Map Generation and Localization based on Height Variance of LiDAR Point Cloud for Autonomous Driving
自動運転におけるLiDAR点群の高さ方向分散に基づく地図生成および自己位置推定
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20225013
- Paper/Info type
- Proceedings (Spring)
No.3-22
- Pages
- 1-6(Total 6 p)
- Date of publication
- May 2022
- Publisher
- JSAE
- Language
- Japanese
- Event
- 2022 JSAE Annual Congress (Spring)
Detailed Information
| Author(J) | 1) 柳瀬 龍, 2) 川堰 未弥, 3) Mohammad Aldibaja, 4) 米陀 佳祐, 5) 菅沼 直樹 |
|---|---|
| Author(E) | 1) Ryo Yanase, 2) Miya Kawaseki, 3) Mohammad Aldibaja, 4) Keisuke Yoneda, 5) Naoki Suganuma |
| Affiliation(J) | 1) 金沢大学, 2) 金沢大学, 3) 金沢大学, 4) 金沢大学, 5) 金沢大学 |
| Affiliation(E) | 1) Kanazawa University, 2) Kanazawa University, 3) Kanazawa University, 4) Kanazawa University, 5) Kanazawa University |
| Abstract(J) | 自動運転の自己位置推定技術として，LiDARの3次元点群地図を用いた点群マッチングに基づく手法が挙げられる．しかし，点群地図は管理コストが大きく季節による植物の形状変化が起こる．点群の高さ方向の分散に基づいて柱状物体などの特徴を得ることで，2次元画像地図生成および自己位置推定の手法を提案する． Translation |
| Abstract(E) | LiDAR has been popularly used for self-localization due to its accurate ranging, and one of the main methods is based on matching point clouds using a 3D point cloud map. However, the maintenance cost is higher than that of a 2D image map, and when the map contains points such as plants, the shape of the map changes depending on the season, which has a large influence on the position estimation. In this paper, we propose a method for generating 2D image maps and localization by extracting features such as pole-like objects based on the height variance of point clouds. |
