MegaParticles: Range-based 6-DoF Monte Carlo Localization with GPU-Accelerated Stein Particle Filter

TL;DR

This paper introduces a GPU-accelerated Monte Carlo localization method using Stein particle filters and neighbor search techniques, enabling real-time, robust 6-DoF pose estimation even under severe occlusion.

Contribution

It proposes a novel GPU-accelerated Stein particle filter with neighbor search for efficient, large-scale 6-DoF localization without initial pose.

Findings

Real-time evaluation of one million particles on a single GPU.

High robustness to sensor occlusion and kidnapping scenarios.

Accurate pose initialization and re-localization without prior information.

Abstract

This paper presents a 6-DoF range-based Monte Carlo localization method with a GPU-accelerated Stein particle filter. To update a massive amount of particles, we propose a Gauss-Newton-based Stein variational gradient descent (SVGD) with iterative neighbor particle search. This method uses SVGD to collectively update particle states with gradient and neighborhood information, which provides efficient particle sampling. For an efficient neighbor particle search, it uses locality sensitive hashing and iteratively updates the neighbor list of each particle over time. The neighbor list is then used to propagate the posterior probabilities of particles over the neighbor particle graph. The proposed method is capable of evaluating one million particles in real-time on a single GPU and enables robust pose initialization and re-localization without an initial pose estimate. In experiments, the proposed method showed an extreme robustness to complete sensor occlusion (i.e., kidnapping), and enabled pinpoint sensor localization without any prior information.