Guided Visual Attention Model Based on Interactions Between Top-down and Bottom-up Prediction for Robot Pose Prediction

Hyogo Hiruma, Hiroki Mori, Hiroshi Ito, Tetsuya Ogata

研究成果: Conference contribution

抄録

Deep robot vision models are widely used for recognizing objects from camera images, but shows poor performance when detecting objects at untrained positions. Although such problem can be alleviated by training with large datasets, the dataset collection cost cannot be ignored. Existing visual attention models tackled the problem by employing a data efficient structure which learns to extract task relevant image areas. However, since the models cannot modify attention targets after training, it is difficult to apply to dynamically changing tasks. This paper proposed a novel Key-Query-Value formulated visual attention model. This model is capable of switching attention targets by externally modifying the Query representations, namely top-down attention. The proposed model is experimented on a simulator and a real-world environment. The model was compared to existing end-to-end robot vision models in the simulator experiments, showing higher performance and data efficiency. In the real-world robot experiments, the model showed high precision along with its scalability and extendibility.

本文言語English
ホスト出版物のタイトルIECON 2022 - 48th Annual Conference of the IEEE Industrial Electronics Society
出版社IEEE Computer Society
ISBN(電子版)9781665480253
DOI
出版ステータスPublished - 2022
イベント48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022 - Brussels, Belgium
継続期間: 2022 10月 172022 10月 20

出版物シリーズ

名前IECON Proceedings (Industrial Electronics Conference)
2022-October

Conference

Conference48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022
国/地域Belgium
CityBrussels
Period22/10/1722/10/20

ASJC Scopus subject areas

  • 制御およびシステム工学
  • 電子工学および電気工学

フィンガープリント

「Guided Visual Attention Model Based on Interactions Between Top-down and Bottom-up Prediction for Robot Pose Prediction」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