Paper Info
Title
Cognitive representation and Bayeisan model of spatial object contexts for robot localization
Abstract
This paper proposes a cognitive representation and Bayesian model for spatial relations among objects that can be constructed with perception data acquired by a single consumer-grade camera. We first suggest a cognitive representation to be shared by humans and robots consisting of perceived objects and their spatial relations. We then develop Bayesian models to support our cognitive representation with which the location of a robot can be estimated sufficiently well to allow the robot to navigate in an indoor environment. Based on extensive localization experiments in an indoor environment, we show that our cognitive representation is valid in the sense that the localization accuracy improves whenever new objects and their spatial relations are detected and instantiated.
Year
DOI
Venue
2008
10.1007/978-3-642-02490-0_91
ICONIP (1)
Keywords
Field
DocType
localization accuracy,cognitive representation,bayeisan model,extensive localization experiment,spatial object context,robot localization,single consumer-grade camera,perception data,indoor environment,spatial relation,new object,bayesian model
Spatial relation,Computer vision,Robot localization,Bayesian inference,Computer science,Artificial intelligence,Robot,Cognition,Perception,Machine learning,Bayesian probability
Conference
Volume
ISSN
ISBN
5506
0302-9743
3-642-02489-0
Citations 
PageRank 
References 
5
0.57
10
Authors
5
Name
Order
Citations
PageRank
Chuho Yi1396.22
Il Hong Suh2780110.60
Gi Hyun Lim316217.33
Seungdo Jeong4258.82
Byung-Uk Choi55014.62