- Conference Paper
Rights / licenseIn Copyright - Non-Commercial Use Permitted
We introduce a novel method for oriented place recognition with 3D LiDAR scans. A Convolutional Neural Network is trained to extract compact descriptors from single 3D LiDAR scans. These can be used both to retrieve near-by place candidates from a map, and to estimate the yaw discrepancy needed for bootstrapping local registration methods. We employ a triplet loss function for training and use a hard-negative mining strategy to further increase the performance of our descriptor extractor. In an extensive evaluation on the NCLT and KITTI datasets, we demonstrate that our method outperforms related state-of-the-art approaches based on both data-driven and handcrafted data representation in challenging long-term outdoor conditions. Show more
Book title2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Pages / Article No.
SubjectLocalization; Deep Learning in Robotics and Automation; Range Sensing
Organisational unit03737 - Siegwart, Roland Y. / Siegwart, Roland Y.
688652 - Collaborative Perception, Reasoning and Decision-making for Automated Transportation Services (SBFI)
NotesConference lecture held on November 6, 2019
MoreShow all metadata