Information-Based Compact Pose SLAM
Open accessThe DOI matches its Crossref record; 43 of the 46 references it cites were found in a registry or an index.
Abstract
Pose SLAM is the variant of simultaneous localization and map building (SLAM) is the variant of SLAM, in which only the robot trajectory is estimated and where landmarks are only used to produce relative constraints between robot poses. To reduce the computational cost of the information filter form of Pose SLAM and, at the same time, to delay inconsistency as much as possible, we introduce an approach that takes into account only highly informative loop-closure links and nonredundant poses. This approach includes constant time procedures to compute the distance between poses, the expected information gain for each potential link, and the exact marginal covariances while moving in open loop, as well as a procedure to recover the state after a loop closure that, in practical situations, scales linearly in terms of both time and memory. Using these procedures, the robot operates most of the time in open loop, and the cost of the loop closure is amortized over long trajectories. This way, the computational bottleneck shifts to data association, which is the search over the set of previously visited poses to determine good candidates for sensor registration. To speed up data association, we introduce a method to search for neighboring poses whose complexity ranges from logarithmic in the usual case to linear in degenerate situations. The method is based on organizing the pose information in a balanced tree whose internal levels are defined using interval arithmetic. The proposed Pose-SLAM approach is validated through simulations, real mapping sessions, and experiments using standard SLAM data sets.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Ila et al. [115] use an information-theoretic approach to add only non-redundant nodes and highly-informative measurements to the graph.”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [115]
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 1×
“Stereo images were used to find constraints (visual odometry and loop closure links) between corresponding poses iterating as follows: First, SIFT image features [42] are extracted and matched from candidate stereo image pairs.”
MethodRayward-Smith, V. J. (1991) · Journal of the Operational Research Society · doi:10.1057/jors.1991.155 · Cited by 16,821
Estimation with Applications to Tracking and Navigation: Theory, Algorithms and Software
Bar‐Shalom, Y., Li, X. ‐., & Kirubarajan, T. (2002) · doi:10.1002/0471221279 · Cited by 6,782
A solution to the simultaneous localization and map building (SLAM) problem
Dissanayake, M. W. M. G., Newman, P., Clark, S., Durrant-Whyte, H. F., & Csorba, M. (2001) · IEEE Transactions on Robotics and Automation · doi:10.1109/70.938381 · Cited by 2,661
FAB-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×
“Our Pose-SLAM method was compared with a state-of-the-art placerecognition technique [39].”
MethodGlobally Consistent Range Scan Alignment for Environment Mapping
Lu, F., & Milios, E. (1997) · Autonomous Robots · doi:10.1023/a:1008854305733 · Cited by 1,304
Matrix Algebra From a Statistician’s Perspective
Harville, D. A. (1997) · Springer eBooks · doi:10.1007/b98818 · Cited by 1,159
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 1×
“Section VII summarizes the Pose-SLAM algorithm introduced in this paper and Section VIII evaluates it using synthetic and real data sets.”
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 3×
“, [6], [19], [26], address the second source of error.”
BackgroundInfluentialMatrix Algebra from a Statistician's Perspective
Ziegel, E. R., & Harville, D. A. (1998) · Technometrics · doi:10.2307/1270666 · Cited by 880
Research works printed but not linked: 4
- moore, 1966, Interval Analysis
- esteban, 2008, slam for extremely large environments, presented at the Proc 14th Annu Conf Adv School Comput Imag
- ranganathan, 2007, loopy sam, Proc Int Joint Conf Artif Intell, 2191
- montemerlo, 2007, FastSLAM A Scalable Method for the Simultaneous Localization and Mapping Problem in Robotic
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
“[115] use an information-theoretic approach to add only nonredundant nodes and highly informative measurements to the graph.”
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. 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 Active Simultaneous Localization and Mapping: State of the Art and New Frontiers
Placed, J. A., Strader, J., Carrillo, H., Atanasov, N., Indelman, V., Carlone, L., & Castellanos, J. A. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3248510 · Cited by 332
“[53] Pose SLAM [41] Lidar COM Modular Frontiers MI & distance Simulation Coverage ✓”
BackgroundA Hybrid Path Planning Method in Unmanned Air/Ground Vehicle (UAV/UGV) Cooperative Systems
Li, J., Deng, G., Luo, C., Lin, Q., Yan, Q., & Ming, Z. (2016) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2016.2623666 · Cited by 306
“In 2010, Ila et al. have proposed a method that is defined using interval arithmetic based on organizing the pose information in a balanced tree whose internal levels [15].”
MethodReal-Time Visual SLAM for Autonomous Underwater Hull Inspection Using Visual Saliency
Kim, A., & Eustice, R. M. (2013) · IEEE Transactions on Robotics · doi:10.1109/tro.2012.2235699 · Cited by 263
“Necessarily, this task involves intelligently choosing loopclosure candidates because 1) the computational cost of attempting the camera-derived relative-pose constraint (1) is not insignificant, and 2) adding unnecessary/redundant edges to the SLAM pose-graph increases inference complexity and can also lead to overco…”
BackgroundMethodInfluentialDeep Reinforcement Learning-Based Automatic Exploration for Navigation in Unknown Environment
Li, H., Zhang, Q., & Zhao, D. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2927869 · Cited by 261
“[18] defined mutual information gain for a new edge in the pose graph.”
BackgroundVDO-SLAM: A Visual Dynamic Object-aware SLAM SystemPreprint
Zhang, J., Henein, M., Mahony, R. E., & Ila, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.11052 · Cited by 235
“ssue to be reduced is the computational complexity of SLAM with dynamic objects. In long-term applications, different techniques can be applied to limit the growth of the graph (Strasdat et al.(2011);Ila et al. (2010)). In fact, history summarisation/deletion of map points pertaining to dynamic objects observed far in…”
BackgroundSelf-citationMotion removal for reliable RGB-D SLAM in dynamic environments
Sun, Y., Liu, M., & Meng, M. Q.-H. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.07.002 · Cited by 201
Active Mapping and Robot Exploration: A Survey
Lluvia, I., Lazkano, E., & Ansuategi, A. (2021) · Sensors · doi:10.3390/s21072445 · Cited by 200
“They present an active exploration strategy integrated with Pose SLAM [128], a variant of SLAM in which only the robot trajectory is estimated and where landmarks are used to generate relative constraints between robot poses.”
MethodSimultaneous Localization and Mapping
Stachniss, C., Leonard, J. J., & Thrun, S. (2016) · Springer handbooks · doi:10.1007/978-3-319-32552-1_46 · Cited by 172
Visual SLAM: What Are the Current Trends and What to Expect?
Tourani, A., Bavle, H., Sánchez-López, J. L., & Voos, H. (2022) · Sensors · doi:10.3390/s22239297 · Cited by 155
“Their keyframe-based solution expands Pose SLAM [108] that only keeps non-redundant poses for producing a compact map, adds dense visual odometry characteristics, and effectively utilizes the information from camera frames for a reliable camera motion estimation.”
BackgroundDynamic SLAM: The Need For Speed
Henein, M., Zhang, J., Mahony, R. E., & Ila, V. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196895 · Cited by 131
“In long-term applications, different techniques can be applied to limit the growth of the graph [40], [41].”
BackgroundSelf-citationZhao, S., Chen, Y., & Farrell, J. A. (2016) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2016.2529000 · Cited by 127
“The problem of choosing the set Vk can be formulated as an optimization problem [41]:”
BackgroundAttention and Anticipation in Fast Visual-Inertial Navigation
Carlone, L., & Karaman, S. (2017) · IEEE Transactions on Robotics · doi:10.1109/icra.2017.7989448 · Cited by 126
“c model is used to quickly filter out less relevant data. Second, we consider different performance metrics, going beyond the determinant criterion used in [31] and related work on graph sparsification [33]. Third, we perform feature selection in a single stage and leverage submodularity to provide formal performance gu…”
Information-theoretic compression of pose graphs for laser-based SLAM
Kretzschmar, H., & Stachniss, C. (2012) · The International Journal of Robotics Research · doi:10.1177/0278364912455072 · Cited by 109
“Ila et al. (2010) propose to only incorporate nonredundant poses and informative constraints based on the relative distance between poses in information space and the expected information gain of candidate loop closures.”
BackgroundGaussian processes autonomous mapping and exploration for range-sensing mobile robots
Jadidi, M. G., Miro, J. V., & Dissanayake, G. (2017) · Autonomous Robots · doi:10.1007/s10514-017-9668-3 · Cited by 122
“Similar to this work, these techniques use Pose SLAM (Ila et al. 2010; Valencia et al. 2013), a delayed-state SLAM algorithm from the pose graph family.”
BackgroundMethodCommunication-constrained multi-AUV cooperative SLAM
Paull, L., Huang, G., Seto, M., & Leonard, J. J. (2015) · 2015 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2015.7139227 · Cited by 116
“In [28], pose-graph compression is proposed for laserbased SLAM by utilizing an approximate marginalization based on the Chow-Liu tree (CLT), while the method in [29] uses an information criterion to selectively remove uninformative loop closures.”
MethodCarlone, L., Kira, Z., Beall, C., Indelman, V., & Dellaert, F. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907483 · Cited by 116
“In [4], Polok et al. propose ad-hoc techniques for speeding-up solution of normal equations, exploiting problem structure.”
BackgroundPose-Graph SLAM Using Forward-Looking Sonar
Li, J., Kaess, M., Eustice, R. M., & Johnson‐Roberson, M. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2809510 · Cited by 114
“[23] in which one only adds informative links to keep the SLAM graph compact.”
BackgroundGeneric Node Removal for Factor-Graph SLAM
Carlevaris-Bianco, N., Kaess, M., & Eustice, R. M. (2014) · IEEE Transactions on Robotics · doi:10.1109/tro.2014.2347571 · Cited by 96
“Index Terms—Factor-graphs, long-term autonomy, marginalization, mobile robotics, simultaneous localization and mapping (SLAM).”
BackgroundValencia, R., Valls Miro, J., Dissanayake, G., & Andrade-Cetto, J. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6385637 · Cited by 86
Self-citationSLAM++-A highly efficient and temporally scalable incremental SLAM framework
Ila, V., Polok, L., Šolony, M., & Svoboda, P. (2017) · The International Journal of Robotics Research · doi:10.1177/0278364917691110 · Cited by 98
“Johannsson et al. (2013), on the other hand, introduced an incremental strategy which avoids marginalization and which is similar to the one proposed in Ila et al.”
BackgroundMethodResultInfluentialSelf-citationDARE-SLAM: Degeneracy-Aware and Resilient Loop Closing in Perceptually-Degraded Environments
Ebadi, K., Palieri, M., Wood, S. L., Padgett, C. W., & Agha–mohammadi, A. (2021) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-021-01362-w · Cited by 97
Jadidi, M. G., Miro, J. V., & Dissanayake, G. (2019) · The International Journal of Robotics Research · doi:10.1177/0278364919844575 · Cited by 88
“This requires solving the SLAM problem for localization possibly using observations to features in the environment.”
MethodInfluentialPlanning Reliable Paths With Pose SLAM
Valencia, R., Morta, M., Andrade-Cetto, J., & Porta, J. M. (2013) · IEEE Transactions on Robotics · doi:10.1109/tro.2013.2257577 · Cited by 75
“, the difference in entropy on the entire map before and after the link is established, can be evaluated as [17]”
InfluentialSelf-citationGao, H., Zhang, X., Wen, J. G., Yuan, J., & Fang, Y. (2018) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2018.2883587 · Cited by 80
“Valencia et al. [29] present an new exploration strategy that tightly integrated Pose SLAM [30], and Vallvé and Andrade-Cetto [31] also make use of Pose SLAM to update path estimate.”
MethodEKF-SLAM for AUV navigation under probabilistic sonar scan-matching
Mallios, A., Ridao, P., Ribas, D., Maurelli, F., & Pétillot, Y. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5649246 · Cited by 77
“With the aim of reducing as much as possible the size of information vector, as well as to delay inconsistency [13] have recently proposed methods to keep only high informative loop-closure links as well as non redundant poses within the information vector.”
MethodA critique of current developments in simultaneous localization and mapping
Huang, S., & Dissanayake, G. (2016) · International Journal of Advanced Robotic Systems · doi:10.1177/1729881416669482 · Cited by 70
Khosoussi, K., Giamou, M., Sukhatme, G. S., Huang, S., Dissanayake, G., & How, J. P. (2019) · The International Journal of Robotics Research · doi:10.1177/0278364918823086 · Cited by 72
“Inspired by Ila et al. (2010), we also present a front-end (potential) loop-closure selection scheme based on tree connectivity to perform sensor registration only for information-rich candidate loop closures (detected based on visual similarity or geometry).”
BackgroundMethodInfluentialConsistent sparsification for graph optimization
Huang, G., Kaess, M., & Leonard, J. J. (2013) · 2013 European Conference on Mobile Robots · doi:10.1109/ecmr.2013.6698835 · Cited by 70
“More recently, an information-theoretic approach is proposed to compress the pose graph, only for laser-based SLAM [7].”
BackgroundMethodInfluentialExploration on continuous Gaussian process frontier maps
Jadidi, M. G., Miró, J. V., Valencia, R., & Andrade‐Cetto, J. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907754 · Cited by 67
“The C-frontier map is in turn extracted from another continuous representation that models the occupancy probability distribution from sensor data.”
BackgroundSelf-citationLocalization in highly dynamic environments using dual-timescale NDT-MCL
Valencia, R., Saarinen, J., Andreasson, H., Vallve, J., Andrade-Cetto, J., & Lilienthal, A. J. (2014) · 2014 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2014.6907433 · Cited by 54
“methods: gmapping [24]4, mapping and tracking based on the NDT-2-NDT registration [20] and a ROS implementation of Pose SLAM [25]5.”
BackgroundMethodInfluentialSelf-citationNonlinear factor recovery for long-term SLAM
Mazuran, M., Burgard, W., & Tipaldi, G. D. (2016) · The International Journal of Robotics Research · doi:10.1177/0278364915581629 · Cited by 63
“Ila et al. (2010) proposed an information-theoretic approach to add only non-redundant nodes and highly informative edges to the graph.”
BackgroundMutual information-based exploration on continuous occupancy maps
Jadidi, M. G., Miró, J. V., & Dissanayake, G. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7354244 · Cited by 61
“In all of the presented results, Pose SLAM [18] is included as the backbone to provide localization data together with number of closed loops.”
MethodInfluentialIn‐water visual ship hull inspection using a hover‐capable underwater vehicle with stereo vision
Hong, S., Chung, D., Kim, J., Kim, Y., Kim, A., & Yoon, H. K. (2018) · Journal of Field Robotics · doi:10.1002/rob.21841 · Cited by 61
Dayoub, F., Cielniak, G., & Duckett, T. (2011) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2011.02.013 · Cited by 59
“…in our work that the robot has already acquired an initial map using a state-of-the-art method (see, for example, the approach of Ila et al. [23] in which nodes and links are added to the map with regards to information content), and we also do not address the problem of topological changes…”
MethodRGB-D Point Cloud Registration Based on Salient Object Detection
Wan, T., Du, S., Cui, W., Yao, R., Ge, Y., Li, C., Gao, Y., & Zheng, N. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3053274 · Cited by 58
Terrain Classification in Complex Three‐dimensional Outdoor Environments
Santamaria‐Navarro, À., Teniente, E. H., Garriga, M. M., & Andrade‐Cetto, J. (2014) · Journal of Field Robotics · doi:10.1002/rob.21521 · Cited by 56
“Using two variants of supervised learning—GP regression and GP classification— we are able to classify dense point clouds acquired with Pose SLAM (Ila et al., 2010). We showed that with only two features, one for local roughness and one for slope, we can get a classification performance with f-scores better than SVM a…”
MethodInfluentialSelf-citationNovel insights into the impact of graph structure on SLAM
Khosoussi, K., Huang, S., & Dissanayake, G. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942932 · Cited by 56
Learning object deformation models for robot motion planning
Frank, B., Stachniss, C., Schmedding, R., Teschner, M., & Burgard, W. (2014) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.04.005 · Cited by 55
“There exists a variety of approaches for robots to autonomously generate an appropriate model of the environment by addressing the simultaneous localization and mapping problem [1, 2, 3, 4], by autonomous exploration [5, 6, 7], or by addressing both problems jointly [8, 9].”
BackgroundObject modeling using a ToF camera under an uncertainty reduction approach
Foix, S., Alenyà, G., Andrade‐Cetto, J., & Carme Torras, A. (2010) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2010.5509197 · Cited by 54
“The view-based SLAM technique used in our experiments is based on a delayed-state information-form algorithm [21], [13].”
BackgroundMethodSelf-citationInformation Sparsification in Visual-Inertial Odometry
Hsiung, J., Hsiao, M., Westman, E., Valencia, R., & Kaess, M. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594007 · Cited by 54
“Existing literature in sparsification focuses on the context of large SLAM pose graphs [20, 6, 17, 10].”
BackgroundGeneric factor-based node marginalization and edge sparsification for pose-graph SLAM
Carlevaris-Bianco, N., & Eustice, R. M. (2013) · 2013 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2013.6631403 · Cited by 52
“In [6], an information-theoretic approach is used to add only non-redundant nodes and highly-informative measurements to the graph.”
MethodInformation-based reduced landmark SLAM
Choudhary, S., Indelman, V., Christensen, H. I., & Dellaert, F. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139839 · Cited by 51
“[13] proposed to add only non-redundant and informative links to the graph.”
BackgroundPotential information fields for mobile robot exploration
Vallvé, J., & Andrade-Cetto, J. (2015) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.08.009 · Cited by 50
“In Pose SLAM [7], a probabilistic estimate of the robot pose history is maintained as a sparse graph with a canonical parametrization p(x) = N−1(η,Λ), using an information filter, with information vector η = Λμ, and information matrix Λ = Σ−1.”
MethodSelf-citationPath planning in belief space with pose SLAM
Valencia, R., Andrade-Cetto, J., & Porta, J. M. (2011) · 2011 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2011.5979742 · Cited by 42
“In this paper, we aim to overcome this limitation noting that the map generated by Pose SLAM [10] (or in any other delayed-state SLAM algorithm [11, 12]) is perfectly suited to be used as a belief roadmap.”
BackgroundMethodSelf-citationEfficient information-theoretic graph pruning for graph-based SLAM with laser range finders
Kretzschmar, H., Stachniss, C., & Grisetti, G. (2011) · 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2011.6094414 · Cited by 48
“Ila et al. [7] propose to only incorporate nonredundant poses and informative constraints based on the relative distance between poses in information space and the expected information gain of candidate loop closures.”
BackgroundDecentralized Sensor Fusion for Ubiquitous Networking Robotics in Urban Areas
Sanfeliu, A., Andrade‐Cetto, J., Barbosa, M., Bowden, R., Capitán, J., Corominas, A., Gilbert, A., Illingworth, J., Merino, L., Mirats, J. M., et al. (2010) · Sensors · doi:10.3390/s100302274 · Cited by 48
“Our technique to Simultaneous Localization and Mapping (SLAM) is described in detail in [7, 11, 12], and is summarized here.”
BackgroundMethodInfluentialSelf-citationDecoupled, consistent node removal and edge sparsification for graph-based SLAM
Eckenhoff, K., Paull, L., & Huang, G. P. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759505 · Cited by 48
“These approaches store the entire history of robot poses (and landmark positions in the case of feature-based SLAM) as nodes in the graph, while measurements between nodes are represented as edges (factors).”
BackgroundInfluentialFrontier Detection and Reachability Analysis for Efficient 2D Graph-SLAM Based Active Exploration
Sun, Z., Wu, B., Xu, C., Sarma, S. E., Yang, J. J., & Kong, H. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341735 · Cited by 47
“It should be emphasized that our method of adaptively selecting the span of frontier detection is not only applicable to Cartographer, but also to all key-frames based SLAM, such as active Pose SLAM [10].”
MethodVallvé, J., & Andrade‐Cetto, J. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139485 · Cited by 47
“In the following section we describe succinctly what Pose SLAM is, and refer the reader to the original paper for a full understanding for sake of space [12].”
BackgroundMethodInfluentialSelf-citationActive SLAM for Autonomous Underwater Exploration
Palomeras, N., Carreras, M., & Andrade‐Cetto, J. (2019) · Remote Sensing · doi:10.3390/rs11232827 · Cited by 45
“Hi and Hk are the Jacobians of h with respect to poses i and k evaluated at the state means μi and μk (see Appendix B), Σii and Σkk are the marginal covariances of vpi and vpk respectively, and Σik is their cross correlation [34].”
BackgroundSelf-citationFast topology estimation for image mosaicing using adaptive information thresholding
Elibol, A., Gracias, N., & García, R. (2012) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2012.10.010 · Cited by 44
“[25] proposed a method to keep the most informative links between robot poses using mutual information within a Simultaneous Localization andMapping (SLAM) context.”
MethodGiamou, M., Khosoussi, K., & How, J. P. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460783 · Cited by 42
“, see [16], [17]—nor does it tell them what to do with the exchanged data—i.”
BackgroundDistributed Data Association in Robotic Networks With Cameras and Limited Communications
Montijano, E., Aragüés, R., & Sagüés, C. (2013) · IEEE Transactions on Robotics · doi:10.1109/tro.2013.2273843 · Cited by 41
“In simultaneous localization and mapping (SLAM) problems, 3-D points with uncertainties are matched using the nearest neighbor [5], maximum likelihood [6], or B-splines [7].”
MethodTemporally scalable visual SLAM using a reduced pose graph
Johannsson, H., Kaess, M., Fallon, M., & Leonard, J. J. (2013) · 2013 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2013.6630556 · Cited by 39
“[11] uses an information-theoretic method to decide which constraints should be added.”
MethodInformation-Driven Direct RGB-D Odometry
Fontan, A., Civera, J., & Triebel, R. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00498 · Cited by 39
“[13] proposes a method to add only non-redundant and informative links to a pose graph, and [16] uses mutual information to remove low informative laser scans from the graph.”
MethodMapping, planning and exploration with Pose SLAM
Carreño, R. V. (2013) · UPCommons institutional repository (Universitat Politècnica de Catalunya) · doi:10.5821/dissertation-2117-94927 · Cited by 39
Action Selection for Single-Camera SLAM
Vidal‐Calleja, T., Sanfeliu, A., & Andrade‐Cetto, J. (2010) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2010.2043528 · Cited by 38
Self-citationGraph SLAM Sparsification With Populated Topologies Using Factor Descent Optimization
Vallvé, J., Solà, J., & Andrade‐Cetto, J. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2798283 · Cited by 37
“[5] V. Ila, J. M. Porta, and J. Andrade-Cetto, “Information-based compact Pose SLAM,” IEEE Trans.”
BackgroundSelf-citationHu, X., Zheng, L., Wu, J., Geng, R., Yu, Y., Wei, H., Tang, X., Wang, L., Jiao, J., & Liu, M. (2024) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2024.3362902 · Cited by 36
“2) Our research utilizes pose SLAM [32], where only poses are included in the graph, ensuring efficiency and optimal map construction.”
Dual-Layer Path Planning With Pose SLAM for Autonomous Exploration in GPS-Denied Environments
Shi, Z., Cui, R., Yan, W., & Li, Y. (2023) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2023.3288187 · Cited by 35
“Inspired by Ila et al. [30], we update D n and Σ ( n ) using a mixed Kalman-information filter.”
MethodTrajectory-Based Visual Localization in Underwater Surveying Missions
Burguera, A., Font, F. B., & Oliver, G. (2015) · Sensors · doi:10.3390/s150101708 · Cited by 35
“This is consistent with [25], where the authors reduce the computation time by avoiding non-informative poses.”
BackgroundInfluentialOn the Structure of Nonlinearities in Pose Graph
Wang, H., Hu, G., Huang, S., & Dissanayake, G. (2012) · Robotics: Science and Systems VIII · doi:10.15607/rss.2012.viii.054 · Cited by 31
“In pose graph SLAM, the property that the Jacobian and information matrix are exactly sparse [14] has been exploited in most of the recent efficient pose graph SLAM algorithms.”
MethodFast covariance recovery in incremental nonlinear least square solvers
Ila, V., Polok, L., Šolony, M., Smrž, P., & Zemčík, P. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139841 · Cited by 32
“In our multimedia attachment1, we demonstrate the usefulness of the incremental covariances calculation in a data association context, where the number of expensive sensor registrations can be reduced by applying distance tests [11].”
BackgroundMethodSelf-citationWarped Gaussian Processes Occupancy Mapping With Uncertain Inputs
Jadidi, M. G., Miro, J. V., & Dissanayake, G. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2017.2651154 · Cited by 31
“The core idea is to map the target values through a warping (transforming) function to capture the nonlinear behavior of the observations.”
BackgroundMethodIncremental unsupervised topological place discovery
Murphy, L., & Sibley, G. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907022 · Cited by 30
“Recently, attention in the field has turned towards enabling compact graph-based approaches that can operate robustly over the long-term, through information theory based approaches to pruning the graph [4] [5] or by deleting out-of-date views [6].”
BackgroundElibol, A., Gracias, N., & García, R. (2010) · Journal of Field Robotics · doi:10.1002/rob.20357 · Cited by 30
Long-term simultaneous localization and mapping with generic linear constraint node removal
Carlevaris‐Bianco, N., & Eustice, R. M. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696478 · Cited by 29
“In [11], an information-theoretic approach is used to slow the rate of the graph growth by avoiding the addition of uninformative poses.”
MethodIncremental light bundle adjustment for robotics navigation
Indelman, V., Melim, A., & Dellaert, F. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696615 · Cited by 29
“In pose-SLAM approaches, pairs of poses are linked using relative pose constraints that are straightforward to estimate in a stereo camera setup [7], [17], but become more challenging when relying only on a single camera.”
BackgroundKopitkov, D., & Indelman, V. (2017) · The International Journal of Robotics Research · doi:10.1177/0278364917721629 · Cited by 27
“, 2012), with decision corresponding to determining what nodes to marginalize out (Ila et al., 2010; Kretzschmar and Stachniss, 2012), and avoiding the resulting fill-in in an information matrix by resorting to sparse approximations of the latter (Carlevaris-Bianco et al.”
BackgroundMethodInfluentialA convex optimization based approach for pose SLAM problems
Liu, M., Huang, S., Dissanayake, G., & Wang, H. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6385742 · Cited by 26
“Since the state vector only contains the robot poses and only nearby poses have relative pose constraints, pose SLAM problem has exactly sparse information matrix [2].”
BackgroundDense entropy decrease estimation for mobile robot exploration
Vallvé, J., & Andrade‐Cetto, J. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907755 · Cited by 25
“For each pose in the Pose SLAM graph, we annotate the cells inside their match area in a C-space grid with the corresponding information gain.”
BackgroundInfluentialSelf-citationUncertainty-Aware Autonomous Robot Exploration Using Confidence-Rich Localization and Mapping
Xu, Y., Zheng, R., Zhang, S., Liu, M., & Yu, J. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3360442 · Cited by 24
“The OGMI and CRMI both use Gmapping [17] as the localization method, while GPVR and UGPVR both use Pose SLAM [21] instead to provide the pose uncertainty as in [14].”
Pose-graph SLAM sparsification using factor descent
Vallvé, J., Solà, J., & Andrade‐Cetto, J. (2019) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2019.06.004 · Cited by 24
“[8] V. Ila, J. M. Porta, J. Andrade-Cetto, Information-based compact Pose SLAM, IEEE Trans.”
BackgroundSelf-citationA brain-inspired compact cognitive mapping system
Zeng, T., & Si, B. (2020) · Cognitive Neurodynamics · doi:10.1007/s11571-020-09621-6 · Cited by 24
Recent advances on simultaneous localization and mapping for mobile robots
Zamora, E., & Yu, W. (2013) · IETE Technical Review · doi:10.4103/0256-4602.125671 · Cited by 23
“[51] introduced an information‑based compact pose SLAM to reduce the computational cost by adding only highly informative loop‑closure links and non‑redundant poses to the robot path.”
BackgroundSLIM: Scalable and Lightweight LiDAR Mapping in Urban Environments
Yu, Z., Qiao, Z., Liu, W., Yin, H., & Shen, S. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3554400 · Cited by 22
“In pose graph-based SLAM, sensing information on poses can compact the graph structure [65], [66].”
Two-Stage Focused Inference for Resource-Constrained Collision-Free Navigation
Mu, B., Agha–mohammadi, A., Paull, L., Graham, M. C., How, J. P., & Leonard, J. J. (2015) · Robotics: Science and Systems · doi:10.15607/rss.2015.xi.004 · Cited by 22
“Upon further inspection of (15), calculating J k Λ −1 zk−1 Jk has a computational complexity of O(|x{k}|(4)) (similar to [5]).”
BackgroundMethodInfluentialEfficient Topology Estimation for Large Scale Optical Mapping
Elibol, A., Gracias, N., & García, R. (2012) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-30313-5 · Cited by 21
“[55] proposed a method to keep the most informative links between robot poses using mutual information within a SLAM context, which relates to the work in this chapter.”
MethodValencia, R., & Andrade‐Cetto, J. (2017) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-60603-3_5 · Cited by 21
Self-citationEfficient Autonomous Exploration and Mapping in Unknown Environments
Feng, A., Xie, Y., Sun, Y., Wang, X., Jiang, B., & Xiao, J. H. (2023) · Sensors · doi:10.3390/s23104766 · Cited by 20
“Based on this, Ila et al. [37] de-fined an MI gain and selected paths that minimize map entropy to explore the environment.”
BackgroundKim, A., & Eustice, R. M. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094820 · Cited by 20
“More intelligently, we could additionally calculate the predicted information gain that would be obtained from making such a measurement—retaining only those candidate links that have high expected information gain [1].”
BackgroundMethodInfluentialOn the Redundancy Detection in Keyframe-Based SLAM
Schmuck, P., & Chli, M. (2019) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00071 · Cited by 20
“[14] move the distance criterion to the information space and apply it to filterbased SLAM, adding only measurements to the estimate”
MethodA unified resource-constrained framework for graph SLAM
Paull, L., Huang, G. P., & Leonard, J. J. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487268 · Cited by 19
“[11] provided a relative information metric to evaluate whether edges should even be added to the pose graph in the first place, as well as to remove uninformative loop closure constraints.”
BackgroundAdaptive localization and mapping with application to planetary rovers
Hidalgo‐Carrió, J., Poulakis, P., & Kirchner, F. (2018) · Journal of Field Robotics · doi:10.1002/rob.21790 · Cited by 19
“This article presents the research to develop a solution that models an error function to provide informative nodes in the graph, as in Ila et al. (2010) but adapting to the current navigation”
Mobile robot exploration with potential information fields
Vallvé, J., & Andrade‐Cetto, J. (2013) · European Conference on Mobile Robots · doi:10.1109/ecmr.2013.6698846 · Cited by 18
“In Pose SLAM [14], a probabilistic estimate of the robot pose history is maintained as a sparse graph.”
BackgroundSelf-citationRobust point cloud registration based on semantic iterative closest point algorithm
Du, S., Shao, T., Tang, C., Zeng, W., & Tian, Z. (2025) · Fundamental Research · doi:10.1016/j.fmre.2024.04.025 · Cited by 17
Invariant filtering for Pose EKF-SLAM aided by an IMU
Barrau, A., & Bonnabel, S. (2015) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2015.7402522 · Cited by 17
Active Visual SLAM with Exploration for Autonomous Underwater Navigation.
Kim, A. (2012) · Deep Blue (University of Michigan) · Cited by 16
Chojnacki, M., & Indelman, V. (2018) · International Journal of Micro Air Vehicles · doi:10.1177/1756829318756354 · Cited by 16
“g2v xl; xm; zl; zm ð Þ 1⁄4 ql ðtl!m qmÞ (23)”
A review of optimisation strategies used in simultaneous localisation and mapping
Huang, S. (2018) · Journal of Control and Decision · doi:10.1080/23307706.2018.1552207 · Cited by 16
“One strategy is use keyframes (Ila et al., 2010; Konolige & Agrawal, 2009) where only poses with highly informative measurements are added.”
MethodAn homogeneous space geometry for simultaneous localisation and mapping
Mahony, R. E., Hamel, T., & Trumpf, J. (2021) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2021.04.012 · Cited by 16
Simultaneous Localization and Mapping
Stachniss, C. (2016) · Springer eBooks · doi:10.1007/978-3-662-46900-2_49-2 · Cited by 16
Ila, V., Porta, J. M., & Andrade‐Cetto, J. (2011) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2011.02.010 · Cited by 14
“This can be done, for instance, in logarithmic time per iteration using a tree structures [15, 19] or even in constant time using grid techniques when covariances are bounded [20].”
BackgroundMethodInfluentialSelf-citationRobot-Beacon Distributed Range-Only SLAM for Resource-Constrained Operation
Torres‐González, A., Dios, J. R. M., & Ollero, A. (2017) · Sensors · doi:10.3390/s17040903 · Cited by 14
“Work [20] developed an approach that selects highly informative loop-closure links to simplify the Pose SLAM information form and reduce its computational cost.”
BackgroundTorres‐González, A., Dios, J. R. M., & Ollero, A. (2014) · Sensors · doi:10.3390/s140507684 · Cited by 13
“Different devices have been used to provide this kind of information, e.g., wireless sensor network (WSN) nodes [1–3] or RFID units [11,12].”
MethodPath Planning in Belief Space with Pose SLAM
Valencia, R., & Andrade‐Cetto, J. (2017) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-60603-3_4 · Cited by 13
Self-citationLocation utility-based map reduction
Steiner, T. J., Huang, G. P., & Leonard, J. J. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139223 · Cited by 13
“[16] only add measurements when they are sufficiently distant in information space.”
BackgroundPose Graph Compression for Laser-Based SLAM
Stachniss, C., & Kretzschmar, H. (2016) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-29363-9_16 · Cited by 13
“[9] propose to only incorporate non-redundant poses and informative constraints based on the relative distance between poses in information space and the expected information gain of candidate loop closures.”
Background
Metadata
- Authors
- Ila, V., Porta, J. M., & Andrade-Cetto, J.
- Affiliations
- Georgia Institute of Technology (US)
- Consejo Superior de Investigaciones Científicas (ES)
- ORCID
- Venue
- IEEE Transactions on Robotics
- Published
- 2010-02
- Volume
- 26
- Issue
- 1
- Pages
- 78-93
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W2096052462
- Cited by
- 183
- References
- 46
- Citations by year
- 2026: 3 · 2025: 3 · 2024: 7 · 2023: 6 · 2022: 6 · 2021: 6 · 2020: 11 · 2019: 13 · 2018: 16 · 2017: 19 · 2016: 20 · 2015: 15 · 2014: 18 · 2013: 14 · 2012: 11
- FWCI
- 16.83
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Locations
- IEEE Transactions on Robotics (publishedVersion)
- LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) (publishedVersion, other-oa)
- UPCommons institutional repository (Universitat Politècnica de Catalunya) (publishedVersion, other-oa)
- DIGITAL.CSIC (Spanish National Research Council (CSIC)) (submittedVersion, other-oa)
- RECERCAT (Consorci de Serveis Universitaris de Catalunya) (submittedVersion, public-domain)
- Funders
- European Commission
- Ministerio de Ciencia e Innovación
- 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
- information filter, loop closure, data association, expected information gain, open-loop operation, balanced trees, interval arithmetic, robot trajectory estimation, computational efficiency
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.