An agent-based approach to modelling driver route choice behaviour under the influence of real-time information

Abstract

This paper presents an agent-based approach to modelling individual driver behaviour under the influence of real-time traffic information. The driver behaviour models developed in this study are based on a behavioural survey of drivers which was conducted on a congested commuting corridor in Brisbane, Australia. CommutersÕ responses to travel information were analysed and a number of discrete choice models were developed to determine the factors influencing driversÕ behaviour and their propensity to change route and adjust travel patterns. Based on the results obtained from the behavioural survey, the agent behaviour parameters which define driver characteristics, knowledge and preferences were identified and their values determined. A case study implementing a simple agent-based route choice decision model within a microscopic traffic simulation tool is also presented. Driver-vehicle units (DVUs) were modelled as autonomous software components that can each be assigned a set of goals to achieve and a database of knowledge comprising certain beliefs, intentions and preferences concerning the driving task. Each DVU provided route choice decision-making capabilities, based on perception of its environment, that were similar to the described intentions of the driver it represented. The case study clearly demonstrated the feasibility of the approach and the potential to develop more complex driver behavioural dynamics based on the belief-desire-intention agent architecture.

An Agent-Based Approach to Assess Drivers' Interaction with Pre-Trip Information Systems

“…440 We also plan to devise a methodological approach that allows for the representation of more realistic behaviors, including their calibration and validation against real world observation. Dia and Purchase (1999) have proposed a survey of driver behaviors to provide useful insight into the characteristics of commuters, 445 their preferences and thresholds, as further discussed in (Dia, 2002). Results from such a survey could be easily specified in terms of AgentSpeak(L) constructors.…”

“…Hernández et al, 2002). Nonetheless, an increasing effort has also been dedicated to representing driver behavior and its underlying decision-making mechanism, as pro-85 posed in (e.g., Dia, 2002;Rossetti, Bordini, et al, 2002). The analysis of ITS systems through this approximation has been investigated as well (e.g., Wahle et al, 2002), and some other works report on applications to freight transport and optimization of resource use (e.g., Haddadi, 1993;90 Adler and Blue, 2002).…”

Impact of Integrated Multimodal Traveler Information on Auto Commuter’s Mode Switching Propensity

“…This part was divided into four groups in which information about auto commuter's socio-economic characteristics, usual trip preferences, availability and usage of public and private modes was collected. The commuters' socio-economic characteristics were surveyed in order to observe the impact of these characteristics on commuters' travel choice preferences, including: age, gender, education, occupation, personal income, household income, household size, postcode, marital status and type of vehicle owned [20]. Age was divided into four groups of 18 to 35, 36 to 45, 46 to 55, and above 55 years.…”

4D-SAS: A Distributed Dynamic-Data Driven Simulation and Analysis System for Massive Spatial Agent-Based Modeling

“…Thus, road conditions, as an important attribute of mobile agent context, behave as a very influential factor in driver behavior concerning trip-making and route choice. Therefore, the provision of real-time road information can help improve traffic performance and service quality [37][38][39].…”