University of California Transportation Center

This paper describes an advanced processing capability that is based on the use of real-time knowledge-based expert system (KBES) technology to integrate diverse types of traffic surveillance data for freeway monitoring and control purposes, particularly as part of future "Smart Roads" projects. One of the major functions of the prototype system developed is the acquisition and processing of input data drawn from sensors and processes in the real world. The real-time nature of these processes, and the associated need for decision-making information and recommendations, places particular importance on the efficient handling of data to avoid unnecessary overloading of the expert system. The relevant types of data include traffic occupancies and volumes from loop detectors in the pavement, information on traffic conditions from closed circuit television cameras, field reports from police officers and other official personnel, and cellular and emergency telephone calls from motorists. The paper emphasizes the way in which the data are acquired, processed and integrated within a prototype KBES framework in order to achieve the objectives of the incident management tasks, and specifically those of incident detection and verification. Examples are given of the implementation of these features.