NF-iSAM: Incremental Smoothing and Mapping via Normalizing Flows
Abstract
This paper presents a novel non-Gaussian inference algorithm, Normalizing Flow iSAM (NF-iSAM), for solving SLAM problems with non-Gaussian factors and/or non-linear measurement models. NF-iSAM exploits the expressive power of neural networks, and trains normalizing flows to draw samples from the joint posterior of non-Gaussian factor graphs. By leveraging the Bayes tree, NF-iSAM is able to exploit the sparsity structure of SLAM, thus enabling efficient incremental updates similar to iSAM2, albeit in the more challenging non-Gaussian setting. We demonstrate the performance of NF-iSAM and compare it against the state-of-the-art algorithms such as iSAM2 (Gaussian) and mm-iSAM (non-Gaussian) in synthetic and real range-only SLAM datasets.
Cite
@article{arxiv.2105.05045,
title = {NF-iSAM: Incremental Smoothing and Mapping via Normalizing Flows},
author = {Qiangqiang Huang and Can Pu and Dehann Fourie and Kasra Khosoussi and Jonathan P. How and John J. Leonard},
journal= {arXiv preprint arXiv:2105.05045},
year = {2021}
}
Comments
8 pages, 6 figures, to be published in IEEE International Conference on Robotics and Automation (ICRA) 2021