Two-way translation of compound sentences and arm motions by recurrent neural networks

Tetsuya Ogata, Masamitsu Murase, Jim Tani, Kazunori Komatani, Hiroshi G. Okuno

研究成果: Conference contribution

38 被引用数 (Scopus)

抄録

We present a connectionist model that combines motions and language based on the behavioral experiences of a real robot. Two models of recurrent neural network with parametric bias (RNNPB) were trained using motion sequences and linguistic sequences. These sequences were combined using their respective parameters so that the robot could handle many-to-many relationships between motion sequences and linguistic sequences. Motion sequences were articulated into some primitives corresponding to given linguistic sequences using the prediction error of the RNNPB model. The experimental task in which a humanoid robot moved its arm on a table demonstrated that the robot could generate a motion sequence corresponding to given linguistic sequence even if the motions or sequences were not included in the training data, and vice versa.

本文言語English
ホスト出版物のタイトルProceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007
ページ1858-1863
ページ数6
DOI
出版ステータスPublished - 2007 12 1
外部発表はい
イベント2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007 - San Diego, CA, United States
継続期間: 2007 10 292007 11 2

出版物シリーズ

名前IEEE International Conference on Intelligent Robots and Systems

Conference

Conference2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007
CountryUnited States
CitySan Diego, CA
Period07/10/2907/11/2

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

フィンガープリント 「Two-way translation of compound sentences and arm motions by recurrent neural networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル