Abstract
The aim of this paper is to provide a brief overview of vector map techniques used in mobile robotics and to present current state of the research in this field at the Brno University of Technology. Vector maps are described as a part of the simultaneous localization and mapping (SLAM) problem in the environment without artificial landmarks or global navigation system. The paper describes algorithms from data acquisition to map building but particular emphasis is put on segmentation, line extraction and scan matching algorithms. All significant algorithms are illustrated with experimental results.
Highlights
Mapping in robotics is a subject of research for a number of years and large progress was already achieved
Non-optimized solutions have O(n2) or even exponential complexity, but several algorithms are more efficient, for example FastSLAM [5] with O(m log(n)) complexity
Results of this paper clearly show that algorithms such as RANSAC or Hough transform are not fast enough for online processing of point clouds
Summary
Mapping in robotics is a subject of research for a number of years and large progress was already achieved. Paper [1] describes theoretical way, how to build and update a consistent map, which converges to a precise image of the real environment (at certain level of detail). Non-optimized solutions have O(n2) or even exponential complexity, but several algorithms are more efficient, for example FastSLAM [5] with O(m log(n)) complexity (where n is the number of landmarks and m the number of particles in the Rao-Blackwellized filter). This algorithm can handle orders of magnitude more landmarks than O(n2) solutions. Computational efficiency is a key to large maps with a lot of details
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
