大規模環境での長期ロボットナビゲーションのための深層局所特徴を用いた粗密3D LiDAR自己位置推定
A Coarse to Fine 3D LiDAR Localization with Deep Local Features for Long Term Robot Navigation in Large Environments
深層学習モデルMinkUNeXtで点群を記述し、モンテカルロ自己位置推定と点群レジストレーションを粗密に組み合わせて、季節変化のある大規模環境でもロボットの自己位置を推定する手法を提案。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Míriam Máximo, Antonio Santo, Arturo Gil, Mónica Ballesta, David Valiente
分類: cs.RO
原文アブストラクト
The location of a robot is a key aspect in the field of mobile robotics. This problem is particularly complex when the initial pose of the robot is unknown. In order to find a solution, it is necessary to perform a global localization. In this paper, we propose a method that addresses this problem using a coarse-to-fine solution. The coarse localization relies on a probabilistic approach of the Monte Carlo Localization (MCL) method, with the contribution of a robust deep learning model, the MinkUNeXt neural network, to produce a robust description of point clouds of a 3D LiDAR within the observation model. For fine localization, global point cloud registration has been implemented. MinkUNeXt aids this by exploiting the outputs of its intermediate layers to produce deep local features for each point in a scan. These features facilitate precise alignment between the current sensor observation and one of the point clouds on the map. The proposed MCL method incorporating Deep Local Features for fine localization is termed MCL-DLF. Alternatively, a classical ICP method has been implemented for this precise localization aiming at comparison purposes. This method is termed MCL-ICP. In order to validate the performance of MCL-DLF method, it has been tested on publicly available datasets such as the NCLT dataset, which provides seasonal large-scale environments. Additionally, tests have been also performed with own data (UMH) that also includes seasonal variations on large indoor/outdoor scenarios. The results, which were compared with established state-of-the-art methodologies, demonstrate that the MCL-DLF method obtains an accurate estimate of the robot localization in dynamic environments despite changes in environmental conditions. For reproducibility purposes, the code is publicly available at https://github.com/miriammaximo/MCL-DLF.git
