Jump to Content
  1. Queen's
  2. Smith Eng.
  3. ECE

Estimation, Search, and Planning (ESP) Research Group

Surface Edge Explorer (SEE++)

Source Code

An open-source version of SEE++ is now available. You can find SEE++ on our Github repository and usage instructions on the Doxygen webpage.

Description

The Surface Edge Explorer (SEE++) is a Next Best View (NBV) planning approach that uses a novel unstructured density representation to efficiently obtain complete scene observations. SEE++ uses point-based computations to identify boundaries in a scene observation, propose new views to extend the observation and select a next best view while proactively considering occlusions and the attainable improvement in scene coverage. Experimental results show that SEE++ outperforms NBV planning approaches with volumetric representations in terms of the computational cost, travel distance and number of views required to obtain complete scene observations.

Return to Top
  1. Authors
    1. R. Border
    2. J. D. Gammell
    Title
    The Surface Edge Explorer (SEE): A measurement-direct approach to next best view planning
    Publication
    Journal
    The International Journal of Robotics Research (IJRR)
    Volume
    43
    Number
    10
    Pages
    1506–1532
    Date
    Code
    Code
    Videos
    Video
    PDFs
    PDF
    Digital Object Identifier (DOI)
    doi: 10.1177/02783649241230098
    arXiv
    Google Scholar
    Google Scholar
  2. Authors
    1. R. Border
    2. J. D. Gammell
    Title
    Proactive estimation of occlusions and scene coverage for planning next best views in an unstructured representation
    Publication
    Conference
    Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
    Pages
    4219–4226
    Date
    Code
    Code
    Videos
    Video
    Presentations
    Presentation
    PDFs
    PDF
    Digital Object Identifier (DOI)
    doi: 10.1109/IROS45743.2020.9341681
    arXiv
    Google Scholar
    Google Scholar
  3. Author
    R. Border
    Title
    Next best view planning with an unstructured representation
    Publication
    Type
    D.Phil. Thesis
    School
    University of Oxford
    Date
    PDFs
    PDF
    Google Scholar
    Google Scholar
  4. Authors
    1. R. Border
    2. J. D. Gammell
    3. P. Newman
    Title
    Surface Edge Explorer (SEE): Planning next best views directly from 3D observations
    Publication
    Conference
    Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)
    Pages
    1–8
    Location
    Brisbane, Australia
    Date
    Code
    Code
    Videos
    Video
    Presentations
    Presentation
    PDFs
    PDF
    Digital Object Identifier (DOI)
    doi: 10.1109/ICRA.2018.8461098
    arXiv
    Google Scholar
    Google Scholar