Learning globally consistent maps by relaxation

Tom Duckett, Stephen Marsland, Jonathan Shapiro

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


    Mobile robots require the ability to build their own maps to operate in unknown environments. A fundamental problem is that odometry-based dead reckoning cannot be used to assign accurate global position information to a map because of drift errors caused by wheel slippage. This paper introduces a fast, on-line method of learning globally consistent maps, using only local metric information. The approach differs from previous work in that it is computationally cheap, easy to implement and is guaranteed to find a globally optimal solution. Experiments are presented in which large, complex environments were successfully mapped by a real robot, and quantitative performance measures are used to assess the quality of the maps obtained.
    Original languageEnglish
    Title of host publicationProceedings - IEEE International Conference on Robotics and Automation|Proc IEEE Int Conf Rob Autom
    Number of pages5
    Publication statusPublished - 2000
    EventICRA 2000: IEEE International Conference on Robotics and Automation - San Francisco, CA, USA
    Duration: 1 Jul 2000 → …


    ConferenceICRA 2000: IEEE International Conference on Robotics and Automation
    CitySan Francisco, CA, USA
    Period1/07/00 → …
    Internet address


    Dive into the research topics of 'Learning globally consistent maps by relaxation'. Together they form a unique fingerprint.

    Cite this