Deep-Learning-Based Designed Weight Picking Noodle-like Object

DOI
  • Koomklang Nattapat
    Department of Mechanical Information Science and Technology, Kyushu Institute of Technology
  • Chumkamon Sakmongkon
    Department of Mechanical Information Science and Technology, Kyushu Institute of Technology
  • Gamolped Prem
    Department of Mechanical Information Science and Technology, Kyushu Institute of Technology
  • Tsuji Tomofumi
    Department of Mechanical Information Science and Technology, Kyushu Institute of Technology
  • Hayashi Eiji
    Department of Mechanical Information Science and Technology, Kyushu Institute of Technology
  • Mowshowitz Abbe
    Department of Computer Science, The City College of New York

説明

For food packaging line, manual picking up of the noodle-like objects according to specific weight requires worker's experience for picking quickly and accurately. This article presents a robot arm with a 6-finger gripper picking up the noodle-like objects in specific weight using deep-learning-based to find the best possible action. For measuring the action, we use direct variation to probability of picking action at specific weight in this research use value for the likelihood of weight probability given an action. To find likelihood of weight probably deep-learning-based and use normal distribution for model distribution of the systems. For evaluation we passed any possible action to the network and find action that get maximum likelihood.

収録刊行物

キーワード

詳細情報 詳細情報について

  • CRID
    1390859758187572352
  • DOI
    10.5954/icarob.2023.os13-2
  • ISSN
    21887829
  • 本文言語コード
    en
  • データソース種別
    • JaLC
    • Crossref
    • OpenAIRE
  • 抄録ライセンスフラグ
    使用不可

問題の指摘

ページトップへ