A Study on Assembly Work Support System to Foster High Sense of Work Contribution

2023 Fiscal Year Final Research Report

• Project/Area Number: 21K11992
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 61020:Human interface and interaction-related
• Research Institution: Tokyo University of Agriculture and Technology
• Principal Investigator: Fujinami Kaori 東京農工大学, 工学(系)研究科(研究院), 教授 (10409633)
• Co-Investigator(Kenkyū-buntansha): 辻 愛里 東京農工大学, 工学(系)研究科(研究院), 助教 (10774284)
• Project Period (FY): 2021-04-01 – 2024-03-31
• Keywords: 内部状態推定 / 組立作業 / 機械学習 / エージェント / 認知負荷

Outline of Final Research Achievements

This study developed a method to estimate the state of confusion during assembly work to provide support tailored to workers' skill levels. A subtle support method using gaze guidance by an agent was also investigated.
A supervised machine learning model was constructed based on the positional relationship between gaze and hand and electrodermal activity to estimate confusion. The best F1-score of 0.735 in 3-class classification (presence/absence of confusion and type) confirmed the effectiveness of histogram information of hand and gaze positions. The 5-class classification yielded an F1-score of 0.533.
For gaze guidance by agents, the effectiveness of the agent compared to conditions without an agent (only video-based instruction) was confirmed, considering the presence of physicality, i.e., robot and CG agent, and its impact on guidance and impressions. It was also found that there was little difference in impressions between the two types of agents.

Free Research Field

ヒューマンコンピュータインタラクション

Academic Significance and Societal Importance of the Research Achievements

組立作業中の「迷い」という主観的な人間の内部状態を視線や手の位置といった外部から観測可能な情報を用いて0.7程度の精度で推定するモデルの構築方法を明らかになった．また，部品探索効果を上げるためのエージェントの視線誘導方法が明らかになった．このことは，今後，多品種少量生産の組立作業中に適切な支援を行うシステムの実現につながり，労働力不足の解消に貢献すると考える．