Robotic Subsurface Pipeline Mapping with a Ground-penetrating Radar and a Camera Conference Paper uri icon

abstract

  • 2018 IEEE. We propose a novel subsurface pipeline mapping method by fusing Ground Penetrating Radar (GPR) scans and camera images. To facilitate the simultaneous detection of multiple pipelines, we model the GPR sensing process and prove hyperbola response for general scanning with non-perpendicular angles. Furthermore, we fuse visual simultaneous localization and mapping outputs, encoder readings with GPR scans to classify hyperbolas into different pipeline groups. We extensively apply the J-Linkage method and maximum likelihood estimation to improve algorithm robustness and accuracy. As the result, we optimally estimate the radii and locations of all pipelines. We have implemented our method and tested it in physical experiments with representative pipeline configurations. The results show that our method successfully reconstructs all subsurface pipes. Moreover, the average localization error is 4.69cm.

name of conference

  • 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

published proceedings

  • 2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)

altmetric score

  • 6

author list (cited authors)

  • Li, H., Chou, C., Fan, L., Li, B., Wang, D. i., & Song, D.

citation count

  • 5

complete list of authors

  • Li, Haifeng||Chou, Chieh||Fan, Longfei||Li, Binbin||Wang, Di||Song, Dezhen

publication date

  • October 2018