Mobile Robot Localization from Learned Landmarks

Mobile Robot Localization from Learned Landmarks (0)

by Robert Sim , Gregory Dudek

Venue:	in Proceedings of IEEE/RSJ Conference on Intelligent Robots and Systems (IROS
Citations:	43 - 9 self

Datum	Value	Source
TITLE	Mobile robot localization from learned landmarks	INFERENCE
AUTHOR NAME	Robert Sim	SVM HeaderParse 0.1
AUTHOR AFFIL	Centre for Intelligent Machines; McGill University	SVM HeaderParse 0.2
AUTHOR ADDR	3480 University St.; Montreal, QC H3A 2A7	SVM HeaderParse 0.1
AUTHOR NAME	Gregory Dudek	SVM HeaderParse 0.1
AUTHOR AFFIL	Centre for Intelligent Machines; McGill University	SVM HeaderParse 0.2
AUTHOR ADDR	3480 University St.; Montreal, QC H3A 2A7	SVM HeaderParse 0.1
ABSTRACT	This paper presents an approach to vision-based mobile robot localization. In an attempt to capitalize on the benefits of both image and landmark-based methods, we describe a method that combines their strengths. Images are encoded as a set of visual features called landmarks. Potential landmarks are detected using an attention mechanism implemented as a measure of uniqueness. They are then selected and represented by an appearance-based encoding. Localization is performed using a landmark tracking and interpolation method which obtains an estimate accurate to a fraction of the environment sampling density. Experimental results are shown to confirm the feasibility and accuracy of the method. 1	SVM HeaderParse 0.1
YEAR	1998	INFERENCE
VENUE	in Proceedings of IEEE/RSJ Conference on Intelligent Robots and Systems (IROS	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
CITATIONS	25 found	ParsCit 1.0