Map Merging for Multiple Robot Simultaneous Localization and Mapping

PDF

Authors
  1. Saeedi, S.
  2. Paull, L.
  3. Trentini, M.
  4. Li, H.
Corporate Authors
Defence R&D Canada - Suffield, Ralston ALTA (CAN)
Abstract
In robotics, the key requirement for achieving autonomy is to provide robots with the ability to accurately map an environment and localize themselves within that environment simultaneously. This problem is referred to as Simultaneous Localization and Mapping (SLAM). In this research, a decentralized platform for SLAM with multiple robots has been developed. Single vehicle SLAM is achieved through Extended to multiple vehicle SLAM with a novel occupancy grid map fusion algorithm. Map fusion is achieved through a multi-step process that includes image pre-processing, segmentation, cross correlation, approximating the relative transformation matrix, tuning of the transformation through the Radon image transform and a similarity index, and then verification of the result using either map entropy or a verification index. Results are shown from tests performed on real environments with multiple robotic platforms.
Keywords
simultaneous localization and mapping;SLAM;multiple robot;map fusion;segmentation;radon image;image entropy
Report Number
DRDC-SUFFIELD-SL-2012-203 — Scientific Literature
Date of publication
17 Nov 2015
Number of Pages
15
DSTKIM No
CA041473
CANDIS No
802669
Format(s):
Document Image stored on Optical Disk

Permanent link

Document 1 of 1

Date modified: