当前位置: X-MOL 学术Int. J. Robot. Res. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Ford Multi-AV Seasonal Dataset
The International Journal of Robotics Research ( IF 7.5 ) Pub Date : 2020-09-30 , DOI: 10.1177/0278364920961451
Siddharth Agarwal 1 , Ankit Vora 1 , Gaurav Pandey 2 , Wayne Williams 1 , Helen Kourous 1 , James McBride 2
Affiliation  

This article presents a challenging multi-agent seasonal dataset collected by a fleet of Ford autonomous vehicles (AVs) at different days and times during 2017–2018. The vehicles traversed an average route of 66 km in Michigan that included a mix of driving scenarios such as the Detroit airport, freeways, city centers, university campus, and suburban neighborhoods. Each vehicle used in this data collection was a Ford Fusion outfitted with an Applanix POS-LV GNSS/INS system, four HDL-32E Velodyne 3D-lidar scanners, six Point Grey 1.3 MP cameras arranged on the rooftop for 360° coverage, and one Point Grey 5 MP camera mounted behind the windshield for the forward field of view. We present the seasonal variation in weather, lighting, construction, and traffic conditions experienced in dynamic urban environments. We also include data from multiple AVs that were driven in close proximity. This dataset can help design robust algorithms for AVs and multi-agent systems. Each log in the dataset is time-stamped and contains raw data from all the sensors, calibration values, pose trajectory, ground-truth pose, and 3D maps. All data is available in rosbag format that can be visualized, modified, and applied using the open-source Robot Operating System (ROS). We also provide the output of reflectivity-based localization for bench-marking purposes. The dataset can be freely downloaded at avdata.ford.com.

中文翻译:

福特多AV季节性数据集

本文介绍了福特自动驾驶汽车 (AV) 车队在 2017-2018 年不同日期和时间收集的具有挑战性的多智能体季节性数据集。这些车辆在密歇根州平均行驶 66 公里,其中包括底特律机场、高速公路、市中心、大学校园和郊区社区等多种驾驶场景。本次数据收集中使用的每辆车都是配备 Applanix POS-LV GNSS/INS 系统的福特 Fusion、四台 HDL-32E Velodyne 3D 激光雷达扫描仪、六台布置在屋顶上以实现 360° 覆盖的 Point Grey 1.3 MP 摄像机和一台Point Grey 5 MP 摄像头安装在挡风玻璃后面,用于前方视野。我们展示了动态城市环境中天气、照明、建筑和交通条件的季节性变化。我们还包括来自多个近距离驾驶的自动驾驶汽车的数据。该数据集可以帮助为 AV 和多代理系统设计强大的算法。数据集中的每个日志都带有时间戳,并包含来自所有传感器的原始数据、校准值、姿态轨迹、真实姿态和 3D 地图。所有数据都以 rosbag 格式提供,可以使用开源机器人操作系统 (ROS) 进行可视化、修改和应用。我们还提供基于反射率的定位输出,用于基准测试。该数据集可以在 avdata.ford.com 上免费下载。和 3D 地图。所有数据都以 rosbag 格式提供,可以使用开源机器人操作系统 (ROS) 进行可视化、修改和应用。我们还提供基于反射率的定位输出,用于基准测试。该数据集可以在 avdata.ford.com 上免费下载。和 3D 地图。所有数据都以 rosbag 格式提供,可以使用开源机器人操作系统 (ROS) 进行可视化、修改和应用。我们还提供基于反射率的定位输出,用于基准测试。该数据集可以在 avdata.ford.com 上免费下载。
更新日期:2020-09-30
down
wechat
bug