DDF-SAM 2.0: Consistent distributed smoothing and mapping
Open accessThe DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
This paper presents an consistent decentralized data fusion approach for robust multi-robot SLAM in dangerous, unknown environments. The DDF-SAM 2.0 approach extends our previous work by combining local and neighborhood information in a single, consistent augmented local map, without the overly conservative approach to avoiding information double-counting in the previous DDF-SAM algorithm. We introduce the anti-factor as a means to subtract information in graphical SLAM systems, and illustrate its use to both replace information in an incremental solver and to cancel out neighborhood information from shared summarized maps. This paper presents and compares three summarization techniques, with two exact approaches and an approximation. We evaluated the proposed system in a synthetic example and show the augmented local system and the associated summarization technique do not double-count information, while keeping performance tractable.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Cunnigham et al. [54] use Gaussian elimination, and develop an approach, called DDF-SAM, in which each robot exchanges a Gaussian marginal over the separators (i.e., the variables shared by multiple robots).”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [54]
Experimental — accuracy not yet measuredIn the citing paper
“The second reason is that Gaussian elimination is performed on a linearized version of the problem, hence approaches such as DDF-SAM [54] require good linearization points and complex bookkeeping to ensure consistency of the linearization points across the robots.”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [54]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Thrun, S. (2002) · Communications of the ACM · doi:10.1145/504729.504754 · Cited by 7,994
Koller, D., & Friedman, N. (2009) · The MIT Press eBooks · Cited by 7,555
Factor graphs and the sum-product algorithm
Kschischang, F. R., Frey, B. J., & Loeliger, H.-A. (2001) · IEEE Transactions on Information Theory · doi:10.1109/18.910572 · Cited by 6,486 · cited 1×
“Let φ(Θ) be a nonnegative , real-valued function of these variables that factors over subsets Θ i ⊆ Θ, as in φ(Θ r ) = i φ r i (Θ r i ) then a factor graph is a bipartite graph that expresses this factorization [24].”
Background(2009) · Cited by 6,153
iSAM2: Incremental smoothing and mapping using the Bayes tree
Kaess, M., Johannsson, H., Roberts, R., Ila, V., Leonard, J. J., & Dellaert, F. (2012) · The International Journal of Robotics Research · doi:10.1177/0278364911430419 · Cited by 1,362
Self-citationiSAM: Incremental Smoothing and Mapping
Kaess, M., Ranganathan, A., & Dellaert, F. (2008) · IEEE Transactions on Robotics · doi:10.1109/tro.2008.2006706 · Cited by 1,076 · cited 2×
“With a linear system factorized through elimination, we can exploit the structure of the resulting Bayes net to allow for incremental solving [14] of a single solver, in which we update only sections of an existing Bayes net as we add new factors to the system.”
MethodSelf-citationA non-divergent estimation algorithm in the presence of unknown correlations
Julier, S. J., & Uhlmann, J. K. (1997) · Proceedings of the 1997 American Control Conference (Cat. No.97CH36041) · doi:10.1109/acc.1997.609105 · Cited by 999 · cited 1×
“Another method for consistent information fusion is covariance intersection [9], previously applied to singlerobot SLAM [10] with straightforward extensions to multirobot SLAM.”
MethodSquare Root SAM: Simultaneous Localization and Mapping via Square Root Information Smoothing
Dellaert, F., & Kaess, M. (2006) · The International Journal of Robotics Research · doi:10.1177/0278364906072768 · Cited by 922 · cited 2×
“For a more detailed treatment, see [3], [22].”
BackgroundMethodSelf-citationDistributed multirobot localization
Roumeliotis, S. I., & Bekey, G. A. (2002) · IEEE Transactions on Robotics and Automation · doi:10.1109/tra.2002.803461 · Cited by 717
Simultaneous Localization and Mapping with Sparse Extended Information Filters
Thrun, S., Liu, Y., Koller, D., Ng, A. Y., Ghahramani, Z., & Durrant-Whyte, H. (2004) · The International Journal of Robotics Research · doi:10.1177/0278364904045479 · Cited by 651 · cited 1×
“al, presented an extension of the sparse extended information filter for multi-robot scenarios [11], [12], which actively removed information to ensure sparseness at the cost of approximation.”
BackgroundDistributed Multi-Robot Localization
Panzieri, S., Pascucci, F., Sciavicco, L., & Setola, R. (2013) · Robotics · doi:10.4018/978-1-4666-4607-0.ch020 · Cited by 509
Distributed maximum a posteriori estimation for multi-robot cooperative localization
Nerurkar, E. D., Roumeliotis, S. I., & Martinelli, A. (2009) · 2009 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2009.5152398 · Cited by 233 · cited 1×
“[6] develop a MAP estimator with a distributed dataallocation scheme to simultaneously process and update local data while incorporating inter-robot relative measurements.”
MethodUsing covariance intersection for SLAM
Julier, S. J., & Uhlmann, J. K. (2007) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2006.06.011 · Cited by 207 · cited 1×
“Another method for consistent information fusion is covariance intersection [9], previously applied to singlerobot SLAM [10] with straightforward extensions to multirobot SLAM.”
MethodConsistent cooperative localization
Bahr, A., Walter, M. R., & Leonard, J. J. (2009) · 2009 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2009.5152859 · Cited by 191 · cited 1×
“[7] introduced a method for consistent cooperative localization with a bank of filters for tracking the origins of measurements to prevent double-counting.”
MethodMultiple relative pose graphs for robust cooperative mapping
Kim, B., Kaess, M., Fletcher, L., Leonard, J., Bachrach, A., Roy, N., & Teller, S. (2010) · 2010 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2010.5509154 · Cited by 181 · cited 1×
“Centralized graphSLAM techniques allow for easier extension of single-robot SLAM algorithms, such as iSAM [14] applied to multi-robot mapping via pose-graphs [15], but centralizing inference makes scalability to large robot systems with unreliable communication difficult, especially when performing inference online.”
MethodDistributed Multi-Robot Localization
Roumeliotis, S. I., & Bekey, G. A. (2000) · Distributed Autonomous Robotic Systems 4 · doi:10.1007/978-4-431-67919-6_17 · Cited by 167 · cited 1×
“[5] consider an extended Kalman filter (EKF) framework and perform a decentralized calculation”
MethodDDF-SAM: Fully distributed SLAM using Constrained Factor Graphs
Cunningham, A., Paluri, M., & Dellaert, F. (2010) · 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2010.5652875 · Cited by 164 · cited 2×
“0 architecture [1] has three main parts: a) Each robot r updates its own local map with incoming measurements Z from onboard sensors, b) summarizes the local map to form a density Φ̃ (Θ) on exactly the variables to share (usually chosen to be locally observed L), and then distributes this density its neighbors; and c)…”
BackgroundMethodSelf-citationTowards multi-vehicle simultaneous localisation and mapping
Williams, S. B., Dissanayake, G., & Durrant-Whyte, H. (2003) · Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292) · doi:10.1109/robot.2002.1013647 · Cited by 123
The Bayes Tree: An Algorithmic Foundation for Probabilistic Robot Mapping
Kaess, M., Ila, V., Roberts, R. B., & Dellaert, F. (2010) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-17452-0_10 · Cited by 120 · cited 2×
“The structure of the Bayes net in an incremental solver has as a more general structure that we can exploit: the Bayes tree [22], [23] is a tree-structured graphical model that defines a factored density over cliques of variables.”
BackgroundMethodSelf-citationDistributed Consensus on Robot Networks for Dynamically Merging Feature-Based Maps
Aragues, R., Cortes, J., & Sagues, C. (2012) · IEEE Transactions on Robotics · doi:10.1109/tro.2012.2192012 · Cited by 119 · cited 1×
“Several works fuse information from multiple local maps into a global map without updating the local maps with the global solution [18], [19].”
BackgroundDecentralised cooperative localisation for heterogeneous teams of mobile robots
Bailey, T., Bryson, M., Mu, H., Vial, J., McCalman, L., & Durrant-Whyte, H. F. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5979850 · Cited by 95 · cited 1×
“[16] proposed a cooperative localization technique using relative range-bearing measurements between the robots, extending previous work in the context of airborne SLAM [17].”
MethodFully distributed scalable smoothing and mapping with robust multi-robot data association
Cunningham, A., Wurm, K. M., Burgard, W., & Dellaert, F. (2012) · 2012 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2012.6225356 · Cited by 93 · cited 2×
“In our previous work on decentralized robot perception [1], [2], we introduced DDF-SAM (denoted as DDF-SAM 1.”
BackgroundMethodSelf-citationC-SAM: Multi-Robot SLAM using square root information smoothing
Andersson, L. A. A., & Nygards, J. (2008) · 2008 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2008.4543634 · Cited by 82 · cited 1×
“In addition to filtering approaches for multi-robot SLAM, there are a variety of centralized graph-SLAM techniques, such as C-SAM [13], which combines observations from multiple robots in a single factor graph.”
MethodGraph-based distributed cooperative navigation for a general multi-robot measurement model
Indelman, V., Gurfil, P., Rivlin, E., & Rotstein, H. (2012) · The International Journal of Robotics Research · doi:10.1177/0278364912446325 · Cited by 42 · cited 1×
“[8] used a graph-based approach to calculate the correlation terms for consistent information fusion in the EKF framework.”
MethodSelf-citationArchitectures for Cooperative Airborne Simultaneous Localisation and Mapping
Bryson, M., & Sukkarieh, S. (2009) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-008-9303-9 · Cited by 40 · cited 1×
“[16] proposed a cooperative localization technique using relative range-bearing measurements between the robots, extending previous work in the context of airborne SLAM [17].”
MethodConsistent data association in multi-robot systems with limited communications
Aragues, R., Montijano, E., & Sagues, C. (2010) · Robotics: Science and Systems VI · doi:10.15607/rss.2010.vi.013 · Cited by 37 · cited 1×
“This paper assumes known data associations between measurements and landmarks are for both single robot platforms and between robot platforms; for a treatments of data associations between platforms, see [2], [21].”
BackgroundPreliminary Results in Decentralized Estimation for Single-Beacon Acoustic Underwater Navigation
Webster, S. E., Whitcomb, L. L., & Eustice, R. M. (2010) · Robotics: Science and Systems · doi:10.15607/rss.2010.vi.011 · Cited by 34 · cited 1×
“It is possible to avoid this problem by enforcing non-cyclic constraints on network topology [20], but this reduces the resilience of the system to communication and node failures.”
Background
Research works printed but not linked: 1
- [4] H. Durrant-Whyte and M. Stevens, 'Data fusion in decentralized sensing networks,' in 4th Intl. Conf. on Information Fusion , 2001. -
Cited by
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., & Leonard, J. J. (2016) · IEEE Transactions on Robotics · doi:10.1109/tro.2016.2624754 · Cited by 3,596
“[55] use Gaussian elimination, and develop an”
InfluentialPast, present, and future of simultaneous localization and mapping: Toward the robust-perception age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I. D., & Leonard, J. J. (2016) · Zurich Open Repository and Archive (University of Zurich) · doi:10.5167/uzh-138892 · Cited by 3,048
A Survey on Aerial Swarm Robotics
Chung, S.-J., Paranjape, A. A., Dames, P., Shen, S., & Kumar, V. (2018) · IEEE Transactions on Robotics · doi:10.1109/tro.2018.2857475 · Cited by 672
“To this end, researchers have been focusing on minimizing or limiting the amount of data required to perform decentralized mapping [195], [196].”
BackgroundKimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems
Tian, Y., Chang, Y., Herrera Arias, F., Nieto-Granda, C., How, J. P., & Carlone, L. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3137751 · Cited by 288
Schmuck, P., & Chli, M. (2019) · Journal of Field Robotics · doi:10.1002/rob.21854 · Cited by 253
“Cunningham, Indelman, and Dellaert (2013) propose such a fully distributed SLAM system and evaluate it in simulation.”
Background
Metadata
- Authors
- Cunningham, A., Indelman, V., & Dellaert, F.
- Affiliations
- Georgia Institute of Technology (US)
- Venue
- 2013 IEEE International Conference on Robotics and Automation
- Publisher
- IEEE
- Published
- 2013-05
- Pages
- 5220-5227
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2040134986
- Cited by
- 171
- References
- 26
- Citations by year
- 2026: 4 · 2025: 15 · 2024: 11 · 2023: 15 · 2022: 15 · 2021: 20 · 2020: 21 · 2019: 11 · 2018: 14 · 2017: 13 · 2016: 11 · 2015: 13 · 2014: 5 · 2013: 3
- FWCI
- 18.83
- Type
- conference paper
- Language
- en
- Open access
- green
- hdl.handle.net
- Locations
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
- SMARTech Repository (Georgia Institute of Technology) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Computer Science › Artificial Intelligence › Target Tracking and Data Fusion in Sensor Networks
- Physical Sciences › Engineering › Aerospace Engineering › Inertial Sensor and Navigation
- Keywords
- distributed data fusion, multi-robot SLAM, neighborhood information, hazardous environments
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.