A hybrid SLAM representation for dynamic marine environments
The DOI matches its Crossref record; 19 of the 20 references it cites were found in a registry or an index.
Abstract
We present a hybrid SLAM system for marine environments that combines cubic splines to represent the trajectories of dynamic objects, point features to represent stationary objects and an occupancy grid to represent land masses. This hybrid representation enables SLAM to be applied in environments with moving objects, where solutions using point features alone are computationally prohibitive or where dense objects e.g. landmasses can not be represented correctly using point features. Estimation is achieved using a sliding window framework with reversible data-association and reversible model-selection. Our main contributions are: (i) a hybrid representation of the environment; (ii) occupancy grid fusion is continually refined for the duration of the sliding window; (iii) the trajectories of dynamic objects are represented using cubic splines and (iv) radar scans are re-rendered at a sub-scan resolution to compensate for the egomotion during the scan acquisition period. We show that the continual refinement of the occupancy grid greatly improves the quality of the resultant map, leading to a better estimate of the egomotion and therefore better estimates of the trajectories of dynamic objects. We also demonstrate that the use of cubic splines to represent trajectories has two major advantages: (i) the state space is compressed i.e. many vehicle poses can be represented using a single spline section and (ii) the trajectory becomes continuous and so fusing information from asynchronous sensors running at multiple frequencies becomes trivial. The efficacy of our system is demonstrated using real marine radar data, showing that it can successfully estimate the positions/velocities of objects and landmasses observed during a typical voyage on a small boat.
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
“The first SLAM approach of this class was proposed by Bibby and Reid using cubic-splines to represent the continuous trajectory of the robot [12].”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [12]
In the citing paper
“In their approach the nodes in the factor graph represented the control-points (knots) of the spline which were optimized in a sliding window fashion.”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [12]
In the citing paper
“Using a continuoustime framework [12], the estimated trajectory can be approximated by a smooth curve in the space of rigid-body motions using basis functions (e.g., cubic splines), and optimized according to the observed events [177].”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [12]
Citations
Cites
Maximum Likelihood from Incomplete Data Via the EM Algorithm
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1977.tb01600.x · Cited by 50,444
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066
Pattern Recognition and Machine Learning
(2007) · Kybernetes · doi:10.1108/03684920710743466 · Cited by 8,265
Thrun, S. (2002) · Communications of the ACM · doi:10.1145/504729.504754 · Cited by 7,994
Bar‐Shalom, Y. (1988) · Medical Entomology and Zoology · Cited by 3,157
A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants
Neal, R. M., & Hinton, G. E. (1998) · Learning in Graphical Models · doi:10.1007/978-94-011-5014-9_12 · Cited by 2,187 · cited 2×
“The sliding window is used to continually refine the egomotion trajectory and the occupancy grid (similar to [16]), using generalised expectation maximisation [11][8].”
BackgroundMethodSonar-based real-world mapping and navigation
Elfes, A. (1987) · IEEE Journal on Robotics and Automation · doi:10.1109/jra.1987.1087096 · Cited by 1,397
Sensor Fusion in Certainty Grids for Mobile Robots
Moravec, H. P. (1989) · Sensor Devices and Systems for Robotics · doi:10.1007/978-3-642-74567-6_19 · Cited by 964
Square 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
A Probabilistic Approach to Concurrent Mapping and Localization for Mobile Robots
Thrun, S., Burgard, W., & Fox, D. (1998) · Machine Learning · doi:10.1023/a:1007436523611 · Cited by 789
Research works printed but not linked: 1
- sibley, 2007, Constant time sliding window filter SLAM as a basis for metric visual perception, Proc IEEE Int'l Conf on Robotics and Automation
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
“Using a continuous-time framework [13], the esti-”
Self-citationPast, 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
Self-citationCoSLAM: Collaborative Visual SLAM in Dynamic Environments
Zou, D., & Tan, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.104 · Cited by 382
Continuous-time batch estimation using temporal basis functions
Furgale, P., Barfoot, T. D., & Sibley, G. (2012) · 2012 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2012.6225005 · Cited by 259
“The work that is most closely related to ours is that of Bibby et al. [26].”
Continuous-time Gaussian process motion planning via probabilistic inference
Mukadam, M., Dong, J., Yan, X., Dellaert, F., & Boots, B. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364918790369 · Cited by 224
Continuous-Time Visual-Inertial Odometry for Event Cameras
Mueggler, E., Gallego, G., Rebecq, H., & Scaramuzza, D. (2018) · IEEE Transactions on Robotics · doi:10.1109/tro.2018.2858287 · Cited by 193
“The continuous-time framework was also motivated to allow data fusion of multiple sensors working at different rates and to enable increased temporal resolution [6].”
BackgroundSonugür, G. (2022) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2022.104342 · Cited by 154
Batch Continuous-Time Trajectory Estimation as Exactly Sparse Gaussian Process Regression
Barfoot, T., Tong, C. H., & Särkkä, S. (2014) · Robotics: Science and Systems · doi:10.15607/rss.2014.x.001 · Cited by 166
“, linear, spline) directly between nearby discrete poses [3, 4, 9, 15, 19, 29].”
BackgroundLovegrove, S., Patron-Perez, A., & Sibley, G. (2013) · Procedings of the British Machine Vision Conference 2013 · doi:10.5244/c.27.93 · Cited by 106
“A 2D spline-based continuous trajectory representation for a SLAM system is introduced in [4],”
MethodA Spline-Based Trajectory Representation for Sensor Fusion and Rolling Shutter Cameras
Patron-Perez, A., Lovegrove, S., & Sibley, G. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0811-3 · Cited by 104
“A 2D spline-based continuous trajectory representation for a SLAM system is introduced by Bibby and Reid (2010), where splines are used to represent the trajectories of tracked objects, providing a substantial reduction of the state space.”
MethodJoint Smoothing and Tracking Based on Continuous-Time Target Trajectory Function Fitting
Li, T., Chen, H., Sun, S., & Corchado, J. M. (2018) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2018.2882641 · Cited by 116
Anderson, S., & Barfoot, T. D. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353368 · Cited by 132
“Beyond this, more general local motions in the form of splines can enforce smoothness over longer time windows [16], [17], [18], [19], [20].”
BackgroundBatch nonlinear continuous-time trajectory estimation as exactly sparse Gaussian process regression
Anderson, S., Barfoot, T. D., Tong, C. H., & Särkkä, S. (2015) · Autonomous Robots · doi:10.1007/s10514-015-9455-y · Cited by 87
“One approach to continuous-time trajectory representation is to use interpolation (e.g., linear, spline) directly be-tween nearby discrete poses (Bibby and Reid, 2010; Bosse and Zlot, 2009; Dong and Barfoot, 2012; Furgale et al., 2012; Hedborg et al., 2012; Lovegrove et al., 2013).”
BackgroundSimultaneous Localization And Mapping: Present, Future, and the Robust-Perception Age.Preprint
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I. D., & Leonard, J. J. (2016) · arXiv (Cornell University) · Cited by 90
Self-citationContinuous-time batch trajectory estimation using temporal basis functions
Furgale, P., Tong, C. H., Barfoot, T. D., & Sibley, G. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364915585860 · Cited by 79
“, 2010)) as we believe it presents many benefits in terms of reduced state variable size and easy handling of asynchronous measurements (Bibby and Reid, 2010).”
BackgroundInfluentialGaussian Process Gauss–Newton for non-parametric simultaneous localization and mapping
Tong, C. H., Furgale, P., & Barfoot, T. D. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913478672 · Cited by 68
“This approach can be extended to the continuous-time domain by utilizing a continuous state representation, such as piecewise splines (Bibby and Reid, 2010; Fur-gale et al., 2012).”
Towards relative continuous-time SLAM
Anderson, S., & Barfoot, T. D. (2013) · 2013 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2013.6630700 · Cited by 51
“The use of cubic splines to parameterize the robot trajectory can also be seen in the estimation schemes derived by Bibby and Reid [16], and Fleps et al.”
MethodContinuous-Time Trajectory Estimation for Event-based Vision Sensors
Mueggler, E., Gallego, G., & Scaramuzza, D. (2015) · Robotics: Science and Systems XI · doi:10.15607/rss.2015.xi.036 · Cited by 49
“Instead, we adopt a continuous-time framework approach [7] that solves the previous issues and has additional advantages.”
BackgroundMethodInfluentialDirect semi-dense SLAM for rolling shutter cameras
Kim, J.-H., Cadena, C., & Reid, I. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487263 · Cited by 46
“More recent efforts, inspired by the work of [3] who proposed a planar (3-DOF) ego-motion trajectory representation using cubic B-splines, have considered full 6-DOF representations using splines [15], [11].”
BackgroundSelf-citationContinuous-Time Visual-Inertial Odometry for Event Cameras
Mueggler, E., Gallego, G., Rebecq, H., & Scaramuzza, D. (2019) · Zurich Open Repository and Archive (University of Zurich) · doi:10.5167/uzh-175988 · Cited by 46
A hierarchical wavelet decomposition for continuous-time SLAM
Anderson, S., Dellaert, F., & Barfoot, T. D. (2014) · 2014 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2014.6906884 · Cited by 44
“The works by Bibby and Reid [10] and Fleps et al. [11] also exhibit the use of uniformly spaced B-splines to parameterize the robot trajectory in a global frame.”
MethodPose Interpolation for Laser‐based Visual Odometry
Tong, C. H., Anderson, S., Dong, H., & Barfoot, T. D. (2014) · Journal of Field Robotics · doi:10.1002/rob.21537 · Cited by 37
“This approach is discussed in Bosse and Zlot (2009), with recent examples utilizing a piecewise spline representation of the state (Bibby & Reid, 2010; Furgale, Barfoot, & Sibley, 2012) and a Gaussian process in GPGN (Tong et al., 2013).”
MethodPöppl, F., Neuner, H., Mandlburger, G., & Pfeifer, N. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.12.022 · Cited by 43
Dong, J., Mukadam, M., Boots, B., & Dellaert, F. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8461077 · Cited by 45
“Several popular continuous-time trajectory representations include linear interpolation [3], [4], [5], splines [6], [7], [8], [9], [10], and hierarchical wavelets [11].”
BackgroundContinuous-Time State Estimation Methods in Robotics: A Survey
Talbot, W., Nubert, J., Tuna, T., Cadena, C., Dümbgen, F., Tordesillas, J., Barfoot, T. D., & Hutter, M. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3593079 · Cited by 59
“6] [138].”
InfluentialGaussian Process Gauss-Newton: Non-Parametric State Estimation
Tong, C.-H., Furgale, P., & Barfoot, T. (2012) · 2012 Ninth Conference on Computer and Robot Vision · doi:10.1109/crv.2012.35 · Cited by 29
“This probabilistic representation accounts for uncertainty in the observations, and natively suppresses model complexity to avoid overfitting.”
BackgroundGaussian Process Gauss-Newton for 3D laser-based Visual Odometry
Tong, C. H., & Barfoot, T. D. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631321 · Cited by 29
Robotics: Science and Systems X
(2014) · doi:10.15607/rss.2014.x · Cited by 24
Fitting for smoothing: A methodology for continuous-time target track estimation
Li, T., Prieto, J., & Corchado, J. M. (2016) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2016.7743582 · Cited by 19
“In addition to aforementioned [39-42], fitting has been applied for likelihood calculation to speed up particle filtering [30].”
BackgroundMethodAnderson, S., MacTavish, K., & Barfoot, T. D. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364915589642 · Cited by 19
“The use of uniformly spaced cubic B-splines to parameterize the robot trajectory can also be seen in the estimation schemes derived by Bibby and Reid (2010) and Fleps et al. (2011).”
MethodSheehan, M., Harrison, A., & Newman, P. M. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696382 · Cited by 22
“Bibby and Reid [4] represent vehicle trajectories using cubic splines enabling the use of a SLAM system for a dynamic nautical environment using radar data.”
MethodSparse Gaussian Processes for Continuous-Time Trajectory Estimation on Matrix Lie GroupsPreprint
Dong, J., Boots, B., & Dellaert, F. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.06020 · Cited by 23
“Several popular continuous-time trajectory representations include linear interpolation [10], [11], [12], splines [13], [14], [15], [16], [17], [18], and hierarchical wavelets [19], all of which have been used in both filtering and batch estimation approaches.”
BackgroundA mobile ground-based radar sensor for detection and tracking of moving objects
Vivet, D., Checchin, P., Chapuis, R., Faure, P., Rouveure, R., & Monod, M. (2012) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/1687-6180-2012-45 · Cited by 18
“In the naval field [25], the use of radar sensor for SLAM(MOT) application is self-evident but in ground mobile robotics few works use such a kind of sensor.”
Continuous-Time Visual-Inertial Trajectory Estimation with Event Cameras.Preprint
Mueggler, E., Gallego, G., Rebecq, H., & Scaramuzza, D. (2017) · arXiv (Cornell University) · Cited by 14
Dynamic EKF-based SLAM for autonomous mobile convergence platforms
Oh, S., Hahn, M., & Kim, J. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2093-0 · Cited by 13
“Recently, Bibby and Reid proposed a hybrid SLAM framework that combines an occupancy grid to represent land masses, point features to denote stationary objects, and cubic splines to show the trajectories of dynamic objects [3].”
BackgroundTirado, J., & Civera, J. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3180427 · Cited by 11
A Track-oriented Approach to Target Tracking with Random Finite Set Observations
Li, T., Wang, X., Liang, Y., Yan, J., & Fan, H. (2019) · International Conference on Control, Automation and Information Sciences (ICCAIS) · doi:10.1109/iccais46528.2019.9074599 · Cited by 9
“Continuous time trajectory estimation has also received attention in the context of mobile robot simultaneous localization and mapping [40], [41] and visual tracking [42], [43].”
BackgroundLodeStar: Maritime Radar Descriptor for Semi-Direct Radar Odometry
Jang, H., Jung, M., Jeon, M., & Kim, A. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3349960 · Cited by 8
“However, existing marine odometry with scanning radar have primarily focused on features [17], [18], [19].”
BackgroundDuymaz, E., Oğuz, A. E., & Temeltaş, H. (2017) · Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi · doi:10.17341/gazimmfd.369697 · Cited by 8
“Daha sonra gelişmiş filtre yapısı nedeniyle daha az hata üreten yaklaşımlar deniz ve hava platformlarına da uygulanmıştır [16, 17].”
A survey of crowdsourcing-based indoor map learning methods using smartphones
Li, W., Xu, X., Wang, Y., & Li, D. (2022) · Results in Control and Optimization · doi:10.1016/j.rico.2022.100186 · Cited by 9
The hybrid Cramér-Rao lower bound for simultaneous self-localization and room geometry estimation
Veisman, M., Noam, Y., & Gannot, S. (2021) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-020-00702-6 · Cited by 6
“, drone navigation [1], vehicles in urban areas [2], or marine vessels [3, 4] in ports.”
BackgroundPractical Pose Trajectory Splines With Explicit Regularization
Persson, M., Hager, G., Ovrén, H., & Forssén, P.-E. (2021) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv53792.2021.00026 · Cited by 7
“[6] discuss the connection between spline parameters and the constraints on dynamics.”
BackgroundMethodRandom Fourier Features based SLAM
Kapushev, Y., Kiskun, A., Ferrer, G., & Burnaev, E. V. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636819 · Cited by 4
“The use of cubic splines to parameterize the robot trajectory can also be seen in the estimation schemes in [15], [16], [17].”
MethodDecoupled Representation of the Error and Trajectory Estimates for Ef_cient Pose Estimation
Zheng, X. H., Li, M., & Mourikis, A. I. (2015) · Robotics: Science and Systems · doi:10.15607/rss.2015.xi.009 · Cited by 5
“Earlier works using spline-based representations of the trajectory can be found in [3, 2, 4].”
MethodPerformance analysis of filter based airborne simultaneous localization and mapping methods
Duymaz, E., Oğuz, A. E., & Temeltaş, H. (2015) · International Conference on Recent Advances in Space Technologies · doi:10.1109/rast.2015.7208333 · Cited by 3
Distributed processing of spatiotemporal ocean data: a survey
Li, X., Gu, J., Tan, G., Jiang, W., Cui, A., Shu, L., Ren, K., Zhu, H., Shang, J. S., & Xu, Z. (2022) · World Wide Web · doi:10.1007/s11280-022-01067-6 · Cited by 3
“[20] proposed a hybrid representation method for ocean environment, where stationary objects are represented by point features and trajectories of dynamic objects are represented by cubic splines.”
BackgroundNear-Shore Mapping for Detection and Tracking of Vessels
Dalhaug, N., Stahl, A., Mester, R., & Brekke, E. (2025) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion65864.2025.11124013 · Cited by 2
A Metric for Multi-Target Continuous-Time Trajectory Evaluation
Xin, Y., Yan, S. H., & Li, T. (2022) · International Conference on Control, Automation and Information Sciences (ICCAIS) · doi:10.1109/iccais56082.2022.9990087 · Cited by 2
Visual Odometryin Principle and Practice
Persson, M. (2022) · Linköping studies in science and technology. Dissertations · doi:10.3384/9789179291693 · Cited by 1
Localization and Mapping from Shore Contours and Depth
Codd-Downey, R. (2017) · YorkSpace (York University) · Cited by 1
Continuous Models for Cameras and Inertial Sensors
Ovrén, H. (2018) · Linköping studies in science and technology. Dissertations · doi:10.3384/diss.diva-148766 · Cited by 1
Distributed Processing of Ocean Spatiotemporal Data: A SurveyPreprint
Li, X., Gu, J., Tan, G., Jiang, W., Cui, A., Shu, L., Ren, K., Zhu, H., & Xu, Z. (2022) · Research Square · doi:10.21203/rs.3.rs-1595392/v1
Soliman, A. (2023) · theses.fr (ABES) · doi:10.70675/32a52416z7918z4954z8b84ze91dda8e76dc
Metadata
- Authors
- Bibby, C., & Reid, I.
- Affiliations
- University of Oxford (GB)
- ORCID
- Reid, Ian
- Venue
- 2010 IEEE International Conference on Robotics and Automation
- Publisher
- IEEE
- Published
- 2010-05
- Pages
- 257-264
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2000668356
- Cited by
- 53
- References
- 20
- Citations by year
- 2025: 2 · 2024: 1 · 2023: 2 · 2022: 7 · 2021: 3 · 2019: 2 · 2018: 5 · 2017: 4 · 2016: 5 · 2015: 8 · 2014: 5 · 2013: 5 · 2012: 4
- FWCI
- 5.73
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
- Adelaide Research & Scholarship (AR&S) (University of Adelaide) (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
- cubic splines, rolling window estimation, camera motion estimation
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.