@article{ref1,
title="Markov probabilistic decision making of self-driving cars in highway with random traffic flow: a simulation study",
journal="Journal of intelligent and connected vehicles",
year="2018",
author="Guan, Yang and Li, Shengbo Eben and Duan, Jingliang and Wang, Wenjun and Cheng, Bo",
volume="1",
number="2",
pages="77-84",
abstract="PURPOSE Decision-making is one of the key technologies for self-driving cars. The high dependency of previously existing methods on human driving data or rules makes it difficult to model policies for different driving situations. <br><br>DESIGN/METHODOLOGY/APPROACH In this research, a probabilistic decision-making method based on the Markov decision process (MDP) is proposed to deduce the optimal maneuver automatically in a two-lane highway scenario without using any human data. The decision-making issues in a traffic environment are formulated as the MDP by defining basic elements including states, actions and basic models. Transition and reward models are defined by using a complete prediction model of the surrounding cars. An optimal policy was deduced using a dynamic programing method and evaluated under a two-dimensional simulation environment. <br><br>FINDINGS Results show that, at the given scenario, the self-driving car maintained safety and efficiency with the proposed policy. <br><br>ORIGINALITY/VALUE This paper presents a framework used to derive a driving policy for self-driving cars without relying on any human driving data or rules modeled by hand.<p /> <p>Language: en</p>",
language="en",
issn="2399-9802",
doi="10.1108/JICV-01-2018-0003",
url="http://dx.doi.org/10.1108/JICV-01-2018-0003"
}