Scholarlink

<p>Driving interaction, a critical yet underrepresented element in trajectory datasets, is central to the development and evaluation of autonomous driving systems. This work presents <Emphasis FontCategory="NonProportional">InterHub</Emphasis>, a curated dataset of dense multi-agent interaction events, derived from large-scale naturalistic driving recordings. We employ formal methods to describe and extract multi-agent interaction events, exposing the limitations of existing autonomous driving solutions. The dataset is accompanied by an open-source toolkit that enables users to expand <Emphasis FontCategory="NonProportional">InterHub</Emphasis> by mining additional interaction events from both public and private driving data. By offering a unified taxonomy, rich annotations, and extensible tools, <Emphasis FontCategory="NonProportional">InterHub</Emphasis> supports diverse research needs-from interaction behavior modeling to algorithm benchmarking-and promotes reproducibility, scalability, and cross-dataset comparison in autonomous driving studies.</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

A naturalistic trajectory dataset with dense interaction for autonomous driving

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月1日

查看全文
  • Xiyan Jiang,
  • Xiaocong Zhao,
  • Yiru Liu,
  • Zirui Li,
  • Peng Hang,
  • Lu Xiong,
  • Jian Sun

摘要

Driving interaction, a critical yet underrepresented element in trajectory datasets, is central to the development and evaluation of autonomous driving systems. This work presents InterHub, a curated dataset of dense multi-agent interaction events, derived from large-scale naturalistic driving recordings. We employ formal methods to describe and extract multi-agent interaction events, exposing the limitations of existing autonomous driving solutions. The dataset is accompanied by an open-source toolkit that enables users to expand InterHub by mining additional interaction events from both public and private driving data. By offering a unified taxonomy, rich annotations, and extensible tools, InterHub supports diverse research needs-from interaction behavior modeling to algorithm benchmarking-and promotes reproducibility, scalability, and cross-dataset comparison in autonomous driving studies.