Relationship Analysis between Crossing Pedestrian Characteristics and Actions
歩行者の交差点横断における行動傾向と人の属性に関する解析
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20216226
- Paper/Info type
- Proceedings (Autumn)
No.130-21
- Pages
- 1-6(Total 6 p)
- Date of publication
- Oct 2021
- Publisher
- JSAE
- Language
- Japanese
- Event
- 2021 JSAE Annual Congress (Autumn) [Online]
Detailed Information
| Author(J) | 1) 西澤 智恵子, 2) 脇坂 龍, 3) 伴 和徳 |
|---|---|
| Author(E) | 1) Chieko Nishizawa, 2) Ryo Wakisaka, 3) Kazunori Ban |
| Affiliation(J) | 1) トヨタテクニカルディベロップメント, 2) トヨタテクニカルディベロップメント, 3) トヨタテクニカルディベロップメント |
| Affiliation(E) | 1) Toyota Technical Development, 2) Toyota Technical Development, 3) Toyota Technical Development |
| Abstract(J) | 実環境では困難な評価や検証を行うにはシミュレーションが有効な手段である．より実世界に近い仮想環境を構築するためには様々な人の属性に応じた行動傾向を再現する必要がある．本発表では歩行者の交差点横断において逆強化学習を適用し，人の属性と横断判断時の行動傾向との関連性について解析した結果を報告する． Translation |
| Abstract(E) | Simulation is an effective method for evaluation and verification that are difficult to carry out in a real environment. However, for an advanced virtual environment, it can be necessary to simulate people actions based on their various characteristics. Hence, we tried applying “inverse reinforcement learning” to pedestrian behavior and analyzed the relationship between human characteristics and actions on intersection. In this presentation, we report the results of our trial and analysis. |
