mlsanityData to 7 Oct 2026

Incremental Non-Gaussian Inference for SLAM Using Normalizing Flows

arXiv 2110.00876 ↗First posted 2 Oct 2021cs.RO cs.LG stat.APcited by 1

Not on the map. Why?

Abstract (arXiv)

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 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).

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 74 references that are in the map. First posted on arXiv 2 Oct 2021.

Builds on

22 of 74 references.

References · 22

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2021Convex optimizationcited by 2,479
  4. 2015Variational Inference with Normalizing Flowscited by 2,161
  5. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  6. 2019Neural Spline Flowscited by 590
  7. 2016Input Convex Neural Networkscited by 407
  8. 2016Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Agecited by 405
  9. 2020Normalizing Flows on Tori and Spherescited by 117
  10. 2019PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Trackingcited by 91
  11. 2021Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifoldcited by 65
  12. 2019Sum-of-Squares Polynomial Flowcited by 62
10 more
  1. 2019Coupling techniques for nonlinear ensemble filteringcited by 48
  2. 2020On the representation and learning of monotone triangular transport mapscited by 41
  3. 2019Probabilistic Data Association via Mixture Models for Robust Semantic SLAMcited by 16
  4. 2021Advances in Inference and Representation for Simultaneous Localization and Mappingcited by 16
  5. 2021A Multi-Hypothesis Approach to Pose Ambiguity in Object-Based SLAMcited by 12
  6. 2021Advancing Mixture Models for Least Squares Optimizationcited by 4
  7. 2021NF-iSAM: Incremental Smoothing and Mapping via Normalizing Flowscited by 3
  8. 2021Consensus-Informed Optimization Over Mixtures for Ambiguity-Aware Object SLAMcited by 3
  9. 2021Nested Sampling for Non-Gaussian Inference in SLAM Factor Graphscited by 2
  10. 2020Variational Filtering with Copula Models for SLAMcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024A Slices Perspective for Incremental Nonparametric Inference in High Dimensional State Spacescited by 0