LONER: LiDAR Only Neural Representations for Real-Time SLAM

TL;DR

LONER introduces a real-time LiDAR SLAM system using neural implicit representations that estimates dense maps and trajectories simultaneously, outperforming existing methods in speed and accuracy without groundtruth poses.

Contribution

This work presents the first real-time neural implicit LiDAR SLAM algorithm that estimates dense maps and trajectories concurrently, utilizing a novel loss function for faster convergence.

Findings

Faster convergence with the new loss function.

More accurate geometry reconstruction.

Trajectories comparable to state-of-the-art SLAM methods.

Abstract

This paper proposes LONER, the first real-time LiDAR SLAM algorithm that uses a neural implicit scene representation. Existing implicit mapping methods for LiDAR show promising results in large-scale reconstruction, but either require groundtruth poses or run slower than real-time. In contrast, LONER uses LiDAR data to train an MLP to estimate a dense map in real-time, while simultaneously estimating the trajectory of the sensor. To achieve real-time performance, this paper proposes a novel information-theoretic loss function that accounts for the fact that different regions of the map may be learned to varying degrees throughout online training. The proposed method is evaluated qualitatively and quantitatively on two open-source datasets. This evaluation illustrates that the proposed loss function converges faster and leads to more accurate geometry reconstruction than other loss functions used in depth-supervised neural implicit frameworks. Finally, this paper shows that LONER estimates trajectories competitively with state-of-the-art LiDAR SLAM methods, while also producing dense maps competitive with existing real-time implicit mapping methods that use groundtruth poses.