arXiv Analytics

Sign in

arXiv:1809.09646 [cs.RO]AbstractReferencesReviewsResources

Efficient Constellation-Based Map-Merging for Semantic SLAM

Kristoffer M. Frey, Ted J. Steiner, Jonathan P. How

Published 2018-09-25Version 1

Data association in SLAM is fundamentally challenging, and handling ambiguity well is crucial to achieve robust operation in real-world environments. When ambiguous measurements arise, conservatism often mandates that the measurement is discarded or a new landmark is initialized rather than risking an incorrect association. To address the inevitable "duplicate" landmarks that arise, we present an efficient map-merging framework to detect duplicate constellations of landmarks, providing a high-confidence loop-closure mechanism specifically applicable to semantic SLAM. This approach uses an incrementally-computable approximation of landmark uncertainty that only depends on local information in the SLAM graph, avoiding expensive recovery of the full system covariance matrix. This enables a search based on geometric consistency (GC) (rather than full joint compatibility (JC)) that inexpensively reduces the search space to a handful of "best" hypotheses. Furthermore, we reformulate the commonly-used interpretation tree to allow for more efficient integration of clique-based pairwise compatibility, accelerating the branch-and-bound max-cardinality search. This produces a highly extensible framework that significantly accelerates the branch-and-bound max-cardinality search. Our method is demonstrated to match the performance of full JC methods at significantly-reduced computational cost, facilitating robust object-based loop-closure over large SLAM problems.

Comments: Submitted to IEEE International Conference on Robotics and Automation (ICRA) 2019
Categories: cs.RO
Related articles:
arXiv:1804.09111 [cs.RO] (Published 2018-04-24)
Towards Semantic SLAM: Points, Planes and Objects
arXiv:1804.04011 [cs.RO] (Published 2018-04-10)
QuadricSLAM: Constrained Dual Quadrics from Object Detections as Landmarks in Semantic SLAM