Ultra-AV: A unified longitudinal trajectory dataset for automated vehicle

We processed a unified trajectory dataset for automated vehicles' longitudinal behavior from 14 distinct sources. The extraction and cleaning of the dataset contains the following three steps - 1. extraction of longitudinal trajectory data, 2. general data cleaning, and 3. data-specific cleaning. The dataset obtained from step 2 and step 3 are named as the longitudinal trajectory data and car-following trajectory data. We also analyzed and validated the data by multiple methods. The obtained datasets are provided in this repo. The Python code used to analyze the datasets can be found at https://github.com/CATS-Lab/Filed-Experiment-Data-ULTra-AV. We hope this dataset can benefit the study of microscopic longitudinal AV behaviors.本研究构建了一套覆盖14个独立数据源的自动驾驶车辆纵向行为统一轨迹数据集。该数据集的提取与清洗流程包含以下三个步骤：1. 纵向轨迹数据提取；2. 通用数据清洗；3. 针对性数据清洗。经步骤2与步骤3处理得到的两类数据集分别被命名为纵向轨迹数据集与跟驰轨迹数据集。本研究还通过多种方法对数据集开展了分析与验证工作。本仓库已提供经上述流程处理得到的数据集。用于数据集分析的Python代码可通过以下链接获取：https://github.com/CATS-Lab/Filed-Experiment-Data-ULTra-AV。本数据集期望能为自动驾驶车辆微观纵向行为的相关研究提供助力。