顕著性に基づくロボットの能動的語彙獲得 Lexical Acquisition using the Active Nature Based on Saliency

この論文にアクセスする

この論文をさがす

著者

抄録

Observational studies of human infants tell us that they can successfully acquire lexicon and that the relationship between the meaning and the uttered word can be understood from only one teaching session by a caregiver, even though there are many other possible mappings. This paper proposes a lexical acquisition model that makes use of curiosity to associate visual features of observed objects with the labels that are uttered by a caregiver. A robot changes its attention and learning rate based on the curiosity. In experiments with a humanoid robot, the visual features are represented using self-organizing maps that adaptively represent the shape of the observed objects independent of viewpoint.

収録刊行物

  • 日本ロボット学会誌 = Journal of Robotics Society of Japan  

    日本ロボット学会誌 = Journal of Robotics Society of Japan 26(3), 261-270, 2008-04-15 

    The Robotics Society of Japan

参考文献:  15件

参考文献を見るにはログインが必要です。ユーザIDをお持ちでない方は新規登録してください。

被引用文献:  3件

被引用文献を見るにはログインが必要です。ユーザIDをお持ちでない方は新規登録してください。

各種コード

  • NII論文ID(NAID)
    10021142175
  • NII書誌ID(NCID)
    AN00141189
  • 本文言語コード
    JPN
  • 資料種別
    ART
  • ISSN
    02891824
  • NDL 記事登録ID
    9474343
  • NDL 雑誌分類
    ZN11(科学技術--機械工学・工業)
  • NDL 請求記号
    Z16-1325
  • データ提供元
    CJP書誌  CJP引用  NDL  J-STAGE 
ページトップへ