JAIST Repository >
School of Information Science >
Articles >
Journal Articles >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/12332

Title: Autonomous and Interactive Improvement of Binocular Visual Depth Estimation through Sensorimotor Interaction
Authors: Mann, Timothy A.
Park, Yunjung
Jeong, Sungmoon
Lee, Minho
Choe, Yoonsuck
Keywords: Action and Vision
autonomy
depth estimation
learning
perception
Issue Date: 2012-08-31
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Magazine name: IEEE Transaction on Autonomous Mental Development
Volume: 5
Number: 1
Start page: 74
End page: 84
DOI: 10.1109/TAMD.2012.2216524
Abstract: We investigate how a humanoid robot with a randomly initialized binocular vision system can learn to improve judgments about egocentric distances using action and interaction that might be available to a human infant. First, we show how distance estimation can be improved autonomously. We find that actions that maintain invariant distance are a powerful tool for exposing estimation errors. These errors can be used to train a distance estimator. Furthermore, the simple action used (i.e. neck rotation) does not require high level cognitive processing or fine motor skill. Second, we investigate how interaction with humans can further improve visual distance estimates. We find that human interaction can also improve distance estimates for far targets compared to autonomous learning without human interaction. Together these experiments suggest that both action and interaction are important tools for improving perception.
Rights: This is the author's version of the work. Copyright (C) 2012 IEEE. IEEE Transaction on Autonomous Mental Development, 5(1), 2012, 74-84. 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/10119/12332
Material Type: author
Appears in Collections:b10-1. 雑誌掲載論文 (Journal Articles)

Files in This Item:

File Description SizeFormat
21308.pdf2174KbAdobe 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