KNOWLEDGE-BASED MODELS FOR ADAPTIVE TRAFFIC MANAGEMENT-SYSTEMS

This paper describes a general approach for real rime traffic manageme nt support using knowledge based models. Recognizing that human interv ention is usually required to apply the current automatic traffic cont rol systems, it is argued that there is a need for an additional intel ligent layer to help operators to understand traffic problems and to m ake the best choice of strategic control actions that modify the assum ption framework of the existing systems. The need for an open architec ture is stated, in order to allow users to modify decision criteria ac cording to their experience, given that no skills are available yet to deal with real time strategy decision making. An architecture of know ledge is described that is oriented towards traffic management strateg ic advice applied in the TRYS system developed by the authors. This sy stem has been installed for urban motorway control in several Spanish cities. Finally, an example of knowledge-based modeling, using TRYS, i s presented in a case study where both the TRYS model and its operatio n are described. It is concluded that such an approach is feasible, an d is compatible with existing state of the art traffic control systems .