Proposal of work pattern based on visual line information in the robot tractor cooperative work

2023 Fiscal Year Final Research Report

• Project/Area Number: 20K06315
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 41040:Agricultural environmental engineering and agricultural information engineering-related
• Research Institution: Fukushima University
• Principal Investigator: Kubota Yosuke 福島大学, 食農学類, 准教授 (40535267)
• Project Period (FY): 2020-04-01 – 2024-03-31
• Keywords: ロボットトラクタ / 同時作業 / 作業能率 / 視線計測 / 注視時間

Outline of Final Research Achievements

Japanese agriculture is facing a variety of problems, such as the aging of farmers, a decrease in the number of new farmers, and an increase in the amount of abandoned farmland.
Smart agriculture is attracting attention as a major key to solving these problems. Among them, simultaneous operation by manned and unmanned tractors using robot tractors is expected to contribute to solving labor shortages and significantly reducing production costs.
In this study, we measure the operator's line of sight during simultaneous work by manned and unmanned tractors, and after measuring the line of sight trajectory, gazing point, and gazing time as line of sight information, we construct a line of sight pattern model using image analysis and deep learning. Based on these results, we propose a safe and efficient work pattern for simultaneous tasks.

Free Research Field

生物生産機械学

Academic Significance and Societal Importance of the Research Achievements

本研究では，ロボットトラクタを用いた同時作業の評価と視線計測によるオペレータによる監視状況について検証した。視線計測は,ヒト行動における客観的計測手法として多くの研究に用いられているが，農作業の計測，評価に用いられた例は少ないことから、本研究の視線計測データを利用した解析結果の公表は，学術的意義は大きいと考えられる。また，現地試験によるスマート農機や新たな作業体系による作業時間計測、作業能率の算出または，従来方法との比較評価については、今後のスマート農業の普及に向けて基礎的なデータとなることから、本研究成果は、社会的意義も含まれていると考える。