An Empirical Analysis of Driving Scenes Suitable for Safety Confirmation Diagnostics for Older Drivers
高齢ドライバの安全確認行動診断に適した運転シーンの実証的分析
- Delivery
- Available on the other site
- Click here to order.
- Publication code
- 20264390
- Paper/Info type
- JSAE Transaction
Vol.57 No.3
- Pages
- 518-523(Total 6 p)
- Date of publication
- May 2026
- Publisher
- JSAE
- Language
- Japanese
Detailed Information
| Category(J) | 論文 Translation |
|---|---|
| Category(E) | Paper |
| Author(J) | 1) 吉原 佑器, 2) 江 林京, 3) Karatas Nihan, 4) 金森 等, 5) 原田 あすか, 6) 小島 基資, 7) 田中 貴紘 |
| Author(E) | 1) Yuki Yoshihara, 2) Linjing Jiang, 3) Nihan Karatas, 4) Hitoshi Kanamori, 5) Asuka Harada, 6) Motoshi Kojima, 7) Takahiro Tanaka |
| Affiliation(J) | 1) 名古屋大学, 2) 名古屋大学, 3) 名古屋大学, 4) 名古屋大学, 5) 名古屋大学, 6) トヨタ自動車株式会社, 7) 名古屋大学 |
| Abstract(J) | 交差点は高齢ドライバのリスクが高い. 頭部動作の運転診断は効果的だが, どのようなシーンが評価に適するかは明らかではない. 高齢者19名の自然運転についてリスク行動と頭部動作の最も強い相関は見通しが悪く交通量が少ない場面で生じることを示す.交通条件の適切な特定が運転診断の効果を高めることを示唆する. Translation |
| Abstract(E) | Intersections pose a high crash risk for older drivers. Studies showed that diagnostic feedback, obtained through head-movement monitoring, can improve driving behavior. However, the logic behind which traffic scene facilitates such driver evaluation is lacking. Here, we show that specific visibility and traffic volume enhance evaluation. A multimodal large language model assigned labels to naturalistic data, yielding 1,200 intersection scenes from 19 seniors. We found that the strongest correlation between risky events and head movement occurs at the lowest visibility and smallest traffic volume, and feedback improves safety. The results suggest that suitable identification in traffic conditions enhances driving diagnostics. |
