Curriculum-based Offline Network Training for Improvement of Peg-in-hole Task Performance for Holes in Concrete

Andre Yuji Yasutomi, Hiroki Mori, Tetsuya Ogata

研究成果: Conference contribution

抄録

A method for reducing the time required to train a deep neural network (DNN) via deep reinforcement learning (DRL) to enable a robot to conduct anchor-bolt insertion, a peg-in-hole task for holes in concrete, is proposed. The proposed method is also intended to reduce task execution time. The method consists of two steps. The first step involves creating a map of state observations and search results for holes opened in a concrete wall and using this map to train the DNN via DRL in an offline manner. The second step involves training the DNN with a curriculum that involves gradually increasing the step-size options the DNN can output to command the robot. Experimental evaluations of the method demonstrate that the offline training reduces DNN training time by about 87.5%, while enabling task execution with success rates and execution times that are similar to those obtained with a DNN trained online. Moreover, the evaluations show that curriculum training reduces task execution time, and enables execution of the peg-in-hole task for unknown holes with success rate of 97.5% and execution time of 7.77 s. This result represents a 12.8% higher success rate and a 4.71 s shorter execution time than those obtained with a DNN trained online. These results demonstrate the effectiveness of the proposed method and its applicability to the construction industry. Although the proposed method was applied to anchor-bolt insertion, it can be extended to any other peg-in-hole tasks conducted in discrete steps.

本文言語English
ホスト出版物のタイトル2022 IEEE/SICE International Symposium on System Integration, SII 2022
出版社Institute of Electrical and Electronics Engineers Inc.
ページ712-717
ページ数6
ISBN(電子版)9781665445405
DOI
出版ステータスPublished - 2022
イベント2022 IEEE/SICE International Symposium on System Integration, SII 2022 - Virtual, Narvik, Norway
継続期間: 2022 1月 92022 1月 12

出版物シリーズ

名前2022 IEEE/SICE International Symposium on System Integration, SII 2022

Conference

Conference2022 IEEE/SICE International Symposium on System Integration, SII 2022
国/地域Norway
CityVirtual, Narvik
Period22/1/922/1/12

ASJC Scopus subject areas

  • 人工知能
  • ハードウェアとアーキテクチャ
  • 生体医工学
  • 制御およびシステム工学
  • 機械工学
  • 制御と最適化

フィンガープリント

「Curriculum-based Offline Network Training for Improvement of Peg-in-hole Task Performance for Holes in Concrete」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