文章基本信息

标题：Map Building By Non-linear Dimensionality Reduction of Historical Visibility Data
本地全文：下载
作者：Takehisa Yairi
期刊名称：人工知能学会論文誌
印刷版ISSN：1346-0714
电子版ISSN：1346-8030
出版年度：2007
卷号：22
期号：3
页码：353-363
DOI：10.1527/tjsai.22.353
出版社：The Japanese Society for Artificial Intelligence
摘要：In recent years, simultaneous localization and mapping (SLAM) based on stochastic state-transition / observation models and Bayesian estimation technique has been the mainstream of the mobile robot mapping research. In contrast to this trend, we present an alternative formulation of the map building problem from the viewpoint of non-linear dimensionality reduction or manifold learning. In this framework, the robot map building is interpreted as a problem of reconstructing the coordinates of objects so that proximities between them in the space of robot's observation history as faithfully as possible. Based on this insight, we generalize the covisibility-based mapping method which was established in previous studies into the map building based on dimensionality reduction of historical visibility data. We applied latest non-linear dimensionality reduction techniques to this framework, and compared them with classical techniques such as PCA and MDS in experimental studies.
关键词：map building ; non-linear dimensionality reduction ; manifold learning ; mobile robot