LiTAMIN: LiDAR-based Tracking And Mapping by Stabilized ICP for Geometry Approximation with Normal Distributions

Yokozuka, Masashi; Koide, Kenji; Oishi, Shuji; Banno, Atsuhiko

doi:10.1109/iros45743.2020.9341341

Cited by 42 publications

(23 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This method uses the scan-to-global map matching method to calculate the optimal pose by minimizing geometric residuals and intensity residuals. LiTAMIN 12 uses the Frobenius norm and regularized covariance matrix to normalize the cost function to improve the computational efficiency of ICP. M-LOAM 13 is a SLAM framework that combines multiple LiDARs.…”

Section: Related Workmentioning

confidence: 99%

Self-supervised learning of LiDAR odometry based on spherical projection

Liu

Zhang

et al. 2022

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Recently, the learning-based LiDAR odometry has obtained robust estimation results in the field of mobile robot localization, but most of them are constructed based on the idea of supervised learning. In the network training stage, these supervised learning-based methods rely heavily on real pose labels, which is defective in practical applications. Different from these methods, a novel self-supervised LiDAR odometry, namely SSLO, is proposed in this article. The proposed SSLO only uses unlabeled point cloud data to train the three-view pose network to complete the robot localization task. Specifically, first, due to the sparseness and disorder of the original LiDAR point cloud, it is difficult to use deep convolutional neural networks for feature extraction. In this article, the spherical projection of the point cloud is used to convert the original point cloud into a regular vertex map. Then the vertex map obtained by the projection is used as the input of the neural network. Second, in the network training phase, SSLO uses multiple geometric losses for different situations of matching point clouds and introduces uncertainty weights when calculating the losses to reduce the interference of noise or moving objects in the scene. Last but not least, the proposed method is not only used in the simulation experiments based on the KITTI dataset and Apollo-SouthBay dataset but also applied to a real-world wheeled robot SLAM task. Extensive experimental results show that the proposed method has good performance in different environments.

show abstract

Section: Related Workmentioning

confidence: 99%

Self-supervised learning of LiDAR odometry based on spherical projection

Liu

Zhang

et al. 2022

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…LiDAR SLAM methods can be divided into two categories: ICP-based methods [2]- [8] and feature-based methods [9]- [14].…”

Section: Related Workmentioning

confidence: 99%

“…1 The authors are with the Human-Centered Mobility Research Center (HCMRC), National Institute of Advanced Industrial Science and Technology (AIST), Japan yokotsuka-masashi@aist.go.jp This work was supported in part by the New Energy and Industrial Development Organization (NEDO). Although many studies have been conducted on SLAM benchmarks [1] and methods that emphasize accuracy [2]- [14], few studies have significantly improved the current computational efficiency. In the future, to process a large number of robots and devices intensively and efficiently, it is expected that SLAM will emphasize high speed.…”

Section: Introductionmentioning

confidence: 99%

LiTAMIN2: Ultra Light LiDAR-based SLAM using Geometric Approximation applied with KL-Divergence

Yokozuka¹,

Koide²,

Oishi³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, a three-dimensional light detection and ranging simultaneous localization and mapping (SLAM) method is proposed that is available for tracking and mapping with 500-1000 Hz processing. The proposed method significantly reduces the number of points used for point cloud registration using a novel ICP metric to speed up the registration process while maintaining accuracy. Point cloud registration with ICP is less accurate when the number of points is reduced because ICP basically minimizes the distance between points. To avoid this problem, symmetric KL-divergence is introduced to the ICP cost that reflects the difference between two probabilistic distributions. The cost includes not only the distance between points but also differences between distribution shapes. The experimental results on the KITTI dataset indicate that the proposed method has high computational efficiency, strongly outperforms other methods, and has similar accuracy to the state-of-the-art SLAM method.

show abstract

“…where G is a pose-graph text file (e.g., .g2o format) containing a set of pose nodes' indexes and initial values, odometry edges, and optionally putative intra-session loop edges. This initial pose-graph can be constructed by using any existing LiDAR (-inertial) odometry algorithms [22,23,24,25,26]. We allow potential navigational drifts and overcome the intra-session drifts via multi-session posegraph optimization.…”

Section: Lt-mappermentioning

confidence: 99%

LT-mapper: A Modular Framework for LiDAR-based Lifelong Mapping

Kim¹,

Kim²

2021

Preprint

View full text Add to dashboard Cite

Long-term 3D map management is a fundamental capability required by a robot to reliably navigate in the non-stationary real-world. This paper develops open-source, modular, and readily available LiDAR-based lifelong mapping for urban sites. This is achieved by dividing the problem into successive subproblems: multi-session SLAM (MSS), high/low dynamic change detection, and positive/negative change management. The proposed method leverages MSS and handles potential trajectory error; thus, good initial alignment is not required for change detection. Our change management scheme preserves efficacy in both memory and computation costs, providing automatic object segregation from a large-scale point cloud map. We verify the framework's reliability and applicability even under permanent year-level variation, through extensive real-world experiments with multiple temporal gaps (from day to year).

show abstract

LiTAMIN: LiDAR-based Tracking And Mapping by Stabilized ICP for Geometry Approximation with Normal Distributions

Cited by 42 publications

References 26 publications

Self-supervised learning of LiDAR odometry based on spherical projection

Self-supervised learning of LiDAR odometry based on spherical projection

LiTAMIN2: Ultra Light LiDAR-based SLAM using Geometric Approximation applied with KL-Divergence

LT-mapper: A Modular Framework for LiDAR-based Lifelong Mapping

Contact Info

Product

Resources

About