Three-dimensional outdoor SLAM using rotation invariant descriptors of salient regions

Yong Ju Lee, Joong Tae Park, Jae Bok Song

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    This research proposes a novel approach to outdoor simultaneous localization and mapping (SLAM) based on local 3-D map matching. An iterative closest point (ICP) algorithm is used to match local 3-D maps and estimate a robot pose, but an alignment error is generated by the ICP algorithm due to the false selection of corresponding points. This paper proposes a new method to extract 3-D points that are valid for ICP matching. Rotation invariant descriptors are introduced for robust correspondence. 3-D environmental data acquired by tilting a 2-D laser scanner are used to build local 3-D maps. Experimental results in real environments show the increased accuracy of the ICP-based matching and a reduction in matching time.

    Original languageEnglish
    Title of host publicationICCAS 2011 - 2011 11th International Conference on Control, Automation and Systems
    Pages1174-1177
    Number of pages4
    Publication statusPublished - 2011
    Event2011 11th International Conference on Control, Automation and Systems, ICCAS 2011 - Gyeonggi-do, Korea, Republic of
    Duration: 2011 Oct 262011 Oct 29

    Publication series

    NameInternational Conference on Control, Automation and Systems
    ISSN (Print)1598-7833

    Other

    Other2011 11th International Conference on Control, Automation and Systems, ICCAS 2011
    Country/TerritoryKorea, Republic of
    CityGyeonggi-do
    Period11/10/2611/10/29

    Keywords

    • Mapping
    • Outdoor navigation
    • SLAM
    • Three-dimensional maps

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Science Applications
    • Control and Systems Engineering
    • Electrical and Electronic Engineering

    Fingerprint

    Dive into the research topics of 'Three-dimensional outdoor SLAM using rotation invariant descriptors of salient regions'. Together they form a unique fingerprint.

    Cite this