doi:10.1016/j.robot.2004.03.014 
Copyright © 2004 Elsevier B.V. All rights reserved.
Image-based memory for robot navigation using properties of omnidirectional
images
Emanuele Menegatti
, 
, a,
Takeshi Maedab
and Hiroshi Ishiguroc
a Intelligent Autonomous Systems
Laboratory, Department of Information Engineering (DIE), Faculty of Engineering,
The University of Padua, Via Gradenigo 6/a, 35131, Padova, Italy
b VStone Co. Ltd., Shimaya 4-2-7, Konohana, Osaka
554-0024, Japan
c Department of Adaptive Machine
Systems, Osaka University, Suita, Osaka 565-0871, Japan
Received 25 July
2003; Revised 22 February 2004; accepted 8 March 2004.
Available online 9 June 2004.
Abstract
This paper proposes a new technique for vision-based robot navigation. The
basic framework is to localise the robot by comparing images taken at its
current location with reference images stored in its memory. In this work, the
only sensor mounted on the robot is an omnidirectional camera. The Fourier
components of the omnidirectional image provide a signature for the views
acquired by the robot and can be used to simplify the solution to the robot
navigation problem. The proposed system can calculate the robot position with
variable accuracy (‘hierarchical localisation’) saving computational time when
the robot does not need a precise localisation (e.g. when it is travelling
through a clear space). In addition, the system is able to self-organise its
visual memory of the environment. The self-organisation of visual memory is
essential to realise a fully autonomous robot that is able to navigate in an
unexplored environment. Experimental evidence of the robustness of this system
is given in unmodified office environments.
Author Keywords: Omnidirectional vision; Image-based
navigation; Fourier transform; Hierarchical localisation; Mobile robot
Corresponding author. Tel.: +39-049 827 7856; fax: +39-049
827 7799.
