Efficient Surfel-Based SLAM using 3D Laser Range Data in Urban Environments

By Jens Behley, Cyrill Stachniss. Robotics: Science and Systems Conference, 2018

527 citations recorded by the source corpus.

—Accurate and reliable localization and mapping is a fundamental building block for most autonomous robots. For this purpose, we propose a novel, dense approach to laser- based mapping that operates on three-dimensional point clouds obtained from rotating laser sensors. We construct a surfel-based map and estimate the changes in the robot’s pose by exploiting the projective data association between the current scan and a rendered model view from that surfel map. For detection and veriﬁcation of a loop closure, we leverage the map representation to compose a virtual view of the map before a potential loop closure, which enables a more robust detection even with low overlap between the scan and the already mapped areas. Our approach is efﬁcient and enables real-time capable registration. At the same time, it is able to detect loop closures and to perform map updates in an online fashion. Our experiments show that we are able to estimate globally consistent maps in large scale environments solely based on point cloud data.

Subfields: Aerospace Engineering, Environmental Engineering, Geology

View Paper: https://www.semanticscholar.org/paper/0b1df63f3f387bc2981db8e5a0fec6e90f815be8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Environmental Engineering

In Geology

Citations in the corpus

SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences (2019, methodology): “To this end, we first register and loop close the sequences using an off-the-shelf laser-based SLAM system [5].”
KISS-ICP: In Defense of Point-to-Point ICP – Simple, Accurate, and Robust Registration If Done the Right Way (2022, methodology): “REFERENCES [1] J. Behley and C. Stachniss, “Efficient surfel-based SLAM using 3D laser range data in urban environments,” in Proc.”
LINS: A Lidar-Inertial State Estimator for Robust and Efficient Navigation (2019, background): “Furthermore, the motion distortion [3] and sparse nature of point clouds [4] make it even worse in some challenging scenarios (e.”
Tightly Coupled 3D Lidar Inertial Odometry and Mapping (2019, methodology): “To ensure efficient estimation, many works on lidar mapping, like [7], [1] and [13], separate the task into two parts, the odometry and the mapping.”
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation (2020, unknown): “2D/3D object detection [65,3,41,34], multi-modal fusion [64,17], simultaneous localization and mapping [4,2] and point-cloud segmentation [56,58,35].”
Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-Shot Metric Depth and Surface Normal Estimation (2024, unknown): “These unique attributes render both depth and surface normals indispensable in various computer vision applications, including 3D reconstruction [1], [2], [3], neural rendering (NeRF) [4], [5], [6], [7], autonomous driving [8], [9], [10], and robotics [11], [12], [13].”
SuMa++: Efficient LiDAR-based Semantic SLAM (2019, methodology): “The foundation of our semantic SLAM approach is our Surfel-based Mapping (SuMa) [2] pipeline, which we extend by integrating semantic information provided by a semantic segmentation using the FCN RangeNet++ [21] as illustrated in Fig.”