.png){kind=icon}
返回
A data-driven lane-changing model based on deep learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.trc.2019.07.002.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Lane-changing (LC), which is one of the basic driving behavior, largely impacts on traffic efficiency and safety. Modeling an LC process is challenging due to the complexity and uncertainty of driving behavior. To address this issue, this paper proposes a data-driven LC model based on deep learning models. Deep belief network (DBN) and long short-term memory (LSTM) neural network are employed to model the LC process that is composed of LC decisions (LCD) and LC implementation (LCI). The empirical LC data provided by Next Generation Simulation project (NGSIM) is utilized to train and test the proposed DBN-based LCD model and LSTM-based LCI model. The results indicate that the proposed data-driven model is able to accurately predict the LC process of a vehicle. The sensitivity analysis shows that the most important factor associated with LCD is the relative position of the preceding vehicle in the target lane. This may be the first work that comprehensively models LC using deep learning approaches.
Keyword:
Traffic flow
Driving behavior
Vehicle trajectory
Deep belief network
Long short-term memory
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.9
论文数:
4.9K
被引数:
3.2W
机构
引用论文
Perylenetetracarboxylic diimide covalently bonded with mesoporous g-C3N4 to construct direct Z-scheme heterojunctions for efficient photocatalytic oxidative coupling of amines与介孔g-C3N4共价键合的茈四羧酸二酰亚胺可构建直接Z方案异质结，用于胺的高效光催化氧化偶联
PREAI
分享收藏Multivariate time series prediction of lane changing behavior using deep neural network基于深度神经网络的多变量时间序列换道行为预测.png)
APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏分享收藏
查看更多内容