Machine-Learning-Based Quantification of Subjective Evaluation for Vehicle Cornering Behavior
機械学習を用いた車両旋回時における官能評価の定量化
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20266068
- Paper/Info type
- Proceedings (Autumn)
No.106-26
- Pages
- 1-6(Total 6 p)
- Date of publication
- Oct 2026
- Publisher
- JSAE
- Language
- Japanese
- Event
- 2026 JSAE Annual Congress (Autumn)
Detailed Information
| Author(J) | 1) 金堀 凌也, 2) 清水 友博, 3) 杉山 諭, 4) 岡本 信, 5) 浅野 貴文, 6) 金子 隆 |
|---|---|
| Author(E) | 1) Ryoya Kanahori, 2) Tomohiro Shimizu, 3) Satoru Sugiyama, 4) Makoto Okamoto, 5) Takafumi Asano, 6) Takashi Kaneko |
| Affiliation(J) | 1) SUBARU, 2) SUBARU, 3) SUBARU, 4) SUBARU, 5) SUBARU, 6) SUBARU |
| Affiliation(E) | 1) SUBARU, 2) SUBARU, 3) SUBARU, 4) SUBARU, 5) SUBARU, 6) SUBARU |
| Abstract(J) | 車両運動性能の把握は官能評価に依存しており，設計・制御への定量的反映に多大な工数を要していた．そこで走行データと官能評点を用い，ランダムフォレストと特徴量空間の類似度評価を組み合わせた分析の自動化を実現．高評価挙動に対応する性能指標を短期間かつ再現性高く導出可能とし，設計効率化の基盤技術を構築した． Translation |
| Abstract(E) | The assessment of vehicle dynamic performance has conventionally relied upon subjective evaluation by expert drivers, and translating such qualitative judgments into quantitative inputs for vehicle design and control has required substantial engineering effort. In this study, we developed an automated analysis framework that combines a Random Forest model with similarity assessment in the feature space, using measured driving data and subjective rating scores. The proposed approach enables rapid and reproducible derivation of performance indices that correspond to highly rated vehicle behavior, thereby establishing a foundational technology for improving the efficiency of vehicle dynamics design. |
