Simultaneous Localization and Mapping System Based on Labels

Tong Liu, Panpan Liu, Songtian Shang, Yi Yang*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

In this paper a label-based simultaneous localization and mapping (SLAM) system is proposed to provide localization to indoor autonomous robots. In the system quick response(QR) codes encoded with serial numbers are utilized as labels. These labels are captured by two webcams, then the distances and angles between the labels and webcams are computed. Motion estimated from the two rear wheel encoders is adjusted by observing QR codes. Our system uses the extended Kalman filter (EKF) for the back-end state estimation. The number of deployed labels controls the state estimation dimension. The label-based EKF-SLAM system eliminates complicated processes, such as data association and loop closure detection in traditional feature-based visual SLAM systems. Our experiments include software-simulation and robot-platform test in a real environment. Results demonstrate that the system has the capability of correcting accumulated errors of dead reckoning and therefore has the advantage of superior precision.

Original languageEnglish
Pages (from-to)534-541
Number of pages8
JournalJournal of Beijing Institute of Technology (English Edition)
Volume26
Issue number4
DOIs
Publication statusPublished - 1 Dec 2017

Keywords

  • Artificial landmarks
  • Extended Kalman filter (EKF)
  • Quick response(QR) codes
  • Simultaneous localization and mapping (SLAM)

Fingerprint

Dive into the research topics of 'Simultaneous Localization and Mapping System Based on Labels'. Together they form a unique fingerprint.

Cite this

Liu, T., Liu, P., Shang, S., & Yang, Y. (2017). Simultaneous Localization and Mapping System Based on Labels. Journal of Beijing Institute of Technology (English Edition), 26(4), 534-541. https://doi.org/10.15918/j.jbit1004-0579.201726.0413