Incremental Non-Gaussian Inference for SLAM Using Normalizing Flows

Incremental Non-Gaussian Inference for SLAM Using Normalizing Flows

This paper 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 nor...

Full description

Bibliographic Details
Main Authors: Huang, Qiangqiang, Pu, Can, Khosoussi, Kasra, Rosen, David M., Fourie, Dehann, How, Jonathan P., Leonard, John J.
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers (IEEE) 2024
Subjects:
Electrical and Electronic Engineering
Computer Science Applications
Control and Systems Engineering
Online Access:https://hdl.handle.net/1721.1/153746

Similar Items

Similar Items