Predicting alignment risk to prevent localization failure

Conference item

During localization and mapping the success of point cloud registration can be compromised when there is an absence of geometric features or constraints in corridors or across doorways, or when the volumes scanned only partly overlap, due to occlusions or constrictions between subsequent observations. This work proposes a strategy to predict and prevent laser-based localization failure. Our solution relies on explicit analysis of the point cloud content prior to registration. A model predicting the risk of a failed alignment is learned by analysing the degree of spatial overlap between two input point clouds and the geometric constraints available within the region of overlap. We define a novel measure of alignability for these constraints. The method is evaluated against three real-world datasets and compared to baseline approaches. The experiments demonstrate how our approach can help improve the reliability of laser-based localization during exploration of unknown and cluttered man-made environments.

Authors: Nobili, S; Tinchev, G; Fallon, M

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Institute of Electrical and Electronics Engineers
• Host title: 2018 IEEE International Conference on Robotics and Automation, 21-25 May 2018, Brisbane, Australia
• Journal: IEEE International Conference on Robotics and Automation
• Publication date: 2018-09-13
• Acceptance date: 2018-01-15
• DOI: 10.1109/ICRA.2018.8462890
• EISSN: 2577-087X
• ISBN: 9781538630808