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.

Fundamental to the operation of most Intelligent Vehicle-Highway System (IVHS) projects are advanced systems for surveillance, control and management of integrated freeway and arterial networks. A Major concern in the development of such Smart Roads, and the focus of this paper, is the provision of decision support for traffic management center personnel, particularly for addressing non-recurring congestion in large or complex networks. Decision support for control room staff is necessary to effectively detect, verify and develop response strategies for traffic incidents. These are events that disrupt the orderly flow of traffic, and cause non-recurring congestion and motorist delay. non-recurring congestion can be caused by accidents, spilled loads, stalled or broken down vehicles, maintenance and construction activities, signal and detector malfunctions, and special and unusual events. The ultimate objective of our research is to implement a novel artificial intelligence-based solution approach to the problem of providing operator decision support in integrated freeway and arterial traffic management systems, as part of a more general IVHS. In this paper, we present and discuss the development of FRED (Freeway Real-Time Expert System Demonstration), a component prototype real-time expert system for managing non-recurring congestion on urban freeways in Southern California. The application of FRED to a section of the Riverside Freeway (SR-91) in Orange County is presented as a case study, and illustrates the current capabilities of the system.