mlsanityData to 7 Oct 2026

Learning Flock: Enhancing Sets of Particles for Multi~Sub-State Particle Filtering with Neural Augmentation

arXiv 2408.11348 ↗First posted 21 Aug 2024eess.SP cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

A leading family of algorithms for state estimation in dynamic systems with multiple sub-states is based on particle filters (PFs). PFs often struggle when operating under complex or approximated modelling (necessitating many particles) with low latency requirements (limiting the number of particles), as is typically the case in multi target tracking (MTT). In this work, we introduce a deep neural network (DNN) augmentation for PFs termed learning flock (LF). LF learns to correct a particles-weights set, which we coin flock, based on the relationships between all sub-particles in the set itself, while disregarding the set acquisition procedure. Our proposed LF, which can be readily incorporated into different PFs flow, is designed to facilitate rapid operation by maintaining accuracy with a reduced number of particles. We introduce a dedicated training algorithm, allowing both supervised and unsupervised training, and yielding a module that supports a varying number of sub-states and particles without necessitating re-training. We experimentally show the improvements in performance, robustness, and latency of LF augmentation for radar multi-target tracking, as well its ability to mitigate the effect of a mismatched observation modelling. We also compare and illustrate the advantages of LF over a state-of-the-art DNN-aided PF, and demonstrate that LF enhances both classic PFs as well as DNN-based filters.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 63 references that are in the map. First posted on arXiv 21 Aug 2024.

Builds on

20 of 63 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Knowledge Distillation: A Surveycited by 1,578
  3. 2020Model-Based Deep Learningcited by 136
  4. 2021KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamicscited by 128
  5. 2018Differentiable Particle Filters: End-to-End Learning with Algorithmic Priorscited by 58
  6. 2022Model-Based Deep Learning: On the Intersection of Deep Learning and Optimizationcited by 50
  7. 2019Particle Filter Recurrent Neural Networkscited by 36
  8. 2020Towards Differentiable Resamplingcited by 19
  9. 2023DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Learning Setupcited by 19
  10. 2021Differentiable Particle Filtering without Modifying the Forward Passcited by 18
  11. 2021Unsupervised Learned Kalman Filteringcited by 17
  12. 2023Latent-KalmanNet: Learned Kalman Filtering for Tracking from High-Dimensional Signalscited by 16
8 more
  1. 2021Differentiable Particle Filters through Conditional Normalizing Flowcited by 15
  2. 2022Discriminative and Generative Learning for Linear Estimation of Random Signals [Lecture Notes]cited by 13
  3. 2021RTSNet: Learning to Smooth in Partially Known State-Space Models (Preprint)cited by 11
  4. 2023GSP-KalmanNet: Tracking Graph Signals via Neural-Aided Kalman Filteringcited by 10
  5. 2023Unsupervised Learning of Sampling Distributions for Particle Filterscited by 8
  6. 2021Unrolling Particles: Unsupervised Learning of Sampling Distributionscited by 4
  7. 2020A Multi-Target Track-Before-Detect Particle Filter Using Superpositional Data in Non-Gaussian Noisecited by 2
  8. 2020Innovative And Additive Outlier Robust Kalman Filtering With A Robust Particle Filtercited by 1

Built on by

Not cited yet.