PFilter: Building Persistent Maps through Feature Filtering for Fast and Accurate LiDAR-based SLAM

TL;DR

This paper introduces PFilter, a feature filtering algorithm that enhances LiDAR-based SLAM by reducing computational load and improving accuracy through selective feature point filtering.

Contribution

The paper presents PFilter, a novel feature filtering method that significantly reduces point cloud data and processing time while increasing registration accuracy in LiDAR SLAM.

Findings

PFilter removes about 48.4% of local feature map points.

It reduces feature points in scans by 19.3% on average.

Processing time per frame is reduced by 20.9%.

Abstract

Simultaneous localization and mapping (SLAM) based on laser sensors has been widely adopted by mobile robots and autonomous vehicles. These SLAM systems are required to support accurate localization with limited computational resources. In particular, point cloud registration, i.e., the process of matching and aligning multiple LiDAR scans collected at multiple locations in a global coordinate framework, has been deemed as the bottleneck step in SLAM. In this paper, we propose a feature filtering algorithm, PFilter, that can filter out invalid features and can thus greatly alleviate this bottleneck. Meanwhile, the overall registration accuracy is also improved due to the carefully curated feature points. We integrate PFilter into the well-established scan-to-map LiDAR odometry framework, F-LOAM, and evaluate its performance on the KITTI dataset. The experimental results show that PFilter can remove about 48.4% of the points in the local feature map and reduce feature points in scan by 19.3% on average, which save 20.9% processing time per frame. In the mean time, we improve the accuracy by 9.4%.