Using BDI agents to improve driver modelling in a commuter scenario

The use of multi-agent systems to model and to simulate real systems consisting of intelligent entities capable of autonomously co-operating with each other has emerged as an important field of research. This has been applied to a variety of areas, such as social sciences, engineering, and mathematical and physical theories. In this work, we address the complex task of modelling drivers’ behaviour through the use of agent-based techniques. Contemporary traffic systems have experienced considerable changes in the last few years, and the rapid growth of urban areas has challenged scientific and technical communities. Influencing drivers’ behaviour appears as an alternative to traditional approaches to cope with the potential problem of traffic congestion, such as the physical modification of road infrastructures and the improvement of control systems. It arises as one of the underlying ideas of intelligent transportation systems. In order to offer a good means to evaluate the impact that exogenous information may exert on drivers’ decision making, we propose an extension to an existing microscopic simulation model called Dynamic Route Assignment Combining User Learning and microsimulAtion (DRACULA). In this extension, the traffic domain is viewed as a multi-agent world and drivers are endowed with mental attitudes, which allow rational decisions about route choice and departure time. This work is divided into two main parts. The first part describes the original DRACULA framework and the extension proposed to support our agent-based traffic model. The second part is concerned with the reasoning mechanism of drivers modelled by means of a Beliefs, Desires, and Intentions (BDI) architecture. In this part, we use AgentSpeak(L) to specify commuter scenarios and special emphasis is given to departure time and route choices. This paper contributes in that respect by showing a practical way of representing and assessing drivers’ behaviour and the adequacy of using AgentSpeak(L) as a modelling language, as it provides clear and elegant specifications of BDI agents.     

An investigation of the reliability of real-time information for route choice decisions in a congested traffic system

This paper investigates the reliability of information on prevailing trip times on the links of a network as a basis for route choice decisions by individual drivers. It considers a type of information strategy in which no attempt is made by some central controller or coordinating entity to predict what the travel times on each link would be by the time it is reached by a driver that is presently at a given location. A specially modified model combining traffic simulation and path assignment capabilities is used to analyze the reliability of the real-time information supplied to the drivers. This is accomplished by comparing the supplied travel times (at the link and path levels) to the actual trip times experienced in the network after the information has been given. In addition, the quality of the decisions made by drivers on the basis of this information (under alternative path switching rules) is evaluated ex-post by comparing the actually experienced travel time (given the decision made) to the time that the driver would have experienced without the real-time information. Results of a series of simulation experiments under recurrent congestion conditions are discussed, illustrating the interactions between information reliability and user response.     

A conflict model and interactive simulator (FASTCARS) for predicting enroute driver behavior in response to real-time traffic condition information

This paper proposes a theoretical methodology and practical data collection approach for modeling enroute driver behavioral choice under Advanced Traveler Information Systems (ATIS). The theoretical framework is based on conflict assessment and resolution theories popularized in psychology and applied to models of individual consumer behavior. It is posed that enroute assessment and adjustment is a reactionary process influenced by increased conflict arousal and motivation to change. When conflict rises to a level at which conflict exceeds a personal threshold of tolerance, drivers are likely to alter enroute behavior to alleviate conflict through either route diversion of goal revision. Assessment and response to conflict arousal directly relate to the driver's abilities to perceive and predict network conditions in conjunction with familiarity of network configurations and accessible alternate routes.Data collection is accomplished through FASTCARS (Freeway andArterialStreetTrafficConflictArousal andResolutionSimulator), in interactive microcomputer-based driving simulator. Limited real-world implementation of ATIS has made it difficult to study or predict individual driver reaction to these technologies. It is contended here that in-laboratory experimentation with interactive route choice simulators can substitute for the lack of real-world applications and provide an alternate approach to data collection and driver behavior analysis. This paper will explain how FASTCARS is useful for collecting data and testing theories of driver behavior.     

From user equilibrium to system optimum: a literature review on the role of travel information,bounded rationality and non-selfish behaviour at the network and individual levels

Travel information continues to receive significant attention in the field of travel behaviour research, as it is expected to help reduce congestion by directing the network state from a user equilibrium towards a more efficient system optimum. This literature review contributes to the existing literature in at least two ways. First, it considers both the individual perspective and the network perspective when assessing the potential effects of travel information, in contrast to earlier studies. Secondly, it highlights the role of bounded rationality as well as that of non-selfish behaviour in route choice and in response to information, complementing earlier reviews that mostly focused on bounded rationality only. It is concluded that information strategies should be tailor-made to an individual's level of rationality as well as level of selfishness in order to approach system-optimal conditions on the network level. Moreover, initial ideas and future research directions are provided for assessing the potential of travel information in order to improve network efficiency of existing road networks.     

An exploration of the importance of social influence in the decision to start bicycling in England

The purpose of this paper is to gain a better understanding, through qualitative exploration, of the ways in which social influence affects the decision to start bicycling in England. ‘Social influence’ is defined as the process by which an individual’s thoughts and actions are changed by the thoughts and action of others. Its role was investigated at three levels: the immediate family, household members and significant others (direct social influence); the extended family, friends, peers and colleagues (less direct social influence); and the wider cultural context (indirect social influence). Interviews with 61 individuals living in 12 towns and cities across England were analysed. Half of the interviewees were new regular bicyclists and the other half did not bicycle at all, or only occasionally. Social influence was found to be the dominant factor for a minority of the cases where participants started bicycling regularly. It played a role alongside other factors in other cases. It could take the form of direct influence from family, friends and peers or indirect influence from the social and cultural context. The analysis illustrates the difficulty of capturing social influence which is often hidden and emerges incidentally in the course of the interviews and interacts with other contributing factors. The role of social influence found in this research challenges the rational approach to explaining travel decision making that has traditionally dominated transport studies. The paper suggests that social processes could be harnessed to improve the efficacy of bicycling promotion programs.     

Multi-scenario optimization approach for assessing the impacts of advanced traffic information under realistic stochastic capacity distributions

In this study, to incorporate realistic discrete stochastic capacity distribution over a large number of sampling days or scenarios (say 30–100 days), we propose a multi-scenario based optimization model with different types of traveler knowledge in an advanced traveler information provision environment. The proposed method categorizes commuters into two classes: (1) those with access to perfect traffic information every day, and (2) those with knowledge of the expected traffic conditions (and related reliability measure) across a large number of different sampling days. Using a gap function framework or describing the mixed user equilibrium under different information availability over a long-term steady state, a nonlinear programming model is formulated to describe the route choice behavior of the perfect information (PI) and expected travel time (ETT) user classes under stochastic day-dependent travel time. Driven by a computationally efficient algorithm suitable for large-scale networks, the model was implemented in a standard optimization solver and an open-source simulation package and further applied to medium-scale networks to examine the effectiveness of dynamic traveler information under realistic stochastic capacity conditions.