Estimating Robot Localization Error Using Visual Marker Pose Estimation

• Author / Creator

  Scheideman, Sean

• This thesis proposes a method to estimate robot localization error without having a ground-truth measurement of robot position. Robot localization refers to estimating a robot position and orientation (pose) within a known map, where the error is the difference between the robot’s ground-truth pose and the algorithms estimated pose. Ground-truth measurement systems (eg. motion capture) while accurate are expensive and tend to be difficult to set up in new environments. A new landmark-based method which uses visual markers placed throughout the environment is proposed as an alternative to ground-truth systems.

  The method requires visiting a visual marker twice, collecting the localization pose and robot-to-marker pose on both visits. After enough samples are collected the localization error is calculated using generative latent optimization (GLO). Experiments are run using the proposed method to estimate the localization error for several different open source algorithms. The method is accurate within an order of magnitude of ground-truth established using a motion capture system, inexpensive and easy to setup.
  

• Subjects / Keywords

  • SLAM
  • Mobile Robot Performance Evaluation
  • Localization

• Graduation date

  Fall 2019

• Type of Item

  Thesis

• Degree

  Master of Science

• DOI

  https://doi.org/10.7939/r3-z6b3-v602

• License

  Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of these terms. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.