Scholarlink

<p>Driving style reflects drivers’&#xa0;vehicle manipulation and driving habits, it is essential for understanding and analyzing drivers’ dynamic behavior and decision-making process. To better understand the intrinsic characteristics of how drivers make decisions and control vehicles based on external conditions, this paper proposes an unsupervised framework for dynamic driving style classification based on behavior primitives. The framework consists of three key stages: primitive extraction, model development, and dynamic driving style classification. Unsupervised techniques are employed to extract meaningful behavior primitives from time-series driving data. The primitive serves as the fundamental unit for dynamic driving style analysis, and a driving style evaluation model is built using a linear weighting approach. This model quantifies the risks of primitives and the transition risks between adjacent primitives. The thresholds for classifying cautious, average, and aggressive styles are determined using an improved particle swarm optimization algorithm. The proposed dynamic driving style classification framework comprehensively considers the characteristics of the current primitive and its surrounding context. By preserving the temporal features of driving behavior, the framework provides fine-grained classification of dynamic driving styles. Additionally, a deeper understanding of drivers’&#xa0;dynamic driving style and their long-term driving behavior can be gained based on this framework, which will benefit the development of AVs and ADASs.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Identification of dynamic driving styles based on behavioral primitives

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月26日

查看全文
  • Xuelian Zheng,
  • Wenyu Kang,
  • Yuanyuan Ren,
  • Xiansheng Li,
  • Jianfeng Xi

摘要

Driving style reflects drivers’ vehicle manipulation and driving habits, it is essential for understanding and analyzing drivers’ dynamic behavior and decision-making process. To better understand the intrinsic characteristics of how drivers make decisions and control vehicles based on external conditions, this paper proposes an unsupervised framework for dynamic driving style classification based on behavior primitives. The framework consists of three key stages: primitive extraction, model development, and dynamic driving style classification. Unsupervised techniques are employed to extract meaningful behavior primitives from time-series driving data. The primitive serves as the fundamental unit for dynamic driving style analysis, and a driving style evaluation model is built using a linear weighting approach. This model quantifies the risks of primitives and the transition risks between adjacent primitives. The thresholds for classifying cautious, average, and aggressive styles are determined using an improved particle swarm optimization algorithm. The proposed dynamic driving style classification framework comprehensively considers the characteristics of the current primitive and its surrounding context. By preserving the temporal features of driving behavior, the framework provides fine-grained classification of dynamic driving styles. Additionally, a deeper understanding of drivers’ dynamic driving style and their long-term driving behavior can be gained based on this framework, which will benefit the development of AVs and ADASs.