A self-learning robot vision system

Hisato Kobayashi*, Kenko Uchida, Yutaka Matsuzaki


研究成果: Conference contribution

4 被引用数 (Scopus)


The authors propose a self-learning strategy for robot vision systems which are used to identify the position of the target part handled by a robot. They tried to use a neural network as a decision-making system which determines how to move the robot to reach the exact target on the base of the image acquired by the robot eye. The authors taught this function automatically to the neural network. The total system works as follows: (1) a target object is set at a known position, and the position is taught to the system, (2) the robot moves randomly around the target and the neural network learns the relation between the relative positions and images, and (3) after enough learning, the robot can identify the target located at an arbitrary position.

ホスト出版物のタイトル91 IEEE Int Jt Conf Neural Networks IJCNN 91
Place of PublicationPiscataway, NJ, United States
出版社Publ by IEEE
出版ステータスPublished - 1991
イベント1991 IEEE International Joint Conference on Neural Networks - IJCNN '91 - Singapore, Singapore
継続期間: 1991 11月 181991 11月 21


Other1991 IEEE International Joint Conference on Neural Networks - IJCNN '91
CitySingapore, Singapore

ASJC Scopus subject areas

  • 工学(全般)


「A self-learning robot vision system」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。