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

arXiv: https://arxiv.org/abs/2408.11348 · HTML: https://mlsanity.com/paper/2408.11348/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 63 references that are in the map.
- First posted on arXiv 21 Aug 2024.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Model-Based Deep Learning](https://mlsanity.com/paper/2012.08405/) (2020)
- [KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics](https://mlsanity.com/paper/2107.10043/) (2021)
- [Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors](https://mlsanity.com/paper/1805.11122/) (2018)
- [Model-Based Deep Learning: On the Intersection of Deep Learning and Optimization](https://mlsanity.com/paper/2205.02640/) (2022)
- [Particle Filter Recurrent Neural Networks](https://mlsanity.com/paper/1905.12885/) (2019)
- [Towards Differentiable Resampling](https://mlsanity.com/paper/2004.11938/) (2020)
- [DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Learning Setup](https://mlsanity.com/paper/2306.03897/) (2023)
- [Differentiable Particle Filtering without Modifying the Forward Pass](https://mlsanity.com/paper/2106.10314/) (2021)
- [Unsupervised Learned Kalman Filtering](https://mlsanity.com/paper/2110.09005/) (2021)
- [Latent-KalmanNet: Learned Kalman Filtering for Tracking from High-Dimensional Signals](https://mlsanity.com/paper/2304.07827/) (2023)
- [Differentiable Particle Filters through Conditional Normalizing Flow](https://mlsanity.com/paper/2107.00488/) (2021)
- [Discriminative and Generative Learning for Linear Estimation of Random Signals [Lecture Notes]](https://mlsanity.com/paper/2206.04432/) (2022)
- [RTSNet: Learning to Smooth in Partially Known State-Space Models (Preprint)](https://mlsanity.com/paper/2110.04717/) (2021)
- [GSP-KalmanNet: Tracking Graph Signals via Neural-Aided Kalman Filtering](https://mlsanity.com/paper/2311.16602/) (2023)
- [Unsupervised Learning of Sampling Distributions for Particle Filters](https://mlsanity.com/paper/2302.01174/) (2023)
- [Unrolling Particles: Unsupervised Learning of Sampling Distributions](https://mlsanity.com/paper/2110.02915/) (2021)
- [A Multi-Target Track-Before-Detect Particle Filter Using Superpositional Data in Non-Gaussian Noise](https://mlsanity.com/paper/2003.05778/) (2020)
- [Innovative And Additive Outlier Robust Kalman Filtering With A Robust Particle Filter](https://mlsanity.com/paper/2007.03238/) (2020)

## 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.