Global Data Association for SLAM with 3D Grassmannian Manifold Objects

TL;DR

This paper introduces a novel global data association method for lidar SLAM that simultaneously uses 3D line and plane objects represented on the affine Grassmannian manifold, improving loop closure accuracy and recall.

Contribution

It presents a unified framework for matching and registering line and plane landmarks on the affine Grassmannian, enhancing SLAM performance over pole-only or plane-only methods.

Findings

71% increase in loop closure recall at 100% precision on KITTI dataset

Frame alignment error less than 10 cm and 1 degree

Outperforms pole-only and plane-only approaches

Abstract

Using pole and plane objects in lidar SLAM can increase accuracy and decrease map storage requirements compared to commonly-used point cloud maps. However, place recognition and geometric verification using these landmarks is challenging due to the requirement for global matching without an initial guess. Existing works typically only leverage either pole or plane landmarks, limiting application to a restricted set of environments. We present a global data association method for loop closure in lidar scans using 3D line and plane objects simultaneously and in a unified manner. The main novelty of this paper is in the representation of line and plane objects extracted from lidar scans on the manifold of affine subspaces, known as the affine Grassmannian. Line and plane correspondences are matched using our graph-based data association framework and subsequently registered in the least-squares sense. Compared to pole-only approaches and plane-only approaches, our 3D affine Grassmannian method yields a 71% and 325% increase respectively to loop closure recall at 100% precision on the KITTI dataset and can provide frame alignment with less than 10 cm and 1 deg of error.