JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/12346

Title: Unsupervised Learning Approach to Attention-Path Planning for Large-scale Environment Classification
Authors: Lee, Hosun
Jeong, Sungmoon
Chong, Nak Young
Keywords: unsupervised learning
attention-path planning
submodular optimization
environment classification
Issue Date: 2014-09
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Magazine name: 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014)
Start page: 1447
End page: 1452
DOI: 10.1109/IROS.2014.6942747
Abstract: An unsupervised attention-path planning algorithm is proposed and applied to large unknown area classification with small field-of-view cameras. Attention-path planning is formulated as the sequential feature selection problem that greedily finds a sequence of attentions to obtain more informative observations, yielding faster training and higher accuracies. In order to find the near-optimal attention-path, adaptive submodular optimization is employed, where the objective function for the internal belief is adaptive submodular and adaptive monotone. First, the amount of information of attention areas is modeled as the dissimilarity variance among the environment data set. With this model, the information gain function is defined as a function of variance reduction that has been shown to be submodular and monotone in many cases. Furthermore, adapting to increasing numbers of observations, each information gain for attention areas is iteratively updated by discarding the non-informative prior knowledge, enabling to maximize the expected information gain. The effectiveness of the proposed algorithm is verified through experiments that can significantly enhance the environment classification accuracy, with reduced number of limited field of view observations.
Rights: This is the author's version of the work. Copyright (C) 2014 IEEE. 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014), 2014, 1447-1452. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
URI: http://hdl.handle.net/10119/12346
Material Type: author
Appears in Collections:b11-1. 会議発表論文・発表資料 (Conference Papers)

Files in This Item:

File Description SizeFormat
20338.pdf802KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.


Contact : Library Information Section, Japan Advanced Institute of Science and Technology