CT-ICP: Real-time Elastic LiDAR Odometry with Loop Closure

Dellenbach, Pierre; Deschaud, Jean-Emmanuel; Jacquet, Bastien; Goulette, François

doi:10.1109/icra46639.2022.9811849

Cited by 124 publications

(63 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fusing scans into local maps have shown success for lidarbased odometry methods e.g. in [63]- [65]. Dellenbach et al accumulate points from lidar scans directly into a voxel grid [65].…”

Section: Aggregating Scans For Pose Trackingmentioning

confidence: 99%

See 1 more Smart Citation

Lidar-Level Localization With Radar? The CFEAR Approach to Accurate, Fast, and Robust Large-Scale Radar Odometry in Diverse Environments

Adolfsson¹,

Magnusson²,

Alhashimi³

et al. 2023

IEEE Trans. Robot.

View full text Add to dashboard Cite

This paper presents an accurate, highly efficient, and learning-free method for large-scale odometry estimation using spinning radar, empirically found to generalize well across very diverse environments -outdoors, from urban to woodland, and indoors in warehouses and mines -without changing parameters. Our method integrates motion compensation within a sweep with one-to-many scan registration that minimizes distances between nearby oriented surface points and mitigates outliers with a robust loss function. Extending our previous approach CFEAR, we present an in-depth investigation on a wider range of data sets, quantifying the importance of filtering, resolution, registration cost and loss functions, keyframe history, and motion compensation. We present a new solving strategy and configuration that overcomes previous issues with sparsity and bias, and improves our state-of-the-art by 38%, thus, surprisingly, outperforming radar SLAM and approaching lidar SLAM. The most accurate configuration achieves 1.09% error at 5 Hz on the Oxford benchmark, and the fastest achieves 1.79% error at 160 Hz.

show abstract

“…Fusing scans into local maps have shown success for lidarbased odometry methods e.g. in [63]- [65]. Dellenbach et al accumulate points from lidar scans directly into a voxel grid [65].…”

Section: Aggregating Scans For Pose Trackingmentioning

confidence: 99%

“…in [63]- [65]. Dellenbach et al accumulate points from lidar scans directly into a voxel grid [65]. Saarinen et al [63] fuse points into grid cells using recursive covariance estimation, poses are estimated via scan-to-map registration [60].…”

Section: Aggregating Scans For Pose Trackingmentioning

confidence: 99%

Lidar-Level Localization With Radar? The CFEAR Approach to Accurate, Fast, and Robust Large-Scale Radar Odometry in Diverse Environments

Adolfsson¹,

Magnusson²,

Alhashimi³

et al. 2023

IEEE Trans. Robot.

View full text Add to dashboard Cite

show abstract

“…Recent SLAM advances such as CT-ICP [ 19 ] perform better on fast moving vehicle platforms by compensating for noise in the lidar point cloud induced by motion. Our method operates on costmaps or 2D projections of point clouds, allowing us to complement these methods and provide a robust, long term mapping solution.…”

Section: Related Workmentioning

confidence: 99%

Persistent Mapping of Sensor Data for Medium-Term Autonomy

Nickels

Gassaway

Bries

et al. 2022

Sensors

View full text Add to dashboard Cite

For vehicles to operate in unmapped areas with some degree of autonomy, it would be useful to aggregate and store processed sensor data so that it can be used later. In this paper, a tool that records and optimizes the placement of costmap data on a persistent map is presented. The optimization takes several factors into account, including local vehicle odometry, GPS signals when available, local map consistency, deformation of map regions, and proprioceptive GPS offset error. Results illustrating the creation of maps from previously unseen regions (a 100 m × 880 m test track and a 1.2 km dirt trail) are presented, with and without GPS signals available during the creation of the maps. Finally, two examples of the use of these maps are given. First, a path is planned along roads that have been seen exactly once during the mapping phase. Secondly, the map is used for vehicle localization in the absence of GPS signals.

show abstract

“…Also, they use every data point for matching since there is no specific selection mechanism, which means that their computational complexity is proportional to the number of points. To relieve these issues, voxel-based downsampling or matching method [16], [22], [17], [11] has been proposed to improve GICP performance.…”

Section: Related Work a Rule-based Odometrymentioning

confidence: 99%

“…It would also be useful to generalize this approach to other domains. Our learning based method is complimentary to state of the art methods like CT-GICP [22]. It may be useful to combine such approaches to further improve the performance.…”

Section: Conclusion and Limitationsmentioning

confidence: 99%

WGICP: Differentiable Weighted GICP-Based Lidar Odometry

Son¹,

Ji²,

Ma³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present a novel differentiable weighted generalized iterative closest point (WGICP) method applicable to general 3D point cloud data, including that from lidar. Our method builds on differentiable generalized ICP (GICP) and we use the differentiable K-Nearest Neighbors (KNN) algorithm to enhance differentiability. Our differentiable GICP algorithm provides the gradient of output pose estimation with respect to each input point. This allows us to train a neural network to predict its importance, or weight, in order to estimate the correct pose. In contrast to the other ICP-based methods, our formulation reduces the number of points used for GICP by only selecting those with the highest weights and ignoring redundant ones with lower weights. We show that our method improves both the accuracy (up to 30%) and the speed (up to 2×) over the GICP algorithm on the KITTI dataset. We also demonstrate the benefit of WGICP in terms of developing an improved SLAM system.

show abstract

CT-ICP: Real-time Elastic LiDAR Odometry with Loop Closure

Cited by 124 publications

References 27 publications

Lidar-Level Localization With Radar? The CFEAR Approach to Accurate, Fast, and Robust Large-Scale Radar Odometry in Diverse Environments

Lidar-Level Localization With Radar? The CFEAR Approach to Accurate, Fast, and Robust Large-Scale Radar Odometry in Diverse Environments

Persistent Mapping of Sensor Data for Medium-Term Autonomy

WGICP: Differentiable Weighted GICP-Based Lidar Odometry

Contact Info

Product

Resources

About