The DOI matches its Crossref record; 223 of the 242 references it cites were found in a registry or an index; 12 of the 229 sources its claims cite were checked for support.
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age
Open accessAbstract
Simultaneous localization and mapping (SLAM) consists in the concurrent construction of a model of the environment (the map), and the estimation of the state of the robot moving within it. The SLAM community has made astonishing progress over the last 30 years, enabling large-scale real-world applications and witnessing a steady transition of this technology to industry. We survey the current state of SLAM and consider future directions. We start by presenting what is now the de-facto standard formulation for SLAM. We then review related work, covering a broad set of topics including robustness and scalability in long-term mapping, metric and semantic representations for mapping, theoretical performance guarantees, active SLAM and exploration, and other new frontiers. This paper simultaneously serves as a position paper and tutorial to those who are users of SLAM. By looking at the published research with a critical eye, we delineate open challenges and new research issues, that still deserve careful scientific investigation. The paper also contains the authors' take on two questions that often animate discussions during robotics conferences: Do robots need SLAM? and Is SLAM solved?
Overview
CoChat Summary
TL;DR
This position paper/tutorial surveys 30 years of SLAM, presents the de-facto standard MAP/factor-graph formulation, and argues that SLAM is entering a “robust-perception age” defined by robustness, high-level understanding, resource awareness, and task-driven perception. It concludes that SLAM is not solved as an academic endeavor and that its necessity is application-dependent, though often the answer is yes.
Key findings
- The paper identifies four key requirements for the robust-perception age: robust performance, high-level understanding, resource awareness, and task-driven perception.
- It answers “Do robots need SLAM?” by arguing that SLAM remains necessary for globally consistent maps, loop closure, topology recovery, and applications such as exploration, inspection, and self-driving cars; visual-inertial odometry is described as a reduced SLAM system with loop closure disabled, with drift <0.5% of trajectory length.
- It answers “Is SLAM solved?” by saying the question requires specifying a robot/environment/performance combination; 2D indoor laser SLAM with <10 cm accuracy and low failure rate is “largely solved,” while fast dynamics, highly dynamic environments, strict real-time control, long-term autonomy, and resource-constrained platforms remain open.
- Open challenges include fail-safe/self-tuning SLAM, robust data association and outlier rejection, long-term map maintenance, scalable/distributed mapping, high-level metric and semantic representations, theoretical guarantees, active SLAM, new sensors, and deep learning; event cameras are reported as having 1 ms latency, up to 1 MHz update rate, 140 dB dynamic range vs 60–70 dB for standard cameras, 20 mW vs 1.5 W power, and QVGA spatial resolution.
Methods
- Design: survey, position paper, and tutorial that summarizes and extends the RSS 2015 workshop “The Problem of Mobile Sensors: Setting future goals and indicators of progress for SLAM.”
- Data/sample: no new experimental dataset; the paper reviews published SLAM literature across classical age (1986–2004), algorithmic-analysis age (2004–2015), and the proposed robust-perception age.
- Analysis: qualitative synthesis of SLAM formulations, robustness, scalability, metric and semantic representations, theoretical tools, active SLAM, new sensors, and deep learning, with open problems and the authors’ answers to two community questions.
Limitations
- Stated: the paper is a position paper/tutorial offering “the perspective of part of the community,” not a systematic review; its main focus is metric and semantic SLAM, with topological SLAM deferred to Lowry et al.
- Stated: the paper discusses many open problems rather than providing solutions, and repeatedly notes that several areas lack cohesive formulations or grounded answers.
- Evident: there is no empirical validation, benchmark experiment, or new dataset in the paper; quantitative figures are cited from prior work rather than generated by this study.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
10 Valid · 20 Not valid · 138 Not checked · 115 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“the SLAM research done over the last decade has itself produced the visual-inertial odometry algorithms that currently represent the state of the art, e.g., [163, 175]”
What the sources say
- Partly supportedcites [163] [163] S. Lynen, T. Sattler, M. Bosse, J. Hesch, M. Pollefeys, and R. Siegwart. Get out of my lab: Large-scale, real-time visual-inertial localization. In Proceedings of Robotics: Science and Systems Conference (RSS) , pages 338-347, 2015. - sourceExperimental — accuracy not yet measured
The Introduction (p. 1) describes state-of-the-art visual-inertial localization and the use of SLAM for pose tracking; Local Pose Tracking (p. 4) describes the paper’s visual-inertial estimator. The paper does not establish the claim’s broader history—that a decade of SLAM research produced visual-inertial odometry algorithms that are, as a class, the state of the art. (LLM, conf=0.82)
- Not checked yetcites [175] [175] A. I. Mourikis and S. I. Roumeliotis. A Multi-State Constraint Kalman Filter for Vision-aided Inertial Navigation. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) , pages 3565-3572. IEEE, 2007. - source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, computing this joint probability analytically is, in general, computationally intractable [35, 76, 233].”
What the sources say
- Not checked yetcites [35] [35] L. Carlone, J. Du, M. Kaouk, B. Bona, and M. Indri. Active SLAM and Exploration with Particle Filters Using Kullback-Leibler Divergence. Journal of Intelligent & Robotic Systems , 75(2):291-311, 2014. - source
- Not checked yetcites [76] [76] N. Fairfield and D. Wettergreen. Active SLAM and Loop Prediction with the Segmented Map Using Simplified Models. In Proceedings of International Conference on Field and Service Robotics (FSR) , pages 173-182. Springer, 2010. - source
- Partly supportedcites [233] [233] C. Stachniss, G. Grisetti, and W. Burgard. Information Gain-based Exploration Using Rao-Blackwellized Particle Filters. In Proceedings of Robotics: Science and Systems Conference (RSS) , pages 65-72, 2005. - sourceExperimental — accuracy not yet measured
Our copy supports the weaker, adjacent point: the paper repeatedly says the exact quantities must be approximated because they are costly — Section V (p. 4) states that 'computing the expected information gain based on Eq. (16) is possible but requires a large amount of computational resources,' and Section II (p. 2) says that because they 'reason about a high-dimensional state estimation problem, we have to be content with approximative solutions that rely on strong assumptions'; Section IV (p. 3) likewise calls the trajectory-posterior uncertainty 'more difficult to compute.' What it does not state is the claim as phrased — that the joint probability of the posterior over pose and map is analytically intractable. On the contrary, Section III (p. 2) says the Rao-Blackwellized factorization 'can be solved efficiently since the quantity p(m|x_1:t, z_1:t) can be computed analytically,' and Section IV (p. 3) says 'we can efficiently compute the entropy of a Rao-Blackwellized particle filter for mapping.' So the 'possible but expensive / needs approximation' part is supported, while 'intractable' and the object (the joint posterior itself rather than the expected information gain) are not. (LLM, conf=0.68)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the 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].”
What the sources say
- Not checked yetcites [12] [12] C. Bibby and I. D. Reid. A hybrid SLAM representation for dynamic marine environments. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) , pages 1050-4729. IEEE, 2010. - source
- Supportedcites [177] [177] E. Mueggler, G. Gallego, and D. Scaramuzza. Continuous-Time Trajectory Estimation for Event-based Vision Sensors. In Proceedings of Robotics: Science and Systems Conference (RSS) , 2015. - source
The abstract (p. 1) states almost verbatim that the DVS pose trajectory 'is approximated by a smooth curve in the space of rigid-body motions using cubic splines and it is optimized according to the observed events' within a continuous-time framework. Section IV-A (p. 3) confirms the basis-function aspect: cumulative B-spline basis functions built via the Lie algebra 'produce smooth trajectories in the manifold of rigid-body motions SE(3)', and Sec. V-C2 (p. 4) describes the resulting finite-dimensional optimization of that curve. Sec. V-C (p. 5) shows the per-event pose evaluation and residual minimization against the observed events. (LLM, conf=0.94)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Likewise semantic labeling of pixels in a variety of scene types reaches performance levels of around 80% accuracy or more [74].”
What the sources say
- Partly supportedcites [74] [74] M. Everingham, L. Van-Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes (VOC) Challenge. International Journal of Computer Vision , 88(2):303-338, 2010. - sourceExperimental — accuracy not yet measured
Section 3.6.1 describes assigning class labels to pixels, and §4.2.1 says segmentation was evaluated by the percentage of pixels correctly labelled. Neither passage establishes that accuracy reached around 80% or more across a variety of scene types; §4.2.1 also cautions that its per-class accuracy measure can be misleading. (LLM, conf=0.81)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
In the paper
“mapping a 2D indoor environment with a robot equipped with wheel encoders and a laser scanner, with sufficient accuracy ( < 10 cm) and sufficient robustness (say, low failure rate), can be considered largely solved (an example of industrial system performing SLAM is the Kuka Navigation Solution [145]).”
What the sources say
- Not matchedcites [145] [145] Kuka Robotics. Kuka Navigation Solution. http://www.kuka-robotics. com/res/robotics/Products/PDF/EN/KUKA Navigation Solution EN. pdf, 2016. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
80 more claims
Create a free account to see all 283 claims and to verify the 147 references still open.
- Probably not a substantial claim. 154
- It may state two separate claims as one. 90
- The quote only partly states this claim. 1
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ I. INTRODUCTION · p. 3
“| 2011 | SLAM back-end | Grisetti et al. [97] |”
§ REFERENCES · p. 21
“[97] G. Grisetti, R. K¨ ummerle, C. Stachniss, and W. Burgard. A Tutorial on Graph-based SLAM. IEEE Intelligent Transportation Systems Magazine , 2(4):31-43, 2010.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ I. INTRODUCTION · p. 3
“| 2012 | Visual odometry | Scaramuzza and Fraundofer [85, 218] |”
§ REFERENCES · p. 24
“[218] D. Scaramuzza and F. Fraundorfer. Visual Odometry [Tutorial]. Part I: The First 30 Years and Fundamentals. IEEE Robotics and Automation Magazine , 18(4):80-92, 2011.”
Citations
Cites
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“recognition for the imagenet classes [213] can now, to an extent, be treated as a black box that works well from the perspective of the roboticist or SLAM researcher.”
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599 · cited 1×
“Likewise, semantic labeling of pixels in a variety of scene types reaches performance levels of around 80% accuracy or more [75].”
The Ecological Approach to Visual Perception: Classic Edition
Gibson, J. J. (2014) · doi:10.4324/9781315740218 · Cited by 12,132 · cited 1×
“obal pose of the car as a whole in a single and efficient operation as opposed to update, for 4The term affordances refers to the set of possible actions on a given object/environment by a given agent [110]. While the term actionability includes the expected utility of these actions. 5Reasoning in the sense of localiza…”
Vision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913 · cited 1×
“Topic References Data IMU GPS Labels LIDAR2D LIDAR3D LOC MAP RGB RGBD Stereo Front-ends and back-ends in small / medium scale scenarios [255] X [276] X [202] X [244] X [115, 207] X [108, 274, 275] X [96] X [26] X [218] X Back-ends in small / medium scale scenarios [32, 159] X Front-ends and back-ends in synthetic scen…”
Huber, P. J. (1981) · Wiley Series in Probability and Statistics · doi:10.1002/0471725250 · Cited by 7,066
ORB-SLAM: A Versatile and Accurate Monocular SLAM System
Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D. (2015) · IEEE Transactions on Robotics · doi:10.1109/tro.2015.2463671 · Cited by 6,778 · cited 4×
“They allow to build accurate and robust SLAM systems with automatic relocation and loop closing [179].”
InfluentialFactor 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 2×
“a maximum a posteriori estimation problem, and often use the formalism of factor graphs [143] to reason about the interde-”
Video Google: a text retrieval approach to object matching in videos
Sivic, & Zisserman (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238663 · Cited by 6,367 · cited 1×
“Bag-of-words models [226] avoid this in-”
Parallel Tracking and Mapping for Small AR Workspaces
Klein, G., & Murray, D. (2007) · 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2007.4538852 · Cited by 4,346 · cited 1×
“Some methods approximately decouple localization and mapping in two threads that run in parallel like Klein and Murray [135].”
Simultaneous localization and mapping: part I
Durrant-Whyte, H., & Bailey, T. (2006) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2006.1638022 · Cited by 4,199 · cited 4×
“oses a constraint on a pair of poses. MAP estimation has been proven to be more accurate and efficient than original approaches for SLAM, based on nonlinear filtering. We refer the reader to the survey [13, 86] for an overview on filtering approaches, and to [264] for a comparison between filtering and smoothing approache…”
Influential
Research works printed but not linked: 35
- mendel, 1995, Lessons in Estimation Theory for Signal Processing Communications and Control
- zhao, 0, Linear SLAM: A linear solution to the feature-based and pose graph SLAM based on submap joining, Proc IEEE/RSJ Int Conf Intell Robots Syst, 24
- carlone, 0, Selecting good measurements via $\ell _1$ relaxation: A convex approach for robust estimation over graphs, Proc IEEE/RSJ Int Conf Intell Robots Syst, 2667
- ni, 0, Multi-level submap based SLAM using nested dissection, Proc IEEE/RSJ Int Conf Intell Robots Syst, 2558
- cadena, 2015, Robotics: Science and systems (RSS), workshop
- kümmerle, 0, g2o: A general framework for graph optimization, Proc IEEE Int Conf Robot Autom, 3607
- mackay, 2002, Information Theory Inference & Learning Algorithms
- agarwal, 0, Bundle adjustment in the large, Proc Eur Conf Comput Vis, 29
- aulinas, 0, The SLAM Problem: A survey, Proc Int Conf of the Catalan Assoc Artif Intell, 363
- ferris, 0, WiFi-SLAM using Gaussian process latent variable models, Proc 20th Int Joint Conf Artif Intell, 2480
- pázman, 1986, Foundations of Optimum Experimental Design
- golovin, 2011, Adaptive submodularity: Theory and applications in active learning and stochastic optimization, J Artif Intell Res, 42, 427
- nüchter, 2009, 3D Robotic Mapping The Simultaneous Localization and Mapping Problem with Six Degrees of Freedom, 52
- gallego, 2016, Event-based, 6-DOF camera tracking for high-speed applications, CoRR, 1
- folkesson, 2006, Graphical SLAM for outdoor applications, J Field Robot, 23, 51
- foley, 1992, Computer Graphics Principles and Practice
- forster, 0, SVO: Semi-direct visual odometry for monocular and multi-camera systems, IEEE Trans Robot
- rebecq, 0, EVO: A geometric approach to event-based 6-DOF parallel tracking and mapping in real-time, IEEE Robot Autom Lett
- rényi, 0, On measures of entropy and information, Proc 4th Berkeley Symp Math Statist Prob, 547
- shah, 1995, Parametric and Feature-Based CAD/CAM Concepts Techniques and Applications
- shen, 0, Proc ACM SIGGRAPH, 896
- song, 0, Hilbert space embeddings of hidden Markov models, Proc Int Conf Mach Learning, 991
- thrun, 1995, Exploration in active learning, Handbook of Brain Science and Neural Networks, 381
- ackerman, 2014, Dyson's robot vacuum has 360-degree camera, tank treads, cyclone suction, IEEE Spectr
- kueng, 0, Low-latency visual odometry using event-based feature tracks, Proc IEEE/RSJ Int Conf Intell Robots Syst, 16
- absil, 2007, Optimization Algorithms on Matrix Manifolds
- thrun, 2005, Probabilistic Robotics
- henry, 0, RGB-D mapping: Using depth cameras for dense 3D modeling of indoor environments, Proc Int Symp Exp Robot, 477
- huang, 0, How far is SLAM from a linear least squares problem?, Proc IEEE/RSJ Int Conf Intell Robots Syst, 3011
- whelan, 0, Kintinuous: Spatially extended kinect fusion, Proc of the RGB-D Workshop on Advanced Reasoning with Depth Cameras at RSS
- bibby, 0, Simultaneous localisation and mapping in dynamic environments (SLAMIDE) with reversible data association, Proc Robot Sci Syst Conf, 105
- binford, 0, Visual perception by computer, Proc IEEE Syst Contr Conf, 116
- bloomenthal, 1997, Introduction to Implicit Surfaces
- yu, 0, Tactile exploration: Shape and pose recovery from planar pushing, Proc IEEE/RSJ Int Conf Intell Robots Syst, 1208
- zach, 0, A globally optimal algorithm for robust TV-L1 range image integration, Proc IEEE Int Conf Comput Vis, 1
Cited by
ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM
Campos, C., Elvira, R., Rodriguez, J. J. G., M. Montiel, J. M., & D. Tardos, J. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3075644 · Cited by 4,274
SuperGlue: Learning Feature Matching With Graph Neural Networks
Sarlin, P.-E., DeTone, D., Malisiewicz, T., & Rabinovich, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00499 · Cited by 2,830
Gallego, G., Delbruck, T., Orchard, G., Bartolozzi, C., Taba, B., Censi, A., Leutenegger, S., Davison, A. J., Conradt, J., Daniilidis, K., et al. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3008413 · Cited by 2,566
Self-citationPixel2Mesh: Generating 3D Mesh Models from Single RGB Images
Wang, N., Zhang, Y., Li, Z., Fu, Y., Liu, W., & Jiang, Y.-G. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01252-6_4 · Cited by 1,306
The grand challenges of Science Robotics
Yang, G.-Z., Bellingham, J., Dupont, P. E., Fischer, P., Floridi, L., Full, R., Jacobstein, N., Kumar, V., McNutt, M., Merrifield, R., et al. (2018) · Science Robotics · doi:10.1126/scirobotics.aar7650 · Cited by 1,177
Metadata
- Authors
- Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., & Leonard, J. J.
- Affiliations
- Massachusetts Institute of Technology (US)
- Pontificia Universidad Javeriana (CO)
- The University of Adelaide (AU)
- University of Zurich (CH)
- Universidad de Zaragoza (ES)
- Venue
- IEEE Transactions on Robotics
- Published
- 2016-12
- Volume
- 32
- Issue
- 6
- Pages
- 1309-1332
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W2461937780
- Cited by
- 3,596
- References
- 242
- Citations by year
- 2026: 425 · 2025: 453 · 2024: 485 · 2023: 412 · 2022: 441 · 2021: 418 · 2020: 360 · 2019: 310 · 2018: 210 · 2017: 80 · 2016: 2
- FWCI
- 244.70
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Robotics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Adelaide Research & Scholarship (AR&S) (University of Adelaide) (submittedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Zurich Open Repository and Archive (University of Zurich) (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- MINECO-FEDER (DPI2015-68905-P)
- DGA (T04-FSE)
- ARC (DP130104413, CE140100016, FL130100102)
- NCCR Robotics
- PUJ (6601)
- EU-FP7-ICT-Project TRADR (609763, EU-H2020-688652, SERI-15.0284)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Artificial Intelligence › Target Tracking and Data Fusion in Sensor Networks
- Keywords
- SLAM, robot mapping, robustness, scalability, semantic mapping, active SLAM, robot exploration, performance guarantees
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-04, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-04 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age. https://app.cochat.ai/papers/10.1109/tro.2016.2624754
- The paper
- Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., & Leonard, J. J. (2016). Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age. IEEE Transactions on Robotics. https://doi.org/10.1109/tro.2016.2624754
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.