Evaluation of Driver Operation Variability for the Interpretation of Machine Learning-Based Pedal Operation Predictions
機械学習によるペダル操作予測結果の解釈のためのドライバ操作の変動の評価
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20266268
- Paper/Info type
- Proceedings (Autumn)
No.148-26
- Pages
- 1-2(Total 2 p)
- Date of publication
- Oct 2026
- Publisher
- JSAE
- Language
- Japanese
- Event
- 2026 JSAE Annual Congress (Autumn)
Detailed Information
| Author(J) | 1) 松本 昂洋, 2) 大貫 正明, 3) 廣瀬 敏也 |
|---|---|
| Author(E) | 1) Akihiro Matsumoto, 2) Masaaki Onuki, 3) Toshiya Hirose |
| Affiliation(J) | 1) 芝浦工業大学, 2) 芝浦工業大学, 3) 芝浦工業大学 |
| Affiliation(E) | 1) Shibaura Institute of Technology, 2) Shibaura Institute of Technology, 3) Shibaura Institute of Technology |
| Abstract(J) | ペダル踏み間違い検知に向け，機械学習によるペダル操作予測の活用が検討されている．一方，ドライバの操作は確率的に変動する．そのため，予測モデルの評価では，モデル性能と確率的変動の両者を考慮する必要がある．本研究では，同一条件下の操作ばらつきを定量評価し，予測誤差を解釈する基礎的指標を検討する． Translation |
| Abstract(E) | Toward pedal misapplication detection, machine learning-based prediction of pedal operation has been investigated. However, drivers’ pedal operations are not fully deterministic and may vary even under the same driving conditions. Therefore, when evaluating a prediction model, it is necessary to consider not only the model’s predictive performance but also the stochastic variability inherent in human operation. This study quantitatively evaluates variations in pedal operation under identical conditions and examines basic indices for interpreting prediction errors in machine learning-based pedal operation prediction. |
