LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAM

Cattaneo, Daniele; Vaghi, Matteo; Valada, Abhinav

doi:10.48550/arxiv.2103.05056

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the authors prove the feasibility and robustness of their work and apply it to SA-LOAM [10]. LCDNet [16] proposes the novel LCDNet architecture for loop closure detection and point cloud registration, which consists a shared feature extractor, a place recognition head, and a novel differentiable relative pose head.…”

Section: Related Workmentioning

confidence: 93%

Object Scan Context: Object-centric Spatial Descriptor for Place Recognition within 3D Point Cloud Map

Yuan¹,

Zhang²,

Fan³

et al. 2022

Preprint

View full text Add to dashboard Cite

Place recognition technology endows a SLAM algorithm with the ability to eliminate accumulated errors and to relocalize itself. Existing methods on point cloud-based place recognition often leverage the matching of global descriptors which are lidar-centric. These methods have the following two major defects: place recognition cannot be performed when the distance between the two point clouds is far, and only the rotation angle can be calculated without the offset in the X and Y direction. To solve these two problems, we propose a novel global descriptor, which is built around the Main Object, in this way, descriptors are no longer dependent on the observation position. We analyze the theory that this method can perfectly solve the above two problems, and conduct a lot of experiments in KITTI and some extreme scenarios, which show that our method has obvious advantages over traditional methods.

show abstract

Section: Related Workmentioning

confidence: 93%

Object Scan Context: Object-centric Spatial Descriptor for Place Recognition within 3D Point Cloud Map

Yuan¹,

Zhang²,

Fan³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…2 shows the number of points for each semantic class in our dataset and the number of instances for the relevant classes. The most common stuff classes are drivable surface, manmade, and vegetation, which can be useful for mapping and ground plane estimation [25]. For the thing classes, instances of dynamic object classes such as cars and adult pedestrians occur most frequently.…”

Section: B Dataset Analysismentioning

confidence: 99%

Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking

Fong¹,

Mohan²,

Hurtado³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Panoptic scene understanding and tracking of dynamic agents are essential for robots and automated vehicles to navigate in urban environments. As LiDARs provide accurate illumination-independent geometric depictions of the scene, performing these tasks using LiDAR point clouds provides reliable predictions. However, existing datasets lack diversity in the type of urban scenes and have a limited number of dynamic object instances which hinders both learning of these tasks as well as credible benchmarking of the developed methods. In this paper, we introduce the large-scale Panoptic nuScenes benchmark dataset that extends our popular nuScenes dataset with pointwise groundtruth annotations for semantic segmentation, panoptic segmentation, and panoptic tracking tasks. To facilitate comparison, we provide several strong baselines for each of these tasks on our proposed dataset. Moreover, we analyze the drawbacks of the existing metrics for panoptic tracking and propose the novel instance-centric PAT metric that addresses the concerns. We present exhaustive experiments that demonstrate the utility of Panoptic nuScenes compared to existing datasets and make the online evaluation server available at nuScenes.org. We believe that this extension will accelerate the research of novel methods for scene understanding of dynamic urban environments. † An equivalent task [16] was concurrently proposed on SemanticKITTI.

show abstract

“…An essential task for an autonomous robot deployed in the open world without prior knowledge about its environment is to perform Simultaneous Localization and Mapping (SLAM) to facilitate planning and navigation [1], [2]. To address this task, various variants of SLAM algorithms based on different sensors have been proposed, including non-learning [3] and learning-based [4], [5] approaches. Classical methods typically rely on handcrafted, low-level features, which tend to fail under challenging conditions, e.g., textureless regions.…”

Section: Introductionmentioning

confidence: 99%

Continual SLAM: Beyond Lifelong Simultaneous Localization and Mapping through Continual Learning

Vödisch¹,

Cattaneo²,

Burgard³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

While lifelong SLAM addresses the capability of a robot to adapt to changes within a single environment over time, in this paper we introduce the task of continual SLAM. Here, a robot is deployed sequentially in a variety of different environments and has to transfer its knowledge of previously experienced environments to thus far unseen environments, while avoiding catastrophic forgetting. This is particularly relevant in the context of vision-based approaches, where the relevant features vary widely between different environments. We propose a novel approach for solving the continual SLAM problem by introducing CL-SLAM. Our approach consists of a dual-network architecture that handles both short-term adaptation and long-term memory retention by incorporating a replay buffer. Extensive evaluations of CL-SLAM in three different environments demonstrate that it outperforms several baselines inspired by existing continual learning-based visual odometry methods. The code of our work is publicly available at http://continual-slam.cs.uni-freiburg.de.

show abstract

LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAM

Cited by 3 publications

References 0 publications

Object Scan Context: Object-centric Spatial Descriptor for Place Recognition within 3D Point Cloud Map

Object Scan Context: Object-centric Spatial Descriptor for Place Recognition within 3D Point Cloud Map

Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking

Continual SLAM: Beyond Lifelong Simultaneous Localization and Mapping through Continual Learning

Contact Info

Product

Resources

About