文献类型：期刊文献

英文题名：A review of vehicle lane change decisions in human-machine mixed driving environments

作者：Huang, Zheng Fang, Hua Lin, Yongliang Hu, Xinyue

第一作者：Huang, Zheng;黄政

通信作者：Fang, H[1]

机构：[1]Guizhou Inst Technol, Sch Transportat Engn, Guiyang 550025, Peoples R China;[2]Guilin Univ Elect Technol, Sch Architecture & Transportat Engn, Guilin 541004, Peoples R China

第一机构：贵州理工学院

通信机构：corresponding author), Guilin Univ Elect Technol, Sch Architecture & Transportat Engn, Guilin 541004, Peoples R China.

年份：2025

卷号：4

期号：4

起止页码：298-311

外文期刊名：DIGITAL TRANSPORTATION AND SAFETY

收录：WOS:【ESCI(收录号:WOS:001693804600001)】；

基金：This work is supported by the research project on urban intersection control methods under Intelligent Connected Vehicle Environments (Grant No. H2024-107) .

语种：英文

外文关键词：Human-machine mixed driving; Vehicle lane change decisions; Risk assessment; Data-driven model; Autonomous driving

摘要：With the development of autonomous driving technology, the human-machine mixed driving environment has become the predominant form of future road traffic. This paper presents a systematic review of lane change decision-making in mixed driving scenarios. First, the behavioral characteristics of discretionary and mandatory lane changes are analyzed, and the lane change process is divided into decision-making and execution stages. From the perspective of driving safety, the importance of behavior prediction and risk assessment in ensuring the safety of decision-making is emphasized. It comprehensively reviews existing lane change risk evaluation methods, including probabilistic models and traffic conflict indicators, aiming to reduce traffic accidents caused by hazardous lane change behaviors through accurate risk evaluation. Then, through the analysis of existing lane change decision models, they are categorized into three major types: rule-based, data-driven, and game theory-based models. From the perspectives of input features and applied algorithms, the advantages, limitations, and applicable scenarios of models are compared and analyzed. Finally, current shortcomings and challenges are discussed. Key issues include insufficient consideration of human-machine interactions, low efficiency in multi-vehicle coordination, and high dependency on data. Future research directions are proposed to address these challenges. This study provides theoretical support for constructing safe and efficient lane change decision models in mixed traffic environments.