Information Sparsification in Visual-Inertial Odometry

Hsiung, Jerry; Hsiao, Ming; Westman, Eric; Valencia, Rafael; Kaess, Michael

doi:10.1109/iros.2018.8594007

Cited by 36 publications

(23 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several other approaches suggest to sparsify the graph using the Chow-Liu tree approximation, and show that the KL-divergence from the original graph remains low Kretzschmar and Stachniss 2012). Hsiung et al (2018) reach similar conclusions for fixedlag Markov blankets. The approach described by Mu et al (2017) separated the sparsification into two stages: problemspecific removal of nodes, and problem-agnostic removal of correlations.…”

Section: Related Worksupporting

confidence: 52%

Fast Action Elimination for Efficient Decision Making and Belief Space Planning Using Bounded Approximations

Elimelech

Indelman

2019

Springer Proceedings in Advanced Robotics

View full text Add to dashboard Cite

In this work, we introduce a new approach for the efficient solution of autonomous decision and planning problems, with a special focus on decision making under uncertainty and belief space planning (BSP) in high-dimensional state spaces. Usually, to solve the decision problem, we identify the optimal action, according to some objective function. Instead, we claim that we can sometimes generate and solve an analogous yet simplified decision problem, which can be solved more efficiently. Furthermore, a wise simplification method can lead to the same action selection, or one for which the maximal loss can be guaranteed. This simplification is separated from the state inference, and does not compromise its accuracy, as the selected action would finally be applied on the original state. At first, we develop the concept for general decision problems, and provide a theoretical framework of definitions to allow a coherent discussion. We then practically apply these ideas to BSP problems, in which the problem is simplified by considering a sparse approximation of the initial belief. The scalable sparsification algorithm we provide is able to yield solutions which are guaranteed to be consistent with the original problem. We demonstrate the benefits of the approach in the solution of a highly realistic active-SLAM problem, and manage to significantly reduce computation time, with practically no loss in the quality of solution. This rigorous and fundamental work is conceptually novel, and holds numerous possible extensions.

show abstract

Section: Related Worksupporting

confidence: 52%

Fast Action Elimination for Efficient Decision Making and Belief Space Planning Using Bounded Approximations

Elimelech

Indelman

2019

Springer Proceedings in Advanced Robotics

View full text Add to dashboard Cite

show abstract

“…The above methods need to discard keypoints and observations that are observed in marginalized keyframes in order to maintain the sparse structure of the marginalization prior. Hsiung et al [6] apply non-linear factor recovery to achieve a sparse marginalization prior without discarding information about observed keypoints. This way, the approach can further refine the keypoints and achieve higher accuracy, but in contrast to our work it is limited to local BA.…”

Section: Related Workmentioning

confidence: 99%

“…This is an instance of the convex MAXDET problem [25]. For full-rank and invertible J r , [12,6] showed that the following closed-form solution exists,…”

Section: Non-linear Factor Recoverymentioning

confidence: 99%

Visual-Inertial Mapping With Non-Linear Factor Recovery

Usenko¹,

Demmel²,

Schubert³

et al. 2020

IEEE Robot. Autom. Lett.

178

View full text Add to dashboard Cite

Cameras and inertial measurement units are complementary sensors for ego-motion estimation and environment mapping. Their combination makes visual-inertial odometry (VIO) systems more accurate and robust. For globally consistent mapping, however, combining visual and inertial information is not straightforward. To estimate the motion and geometry with a set of images large baselines are required. Because of that, most systems operate on keyframes that have large time intervals between each other. Inertial data on the other hand quickly degrades with the duration of the intervals and after several seconds of integration, it typically contains only little useful information.In this paper, we propose to extract relevant information for visual-inertial mapping from visual-inertial odometry using non-linear factor recovery. We reconstruct a set of non-linear factors that make an optimal approximation of the information on the trajectory accumulated by VIO. To obtain a globally consistent map we combine these factors with loop-closing constraints using bundle adjustment. The VIO factors make the roll and pitch angles of the global map observable, and improve the robustness and the accuracy of the mapping. In experiments on a public benchmark, we demonstrate superior performance of our method over the state-of-the-art approaches.

show abstract

“…The literature characterizes different approaches into tightly-coupled system [5]- [7], in which visual information and inertial measurements are jointly optimized, or loosely-coupled system [8]- [11], in which IMU is a separate module and fused with a visiononly state estimator. The approaches could be further divided into either filtering-based [11]- [16] or graph-optimization based [5]- [7], [17], [18]. Tightly-coupled optimization-based approaches, taking the benefit of minimizing residuals iteratively, usually achieve better accuracy and robustness with a higher computation cost.…”

Section: Related Workmentioning

confidence: 99%

Stereo Visual Inertial LiDAR Simultaneous Localization and Mapping

Shao

Vijayarangan

Liu

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Simultaneous Localization and Mapping (SLAM) is a fundamental task to mobile and aerial robotics. LiDAR based systems have proven to be superior compared to vision based systems due to its accuracy and robustness. In spite of its superiority, pure LiDAR based systems fail in certain degenerate cases like traveling through a tunnel. We propose Stereo Visual Inertial LiDAR (VIL) SLAM that performs better on these degenerate cases and has comparable performance on all other cases. VIL-SLAM accomplishes this by incorporating tightly-coupled stereo visual inertial odometry (VIO) with LiDAR mapping and LiDAR enhanced visual loop closure. The system generates loop-closure corrected 6-DOF LiDAR poses in real-time and 1cm voxel dense maps near real-time. VIL-SLAM demonstrates improved accuracy and robustness compared to state-of-the-art LiDAR methods.

show abstract

Information Sparsification in Visual-Inertial Odometry

Cited by 36 publications

References 38 publications

Fast Action Elimination for Efficient Decision Making and Belief Space Planning Using Bounded Approximations

Fast Action Elimination for Efficient Decision Making and Belief Space Planning Using Bounded Approximations

Visual-Inertial Mapping With Non-Linear Factor Recovery

Stereo Visual Inertial LiDAR Simultaneous Localization and Mapping

Contact Info

Product

Resources

About