Consensus-Informed Optimization Over Mixtures for Ambiguity-Aware Object SLAM
Name
2107.09265.pdf
Size
5.71 MB
Format
Adobe PDF
Checksum (MD5)
62e8c07e3cf40c4a16c89ff0c0542579
Author(s)
Lu, Ziqi
Huang, Qiangqiang
Doherty, Kevin
Leonard, John J.
Date Issued
September 27, 2021
Publisher
IEEE
Citation
Lu, Ziqi, Huang, Qiangqiang, Doherty, Kevin and Leonard, John J. 2021. "Consensus-Informed Optimization Over Mixtures for Ambiguity-Aware Object SLAM."
Version
Author's final manuscript
Abstract
Building object-level maps can facilitate robot-environment interactions (e.g. planning and manipulation), but objects could often have multiple probable poses when viewed from a single vantage point, due to symmetry, occlusion or perceptual failures. A robust object-level simultaneous localization and mapping (object SLAM) algorithm needs to be aware of this pose ambiguity. We propose to maintain and subsequently disambiguate the multiple pose interpretations to gradually recover a globally consistent world representation. The max-mixtures model is applied to implicitly and efficiently track all pose hypotheses, but the resulting formulation is non-convex, and therefore subject to local optima. To mitigate this problem, temporally consistent hypotheses are extracted, guiding the optimization into the global optimum. This consensus-informed inference method is applied online via landmark variable re-initialization within an incremental SLAM framework, iSAM2, for robust real-time performance. We demonstrate that this approach improves SLAM performance on both simulated and real object SLAM problems with pose ambiguity.
Description
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) September 27 - October 1, 2021. Prague, Czech Republic
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-ShareAlike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/iros51168.2021.9636213
