CELLO-3D: Estimating the Covariance of ICP in the Real World

TL;DR

This paper introduces a data-driven method to accurately estimate the covariance of ICP registrations in real-world 3D point cloud data, improving uncertainty estimation for better SLAM and localization.

Contribution

It presents a novel data-driven approach for ICP covariance estimation that outperforms existing closed-form methods on large real-world datasets.

Findings

Outperforms existing covariance estimation methods

Accurately predicts ICP uncertainty in diverse environments

Enhances trajectory uncertainty estimation in SLAM

Abstract

The fusion of Iterative Closest Point (ICP) reg- istrations in existing state estimation frameworks relies on an accurate estimation of their uncertainty. In this paper, we study the estimation of this uncertainty in the form of a covariance. First, we scrutinize the limitations of existing closed-form covariance estimation algorithms over 3D datasets. Then, we set out to estimate the covariance of ICP registrations through a data-driven approach, with over 5 100 000 registrations on 1020 pairs from real 3D point clouds. We assess our solution upon a wide spectrum of environments, ranging from structured to unstructured and indoor to outdoor. The capacity of our algorithm to predict covariances is accurately assessed, as well as the usefulness of these estimations for uncertainty estimation over trajectories. The proposed method estimates covariances better than existing closed-form solutions, and makes predictions that are consistent with observed trajectories.