Variational Filtering with Copula Models for SLAM

TL;DR

This paper introduces a novel SLAM approach that uses copula models to represent complex dependencies between variables, relaxing the common Gaussian assumption and improving performance in challenging environments.

Contribution

It presents a method integrating copula-based dependency modeling into a Sequential Monte Carlo framework for SLAM, with learnable parameters via gradient optimization.

Findings

Effective in environments with uncertain data association

Handles nonlinear transition models better than Gaussian-based methods

Demonstrates improved localization accuracy in complex scenarios

Abstract

The ability to infer map variables and estimate pose is crucial to the operation of autonomous mobile robots. In most cases the shared dependency between these variables is modeled through a multivariate Gaussian distribution, but there are many situations where that assumption is unrealistic. Our paper shows how it is possible to relax this assumption and perform simultaneous localization and mapping (SLAM) with a larger class of distributions, whose multivariate dependency is represented with a copula model. We integrate the distribution model with copulas into a Sequential Monte Carlo estimator and show how unknown model parameters can be learned through gradient-based optimization. We demonstrate our approach is effective in settings where Gaussian assumptions are clearly violated, such as environments with uncertain data association and nonlinear transition models.