Driver state estimation based on body movement and its application to the safe driving support

2021 Fiscal Year Final Research Report

• Project/Area Number: 19K14924
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 20010:Mechanics and mechatronics-related
• Research Institution: Toyohashi University of Technology
• Principal Investigator: Akiduki Takuma 豊橋技術科学大学, 工学(系)研究科(研究院), 助教 (40632922)
• Project Period (FY): 2019-04-01 – 2022-03-31
• Keywords: 漫然運転 / 注意散漫 / 不安全運転行動 / 加速度センサ / ウェアラブルセンサ

Outline of Final Research Achievements

To assist drivers in driving safely, we have proposed a measure for evaluating driver inattention based on hand activities and developed a detection algorithm for the measures. The proposed method detects the driver's hand activities as acceleration signals using inertial sensors attached to the wrists. Furthermore, we showed that the detected hand acceleration signals could be used to detect inattentive driving behaviors and their mental states, i.e., drowsiness and visual/manual/cognitive distractions in driving, by applying machine learning methods. These results show it succeeded in the studies on developing the evaluation method for driver vigilance based on hand activities and its application to driver state estimation, which was the goal of this research project.

Free Research Field

行動計測

Academic Significance and Societal Importance of the Research Achievements

ドライバの注意力低下が手の動きに及ぼす影響を調査し、その変化を検出するためのアルゴリズムを検討した。無意識的な手の動きの変化を指標化し、注意力低下のような人の内的状態の変化を予測できる可能性を示した。また、提案手法はステレオカメラや車載センサを用いることなく、小型・安価な設備で実現可能である。このことから、本研究をさらに展開することで、ドライバの心身状態を低コスト・低負荷に計測する技術として、安全運転支援やバス・トラック等の交通・物流における安全運行への活用を期待できる。