the creation of passenger information, also contributes to improved working conditions and operational efficiency.
Note: The research and development project "Competence Center KARL" is funded by the Federal Ministry of Research, Technology, and Space (BMFTR) as part of the program "The Future of Value Creation – Research on Production, Services, and Work" (funding code: 02L19C250) and supervised by the Project Management Agency Karlsruhe (PTKA). The author is responsible for the content of this publication.
Are you facing similar challenges in the area of mobility or public transportation?
Whether it's control centers, operations, planning, or data management—many issues cannot be transferred one-to-one, but the approach can. We would be happy to show you which approaches and offerings may be useful for your organization.
Isabel Ernst: Let's find out together how AI can benefit your company in concrete terms.
- Project management AI Innovation Lab
- isabel.ernst@cyberforum.de
- 0721 602 897-717