穴の位置とワイヤ姿勢が不確実な挿入作業のための視差に基づく模倣学習

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2023/09/01

タイトル(英語): Parallax-based Imitation Learning for Insertion Tasks with Uncertainties of Hole Position and Wire Pose

著者名: 丹羽　靖治（岐阜大学工学部），加藤　邦人（岐阜大学工学部），中島　康博（岐阜大学工学部），八田　禎之（岐阜大学工学部），伊藤　和晃（岐阜大学工学部）

著者名(英語): Yasuharu Niwa (Department of Engineering, Gifu University), Kunihito Kato (Department of Engineering, Gifu University), Yasuhiro Nakajima (Department of Engineering, Gifu University), Yoshiyuki Hatta (Department of Engineering, Gifu University), Kazuaki I

キーワード: 模倣学習，深層学習，画像処理，セーフティワイヤ　　imitation learning，deep learning，image processing，safety wire

要約(英語): Standard insertion machines require pre-determined component position and posture. If they change every time, we must solve this problem. Most conventional methods attempted to solve this task by identifying the position and posture. However, these methods require a multi-step strategy following the handmade rule. This paper proposes an imitation learning method to automate the wire insertion task with uncertainties in position and posture. The proposed model learns the motion policy through human demonstrations and maps image data to the robot's action in a single step. Moreover, the model considers the parallax of the stereo images for accurate insertion. In addition, the model outputs the insertion action and recovery action to recover from insertion failures. However, the standard data collection method cannot collect recovery actions, and manual labeling of action classes is essential. This paper proposes a novel data collection method called "Labeling with Human Intervention (LHI)" to tackle this problem. This method automatically generates action labels and collects recovery action with human intervention. We conducted real-space insertion tests and found that our approach achieved 97.2% (35/36).

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.143 No.9 （2023） 特集：知能メカトロニクス分野と連携する知覚情報技術

本誌掲載ページ: 862-870 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/143/9/143_862/_article/-char/ja/