Y. Luo and L. Bölöni

Modeling the conscious behavior of drivers for multi-lane highway driving


Cite as:

Y. Luo and L. Bölöni. Modeling the conscious behavior of drivers for multi-lane highway driving. In 7th International Workshop on Agents in Traffic and Transportation (ATT-2012), pp. 95–103, June 2012.

Download:

Download 

Abstract:

The current state of the art in simulating highway driving extensively relies on models using formulas similar to those describing physical phenomena such as forces, viscosity or potential fields. While the parametrization of these formulas can account for the limitations of the driver (such as reaction delay), they are badly suited for modeling conscious behavior. In this paper we describe our simulation architecture which uses an agent-based model to represent the conscious tactical and strategic behavior of the agent. This model will act as a high level input to a state-of-the-art virtual physics model which models the physical vehicle and the subconscious aspects of the driver behavior. The concrete aspects of driving modeled in this paper are the strategic lane preferences of the drivers, with a special attention to the optimal lane positioning for a safe exit. We have used the model to simulate the traffic on Orlando's Highway 408. The results match well with the real world traffic data. The increased simulation detail can be applied to crash prediction and the control of intelligent transportation system devices, such as variable speed limits.

BibTeX:

@inproceedings{Luo-2012-ATT,
   title = "Modeling the conscious behavior of drivers for multi-lane highway driving",
   author = "Y. Luo and L. B{\"o}l{\"o}ni",
   booktitle = "7th International Workshop on Agents in Traffic and Transportation (ATT-2012)",
   year = "2012",
   pages = "95-103",
   month = "June",
   location = "Valencia, Spain",
   abstract = {
    The current state of the art in simulating highway driving
    extensively relies on models using formulas similar to those
    describing physical phenomena such as forces, viscosity or potential
    fields. While the parametrization of these formulas can account for
    the limitations of the driver (such as reaction delay), they are
    badly suited for modeling conscious behavior. In this paper we
    describe our simulation architecture which uses an agent-based model
    to represent the conscious tactical and strategic behavior of the
    agent. This model will act as a high level input to a
    state-of-the-art virtual physics model which models the physical
    vehicle and the subconscious aspects of the driver behavior.
    The concrete aspects of driving modeled in this paper are the
    strategic lane preferences of the drivers, with a special attention
    to the optimal lane positioning for a safe exit. We have used the
    model to simulate the traffic on Orlando's Highway 408. The results
    match well with the real world traffic data. The increased
    simulation detail can be applied to crash prediction and the control
    of intelligent transportation system devices, such as variable speed
    limits.
   },
}

Generated by bib2html.pl (written by Patrick Riley, Lotzi Boloni ) on Fri Oct 06, 2017 18:15:24