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

TL;DR

This paper introduces Learning Flock, a neural augmentation for particle filters that improves multi-target tracking accuracy and robustness with fewer particles, enabling faster and more reliable state estimation in complex systems.

Contribution

The paper proposes a novel neural augmentation called Learning Flock that enhances particle filters by correcting particle weights based on sub-particle relationships, supporting rapid and accurate multi-target tracking.

Findings

Learning Flock improves tracking accuracy with fewer particles.

LF enhances robustness against model mismatches.

LF outperforms existing DNN-aided particle filters.

Abstract

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.