车辆换道轨迹数据集

车辆换道轨迹数据集中人工驾驶数据基于公开轨迹数据集Interaction提取而来，以10Hz采样频率对4K无人机视角视频约中的车辆轨迹数据进行提取与标定。本数据集以车辆横向位移连续变化的起止点作为车辆换道起止点，查询换道车辆及其交互车辆的id并获取轨迹数据，基于此提取并整理上海快速路中通耀路和耀华路匝道汇入场景下，约95分钟交通流数据下的换道事件共20组。此外，使用Matlab对换道场景进行重建与仿真，将换道车辆替换成自动驾驶车辆并输出仿真车辆的轨迹信息，共得到自动驾驶场景下换道案例20组。

The manual driving data of the vehicle lane-changing trajectory dataset is extracted from the public trajectory dataset Interaction. Vehicle trajectory data was extracted and calibrated from approximately 4K drone-view videos at a sampling frequency of 10Hz. This dataset defines the start and end points of a lane change as those corresponding to the continuous variation of the vehicle's lateral displacement, then queries the IDs of the lane-changing vehicle and its interacting counterparts to obtain their trajectory data. Based on this, 20 lane-changing events were extracted and organized under the ramp merging scenario between Tongyao Road and Yaohua Road on the Shanghai Expressway, utilizing approximately 95 minutes of traffic flow data. In addition, the lane-changing scenarios were reconstructed and simulated using Matlab, where the original manual lane-changing vehicles were replaced with autonomous vehicles, and the trajectory information of the simulated vehicles was output, yielding a total of 20 lane-changing cases in autonomous driving scenarios.

搜集汇总

背景与挑战

背景概述

该数据集包含上海快速路匝道汇入场景下的车辆换道轨迹数据，基于公开数据集Interaction提取，采样频率为10Hz，涵盖约95分钟交通流中的20组换道事件。数据集同时提供人工驾驶和通过Matlab仿真生成的自动驾驶换道案例各20组，适用于自动驾驶换道交互和人机混驾研究。