Information-based reduced landmark SLAM

Choudhary, Siddharth; Indelman, Vadim; Christensen, Henrik I.; Dellaert, Frank

doi:10.1109/icra.2015.7139839

Cited by 37 publications

(23 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using these measures, the authors identify measurements providing a small amount of information and discard them. In [5], the authors aim at finding a set of reduced landmarks and poses by minimizing an objective function that takes into account memory requirements and estimation accuracy. Carlone et al [3] reduce the pose graph by looking for the maximal subset of measurements that are internally "coherent" and observable.…”

Section: Related Workmentioning

confidence: 99%

On the Redundancy Detection in Keyframe-Based SLAM

Schmuck

Chli

2019

2019 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

Egomotion and scene estimation is a key component in automating robot navigation, as well as in virtual reality applications for mobile phones or head-mounted displays. It is well known, however, that with long exploratory trajectories and multi-session mapping for long-term autonomy or collaborative applications, the maintenance of the everincreasing size of these maps quickly becomes a bottleneck. With the explosion of data resulting in increasing runtime of the optimization algorithms ensuring the accuracy of the Simultaneous Localization And Mapping (SLAM) estimates, the large quantity of collected experiences is imposing hard limits on the scalability of such techniques. Considering the keyframe-based paradigm of SLAM techniques, this paper investigates the redundancy inherent in SLAM maps, by quantifying the information of different experiences of the scene as encoded in keyframes. Here we propose and evaluate different information-theoretic and heuristic metrics to remove dispensable scene measurements with minimal impact on the accuracy of the SLAM estimates. Evaluating the proposed metrics in two state-of-the-art centralized collaborative SLAM systems, we provide our key insights into how to identify redundancy in keyframe-based SLAM.

show abstract

Section: Related Workmentioning

confidence: 99%

On the Redundancy Detection in Keyframe-Based SLAM

Schmuck

Chli

2019

2019 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

show abstract

“…This measurement has the maximum mutual information between the state and measurement, and can be easily calculated using Equation 9. However, the marginal covariance for each feature z i , must first be constructed by selecting the relevant variables from Equation 16.…”

Section: A Information-theoretic Feature Selection Criteriamentioning

confidence: 99%

Network Uncertainty Informed Semantic Feature Selection for Visual SLAM

Ganti

Waslander

2019

2019 16th Conference on Computer and Robot Vision (CRV)

View full text Add to dashboard Cite

In order to facilitate long-term localization using a visual simultaneous localization and mapping (SLAM) algorithm, careful feature selection can help ensure that reference points persist over long durations and the runtime and storage complexity of the algorithm remain consistent. We present SIVO (Semantically Informed Visual Odometry and Mapping), a novel information-theoretic feature selection method for visual SLAM which incorporates semantic segmentation and neural network uncertainty into the feature selection pipeline. Our algorithm selects points which provide the highest reduction in Shannon entropy between the entropy of the current state and the joint entropy of the state, given the addition of the new feature with the classification entropy of the feature from a Bayesian neural network. Each selected feature significantly reduces the uncertainty of the vehicle state and has been detected to be a static object (building, traffic sign, etc.) repeatedly with a high confidence. This selection strategy generates a sparse map which can facilitate longterm localization. The KITTI odometry dataset is used to evaluate our method, and we also compare our results against ORB SLAM2. Overall, SIVO performs comparably to the baseline method while reducing the map size by almost 70%.

show abstract

“…When all factors other than k are unchanged, the optimalΩ k can be computed analytically by finding the null derivative of (8). This can be done in different manners depending on the particular properties of Υ k andJ k .…”

Section: Factor Recovery With Factor Descentmentioning

confidence: 99%

“…Kretzschmar and Stachniss [7] present an information-based compression method for laser-based pose graph SLAM, in which they compute a subset of nodes containing the scans that maximize the mutual information of the map for that subset. Chouldhary et al [8] also propose to discard some landmarks depending on their information content using an entropy-based cost function.…”

Section: Introductionmentioning

confidence: 99%

Graph SLAM Sparsification With Populated Topologies Using Factor Descent Optimization

Vallvé

Solà

Andrade‐Cetto

2018

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Abstract-Current solutions to the simultaneous localization and mapping (SLAM) problem approach it as the optimization of a graph of geometric constraints. Scalability is achieved by reducing the size of the graph, usually in two phases. First, some selected nodes in the graph are marginalized and then, the dense and non-relinearizable result is sparsified. The sparsified network has a new set of relinearizable factors and is an approximation to the original dense one. Sparsification is typically approached as a Kullback-Liebler divergence (KLD) minimization between the dense marginalization result and the new set of factors. For a simple topology of the new factors, such as a tree, there is a closed form optimal solution. However, more populated topologies can achieve a much better approximation because more information can be encoded, although in that case iterative optimization is needed to solve the KLD minimization. Iterative optimization methods proposed by the state-of-art sparsification require parameter tuning which strongly affect their convergence. In this paper, we propose factor descent and non-cyclic factor descent, two simple algorithms for SLAM sparsification that match the state-of-art methods without any parameters to be tuned. The proposed methods are compared against the state of the art with regards to accuracy and CPU time, in both synthetic and real world datasets.

show abstract

Information-based reduced landmark SLAM

Cited by 37 publications

References 26 publications

On the Redundancy Detection in Keyframe-Based SLAM

On the Redundancy Detection in Keyframe-Based SLAM

Network Uncertainty Informed Semantic Feature Selection for Visual SLAM

Graph SLAM Sparsification With Populated Topologies Using Factor Descent Optimization

Contact Info

Product

Resources

About