ニューラルネットワークによるロボットの作業対象物の運動拘束認識

• 関 啓明

  金沢大学工学部

• 佐々木 健

  東京大学工学部

• 高野 政晴

  関西大学工学部

書誌事項

タイトル別名

• Detection of Kinematic Constraint from Search Motion of a Robot Using Neural Network.
• ニューラル ネットワーク ニヨル ロボット ノ サギョウ タイショウブツ ノ

抄録

In this paper, a method for detecting kinematic constraints in a plane when the shapes of the grasped object and the environment are not given is presented.It is one of the important function for intelligent tasks of home, maintenance, assembly and disassembly robots. This method utilizes the displacement and force information obtained by“active search motion”of a robot. In reality, this information includes some uncertainties such as friction, slack and elasticity. A new neural network configuration for this detection is proposed. It consists of two multilayer networks (primary and secondary network) . The primary network learns the movable space (constraint) obtained by the search motion. By the generated link weights which reflect the movable space, the secondary network determines the type and the orientation of the constraint. Simulation and experimental results are presented and analyzed.

収録刊行物

• 日本ロボット学会誌

  日本ロボット学会誌 16 (2), 265-273, 1998

  一般社団法人 日本ロボット学会

キーワード

• Constraint
• Search Motion
• Movable Space
• Neural Network
• Link Weights

詳細情報

• CRID: 1390001204725257472
• NII論文ID: 10007441385
• NII書誌ID: AN00141189
• DOI: 10.7210/jrsj.16.265
• ISSN: 18847145
• ISSN: 02891824
• NDL書誌ID: 4424182
• Web Site: http://hdl.handle.net/2297/28576
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I4424182
• 本文言語コード: ja
• データソース種別:
  • JaLC
  • IRDB
  • NDL
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可