Nikunj C. Oza's Publications

Sorted by DateClassified by Publication TypeClassified by Research Category

Probabilistic Models of Driver Behavior

Probabilistic Models of Driver Behavior, Nikunj C. Oza, Master's Thesis

Download

[PDF]297.2kB  

Abstract

The BATMobile [1] is one approach to the implementation of a system capable of driving autonomously in normal highway traffc. As with human drivers, the BATMobile would be a superior driver if it were able to make predictions about the actions of other drivers, effectively giving it the ability to respond before such actions even occur. The ability to predict driver behavior would also be helpful in the creation of accurate models of traffic behavior used in freeway design and analysis. In this report, we discuss the creation of dynamic probabilistic networks (DPNs) that constitute models of driver behavior. Specifically, we discuss three model structures we have created, the data used to learn the models, and how well the models predict driver behavior. We compare the three models to observe the benefits of modeling hidden state and using deterministic variables. We also analyze the models to see what aspects of driver behavior the models have learned.

BibTeX Entry

@thesis{oza98,
	author="Nikunj C. Oza",
	title="Probabilistic Models of Driver Behavior",
	department={Electrical Engineering and Computer Science},
	school={The University of California},
	address={Berkeley, CA},
	month={May},
	note = {Probabilistic Models of Driver Behavior, Nikunj C. Oza, Master's Thesis},
abstract={The BATMobile [1] is one approach to the implementation of a system capable of driving autonomously in normal highway traffc. As with human drivers, the BATMobile would be a superior driver if it were able to make predictions about the actions of other drivers, effectively giving it the ability to respond before such actions even occur. The ability to predict driver behavior would also be helpful in the creation of accurate models of traffic behavior used in freeway design and analysis. In this report, we discuss the creation of dynamic probabilistic networks (DPNs) that constitute models of driver behavior. Specifically, we discuss three model structures we have created, the data used to learn the models, and how well the models predict driver behavior. We compare the three models to observe the benefits of modeling hidden state and using deterministic variables. We also analyze the models to see what aspects of driver behavior the models have learned.}
bib2html_pubtype = {Other},
bib2html_rescat = {Other Topics},
	year ={1998}
}

Generated by bib2html.pl (written by Patrick Riley ) on Sun Jan 13, 2008 22:02:08