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/10119/11613

Title: Attention-Path Planning Based on Adaptive Submodular Optimization
Authors: Lee, Hosun
Jeong, Sungmoon
Nakashima, Tokuichi
Lee, Geunho
Chong, Nak Young
Keywords: attention path planning
submodular optimization
information gain
face recognition
Issue Date: 2013-08-26
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Magazine name: 2013 IEEE RO-MAN: The 22nd IEEE International Symposium on Robot and Human Interactive Communication
Start page: 304
End page: 305
DOI: 10.1109/ROMAN.2013.6628503
Abstract: This paper proposes a new attention-path planning algorithm that allows robots with limited sensing coverage to identify an unknown entity efficiently. Our focus is placed on how to plan optimal sequences of views to access more useful information needed to understand the entity. The adaptive submodular optimization technique guaranteed to achieve near-optimal performance is used to maximize the expected information gain. We verified the validity of the proposed approach to the face recognition problem through preliminary experiments.
Rights: This is the author's version of the work. Copyright (C) 2013 IEEE. 2013 IEEE RO-MAN: The 22nd IEEE International Symposium on Robot and Human Interactive Communication, 2013, 304-305. 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/10119/11613
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
19477.pdf230KbAdobe PDFView/Open

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

 


Contact : Library Information Section, JAIST (ir-sys[at]ml.jaist.ac.jp)