Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM

TL;DR

This paper introduces LCR-Net, a novel multi-head neural network that enhances LiDAR SLAM by providing fast, accurate loop closing and relocalization, significantly improving robustness and generalization in outdoor environments.

Contribution

We propose LCR-Net, a new deep learning model that unifies loop closing and relocalization tasks within a single framework for LiDAR SLAM.

Findings

LCR-Net outperforms state-of-the-art methods in all evaluated tasks.

LCR-Net achieves high accuracy without time-consuming robust pose estimators.

The integrated SLAM system demonstrates robust online performance in outdoor driving environments.

Abstract

Loop closing and relocalization are crucial techniques to establish reliable and robust long-term SLAM by addressing pose estimation drift and degeneration. This article begins by formulating loop closing and relocalization within a unified framework. Then, we propose a novel multi-head network LCR-Net to tackle both tasks effectively. It exploits novel feature extraction and pose-aware attention mechanism to precisely estimate similarities and 6-DoF poses between pairs of LiDAR scans. In the end, we integrate our LCR-Net into a SLAM system and achieve robust and accurate online LiDAR SLAM in outdoor driving environments. We thoroughly evaluate our LCR-Net through three setups derived from loop closing and relocalization, including candidate retrieval, closed-loop point cloud registration, and continuous relocalization using multiple datasets. The results demonstrate that LCR-Net excels in all three tasks, surpassing the state-of-the-art methods and exhibiting a remarkable generalization ability. Notably, our LCR-Net outperforms baseline methods without using a time-consuming robust pose estimator, rendering it suitable for online SLAM applications. To our best knowledge, the integration of LCR-Net yields the first LiDAR SLAM with the capability of deep loop closing and relocalization. The implementation of our methods will be made open-source.