一种基于High Definition Map的可复制合并行为分析方法
A reproducible approach to merging behavior analysis based on High Definition Map
摘要：
现有的关于合并行为的研究通常优先考虑各种算法的应用，但往往忽视了对轨迹的细粒度处理和分析。这就导致了对周边车辆匹配的忽视、指标定义的不透明和可复制性危机。为了解决这些差距，本文提出了一种可重复的方法来合并行为分析。具体来说，我们概述了现有研究中的主观性和不可再现性的原因。此后，我们采用lanelet2高清（HD）地图构建一个可重复的框架，最大限度地减少主观性，定义标准化指标，识别旁边的车辆，并划分场景。随后进行了比较宏观和微观分析。更重要的是，本文坚持可复制的研究概念，提供所有的源代码和复制说明。我们的研究结果表明，虽然与并排车辆的情况下发生在不到6%的情况下，他们的特点是显着不同的，这些情况下往往伴随着高风险。本文提炼了对合并行为的理解，提高了对可重复研究的认识，并成为一个分水岭。
英文摘要：
Existing research on merging behavior generally prioritize the application of various algorithms, but often overlooks the fine-grained process and analysis of trajectories. This leads to the neglect of surrounding vehicle matching, the opaqueness of indicators definition, and reproducible crisis. To address these gaps, this paper presents a reproducible approach to merging behavior analysis. Specifically, we outline the causes of subjectivity and irreproducibility in existing studies. Thereafter, we employ lanelet2 High Definition (HD) map to construct a reproducible framework, that minimizes subjectivities, defines standardized indicators, identifies alongside vehicles, and divides scenarios. A comparative macroscopic and microscopic analysis is subsequently conducted. More importantly, this paper adheres to the Reproducible Research concept, providing all the source codes and reproduction instructions. Our results demonstrate that although scenarios with alongside vehicles occur in less than 6% of cases, their characteristics are significantly different from others, and these scenarios are often accompanied by high risk. This paper refines the understanding of merging behavior, raises awareness of reproducible studies, and serves as a watershed moment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
