Robustness Evaluation of Vehicle Localization in 3D Map using Convergence of Scan Matching
Robustness Evaluation of Vehicle Localization in 3D Map using Convergence of Scan Matching
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20225012
- Paper/Info type
- Proceedings (Spring)
No.3-22
- Pages
- 1-2(Total 2 p)
- Date of publication
- May 2022
- Publisher
- JSAE
- Language
- English
- Event
- 2022 JSAE Annual Congress (Spring)
Detailed Information
| Author(E) | 1) Yuki Kitsukawa, 2) Tatsuya Minami, 3) Yudai Yamazaki, 4) Junichi Meguro, 5) Eijiro Takeuchi, 6) Yoshiki Ninomiya, 7) Shinpei Kato, 8) Masato Edahiro |
|---|---|
| Affiliation(E) | 1) Nagoya University/Map IV, 2) Meijo University, 3) Map IV, 4) Meijo University, 5) Tier IV/Nagoya University, 6) Tier IV/Nagoya University, 7) The University of Tokyo, 8) Nagoya University |
| Abstract(J) | 本研究では、自動運転の自己位置推定において、３次元地図とLiDARを用いた手法に存在する位置推定の破綻の可能性を検証する手法を提案する。シミュレータを用いて、スキャンマッチングの探索初期位置・姿勢に意図的に誤差を与えた時の収束性から、ロバスト性を評価し、走行環境の位置推定のリスクを判定する。 Translation |
| Abstract(E) | In this study, we propose a method to verify the possibility of localization failure existing in methods using 3D maps and LiDAR for autonomous driving. Using a simulator, we evaluate the robustness and assess the risk of localization in the driving environment based on the convergence when intentional errors are given to the initial position and orientation of the scan matching between 3D point cloud and LiDAR scan. |
