An indoor localization aid for the visually impaired

Joel A. Hesch, Stergios I. Roumeliotis

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

40 Scopus citations

Abstract

This paper presents an indoor human localization system for the visually impaired. A prototype portable device has been implemented, consisting of a pedometer and a standard white cane, on which a laser range finder and a 3-axis gyroscope have been mounted. A novel pose estimation algorithm has been developed for robustly estimating the heading and position of a person navigating in a known building. The basis of our estimation scheme is a two-layered Extended Kaiman Filter (EKF) for attitude and position estimation. The first layer maintains an attitude estimate of the white cane, which is subsequently provided to the second layer where a position estimate of the user is generated. Experimental results are presented that demonstrate the reliability of the proposed method for accurate, real-time human localization.

Original languageEnglish (US)
Title of host publication2007 IEEE International Conference on Robotics and Automation, ICRA'07
Pages3545-3551
Number of pages7
DOIs
StatePublished - 2007
Externally publishedYes
Event2007 IEEE International Conference on Robotics and Automation, ICRA'07 - Rome, Italy
Duration: Apr 10 2007Apr 14 2007

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729

Other

Other2007 IEEE International Conference on Robotics and Automation, ICRA'07
Country/TerritoryItaly
CityRome
Period4/10/074/14/07

Fingerprint

Dive into the research topics of 'An indoor localization aid for the visually impaired'. Together they form a unique fingerprint.

Cite this