Evaluation of Autonomous Driving Monitoring Behavior using Functional Near-Infrared Spectroscopy
機能的近赤外分光法を用いた運転監視行動の評価
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.):¥1,100 Members (tax incl.):¥880
- Publication code
- 20216140
- Paper/Info type
- Proceedings (Autumn)
No.111-21
- Pages
- 1-7(Total 7 p)
- Date of publication
- Oct 2021
- Publisher
- JSAE
- Language
- English
- Event
- 2021 JSAE Annual Congress (Autumn) [Online]
Detailed Information
Author(J) | 1) Quanfeng Liu, 2) Toshiyuki Shimizu, 3) Atsushi Horai, 4) Lucian Gheorghe |
---|---|
Author(E) | 1) Quanfeng Liu, 2) Toshiyuki Shimizu, 3) Atsushi Horai, 4) Lucian Gheorghe |
Affiliation(J) | 1) Nissan Motor, 2) Nissan Motor, 3) Nissan Motor, 4) Nissan Motor |
Affiliation(E) | 1) Nissan Motor, 2) Nissan Motor, 3) Nissan Motor, 4) Nissan Motor |
Abstract(J) | 自動運転の機能限界や故障時にはシステムに代わってドライバが運転に対応することが求められる.そのためドライバ状態の評価を目的に,自動運転を監視している状態と他の考え事をしているメンタルワンダリング状態を作り脳活動の評価を行った.その結果,脳血流の機械学習からドライバ状態判別の可能性を示すことができた. Translation |
Abstract(E) | Partial autonomous driving system requires monitoring for driving authority delivery during emergency. Therefore, it is essential to understand the driver’s state to guarantee sudden vehicle control. Our study simulated driver’s states of the autonomous-driving focused monitoring and mental wandering which indicates that the driver is considering other things during monitoring. The brain activity of each state is evaluated by brain blood flow detection and analysis. As a result, significant blood flow increase was found during mental wandering, and decrease during monitoring only, basing on which, the driver states judgment seems possible. The discrimination rate was evaluated using machine learning. |