SART: A system for supporting operators with contextual knowledge

The regulation of the subway line traffic is a domain where human controllers must deal with a huge quantity of knowledge pieces more or less implicit in the regulation itself. When an incident occurs on a subway line, the operator--the controller who has currently the responsibility of the subway line--must choose the best strategy to apply for moving from the incidental context to the operational one. An incident on the subway line may cause traffic delay or service interruption, and may last for a long or short time, depending on the nature of the incident and many other elements. Operators mainly focus on contextual information for incident solving. An operator said that "When an incident occurs, I first look at what the incident context is." We propose to support subway line traffic controllers in incident-solving with the SART system (French acronym for support system in the traffic regulation). SART is a decision support system based on the contextual analysis of events that arise at the time of the incident. It uses a context-based representation of incidents and applies a context-based reasoning. We discuss in this paper a context-based representation of incidents on the basis of the onion metaphor. The SART project now enters the second year of system design and development and implies two universities and two subway companies in France and Brazil.