期刊
JOURNAL OF FIELD ROBOTICS
卷 38, 期 1, 页码 105-120出版社
WILEY
DOI: 10.1002/rob.21976
关键词
aerial robotics; data set; sewer inspection; subterranean robotics; terrestrial robotics
类别
资金
- Ministerio de Ciencia, Innovacion y Universidades [RTI2018-100847-B-C22]
- FP7 Information and Communication Technologies [601116]
- Ministerio de Ciencia e Innovacion [FJCI-2015-25700]
This paper presents a unique dataset collected in the visitable sewers of Barcelona, involving ground and aerial robots. The dataset includes a variety of sensor data, with experiments exceeding 5 km in length. Users can utilize this dataset for testing localization, SLAM, and classification algorithms in underground environments.
This paper presents an unprecedented set of data in a challenging underground environment: the visitable sewers of Barcelona. To the best of our knowledge, this is the first data set involving ground and aerial robots in such scenario: the sewer inspection autonomous robot (SIAR) ground robot and the autonomous robot for sewer inspection aerial platform. These platforms captured data from a great variety of sensors, including sequences of red green blue-depth (RGB-D) images with their onboard cameras. The set consists of 14 logs of experiments that were obtained in more than 10 different days and in four different locations. The complete length of the experiments in the data set exceeds 5 km. In addition, we provide the users with a partial ground-truth and baselines of the localization of the platforms, which can be used for testing their localization and simultaneous localization and mapping (SLAM) algorithms. We also provide details on the setup and execution of each mission and a partial labeling of the elements found in the sewers. All the data were recorded by using the rosbag tool from robot operating system framework. Our goal is to make the data available to the scientific community as a benchmark to test localization, SLAM and classification algorithms in underground environments. The data set are available at .
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据