Game Theory-Based Discretionary Lane Changing Controlling Compulsory Behavior In Conflicting Situation
Loading...
Date
2021-04
Authors
Rahman, Md Mijanoor
Journal Title
Journal ISSN
Volume Title
Publisher
Universiti Sains Malaysia
Abstract
The challenging and contradictory Discretionary Lane Changing (DLC) is to happen
for comfortable or safe journey in urban roadway. For the last two decades, many
studies have been trying to solve this problem by using the binary decisions-based lane
changing model. However, very few researches were conducted to handle this type of
problem by using the Nash equilibrium-based game theory model as an at-least four
decisions-based model. Despite bounded rational behavior of the game theory players
(lane changing vehicle driver and target rear vehicle driver in urban traffic system),
existing researches apply the Nash-equilibrium game theory model including the full
rational behavior. This challenging task needs to be overcome by applying the Quantal
Response Equilibrium (QRE) game theory including the bounded rational players.
The QRE model provides the interactive lane changing decision by using different
trajectory factors. These factors are found in car-following and lane-changing traffic
researches. The Intelligent Driver Model (IDM) as a car-following model incorporates
the desired speed factor, and the lane-changing trajectory planning model provides a
safety gap factor. By avoiding these two factors, the above-mentioned research-based
solution may not be possible, whereas literature suggested to include such factors in
driving behavior-based traffic research. This research collects the desired speed factor
from calibrated IDM, and safety gap factor from lane changing trajectory model, to
propose the QRE-based lane changing decision model for urban congested traffic areas.
The calibration method uses Genetic Algorithm (GA) against the real dataset,
Next Generation Simulation (NGSIM). GA is also used to calibrate the modified lane changing trajectory model, and determine efficient model parameters. Further, a bi-level
programming problem includes the QRE-based game theory model in this research.
The bi-level programming calibrates parameters of game theory utilities (factors) and
driver decision probabilities by using GA. Therefore, this game theory model employs
the calibration by using 70% (92 lane-changing instances) of dataset to propose
the DLC driver behavior. Further, this model check the validation by using 30% (40
lane-changing instances) of dataset. This research finds false alarm rates of the model,
10.81% (lane changing decision of subject vehicle), 0.00% (non-lane changing decision
of subject vehicle), 36.36% (yielding decision of target rear vehicle), and 42.86%
(forbidding decision of target rear vehicle) by using validation test. Further, finding
results suggest overcoming conflicts in this dataset by controlling the used dynamic
factors. High performance-based traffic simulation software in the future can use the
further developed model to decrease traffic crashes, bottlenecks, and long signals in
the intersection.
Description
Keywords
Mathematics