Paper Info
Title
Ceiling vision based localizer for mobile robot
Abstract
When mobile robots perform their missions, the self-localization is needed basically. Several past researches established how to obtain their location information from the environment by using a distance sensor or a camera. However, these methods have map-making problem when the environment changes and localization problem while the robot moves from sensing features has typical affine and occlusion characteristics. This paper presents a localizer for mobile robot that travels around indoor environments. Our module uses the only one sensor, a single camera looking up the ceiling. There is no efficient enough SLAM* (Simultaneous Localization And Mapping) algorithm working on embedded system. The initial difficulty of vision based SLAM is computational complexity to acquire reliable feature on their algorithm. To reduce the computational complexity, we use the ceiling segmentation to extract line features of ceiling area. Line features are extracted from the boundaries between the ceiling and walls. The line features have advantages over point features for its robustness to environmental variation and structural information helpful to data association. Extended Kalman Filter is used to estimate the pose of a robot and build the ceiling map with line features. The experiment is practiced in our indoor test bed and the proposed algorithm is proved by the experimental results. *SLAM: Simultaneous localization and mapping is a technique used by robots and autonomous vehicles to build up a map within an unknown environment or to update a map within a known environment while at the same time keeping track of their current location.
Year
DOI
Venue
2011
10.1145/1999320.1999374
COM.Geo
Keywords
Field
DocType
ceiling segmentation,environment change,mobile robot,line feature,ceiling area,simultaneous localization,indoor environment,ceiling map,computational complexity,ceiling vision,known environment,logistic regression,likelihood ratio,extended kalman filter,test bed,gis,artificial neural network,embedded system,simultaneous localization and mapping
Affine transformation,Computer vision,Extended Kalman filter,Computer science,Ceiling (aeronautics),Robustness (computer science),Artificial intelligence,Simultaneous localization and mapping,Robot,Mobile robot,Computational complexity theory
Conference
Citations 
PageRank 
References 
0
0.34
0
Authors
3
Name
Order
Citations
PageRank
Seunghun Kim1316.05
Chang-Woo Park217421.54
Sewoong Jun310.70