Environment identification by comparing maps of landmarks

Author

Guttman, J.-S. ; Fukuchi, Masaki ; Sabe, Kohtaro

Author_Institution

Digital Creatures Lab., Sony Corp., Tokyo, Japan

Volume

1

fYear

2003

fDate

14-19 Sept. 2003

Firstpage

262

Abstract

This paper describes a method for identifying an environment a robot is operating in by comparing the geometry of landmarks of a map the robot is currently building with a set of previously created maps. Landmark maps are created using the stochastic map approach originally presented by Smith, Self and Cheeseman [1990]. The paper provides a method for measuring the similarity of such maps and presents a closed form solution for the special case that covariances are constant. Experiments carried out on a developer version of the AlBO robot and on a prototype of the humanoid SDR-4X robot show that the approach is applicable even for robots with poor odometry.

Keywords

covariance analysis; mobile robots; navigation; path planning; prototypes; stochastic processes; AIBO robot; closed form solution; covariances; environment identification; humanoid SDR-4X robot prototype; landmark geometry; landmark map comparison; map building; map similarity measurement; mobile robot navigation; poor odometry; stochastic map approach; Buildings; Databases; Humanoid robots; Humans; Laboratories; Mobile robots; Navigation; Prototypes; Robot sensing systems; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation, 2003. Proceedings. ICRA '03. IEEE International Conference on

ISSN

1050-4729

Print_ISBN

0-7803-7736-2

Type

conf

DOI

10.1109/ROBOT.2003.1241606

Filename

1241606