학술논문
Incremental Non-Gaussian Inference for SLAM Using Normalizing Flows
Document Type
Periodical
Author
Source
IEEE Transactions on Robotics IEEE Trans. Robot. Robotics, IEEE Transactions on. 39(2):1458-1475 Apr, 2023
Subject
Language
ISSN
1552-3098
1941-0468
1941-0468
Abstract
This article presents normalizing flows for incremental smoothing and mapping (NF-iSAM), a novel algorithm for inferring the full posterior distribution in SLAM problems with nonlinear measurement models and non-Gaussian factors. NF-iSAM exploits the expressive power of neural networks, and trains normalizing flows to model and sample the full posterior. By leveraging the Bayes tree, NF-iSAM enables efficient incremental updates similar to iSAM2, albeit in the more challenging non-Gaussian setting. We demonstrate the advantages of NF-iSAM over state-of-the-art point and distribution estimation algorithms using range-only SLAM problems with data association ambiguity. NF-iSAM presents superior accuracy in describing the posterior beliefs of continuous variables (e.g., position) and discrete variables (e.g., data association).