Tactile object recognition using deep learning and dropout

研究成果: Conference contribution

44 被引用数 (Scopus)

抄録

Recognizing grasped objects with tactile sensors is beneficial in many situations, as other sensor information like vision is not always reliable. In this paper, we aim for multimodal object recognition by power grasping of objects with an unknown orientation and position relation to the hand. Few robots have the necessary tactile sensors to reliably recognize objects: in this study the multifingered hand of TWENDY-ONE is used, which has distributed skin sensors covering most of the hand, 6 axis F/T sensors in each fingertip, and provides information about the joint angles. Moreover, the hand is compliant. When using tactile sensors, it is not clear what kinds of features are useful for object recognition. Recently, deep learning has shown promising results. Nevertheless, deep learning has rarely been used in robotics and to our best knowledge never for tactile sensing, probably because it is difficult to gather many samples with tactile sensors. Our results show a clear improvement when using a denoising autoencoder with dropout compared to traditional neural networks. Nevertheless, a higher number of layers did not prove to be beneficial.

本文言語English
ホスト出版物のタイトル2014 IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014
出版社IEEE Computer Society
ページ1044-1050
ページ数7
ISBN(電子版)9781479971749
DOI
出版ステータスPublished - 2015 2 12
イベント2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014 - Madrid, Spain
継続期間: 2014 11 182014 11 20

出版物シリーズ

名前IEEE-RAS International Conference on Humanoid Robots
2015-February
ISSN(印刷版)2164-0572
ISSN(電子版)2164-0580

Other

Other2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014
国/地域Spain
CityMadrid
Period14/11/1814/11/20

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ ビジョンおよびパターン認識
  • ハードウェアとアーキテクチャ
  • 人間とコンピュータの相互作用
  • 電子工学および電気工学

フィンガープリント

「Tactile object recognition using deep learning and dropout」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