Towards a robust back-end for pose graph SLAM
The DOI matches its Crossref record; 28 of the 33 references it cites were found in a registry or an index.
Abstract
Current state of the art solutions of the SLAM problem are based on efficient sparse optimization techniques and represent the problem as probabilistic constraint graphs. For example in pose graphs the nodes represent poses and the edges between them express spatial information (e.g. obtained from odometry) and information on loop closures. The task of constructing the graph is delegated to a front-end that has access to the available sensor information. The optimizer, the so called back-end of the system, relies heavily on the topological correctness of the graph structure and is not robust against misplaced constraint edges. Especially edges representing false positive loop closures will lead to the divergence of current solvers. We propose a novel formulation that allows the back-end to change parts of the topological structure of the graph during the optimization process. The back-end can thereby discard loop closures and converge towards correct solutions even in the presence of false positive loop closures. This largely increases the overall robustness of the SLAM system and closes a gap between the sensor-driven front-end and the back-end optimizers. We demonstrate the approach and present results both on large scale synthetic and real-world datasets.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Thrun, S. (2002) · Communications of the ACM · doi:10.1145/504729.504754 · Cited by 7,994 · cited 1×
“, see [30] for an introduction to these methods), optimization-based approaches build upon efficient algorithms for nonlinear optimization that exploit the sparsity inherent in the SLAM problem.”
MethodFactor 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×
“The pose graph SLAM problem can be conveniently modelled as a factor graph [17].”
BackgroundRobust Regression: Asymptotics, Conjectures and Monte Carlo
Huber, P. J. (1973) · The Annals of Statistics · doi:10.1214/aos/1176342503 · Cited by 2,328 · cited 1×
“So called robust cost functions, like the Huber function [12], can reduce the influence of potential outliers.”
BackgroundG2o: A general framework for graph optimization
Kummerle, R., Grisetti, G., Strasdat, H., Konolige, K., & Burgard, W. (2011) · 2011 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2011.5979949 · Cited by 1,982 · cited 6×
“Due to its inherent sparse structure the problem can be solved efficiently with state of the art frameworks like g2o [18] or GTSAM [1] that use iterative solvers such as Gauss-Newton or LevenbergMarquardt.”
BackgroundMethodInfluentialFAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance
Cummins, M., & Newman, P. (2008) · The International Journal of Robotics Research · doi:10.1177/0278364908090961 · Cited by 1,472 · cited 2×
“Furthermore, the front-end part of the system can detect loop closures between two poses xi and xj , for example by a visual place recognition system like [4] or [29].”
BackgroundGlobally Consistent Range Scan Alignment for Environment Mapping
Lu, F., & Milios, E. (1997) · Autonomous Robots · doi:10.1023/a:1008854305733 · Cited by 1,304
iSAM: 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 3×
“The datasets City and Sphere shipped with the open-source implementation of iSAM [14].”
BackgroundMethodSquare 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 10×
“1, which shows the results of iSAM [14] version 1.5. for 10 outlier constraints.”
BackgroundInfluentialData association in stochastic mapping using the joint compatibility test
Neira, J., & Tardos, J. D. (2001) · IEEE Transactions on Robotics and Automation · doi:10.1109/70.976019 · Cited by 772 · cited 1×
“Although many of these strategies [2], [4], [15], [23], [25], [27] are appealing and reach high precision and recall measures in several benchmarks, the bottom line is that none of the current approaches can guarantee to always work perfectly and never let a false positive pass.”
BackgroundEfficient Sparse Pose Adjustment for 2D mapping
Konolige, K., Grisetti, G., Kümmerle, R., Burgard, W., Limketkai, B., & Vincent, R. (2010) · 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2010.5649043 · Cited by 395 · cited 2×
“{niko.suenderhauf, peter.protzel}@etit.tu-chemnitz.de iSAM [14] and very recently Sparse Pose Adjustment [16], iSAM2 [13], and g2o [18].”
Background
Research works printed but not linked: 2
- ku?mmerle, 0, G2o: A general framework for graph optimization, Proc of the IEEE Int Conf on Robotics and Automation (ICRA) 2011
- olson, 0, Fast iterative optimization of pose graphs with poor initial estimates, Inl Conf on Robotics and Automation ICRA 2006
Cited by
Items 101–198 of 198
Enabling Autonomous Navigation for Affordable Scooters
Liu, K., & Mulky, R. S. (2018) · Sensors · doi:10.3390/s18061829 · Cited by 10
Open-Source Factor Graph Optimization Package for GNSS: Examples and Applications
Suzuki, T. (2025) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans61210.2025.11028440 · Cited by 9
“In optimization, robust error models are typically used to reduce the effects of outliers [30].”
Awakening history: Preparing a museum tour guide robot for augmenting exhibits
Donner, M. D., Himstedt, M., Hellbach, S., & Boehme, H.-J. (2013) · European Conference on Mobile Robots · doi:10.1109/ecmr.2013.6698864 · Cited by 9
“As the mentioned approaches, Switchable Constraints and Sparse Surface Adjustment, are incorporated in our mapping framework, more detailed descriptions are given in the remainder of this paper.”
BackgroundMethodInfluentialShienman, M., & Indelman, V. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811984 · Cited by 12
View management for lifelong visual maps
Banerjee, N., Connolly, R. C., Lisin, D. A., Briggs, J., & Munich, M. E. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968245 · Cited by 9
“[5], [6]) thus correcting for the drift.”
Integrity-constrained Factor Graph Optimization for GNSS Positioning
Xia, X., Hsu, L., & Wen, W. (2023) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans53410.2023.10140009 · Cited by 8
“According to [24, 25], the effect of switch variables over covariance can be interpreted as follows: qr sItu$' , , ' , , .”
BackgroundPerformance Specified State Estimation With Minimum Risk
Aghapour, E., & Farrell, J. A. (2018) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc.2018.8431239 · Cited by 8
Suzuki, T., Ohno, K., Kojima, S., Miyamoto, N., Suzuki, T., Komatsu, T., Shibata, Y., Asano, K., & Nagatani, K. (2021) · Advanced Robotics · doi:10.1080/01691864.2021.1974942 · Cited by 11
Hu, E., & Sun, L. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2022.05.021 · Cited by 8
“Local M-estimation solvers (e.g. Agarwal et al., 2013; Kümmerle et al., 2011; Sünderhauf and Protzel, 2012) have been applied to earlier computer vision problems but it has been afflicted by the inevitable need of the initial guess.”
Pfingsthorn, M. F., & Birk, A. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907481 · Cited by 8
RGB-Depth SLAM ReviewPreprint
Jamiruddin, R., Sari, A. O., Shabbir, J., & Anwer, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.07696 · Cited by 8
“a new line of research has been initiated specifically to deal with this problem as identified in [50] and [51].”
BackgroundGraph Optimization with Unstructured Covariance: Fast, Accurate, Linear Approximation
Carlone, L., Yin, J., Rosa, S., & Yuan, Z. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-34327-8_25 · Cited by 7
“[16] stressed the topic of outliers rejection in pose graph optimization, proposing a strategy for discarding erroneous loop closure constraints.”
BackgroundOutlier Accommodation By Risk-Averse Performance-Specified Linear State Estimation
Aghapour, E., Rahman, F., & Farrell, J. A. (2018) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2018.8619401 · Cited by 7
“In [20], [21] latent variables are introduced to deactivate outliers in pose graph problems.”
BackgroundGroup-$k$ Consistent Measurement Set Maximization for Robust Outlier Detection
Forsgren, B., Vasudevan, R., Kaess, M., McLain, T. W., & Mangelson, J. G. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9982057 · Cited by 8
“C({zo, · · · , zk}) ≤ γ, ∀ {z0, · · · , zk} ∈ Pk(Z̃) (2)”
Fuzzy ART-based place recognition for visual loop closure detection
Rebai, K., Azouaoui, O., & Achour, N. (2012) · Biological Cybernetics · doi:10.1007/s00422-012-0539-x · Cited by 8
Robust loop closures for scene reconstruction by combining odometry and visual correspondences
Laskar, Z., Huttunen, S., Daniel Herrera, C., Rahtu, E., & Kannala, J. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532830 · Cited by 7
“wm ∈ [0, 1] are switch variables [17, 8] associated with potential erroneous constraints.”
BackgroundMethodLi, S., & Li, T. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3413958 · Cited by 7
“These incorrect loop closures can significantly degrade the quality of the maximum a posteriori estimate, thereby reducing localization accuracy [20].”
BackgroundBatch SLAM With PMBM Data Association Sampling and Graph-Based Optimization
Ge, Y., Kaltiokallio, O., Xia, Y., García‐Fernández, Á. F., Kim, H., Talvitie, J., Valkama, M., Wymeersch, H., & Svensson, L. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3567916 · Cited by 15
“Algorithmically this is done either by switching off potential outlier constraints [17], [18] or re-placing the quadratic cost function in the nonlinear optimization problem to a robust cost function [19], [20], such as the Huber robust cost function used in ORB-SLAM [19].”
DA-BSP: Towards Data Association Aware Belief Space Planning for Robust Active Perception
Pathak, S., Thomas, A., Feniger, A., & Indelman, V. (2016) · Frontiers in artificial intelligence and applications · doi:10.3233/978-1-61499-672-9-1610 · Cited by 6
“[1, 3, 6, 10]) focus on the passive case, where robot actions are externally determined and given.”
BackgroundVIMO: A Visual-Inertial-Magnetic Navigation System Based on Non-Linear Optimization
Wang, J., Li, L., Yu, H., Gui, X., & Li, Z. (2020) · Sensors · doi:10.3390/s20164386 · Cited by 6
“The standard pose graph optimization problem is then presented as As [39] suggests, optimization of a pose graph is no more than a plain nonlinear least squares problem.”
MethodNonmyopic Distilled Data Association Belief Space Planning Under Budget Constraints
Shienman, M., & Indelman, V. (2023) · Springer proceedings in advanced robotics · doi:10.1007/978-3-031-25555-7_8 · Cited by 7
Recent Advances in Robot Visual SLAM
Zhang, H., Jin, H., & Ma, S. (2023) · Recent Advances in Computer Science and Communications · doi:10.2174/2666255816666230509153317 · Cited by 7
An improved RGB-D SLAM algorithm based on Kinect sensor
Zhang, L., Shen, P., Ding, J., Song, J., Liu, J., & Yi, K. (2015) · IEEE International Conference on Advanced Intelligent Mechatronics (AIM) · doi:10.1109/aim.2015.7222594 · Cited by 6
Comparison of methods to efficient graph SLAM under general optimization framework
Li, H., Zhang, Q., & Zhao, D. (2017) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac.2017.7967427 · Cited by 6
“However, as these methods are sensitive to outliers, many robust approaches have been proposed [7] [8].”
BackgroundInfluentialApplying Graph-based SLAM Algorithm in a Simulated Environment
Zaman, N. A. B., Abdul-Rahman, S., Mutalib, S., & Shamsuddin, M. R. (2020) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/769/1/012035 · Cited by 6
“First introduced in the 2000s, graph optimization consists of two processes namely graph construction and optimization [14].”
BackgroundRotational Outlier Identification in Pose Graphs using Dual Decomposition
Karimian, A., Yang, Z., & Tron, R. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58577-8_24 · Cited by 7
“For the problem of outliers, traditional approaches rely on local optimization from an initial guess, and either discount outliers using robust cost functions [2,30,38]), or attempt to directly identify them [12,23,29,46,47].”
BackgroundSimultaneous localization and planning on multiple map hypotheses
Morris, T., Dayoub, F., Corke, P., & Upcroft, B. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6943204 · Cited by 6
“Therefore similar to [15] we can find the conditional probability over all variables”
An introduction for the indoor localization systems and the position estimation algorithms
Zeng, Z., Wang, L., & Liu, S. (2019) · World Conference on Smart Trends in Systems, Security and Sustainability (WorldS4) · doi:10.1109/worlds4.2019.8904011 · Cited by 5
K-Best Transformation Synchronization
Sun, Y., Zhuo, J., Mohan, A., & Huang, Q. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01035 · Cited by 9
“A recent line of transformation synchronization techniques focuses on non-convex optimizations, including alternating minimization [48], reweighted least squares [21, 12, 25], reweighted factorization [1], and continuous optimization [38, 28].”
BackgroundA tight coupling mapping method to integrate the ESKF, g2o, and point cloud alignment
Bao, S., Shi, W., Fan, W., Chen, P., Nie, M., & Xiang, H. (2021) · The Journal of Supercomputing · doi:10.1007/s11227-021-03900-7 · Cited by 5
“Each vertex corresponds to a six-degrees-of-freedom pose [18].”
BackgroundFast Loop Closure Selection Method with Spatiotemporal Consistency for Multi-Robot Map Fusion
Chen, W., Sun, J., & Zheng, Q. (2022) · Applied Sciences · doi:10.3390/app12115291 · Cited by 6
Collaborative Navigation-Aware Coverage in Feature-Poor Environments
Özkahraman, Ö., & Ögren, P. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981547 · Cited by 5
“The Graphical SLAM algorithm can be divided into two parts, the back-end and the front-end [33].”
MethodImproved EKF-SLAM Algorithm of Unmanned Helicopter Autonomous Landing on Ship
Wu, P., Shi, Z., & Yan, P. (2018) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2018.8483338 · Cited by 6
A Novel SLAM Method Using Wi-Fi Signal Strength and RGB-D Images
Yang, S., Sun, Q., Dong, X., & Jing, Y. (2018) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber.2018.8688344 · Cited by 5
“3) Loop Closure Detection and Graph Optimization: Loop closures are of great importance in reducing the accumulated error in the process of the frame-to-frame alignment [21][22][23].”
BackgroundProbabilistic Mapping and Navigation: A Survey of Bayesian Meta-Learning for Autonomous Robots
Pal, S., & Nayak, S. K. (2025) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-025-02283-8 · Cited by 4
“Modern SLAM systems have shifted towards optimization-based approaches, particularly pose graph SLAM [40], which globally optimizes odometry and loop closure spatial constraints using nonlinear solvers.”
Forsgren, B., Kaess, M., Vasudevan, R., McLain, T. W., & Mangelson, J. G. (2024) · The International Journal of Robotics Research · doi:10.1177/02783649241256970 · Cited by 14
“Sünderhauf and Protzel (2012) use switchable constraints, which introduces a switchable error factor that can be turned off if the residual error becomes too high.”
Robust Posegraph Optimization Using Proximity Points
Tazaki, Y., Wada, K., Nagano, H., & Yokokohji, Y. (2023) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2023.p1480 · Cited by 4
Vision-Based Hybrid Map Building for Mobile Robot Navigation
Üzer, F., Korrapati, H., Royer, E., Mezouar, Y., & Lee, S. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-08338-4_11 · Cited by 4
Orientation constraints for Wi-Fi SLAM using signal strength gradients
Yen, H.-C., Wang, C.-C., & Chou, C. (2020) · Autonomous Robots · doi:10.1007/s10514-020-09914-z · Cited by 4
“2013), existing works that deal with such outlier constraints in the robust pose graph SLAM literature (Olson and Agarwal 2013; Sünderhauf and Protzel 2012; Agarwal et al. 2013; Pfingsthorn and Birk 2016) generally involve modifying the SLAM cost function to penalize outlier constraints, and use iterative solvers to j…”
BackgroundMethodInfluentialHelmert's and Bowie's geodetic mapping methods and their relation to graph-based SLAM
Agarwal, P., Burgard, W., & Stachniss, C. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907382 · Cited by 4
“Linearizing the error function leads to a quadratic form that can be minimized by computing its derivative and settung up a linear system.”
BackgroundVisual-Inertial RGB-D SLAM for Mobile Augmented Reality
Williem, W., Ivan, A., Seok, H., Lim, J., Yoon, K., Cho, I.-H., & Park, I. K. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-77383-4_91 · Cited by 4
“When a loop closure occurs, a pose graph composed of visual odometer edges and loop edges is constructed, and pose graph optimization is performed to minimize the accumulated keyframes pose errors [17].”
MethodRobust Active Perception via Data-association aware Belief Space planningPreprint
Pathak, S., Thomas, A., Feniger, A., & Indelman, V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.05124 · Cited by 6
“In the last few years, the SLAM research community has investigated approaches to be resilient to false data association (outliers) overlooked by front-end algorithms (e.g. image matching), see e.g. [7, 13, 14, 21, 31].”
Aghapour, E., & Farrell, J. A. (2019) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc40024.2019.9029826 · Cited by 3
“In [8], [9] latent variables are introduced to deactivate outliers in pose graph problems.”
BackgroundCo-Operatively Increasing Smoothing and Mapping Based on Switching Function
Wang, R., & Deng, Z. (2024) · Applied Sciences · doi:10.3390/app14041543 · Cited by 4
Fusion of dependent information in posegraphs
Julier, S. (2012) · IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) · doi:10.1109/mfi.2012.6343052 · Cited by 3
“Sünderhauf [21] adopted this approach to consider the problem in which the structure of the posegraph itself was random — there is a non-zero probability that an edge does not exist.”
MethodDynamic adaptive simultaneous localization and mapping technique for scene change
Shi, D., Tong, Z., Yang, S., Zhang, Y., & Yi, X. (2018) · Scientia Sinica Technologica · doi:10.1360/n092018-00197 · Cited by 5
Multi-Robot Mapping and Navigation Using Topological Features
Ravankar, A. A., Ravankar, A. A., Emaru, T., & Kobayashi, Y. (2019) · International Electronic Conference on Sensors and Applications (ECSA) · doi:10.3390/ecsa-6-06580 · Cited by 3
“Each of the poses is represented as a graph connected by edges which represents the constraints between the two poses [22].”
BackgroundScan Similarity-based Pose Graph Construction method for Graph SLAM
Yoo, W., Kim, H., Hong, H., & Lee, B. H. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593605 · Cited by 4
“Though these approaches are known to the community since the work of Lu and Milios [5], they have become more popular as efficient algorithms for solving the optimization problems are now available [6].”
BackgroundURSIM: Unique Regions for Sketch Map Interpretation and Matching
Mielle, M., Magnusson, M., & Lilienthal, A. J. (2019) · Robotics · doi:10.3390/robotics8020043 · Cited by 3
“They performed matching between maps from different modalities by using maximum a posteriori pose-graph-based SLAM system [15].”
MethodFarhi, E. I., & Indelman, V. (2022) · Autonomous Robots · doi:10.1007/s10514-022-10045-w · Cited by 5
“Recent research thus focused on developing approaches that are robust to incorrect DA, considering both passive Carlone et al. (2014); Indelman et al. (2016); Olson and Agarwal (2013); Sunderhauf and Protzel (2012) and active perception Pathak et al. (2018).”
BackgroundCustomized fastSLAM algorithm: analysis and assessment on real mobile platform
Maziarz, B., & Domański, P. D. (2022) · Nonlinear Dynamics · doi:10.1007/s11071-022-07633-x · Cited by 3
“False positive loop closure constraints are a severe problem has been assessed and solved using the cost function augmented by switched loop closure constraints and switch prior constraints [34].”
BackgroundBredu, J. A. (2022) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.11495 · Cited by 3
FracGM: A Fast Fractional Programming Technique for Geman-McClure Robust Estimator
Chen, B.-S., Lin, Y.-K., Chen, J., Huang, C., Chern, J., & Sun, C. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3495372 · Cited by 7
“Recent studies have used various types of robust functions in different applications, such as rotation averaging [1], [2], [3], [4], point cloud registration [5], [6], [7], [8], [9], pose graph optimization [10], [11], [12], and satellite navigation [13], [14].”
Improved moving horizon estimation for ultra-wideband localization on small drones
Pfeiffer, S., Wagter, C. D., & de Croon, G. (2025) · International Journal of Micro Air Vehicles · doi:10.1177/17568293251340100 · Cited by 2
“12 Applying this concept to our MHE, we introduce for each measurement y i , k an associated switching variable s i , k .”
Pfingsthorn, M. F., Birk, A., Ferreira, F., Veruggio, G., Caccia, M., & Bruzzone, G. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6943209 · Cited by 2
“Specifically, Sünderhauf and Protzel [17], [18] reformulated the cost function and added additional switching terms (Switchable Constraints) to weight the impact of specific constraints on the overall optimization.”
BackgroundMethodInfluentialCheng, J., Jiang, Z., Zhang, Y., & Kim, J. (2014) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2014.6885783 · Cited by 2
“According to current popular robust methods [18], [19] applied in nonlinear SLAM, we further analysis the structure of Linear SLAM and describe our robust method to enhance the performance of Linear SLAM by three steps.”
MethodPerformance-Specified Moving-Horizon State Estimation With Minimum Risk
Aghapour, E., & Farrell, J. A. (2018) · European Control Conference (ECC) · doi:10.23919/ecc.2018.8550605 · Cited by 2
TomoSLAM: factor graph optimization for rotation angle refinement in microtomography
Griguletskii, M., Chekanov, M., Shipitko, O., Ingacheva, A. S., & Kibalov, V. (2022) · International Conference on Machine Vision · doi:10.1117/12.2623572 · Cited by 2
Merging of 3D visual maps based on part-map retrieval and path consistency
Tomono, M. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6697104 · Cited by 3
“In [20] and [23], outlier rejection process is incorporated into the pose graph optimization.”
BackgroundResultCazorla, M., Gil, P., Méndez, S. T. P., Muñoz, J., & Pastor, D. (2014) · Advanced Robotics · doi:10.1080/01691864.2014.920720 · Cited by 2
“In [20] and [21], the convergence rate to solve the SLAM problem using several techniques including LAGO, TORO, and g2o are studied.”
MethodLiDAR-Based High-Precision Mapping and GNSS-Denied Localiztion for UAV
Tu, Z., Fu, H., & Sun, Z. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-0479-2_275 · Cited by 2
Wang, Q., Zeng, Y., Zou, Y.-K., & Li, Q.-Z. (2020) · Sensors and Materials · doi:10.18494/sam.2020.2879 · Cited by 2
Human Pose Estimation in UAV-Human Workspace
Wang, J., Choi, W., Shtau, I., Ferro, T. J., Wu, Z., & Trott, C. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-90963-5_13 · Cited by 2
Nielsen, K., & Hendeby, G. (2023) · The International Journal of Robotics Research · doi:10.1177/02783649231215095 · Cited by 2
“In Sünderhauf and Protzel (2012a, 2012b) switchable constraints are introduced where loop closure factors in practice can be activated or deactivated as part of the optimization process.”
BackgroundFeng, Z., Chen, J., Liang, Y., Liu, W., & Peng, Y. (2025) · Sensors · doi:10.3390/s25175330 · Cited by 1
PGTI: Pose-Graph Topological Integrity for Map Quality Assessment in SLAM
Xie, S., Sakurada, K., Ishikawa, R., Onishi, M., & Oishi, T. (2025) · Robotics · doi:10.3390/robotics14120189 · Cited by 1
“Perceptual aliasing is another common issue that causes erroneous loop closures, damaging graph topology [14,32].”
Principled Uncertainty Propagation for Stereo Visual Odometry
Buonomo, F. V., Andolfo, S., & Genova, A. (2026) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-026-02358-0 · Cited by 1
“The stereo-based visual odometry pipeline developed in this work follows a modular architecture commonly adopted in the literature, comprising two main components: frontend and backend [54].”
Robust Localization Based on Regularization With Adaptive Scaling: Model, Algorithm, and Application
Chen, W., Wang, T., Li, Z., & Lu, M. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3674674 · Cited by 1
“Sunderhauf and Protzel proposed the SC mechanism for pose graph SLAM, and originally derived how SC modulates the weight of the information matrix of loop closure constraints without altering the sparse structure of the matrix [33].”
A New Landmark Detection Approach for Slam Algorithm Applied in Mobile Robot
Nguyen, X.-H., Nguyen, V., & Ngo, T.-T. (2020) · Journal of Science and Technology - Technical Universities · doi:10.51316/30.7.6 · Cited by 1
Robust optimization with credibility factor for graph-based SLAM
Chen, L. F., Yang, J., He, Y., & Huang, K. (2015) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2015.7418886 · Cited by 1
Utility-based map reduction for ground and flight vehicle navigation
Steiner, T. J. (2015) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 1
Statistical Outlier Identification in Multi-robot Visual SLAM using Expectation MaximizationPreprint
Karimian, A., Yang, Z., & Tron, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.02638 · Cited by 1
“Previous approaches for outlier detection usually rely on an initial trajectory guess and either try to mitigate the effect of outliers using M-estimators [1], [25], [31] or attempt to directly identify them [8], [17], [24], [37], [38] within a single map.”
MethodSun, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.05075 · Cited by 1
Odometry-driven inference to link multiple exemplars of a location
Lowry, S. M., Wyeth, G. F., & Milford, M. J. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696403 · Cited by 1
“Topological information can also be used to correct data association errors caused by faulty loop closures [9] [10].”
CAT-GRAPH+: Towards Odometry-driven Place Consolidation in Changing Environments
Lowry, S. M., Wyeth, G. F., & Milford, M. J. (2012) · QUT ePrints (Queensland University of Technology)
Map merging using cycle consistency check and RANSAC-based spanning tree selection
Tomono, M., & Uno, T. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7354181
“In references [13], [14], [15], [17], outlier rejection is incorporated into pose graph optimization.”
BackgroundDistributed Navigation with Unknown Initial Poses and Data Association via Expectation Maximization
Indelman, V., Michael, N., & Dellaert, F. (2015) · SMARTech Repository (Georgia Institute of Technology)
Valencia, R., & Andrade‐Cetto, J. (2017) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-60603-3_3
Delayed optimisation for robust and linear pose-graph SLAM
Kim, J., & Cheng, J. (2014) · ANU Open Research (Australian National University)
Developments in Mobile Robot Localization Research
Wang, X., Wang, X., & Wilkes, D. M. (2019) · Springer eBooks · doi:10.1007/978-981-13-9217-7_2
Arakawa, T., Takanose, A., MIZUTANI, S., Takikawa, K., & MEGURO, J. (2019) · Transactions of the Society of Instrument and Control Engineers · doi:10.9746/sicetr.55.754 · Cited by 1
Persistent Mapping in Quasi-static Dynamic Environments using Unmanned Aerial Vehicles
Deeb, A. (2021) · DalSpace (Dalhousie University) · Cited by 1
Research on Fast Three-Dimensional Map Construction Technology Based on Object Model
Yuming, S., & Xinxin, H. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-4109-2_20
Sünderhauf, N. (2023) · Springer tracts in advanced robotics · doi:10.1007/978-3-031-24017-1_11
Sünderhauf, N. (2023) · Springer tracts in advanced robotics · doi:10.1007/978-3-031-24017-1_5
Sünderhauf, N. (2023) · Springer tracts in advanced robotics · doi:10.1007/978-3-031-24017-1_1
Takanose, A., Takeuchi, E., Carballo, A., MEGURO, J., & Takeda, K. (2023) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv55152.2023.10186672
“Graph optimization has been proposed as an approach to solve the SLAM problem as a typical example [18]–[20].”
MethodPerformance evaluation of 3D point cloud matching with short-range dense 2D rang
Wang, J., Mohammed, A. F., & Patterson, G. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386813
“SLAM system often utilize a graph-based optimization technique to improve global accuracy [6, 7] by minimizing the distance between observation nodes and edges.”
BackgroundMethodChapter 7. Autonomous Navigation for Inspection and Maintenance Ground Robotics
Ivarsen, P. Ø., Keller, J., Sramota, J., Reijgwart, V., Gerhardsen, M. E., Cadena, C., Lundkvist, H., & Moore, R. J. D. (2024) · doi:10.1561/9781638282839.ch7
Warke, W. D., Ramos, J. H., Ganesh, P., Brink, K., & Hale, M. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802328 · Cited by 2
“PGO is a backend component for numerous applications in robotics and computer vision, including simultaneous localization and mapping (SLAM) [1], [2], bundle adjustment [3], structure from motion [4], and photogrammetry [5].”
Yang, Z., Wang, Y., & Shen, Y. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3573655 · Cited by 1
“Research on the application of FGO to GNSS localization has been conducted by the Chemnitz University of Technology team [24], [25], [26], [27] and the Hong Kong Polytechnic team [28], [29], [30].”
SDF-guided Keyframe Selection: Novel Boost for NeRF SLAM Loop Closure
Ma, H., Liu, Y., & Cheng, J. S. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246937
“Pose graph optimization techniques [2], [7], [8] aim to find the optimal set of camera poses by minimizing a cost function that measures the consistency between loop closure constraints.”
Positioning and Mapping with Clustering-based Landmark Optimization
Zhang, J., Li, X., Gong, X., Wang, Q., Stirling-Gallacher, R. A., & Caire, G. (2025) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc62392.2025.11275244
“However, an optimization-based approach in multipath joint localization and environmental mapping is not fully studied, which could leverage efficient algorithms for nonlinear optimization, exploiting the sparsity inherent in the positioning and environmental mapping problem [14], [15].”
Autonomous Navigation for Inspection and Maintenance Ground Robotics
Ivarsen, P. Ø., Keller, J., Sramota, J., Reijgwart, V., Gerhardsen, M. E., Cadena, C., Lundkvist, H., & Moore, R. J. D. (2024) · Emerald Group Publishing Limited eBooks · doi:10.1561/978-1-63828-283-920251008
Jin, M., Zang, N., Cheng, J., Bai, R., Chen, S., & Li, P. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3695048
“To address issues such as biased loop detection or measurement outliers, some scholars [8], [31], [32] have proposed node-checking or switchable constraint-based methods to suppress false positives.”
Enhanced MSIS-Based Place Recognition and Localization in Various Underwater Environments
Ming, L., Wu, C., Chao, Y., Song, Z., & Wang, J. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3695816
“Once an incorrect loop closure is inserted into the back-end graph, it may propagate trajectory drift or even lead to divergence [39], [40].”
Metadata
- Authors
- Sunderhauf, N., & Protzel, P.
- Affiliations
- Chemnitz University of Technology (DE)
- ORCID
- Protzel, Peter
- Venue
- 2012 IEEE International Conference on Robotics and Automation
- Publisher
- IEEE
- Published
- 2012-05
- Pages
- 1254-1261
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W1991172434
- Cited by
- 198
- References
- 33
- Citations by year
- 2026: 4 · 2025: 10 · 2024: 10 · 2023: 14 · 2022: 19 · 2021: 12 · 2020: 19 · 2019: 13 · 2018: 23 · 2017: 10 · 2016: 12 · 2015: 13 · 2014: 16 · 2013: 13 · 2012: 10
- FWCI
- 30.98
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
- Funders
- Technische Universität Chemnitz
- Queensland University of Technology
- University of Queensland
- 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 › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Keywords
- pose graph SLAM, back-end optimization, loop closure detection, robust optimization, sparse optimization, topological correctness
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.