Scholarlink

<p>With the introduction of mobile mapping technologies, geomonitoring has become increasingly efficient and automated. The integration of Simultaneous Localization and Mapping (SLAM) and robotics has addressed the challenges posed by many monitoring technologies, such as by Global Navigation Satellite System (GNSS) and uncrewed aerial vehicles, which fail to work in underground environments. However, the complexity of underground environments, the high cost of research in this area, and the limited availability of experimental sites have hindered the progress of relevant research in the field of SLAM-based underground geomonitoring. In response, we present SubSurfaceGeoRobo, a&#xa0;dataset specifically focused on underground environments with unique characteristics of subsurface settings, such as extremely narrow passages, high humidity, standing water, reflective surfaces, uneven illumination, dusty conditions, complex geometry, and texture-less areas. This aims to provide researchers with a&#xa0;free platform to develop, test, and train their methods, ultimately promoting the advancement of SLAM, navigation, and SLAM-based geomonitoring in underground environments. SubSurfaceGeoRobo was collected in the Reiche Zeche Research Mine in Freiberg, Germany, using an uncrewed ground vehicle equipped with a&#xa0;multi-sensor system, including radar, 3D LiDAR, depth and RGB cameras, IMUs, and 2D laser scanners. Data from all sensors are stored in ROS bag files, allowing researchers to reuse the collected data for their specific purposes. To ensure the accuracy and usability of the dataset, as well as the effective fusion of sensors, all sensors have been jointly calibrated. The calibration methods and results are included as part of this dataset. Finally, a&#xa0;3D point cloud ground truth with an accuracy of less than 2 mm, captured using a&#xa0;RIEGL terrestrial laser scanner (TLS), along with the coordinate of the designed control points, is provided as a&#xa0;reference standard.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SubSurfaceGeoRobo: a Comprehensive Underground Dataset for SLAM-Based Geomonitoring with Sensor Calibration

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月15日

查看全文
  • Jing Li,
  • Jörg Benndorf,
  • Christian Köhler,
  • Paulina Loskot

摘要

With the introduction of mobile mapping technologies, geomonitoring has become increasingly efficient and automated. The integration of Simultaneous Localization and Mapping (SLAM) and robotics has addressed the challenges posed by many monitoring technologies, such as by Global Navigation Satellite System (GNSS) and uncrewed aerial vehicles, which fail to work in underground environments. However, the complexity of underground environments, the high cost of research in this area, and the limited availability of experimental sites have hindered the progress of relevant research in the field of SLAM-based underground geomonitoring. In response, we present SubSurfaceGeoRobo, a dataset specifically focused on underground environments with unique characteristics of subsurface settings, such as extremely narrow passages, high humidity, standing water, reflective surfaces, uneven illumination, dusty conditions, complex geometry, and texture-less areas. This aims to provide researchers with a free platform to develop, test, and train their methods, ultimately promoting the advancement of SLAM, navigation, and SLAM-based geomonitoring in underground environments. SubSurfaceGeoRobo was collected in the Reiche Zeche Research Mine in Freiberg, Germany, using an uncrewed ground vehicle equipped with a multi-sensor system, including radar, 3D LiDAR, depth and RGB cameras, IMUs, and 2D laser scanners. Data from all sensors are stored in ROS bag files, allowing researchers to reuse the collected data for their specific purposes. To ensure the accuracy and usability of the dataset, as well as the effective fusion of sensors, all sensors have been jointly calibrated. The calibration methods and results are included as part of this dataset. Finally, a 3D point cloud ground truth with an accuracy of less than 2 mm, captured using a RIEGL terrestrial laser scanner (TLS), along with the coordinate of the designed control points, is provided as a reference standard.