Adaptability of a hybrid route choice model to incorporating driver behavior dynamics under information provision
ABSTRACT This paper proposes a seamless framework to incorporate the day-to-day and within-day dynamics of driver route choice decisions under real-time information provision by adapting a hybrid probabilistic-possibilistic model previously developed by the authors. The day-to-day dynamics are captured through the update of driver perception and route choice rules based on the current day's experience. The within-day dynamics are captured through the en-route adjustment of the weights of the driver route choice rules in response to situational factors. Experiments are conducted to analyze the model's ability to capture driver behavior dynamics, and the associated prediction accuracy. The results suggest that the framework can reflect the evolution of driver route choice behavior over time, and adapt to the within-day variability in ambient driving conditions. This is illustrated by its ability to capture phenomena such as inertia, compliance, delusion, freezing, and perception update under information provision, in addition to the effects of familiarity and route complexity. In the within-day context, the results highlight the sensitivity to the situational factors unfolding in real-time. The results also illustrate the better prediction power of the hybrid model compared to that of a traditional multinomial probit model; however, this gap reduces with increasing heterogeneity in driver behavioral class fractions. Elsewhere, the authors show that the proposed framework can be used to predict the ambient driver class fractions, thereby addressing a key deployment limitation of existing dynamic network models for real-time traffic control through route guidance.
Full-textDOI: · Available from: Srinivas Peeta, Jan 05, 2015
- SourceAvailable from: Shuo-Yan Chou[Show abstract] [Hide abstract]
ABSTRACT: With the advent of communication and information technologies, much information about route conditions and driver behaviours can be acquired by the mobile devices and used to guide drivers while driving vehicles to the destination. However, even though with the same starting and destination points, different drivers typically do not go through the same path as they make choices of routes based on different attributes and weighting of the attributes. Driving route guidance systems need to be able to adapt to various behaviours of drivers to generate routes teller-made for individual drivers. The perceptions of the drivers being fed back to the system are linguistic values which are vague. A neural fuzzy approach is used to learn the decision logic with vague attributes from the past driving records of the drivers to make the guidance system adaptive. The adaptive-network-based fuzzy inference system (ANFIS) is used so that the system can self-adjust without user intervention. By integrating this intelligent adaptive capability, a driving route guidance system is proposed in this paper which is capable of adapting to individual drivers gradually to provide different optimum routes automatically based on different preferences.Intelligent Environments, 2008 IET 4th International Conference on; 08/2008
Dataset: Disseminated-2009 TRPB BCOnline
- [Show abstract] [Hide abstract]
ABSTRACT: The need to understand the effects of diverting traffic is emphasized by growing congestion and delays. This paper examines incident-induced diversion behavior by using loop-detector data and incident records on a freeway in Virginia. This work diverges from previous studies by (1) addressing both existence of diversion and its magnitude, (2) relying on field data rather than surveys, and (3) statistically relating diversion behavior and magnitude to quantifiable incident characteristics and traffic conditions. A dynamic programming-based procedure is used to identify diversions by isolating transient level shifts, and the diversions are associated with incident and traffic characteristics and variable message sign (VMS) displays through a binary logit model. The magnitude of the diversion is statistically related to traffic conditions via a linear regression model. The models indicate that the probability of triggering a diversion increases when an incident lasts longer, more general-purpose lanes are blocked, and speeds are lower. The results on the effects of trip purpose/time and information availability are consistent with previous studies. The magnitude of the diversion, measured by diversion rate, is related to instant traffic flow characteristics, general traffic demand considerations, and the incident characteristics. DOI: 10.1061/(ASCE)TE.1943-5436.0000431. (C) 2012 American Society of Civil Engineers.Journal of Transportation Engineering 10/2012; 138(10):1239-1249. DOI:10.1061/(ASCE)TE.1943-5436.0000431 · 0.88 Impact Factor