End-to-End Learning-based Driving System with Branches by Emphasizing Target Direction
目的方向情報の強調による分岐選択可能なEnd-to-End自動運転
- Delivery
- Available on the other site
- Click here to order.
- Publication code
- 20214933
- Paper/Info type
- JSAE Transaction
Vol.52 No.6
- Pages
- 1368-1374(Total 7 p)
- Date of publication
- Nov 2021
- Publisher
- JSAE
- Language
- Japanese
Detailed Information
| Category(J) | 研究論文 Translation |
|---|---|
| Category(E) | ResearchPaper |
| Author(J) | 1) 清谷 竣也, 2) 大谷 健登, 3) カルバヨ アレックサンダー, 4) 竹内 栄二朗, 5) 武田 一哉 |
| Author(E) | 1) Shunya Seiya, 2) Kento Ohtani, 3) Alexander Carballo, 4) Eijiro Takeuchi, 5) Kazuya Takeda |
| Affiliation(J) | 1) 名古屋大学, 2) 名古屋大学, 3) 名古屋大学，ティアファー, 4) 名古屋大学，ティアファー, 5) 名古屋大学，ティアファー |
| Abstract(J) | 本研究では，End-to-End自動運転を用いて分岐含む経路を追従するための手法について研究を行う．本手法では，L2正則化を用いて入力画像の特徴量にかかる重みの大きさを制限し，もう一つの入力である分岐の進行方向を示すベクトルを強調することで，ロボットが分岐を含む経路を追従できる学習手法を提案する． Translation |
| Abstract(E) | End-to-end driving refers to deep learning methods for generating control signals directly from external sensors. Previous methods use a direction vector towards the target to select and turn at intersections. However, the vector has a smaller dimension than the image, and thus it is ignored during training. In this study, we propose a learning method to emphasize that vector by using L2 regularization, which enables a robot to follow trajectories with branches. We validate the system's performance by conducting experiments using several driving scenarios. Our approach allowed an autonomous robot to successfully follow trajectories, including unknown outdoor trajectories. |
