LONER: LiDAR Only Neural Representations for Real-Time SLAM

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Isaacson, Seth, Kung, Pou-Chun, Ramanagopal, Mani, Vasudevan, Ram, Skinner, Katherine A.
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929286285361152
author Isaacson, Seth
Kung, Pou-Chun
Ramanagopal, Mani
Vasudevan, Ram
Skinner, Katherine A.
author_facet Isaacson, Seth
Kung, Pou-Chun
Ramanagopal, Mani
Vasudevan, Ram
Skinner, Katherine A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2309_04937
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle LONER: LiDAR Only Neural Representations for Real-Time SLAM
Isaacson, Seth
Kung, Pou-Chun
Ramanagopal, Mani
Vasudevan, Ram
Skinner, Katherine A.
Robotics
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.
title LONER: LiDAR Only Neural Representations for Real-Time SLAM
topic Robotics
url https://arxiv.org/abs/2309.04937