期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 7, 期 3, 页码 6335-6342出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2022.3156940
关键词
SLAM; computer vision for automation; RGB-D perception
类别
资金
- China Government [2019JZZY010112, 2020JMRH0202]
- SHIELD Project - European Union
This paper proposes a loop closure detection method based on L3Ds, which calculates the metric error between descriptors to accurately detect loops even in cases of small overlaps. The method achieves state-of-the-art accuracy on LiDAR data and improves the localization accuracy of the RESLAM system.
We present a simple yet effective method to address loop closure detection in simultaneous localisation and mapping using local 3D deep descriptors (L3Ds). L3Ds are emerging compact representations of patches extracted from point clouds that are learnt from data using a deep learning algorithm. We propose a novel overlap measure for loop detection by computing the metric error between points that correspond to mutually-nearest-neighbour descriptors after registering the loop candidate point cloud by its estimated relative pose. This novel approach enables us to accurately detect loops and estimate six degrees-of-freedom poses in the case of small overlaps. We compare our L3D-based loop closure approach with recent approaches on LiDAR data and achieve state-of-the-art loop closure detection accuracy. Additionally, we embed our loop closure approach in RESLAM, a recent edge-based SLAM system, and perform the evaluation on real-world RGBD-TUM and synthetic ICL datasets. Our approach enables RESLAM to achieve a better localisation accuracy compared to its original loop closure strategy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据