The work described in this paper is part of an ongoing research project which aims to demonstrate the feasibility of using intelligent agents to model travel behaviour on a congested traffic commuting corridor based on a behavioural survey of drivers in Brisbane. The intelligent agents model developed in this study will be used in conjunction with a traffic simulation component to evaluate the impacts of providing drivers with real-time information. Providing drivers with this information is believed to have the potential to alleviate traffic congestion and enhance the performance of the road network by influencing drivers' route choice decisions. The survey of driver behaviour will provide a useful insight into the characteristics of drivers, how they choose their routes and how their route and departure decisions may be influenced in order to improve mobility and reduce traffic congestion. The results from the behavioural survey will be used to model drivers' behaviour using a relatively recent computing paradigm known as intelligent agents. This approach will allow the modelling of interaction between drivers, coordination of their goals and updating of their decisions on a real-time and day-to-day basis. The model developed in this study will provide road authorities with a valuable tool to evaluate and design effective traveller information systems aimed at influencing travel behaviour, reducing congestion, improving air quality and enhancing the performance of the road network. (a).
Abstract