{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T15:57:18Z","timestamp":1781107038665,"version":"3.54.1"},"reference-count":401,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100018237","name":"Air Force Asian Office of Aerospace Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018237","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Robotics and Autonomous Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.robot.2026.105535","type":"journal-article","created":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T15:28:43Z","timestamp":1778945323000},"page":"105535","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Semantic Visual Simultaneous Localization and Mapping: A survey on state of the art, challenges, and future directions"],"prefix":"10.1016","volume":"203","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6332-1002","authenticated-orcid":false,"given":"Thanh Nguyen","family":"Canh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1742-3754","authenticated-orcid":false,"given":"Haolan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7524-6529","authenticated-orcid":false,"given":"Xiem","family":"HoangVan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5736-0769","authenticated-orcid":false,"given":"Nak Young","family":"Chong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.robot.2026.105535_b1","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1177\/027836498600500404","article-title":"On the representation and estimation of spatial uncertainty","volume":"5","author":"Smith","year":"1986","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.robot.2026.105535_b2","doi-asserted-by":"crossref","DOI":"10.1109\/TRO.2023.3248510","article-title":"A survey on active simultaneous localization and mapping: State of the art and new frontiers","author":"Placed","year":"2023","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.robot.2026.105535_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.cosrev.2022.100510","article-title":"Visual SLAM for underwater vehicles: A survey","volume":"46","author":"Zhang","year":"2022","journal-title":"Comput. Sci. Rev."},{"key":"10.1016\/j.robot.2026.105535_b4","series-title":"2024 IEEE\/SICE International Symposium on System Integration","first-page":"899","article-title":"S3M: Semantic segmentation sparse mapping for UAVs with RGB-d camera","author":"Canh","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2022.104992","article-title":"A review of visual SLAM methods for autonomous driving vehicles","volume":"114","author":"Cheng","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"1","key":"10.1016\/j.robot.2026.105535_b6","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/TIE.2018.2826471","article-title":"A monocular vision sensor-based efficient SLAM method for indoor service robots","volume":"66","author":"Lee","year":"2018","journal-title":"IEEE Trans. Ind. Electron."},{"key":"10.1016\/j.robot.2026.105535_b7","doi-asserted-by":"crossref","first-page":"2453","DOI":"10.1109\/ACCESS.2018.2886627","article-title":"Augmented reality based on SLAM to assess spatial short-term memory","volume":"7","author":"Munoz-Montoya","year":"2018","journal-title":"IEEE Access"},{"issue":"9","key":"10.1016\/j.robot.2026.105535_b8","doi-asserted-by":"crossref","first-page":"3873","DOI":"10.1007\/s00371-022-02530-1","article-title":"A SLAM-based 6dof controller with smooth auto-calibration for virtual reality","volume":"39","author":"Jiang","year":"2023","journal-title":"Vis. Comput."},{"key":"10.1016\/j.robot.2026.105535_b9","series-title":"2016 IEEE International Conference on Robotics and Automation","first-page":"1271","article-title":"Real-time loop closure in 2D LIDAR SLAM","author":"Hess","year":"2016"},{"issue":"7","key":"10.1016\/j.robot.2026.105535_b10","doi-asserted-by":"crossref","first-page":"6907","DOI":"10.1109\/TITS.2021.3063477","article-title":"A comparative analysis of LiDAR SLAM-based indoor navigation for autonomous vehicles","volume":"23","author":"Zou","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.robot.2026.105535_b11","article-title":"A survey of state-of-the-art on visual SLAM","volume":"205","author":"Kazerouni","year":"2022","journal-title":"Expert Syst. Appl."},{"issue":"6","key":"10.1016\/j.robot.2026.105535_b12","doi-asserted-by":"crossref","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","article-title":"Orb-slam3: An accurate open-source library for visual, visual\u2013inertial, and multimap slam","volume":"37","author":"Campos","year":"2021","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.robot.2026.105535_b13","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1023\/A:1008854305733","article-title":"Globally consistent range scan alignment for environment mapping","volume":"4","author":"Lu","year":"1997","journal-title":"Auton. Robots"},{"key":"10.1016\/j.robot.2026.105535_b14","series-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"598","article-title":"Multi-view deep learning for consistent semantic mapping with rgb-d cameras","author":"Ma","year":"2017"},{"key":"10.1016\/j.robot.2026.105535_b15","series-title":"2017 IEEE International Conference on Robotics and Automation","first-page":"4628","article-title":"Semanticfusion: Dense 3d semantic mapping with convolutional neural networks","author":"McCormac","year":"2017"},{"key":"10.1016\/j.robot.2026.105535_b16","series-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"5079","article-title":"Meaningful maps with object-oriented semantic mapping","author":"S\u00fcnderhauf","year":"2017"},{"key":"10.1016\/j.robot.2026.105535_b17","article-title":"Semantic visual simultaneous localization and mapping: A survey","author":"Chen","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.robot.2026.105535_b18","series-title":"2022 11th International Conference on Control, Automation and Information Sciences","first-page":"385","article-title":"Multisensor data fusion for reliable obstacle avoidance","author":"Canh","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b19","unstructured":"F. Dellaert, D.J. Bruemmer, A.C.C. Workspace, Semantic SLAM for Collaborative Cognitive Workspaces., in: AAAI Technical Report (5), 2004, pp. 85\u201386."},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b20","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1109\/TIV.2019.2919432","article-title":"Lidar mapping optimization based on lightweight semantic segmentation","volume":"4","author":"Zhao","year":"2019","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.robot.2026.105535_b21","series-title":"2021 21st International Conference on Control, Automation and Systems","first-page":"693","article-title":"Semantic mapping based on image feature fusion in indoor environments","author":"Jin","year":"2021"},{"key":"10.1016\/j.robot.2026.105535_b22","series-title":"2023 12th International Conference on Control, Automation and Information Sciences","first-page":"139","article-title":"Object-oriented semantic mapping for reliable uavs navigation","author":"Canh","year":"2023"},{"key":"10.1016\/j.robot.2026.105535_b23","series-title":"2018 International Conference on 3D Vision (3DV)","first-page":"32","article-title":"Fusion++: Volumetric object-level slam","author":"McCormac","year":"2018"},{"key":"10.1016\/j.robot.2026.105535_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2022.104830","article-title":"An online semantic mapping system for extending and enhancing visual SLAM","volume":"111","author":"Hempel","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b25","first-page":"879","article-title":"A semantic octomap mapping method based on cbam-pspnet","volume":"21","author":"Ruan","year":"2022","journal-title":"J. Web Eng."},{"key":"10.1016\/j.robot.2026.105535_b26","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/j.aej.2023.05.014","article-title":"Data frame aware optimized octomap-based dynamic object detection and removal in mobile laser scanning data","volume":"74","author":"Liu","year":"2023","journal-title":"Alex. Eng. J."},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b27","doi-asserted-by":"crossref","first-page":"1743","DOI":"10.1109\/TVCG.2022.3225844","article-title":"Vox-surf: Voxel-based implicit surface representation","volume":"30","author":"Li","year":"2022","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"10.1016\/j.robot.2026.105535_b28","series-title":"Voxeland: Probabilistic instance-aware semantic mapping with evidence-based uncertainty quantification","author":"Matez-Bandera","year":"2024"},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b29","doi-asserted-by":"crossref","first-page":"2942","DOI":"10.1109\/LRA.2018.2848308","article-title":"Integrating deep semantic segmentation into 3-d point cloud registration","volume":"3","author":"Zaganidis","year":"2018","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b30","series-title":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"4530","article-title":"Suma++: Efficient lidar-based semantic slam","author":"Chen","year":"2019"},{"key":"10.1016\/j.robot.2026.105535_b31","series-title":"2009 IEEE International Conference on Systems, Man and Cybernetics","first-page":"2161","article-title":"Active-semantic localization with a single consumer-grade camera","author":"Yi","year":"2009"},{"issue":"1\u20133","key":"10.1016\/j.robot.2026.105535_b32","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1177\/0278364915596589","article-title":"Localization from semantic observations via the matrix permanent","volume":"35","author":"Atanasov","year":"2016","journal-title":"Int. J. Robot. Res."},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b33","doi-asserted-by":"crossref","first-page":"4384","DOI":"10.1109\/LRA.2020.2998403","article-title":"Semantic localization considering uncertainty of object recognition","volume":"5","author":"Akai","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b34","doi-asserted-by":"crossref","first-page":"1431","DOI":"10.1109\/LRA.2021.3140062","article-title":"Mobile robot localization considering uncertainty of depth regression from camera images","volume":"7","author":"Akai","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b35","doi-asserted-by":"crossref","unstructured":"C. Toft, E. Stenborg, L. Hammarstrand, L. Brynte, M. Pollefeys, T. Sattler, F. Kahl, Semantic match consistency for long-term visual localization, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 383\u2013399.","DOI":"10.1007\/978-3-030-01216-8_24"},{"key":"10.1016\/j.robot.2026.105535_b36","doi-asserted-by":"crossref","unstructured":"J.L. Sch\u00f6nberger, M. Pollefeys, A. Geiger, T. Sattler, Semantic visual localization, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6896\u20136906.","DOI":"10.1109\/CVPR.2018.00721"},{"key":"10.1016\/j.robot.2026.105535_b37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.robot.2019.03.012","article-title":"Dynamic-SLAM: Semantic monocular visual localization and mapping based on deep learning in dynamic environment","volume":"117","author":"Xiao","year":"2019","journal-title":"Robot. Auton. Syst."},{"key":"10.1016\/j.robot.2026.105535_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2022.104793","article-title":"Learning invariant semantic representation for long-term robust visual localization","volume":"111","author":"Wu","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b39","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-023-4114-6","article-title":"Bev-locator: An end-to-end visual semantic localization network using multi-view images","volume":"68","author":"Zhang","year":"2025","journal-title":"Sci. China Inf. Sci."},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b40","doi-asserted-by":"crossref","first-page":"925","DOI":"10.1109\/TRO.2019.2909168","article-title":"Cubeslam: Monocular 3-d object slam","volume":"35","author":"Yang","year":"2019","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.robot.2026.105535_b41","series-title":"2017 IEEE International Conference on Robotics and Automation","first-page":"1722","article-title":"Probabilistic data association for semantic slam","author":"Bowman","year":"2017"},{"key":"10.1016\/j.robot.2026.105535_b42","series-title":"2021 IEEE International Conference on Robotics and Automation","first-page":"1","article-title":"Active bayesian multi-class mapping from range and semantic segmentation observations","author":"Asgharivaskasi","year":"2021"},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b43","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1109\/LRA.2019.2963823","article-title":"Sloam: Semantic lidar odometry and mapping for forest inventory","volume":"5","author":"Chen","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b44","doi-asserted-by":"crossref","first-page":"9643","DOI":"10.1109\/LRA.2022.3191165","article-title":"Stronger together: Air-ground robotic collaboration using semantics","volume":"7","author":"Miller","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b45","series-title":"2011 IEEE International Conference on Robotics and Automation","first-page":"3607","article-title":"G 2 o: A general framework for graph optimization","author":"K\u00fcmmerle","year":"2011"},{"key":"10.1016\/j.robot.2026.105535_b46","series-title":"Ceres Solver","author":"Agarwal","year":"2023"},{"key":"10.1016\/j.robot.2026.105535_b47","series-title":"Borglab\/gtsam","author":"Dellaert","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b48","series-title":"29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","article-title":"PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph Compilation","author":"Ansel","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b49","doi-asserted-by":"crossref","unstructured":"K. Tateno, F. Tombari, I. Laina, N. Navab, Cnn-slam: Real-time dense monocular slam with learned depth prediction, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 6243\u20136252.","DOI":"10.1109\/CVPR.2017.695"},{"key":"10.1016\/j.robot.2026.105535_b50","series-title":"2017 IEEE International Conference on Robotics and Automation","first-page":"4471","article-title":"Co-fusion: Real-time segmentation, tracking and fusion of multiple objects","author":"R\u00fcnz","year":"2017"},{"key":"10.1016\/j.robot.2026.105535_b51","doi-asserted-by":"crossref","unstructured":"K.-N. Lianos, J.L. Schonberger, M. Pollefeys, T. Sattler, Vso: Visual semantic odometry, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 234\u2013250.","DOI":"10.1007\/978-3-030-01225-0_15"},{"key":"10.1016\/j.robot.2026.105535_b52","series-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1168","article-title":"DS-SLAM: A semantic visual SLAM towards dynamic environments","author":"Yu","year":"2018"},{"key":"10.1016\/j.robot.2026.105535_b53","series-title":"2018 IEEE International Symposium on Mixed and Augmented Reality","first-page":"10","article-title":"Maskfusion: Real-time recognition, tracking and reconstruction of multiple moving objects","author":"Runz","year":"2018"},{"issue":"1","key":"10.1016\/j.robot.2026.105535_b54","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LRA.2018.2866205","article-title":"Quadricslam: Dual quadrics from object detections as landmarks in object-oriented slam","volume":"4","author":"Nicholson","year":"2018","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b55","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"4966","article-title":"EAO-SLAM: Monocular semi-dense object SLAM based on ensemble data association","author":"Wu","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b56","series-title":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"4205","article-title":"Panopticfusion: Online volumetric semantic mapping at the level of stuff and things","author":"Narita","year":"2019"},{"key":"10.1016\/j.robot.2026.105535_b57","series-title":"2020 IEEE International Conference on Robotics and Automation","first-page":"1689","article-title":"Kimera: an open-source library for real-time metric-semantic localization and mapping","author":"Rosinol","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b58","series-title":"Hydra: A real-time spatial perception system for 3D scene graph construction and optimization","author":"Hughes","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b59","doi-asserted-by":"crossref","unstructured":"E. Sucar, S. Liu, J. Ortiz, A.J. Davison, imap: Implicit mapping and positioning in real-time, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 6229\u20136238.","DOI":"10.1109\/ICCV48922.2021.00617"},{"key":"10.1016\/j.robot.2026.105535_b60","doi-asserted-by":"crossref","unstructured":"Z. Zhu, S. Peng, V. Larsson, W. Xu, H. Bao, Z. Cui, M.R. Oswald, M. Pollefeys, Nice-slam: Neural implicit scalable encoding for slam, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 12786\u201312796.","DOI":"10.1109\/CVPR52688.2022.01245"},{"key":"10.1016\/j.robot.2026.105535_b61","doi-asserted-by":"crossref","unstructured":"E. Sandstr\u00f6m, Y. Li, L. Van Gool, M.R. Oswald, Point-slam: Dense neural point cloud-based slam, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 18433\u201318444.","DOI":"10.1109\/ICCV51070.2023.01690"},{"issue":"10","key":"10.1016\/j.robot.2026.105535_b62","doi-asserted-by":"crossref","first-page":"6787","DOI":"10.1109\/LRA.2023.3313051","article-title":"H _{2} -mapping: Real-time dense mapping using hierarchical hybrid representation","volume":"8","author":"Jiang","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b63","doi-asserted-by":"crossref","unstructured":"S. Zhu, G. Wang, H. Blum, J. Liu, L. Song, M. Pollefeys, H. Wang, Sni-slam: Semantic neural implicit slam, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 21167\u201321177.","DOI":"10.1109\/CVPR52733.2024.02000"},{"key":"10.1016\/j.robot.2026.105535_b64","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2024.3430868","article-title":"H3-mapping: Quasi-heterogeneous feature grids for real-time dense mapping using hierarchical hybrid representation","author":"Jiang","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b65","article-title":"Dynamon: Motion-aware fast and robust camera localization for dynamic neural radiance fields","author":"Schischka","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b66","doi-asserted-by":"crossref","unstructured":"N. Keetha, J. Karhade, K.M. Jatavallabhula, G. Yang, S. Scherer, D. Ramanan, J. Luiten, Splatam: Splat track & map 3d gaussians for dense rgb-d slam, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 21357\u201321366.","DOI":"10.1109\/CVPR52733.2024.02018"},{"key":"10.1016\/j.robot.2026.105535_b67","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2024.3451390","article-title":"Neds-slam: A neural explicit dense semantic slam framework using 3d gaussian splatting","author":"Ji","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b68","doi-asserted-by":"crossref","unstructured":"C. Yan, D. Qu, D. Xu, B. Zhao, Z. Wang, D. Wang, X. Li, Gs-slam: Dense visual slam with 3d gaussian splatting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 19595\u201319604.","DOI":"10.1109\/CVPR52733.2024.01853"},{"key":"10.1016\/j.robot.2026.105535_b69","series-title":"European Conference on Computer Vision","first-page":"163","article-title":"Sgs-slam: Semantic gaussian splatting for neural dense slam","author":"Li","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b70","series-title":"Semgauss-slam: Dense semantic gaussian splatting slam","author":"Zhu","year":"2025"},{"key":"10.1016\/j.robot.2026.105535_b71","series-title":"Conceptfusion: Open-set multimodal 3d mapping","author":"Jatavallabhula","year":"2023"},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b72","doi-asserted-by":"crossref","first-page":"2232","DOI":"10.1109\/LRA.2024.3355751","article-title":"Fm-fusion: Instance-aware semantic mapping boosted by vision-language foundation models","volume":"9","author":"Liu","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b73","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"5021","article-title":"Conceptgraphs: Open-vocabulary 3d scene graphs for perception and planning","author":"Gu","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b74","series-title":"LOSS-slam: Lightweight open-set semantic simultaneous localization and mapping","author":"Singh","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b75","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"15988","article-title":"Language-extended indoor slam (lexis): A versatile system for real-time visual scene understanding","author":"Kassab","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b76","series-title":"Hier-slam++: Neuro-symbolic semantic slam with a hierarchically categorical gaussian splatting","author":"Li","year":"2025"},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b77","doi-asserted-by":"crossref","DOI":"10.1109\/TRO.2021.3137751","article-title":"Kimera-multi: Robust, distributed, dense metric-semantic slam for multi-robot systems","volume":"38","author":"Tian","year":"2022","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.robot.2026.105535_b78","series-title":"Slideslam: Sparse, lightweight, decentralized metric-semantic slam for multi-robot navigation","author":"Liu","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b79","article-title":"HAMMER: Heterogeneous, multi-robot semantic Gaussian splatting","author":"Yu","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b80","series-title":"2005 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"2278","article-title":"Multi-hierarchical semantic maps for mobile robotics","author":"Galindo","year":"2005"},{"key":"10.1016\/j.robot.2026.105535_b81","series-title":"Computer Vision\u2013ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2\u20136, 2018, Revised Selected Papers, Part III 14","first-page":"410","article-title":"Structure aware slam using quadrics and planes","author":"Hosseinzadeh","year":"2019"},{"key":"10.1016\/j.robot.2026.105535_b82","series-title":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1352","article-title":"DRG-SLAM: a semantic RGB-d SLAM using geometric features for indoor dynamic scene","author":"Wang","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b83","series-title":"2019 International Conference on Robotics and Automation","first-page":"2419","article-title":"Multimodal semantic slam with probabilistic data association","author":"Doherty","year":"2019"},{"key":"10.1016\/j.robot.2026.105535_b84","series-title":"2020 IEEE International Conference on Robotics and Automation","first-page":"1098","article-title":"Probabilistic data association via mixture models for robust semantic SLAM","author":"Doherty","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b85","series-title":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"4359","article-title":"Probabilistic data association for semantic slam at scale","author":"Michael","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b86","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1007\/s10514-012-9321-0","article-title":"OctoMap: An efficient probabilistic 3D mapping framework based on octrees","volume":"34","author":"Hornung","year":"2013","journal-title":"Auton. Robots"},{"key":"10.1016\/j.robot.2026.105535_b87","doi-asserted-by":"crossref","first-page":"479","DOI":"10.5194\/isprsarchives-XL-5-479-2014","article-title":"Kinect fusion improvement using depth camera calibration","volume":"40","author":"Pagliari","year":"2014","journal-title":"Int. Arch. Photogramm. Remote. Sens. Spat. Inf. Sci."},{"key":"10.1016\/j.robot.2026.105535_b88","series-title":"2022 IEEE International Symposium on Mixed and Augmented Reality","first-page":"499","article-title":"Vox-fusion: Dense tracking and mapping with voxel-based neural implicit representation","author":"Yang","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b89","doi-asserted-by":"crossref","unstructured":"H. Matsuki, R. Murai, P.H. Kelly, A.J. Davison, Gaussian splatting slam, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 18039\u201318048.","DOI":"10.1109\/CVPR52733.2024.01708"},{"key":"10.1016\/j.robot.2026.105535_b90","series-title":"Hier-SLAM: Scaling-up semantics in SLAM with a hierarchically categorical Gaussian splatting","author":"Li","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b91","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.robot.2014.12.006","article-title":"Semantic mapping for mobile robotics tasks: A survey","volume":"66","author":"Kostavelis","year":"2015","journal-title":"Robot. Auton. Syst."},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b92","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1007\/s12555-018-0130-x","article-title":"Simultaneous localization and mapping in the epoch of semantics: a survey","volume":"17","author":"Sualeh","year":"2019","journal-title":"Int. J. Control. Autom. Syst."},{"key":"10.1016\/j.robot.2026.105535_b93","series-title":"Semantic visual simultaneous localization and mapping: A survey","author":"Chen","year":"2022"},{"issue":"13","key":"10.1016\/j.robot.2026.105535_b94","doi-asserted-by":"crossref","first-page":"3010","DOI":"10.3390\/rs14133010","article-title":"An overview on visual slam: From tradition to semantic","volume":"14","author":"Chen","year":"2022","journal-title":"Remote. Sens."},{"issue":"19","key":"10.1016\/j.robot.2026.105535_b95","doi-asserted-by":"crossref","first-page":"22119","DOI":"10.1109\/JSEN.2023.3306371","article-title":"Visual SLAM integration with semantic segmentation and deep learning: A review","volume":"23","author":"Pu","year":"2023","journal-title":"IEEE Sensors J."},{"key":"10.1016\/j.robot.2026.105535_b96","article-title":"A survey of visual SLAM in dynamic environment: The evolution from geometric to semantic approaches","author":"Wang","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"1\u20132","key":"10.1016\/j.robot.2026.105535_b97","first-page":"1","article-title":"Semantics for robotic mapping, perception and interaction: A survey","volume":"8","author":"Garg","year":"2020","journal-title":"Found. Trends\u00ae Robot."},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b98","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1007\/s10514-021-09979-4","article-title":"Semantic visual SLAM in dynamic environment","volume":"45","author":"Wen","year":"2021","journal-title":"Auton. Robots"},{"issue":"19","key":"10.1016\/j.robot.2026.105535_b99","doi-asserted-by":"crossref","first-page":"7265","DOI":"10.3390\/s22197265","article-title":"A review on visual-slam: Advancements from geometric modelling to learning-based semantic scene understanding using multi-modal sensor fusion","volume":"22","author":"Lai","year":"2022","journal-title":"Sensors"},{"issue":"10","key":"10.1016\/j.robot.2026.105535_b100","doi-asserted-by":"crossref","first-page":"4849","DOI":"10.3390\/s23104849","article-title":"From slam to situational awareness: Challenges and survey","volume":"23","author":"Bavle","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.robot.2026.105535_b101","article-title":"Semantic mapping for robotics: Survey, trends and challenges","author":"Georgevich Ferreira","year":"2025","journal-title":"Trends Challenges"},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b102","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1177\/00202940241259903","article-title":"Semantic mapping techniques for indoor mobile robots: Review and prospect","volume":"58","author":"Song","year":"2025","journal-title":"Meas. Control."},{"key":"10.1016\/j.robot.2026.105535_b103","series-title":"Semantic Mapping for Robotics: Survey, Trends and Challenges","author":"Georgevich Ferreira","year":"2025"},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b104","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1145\/504729.504754","article-title":"Probabilistic robotics","volume":"45","author":"Thrun","year":"2002","journal-title":"Commun. ACM"},{"key":"10.1016\/j.robot.2026.105535_b105","series-title":"Probabilistic roboticsv2","author":"Thrun","year":"2005"},{"key":"10.1016\/j.robot.2026.105535_b106","series-title":"Markov decision processes in artificial intelligence","author":"Sigaud","year":"2013"},{"key":"10.1016\/j.robot.2026.105535_b107","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015","journal-title":"Proc. the IEEE Conf. Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.robot.2026.105535_b108","first-page":"2961","article-title":"Mask R-CNN","author":"He","year":"2017","journal-title":"Proc. the IEEE Int. Conf. Comput. Vis."},{"issue":"7","key":"10.1016\/j.robot.2026.105535_b109","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1177\/0278364914561102","article-title":"Planning in the continuous domain: A generalized belief space approach for autonomous navigation in unknown environments","volume":"34","author":"Indelman","year":"2015","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.robot.2026.105535_b110","series-title":"Dual quadrics from object detection boundingboxes as landmark representations in slam","author":"S\u00fcnderhauf","year":"2017"},{"key":"10.1016\/j.robot.2026.105535_b111","doi-asserted-by":"crossref","unstructured":"R.F. Salas-Moreno, R.A. Newcombe, H. Strasdat, P.H. Kelly, A.J. Davison, Slam++: Simultaneous localisation and mapping at the level of objects, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp. 1352\u20131359.","DOI":"10.1109\/CVPR.2013.178"},{"key":"10.1016\/j.robot.2026.105535_b112","series-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b113","doi-asserted-by":"crossref","first-page":"4076","DOI":"10.1109\/LRA.2018.2860039","article-title":"Dynaslam: Tracking, mapping, and inpainting in dynamic scenes","volume":"3","author":"Bescos","year":"2018","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b114","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108225","article-title":"Blitz-SLAM: A semantic SLAM in dynamic environments","volume":"121","author":"Fan","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.robot.2026.105535_b115","doi-asserted-by":"crossref","first-page":"43827","DOI":"10.1109\/ACCESS.2024.3379269","article-title":"Drv-slam: An adaptive real-time semantic visual slam based on instance segmentation toward dynamic environments","volume":"12","author":"Ji","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.robot.2026.105535_b116","series-title":"2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"3005","article-title":"Semantic mapping using object-class segmentation of RGB-d images","author":"St\u00fcckler","year":"2012"},{"key":"10.1016\/j.robot.2026.105535_b117","series-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"385","article-title":"Fast and accurate semantic mapping through geometric-based incremental segmentation","author":"Nakajima","year":"2018"},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b118","doi-asserted-by":"crossref","first-page":"568","DOI":"10.1109\/LRA.2022.3229228","article-title":"SemanticLoop: Loop closure with 3D semantic graph matching","volume":"8","author":"Yu","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b119","article-title":"SemanticTopoLoop: Semantic loop closure with 3D topological graph based on quadric-level object map","author":"Cao","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b120","series-title":"2021 21st International Conference on Control, Automation and Systems","first-page":"21","article-title":"Semantics aware loop closure detection in visual SLAM","author":"Arshad","year":"2021"},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b121","doi-asserted-by":"crossref","first-page":"2455","DOI":"10.1109\/LRA.2022.3145066","article-title":"Towards accurate loop closure detection in semantic SLAM with 3D semantic covisibility graphs","volume":"7","author":"Qian","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b122","doi-asserted-by":"crossref","first-page":"7041","DOI":"10.1109\/LRA.2021.3097242","article-title":"Topology aware object-level semantic mapping towards more robust loop closure","volume":"6","author":"Lin","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b123","doi-asserted-by":"crossref","unstructured":"L. Schmid, M. Abate, Y. Chang, L. Carlone, Khronos: A Unified Approach for Spatio-Temporal Metric-Semantic SLAMin Dynamic Environments, in: Proc. of Robotics: Science and Systems, 2024.","DOI":"10.15607\/RSS.2024.XX.081"},{"key":"10.1016\/j.robot.2026.105535_b124","series-title":"2019 19th International Conference on Advanced Robotics","first-page":"135","article-title":"Visual SLAM in human populated environments: exploring the trade-off between accuracy and speed of YOLO and mask R-CNN","author":"Soares","year":"2019"},{"key":"10.1016\/j.robot.2026.105535_b125","doi-asserted-by":"crossref","first-page":"23772","DOI":"10.1109\/ACCESS.2021.3050617","article-title":"RDS-SLAM: Real-time dynamic SLAM using semantic segmentation methods","volume":"9","author":"Liu","year":"2021","journal-title":"IEEE Access"},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b126","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1007\/s10846-021-01414-1","article-title":"Crowd-SLAM: visual SLAM towards crowded environments using object detection","volume":"102","author":"Soares","year":"2021","journal-title":"J. Intell. Robot. Syst."},{"key":"10.1016\/j.robot.2026.105535_b127","doi-asserted-by":"crossref","first-page":"106981","DOI":"10.1109\/ACCESS.2021.3100426","article-title":"RDMO-slam: Real-time visual SLAM for dynamic environments using semantic label prediction with optical flow","volume":"9","author":"Liu","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.robot.2026.105535_b128","doi-asserted-by":"crossref","unstructured":"J. Redmon, S. Divvala, R. Girshick, A. Farhadi, You only look once: Unified, real-time object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"10.1016\/j.robot.2026.105535_b129","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.robot.2026.105535_b130","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11\u201314, 2016, Proceedings, Part I 14","first-page":"21","article-title":"Ssd: Single shot multibox detector","author":"Liu","year":"2016"},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b131","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"12","key":"10.1016\/j.robot.2026.105535_b132","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.robot.2026.105535_b133","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVIII 16","first-page":"649","article-title":"Solo: Segmenting objects by locations","author":"Wang","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b134","doi-asserted-by":"crossref","unstructured":"A. Kirillov, Y. Wu, K. He, R. Girshick, Pointrend: Image segmentation as rendering, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9799\u20139808.","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"10.1016\/j.robot.2026.105535_b135","doi-asserted-by":"crossref","unstructured":"A. Kirillov, K. He, R. Girshick, C. Rother, P. Doll\u00e1r, Panoptic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 9404\u20139413.","DOI":"10.1109\/CVPR.2019.00963"},{"key":"10.1016\/j.robot.2026.105535_b136","doi-asserted-by":"crossref","unstructured":"B. Cheng, M.D. Collins, Y. Zhu, T. Liu, T.S. Huang, H. Adam, L.-C. Chen, Panoptic-deeplab: A simple, strong, and fast baseline for bottom-up panoptic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 12475\u201312485.","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"10.1016\/j.robot.2026.105535_b137","doi-asserted-by":"crossref","unstructured":"J. Redmon, A. Farhadi, YOLO9000: better, faster, stronger, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 7263\u20137271.","DOI":"10.1109\/CVPR.2017.690"},{"key":"10.1016\/j.robot.2026.105535_b138","series-title":"Yolov3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"10.1016\/j.robot.2026.105535_b139","series-title":"Yolov4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b140","series-title":"Ultralytics YOLOv5","author":"Jocher","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b141","series-title":"YOLOv6: A single-stage object detection framework for industrial applications","author":"Li","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b142","doi-asserted-by":"crossref","unstructured":"C.-Y. Wang, A. Bochkovskiy, H.-Y.M. Liao, YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 7464\u20137475.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"10.1016\/j.robot.2026.105535_b143","series-title":"Ultralytics YOLO","author":"Jocher","year":"2023"},{"key":"10.1016\/j.robot.2026.105535_b144","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"Yolov9: Learning what you want to learn using programmable gradient information","author":"Wang","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b145","doi-asserted-by":"crossref","unstructured":"R. Girshick, J. Donahue, T. Darrell, J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 580\u2013587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"10.1016\/j.robot.2026.105535_b146","doi-asserted-by":"crossref","unstructured":"R. Girshick, Fast r-cnn, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"10.1016\/j.robot.2026.105535_b147","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b148","series-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b149","doi-asserted-by":"crossref","unstructured":"Y. Zhou, O. Tuzel, Voxelnet: End-to-end learning for point cloud based 3d object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 4490\u20134499.","DOI":"10.1109\/CVPR.2018.00472"},{"key":"10.1016\/j.robot.2026.105535_b150","doi-asserted-by":"crossref","unstructured":"C.R. Qi, W. Liu, C. Wu, H. Su, L.J. Guibas, Frustum pointnets for 3d object detection from rgb-d data, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 918\u2013927.","DOI":"10.1109\/CVPR.2018.00102"},{"key":"10.1016\/j.robot.2026.105535_b151","doi-asserted-by":"crossref","unstructured":"C. Wang, D. Xu, Y. Zhu, R. Mart\u00edn-Mart\u00edn, C. Lu, L. Fei-Fei, S. Savarese, Densefusion: 6d object pose estimation by iterative dense fusion, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 3343\u20133352.","DOI":"10.1109\/CVPR.2019.00346"},{"key":"10.1016\/j.robot.2026.105535_b152","first-page":"1","article-title":"YOLO-slam: A semantic SLAM system towards dynamic environment with geometric constraint","author":"Wu","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.robot.2026.105535_b153","series-title":"Chinese Intelligent Systems Conference","first-page":"377","article-title":"YOLO-based semantic segmentation for dynamic removal in visual-inertial SLAM","author":"Xia","year":"2023"},{"issue":"5","key":"10.1016\/j.robot.2026.105535_b154","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6501\/ad2669","article-title":"Real-time visual SLAM based YOLO-fastest for dynamic scenes","volume":"35","author":"Gong","year":"2024","journal-title":"Meas. Sci. Technol."},{"key":"10.1016\/j.robot.2026.105535_b155","series-title":"2021 IEEE International Conference on Progress in Informatics and Computing","first-page":"409","article-title":"A multi-sensory blind guidance system based on YOLO and ORB-SLAM","author":"Rui","year":"2021"},{"issue":"7","key":"10.1016\/j.robot.2026.105535_b156","doi-asserted-by":"crossref","first-page":"343","DOI":"10.3390\/info13070343","article-title":"A multi-sensory guidance system for the visually impaired using yolo and ORB-SLAM","volume":"13","author":"Xie","year":"2022","journal-title":"Information"},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b157","doi-asserted-by":"crossref","first-page":"2847","DOI":"10.1109\/TITS.2023.3284228","article-title":"RGBD-slam based on object detection with two-stream YOLOv4-MobileNetv3 in autonomous driving","volume":"25","author":"Li","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"6","key":"10.1016\/j.robot.2026.105535_b158","doi-asserted-by":"crossref","first-page":"5257","DOI":"10.1109\/TITS.2021.3052812","article-title":"Faster R-CNN learning-based semantic filter for geometry estimation and its application in vSLAM systems","volume":"23","author":"Shao","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.robot.2026.105535_b159","doi-asserted-by":"crossref","first-page":"126525","DOI":"10.1109\/ACCESS.2022.3226212","article-title":"Dynamic semantics SLAM based on improved mask R-CNN","volume":"10","author":"Zhang","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.robot.2026.105535_b160","doi-asserted-by":"crossref","first-page":"75545","DOI":"10.1109\/ACCESS.2018.2873617","article-title":"Semantic SLAM based on object detection and improved octomap","volume":"6","author":"Zhang","year":"2018","journal-title":"IEEE Access"},{"key":"10.1016\/j.robot.2026.105535_b161","doi-asserted-by":"crossref","DOI":"10.1016\/j.robot.2024.104871","article-title":"Advancing autonomous SLAM systems: Integrating YOLO object detection and enhanced loop closure techniques for robust environment mapping","volume":"185","author":"Islam","year":"2025","journal-title":"Robot. Auton. Syst."},{"key":"10.1016\/j.robot.2026.105535_b162","series-title":"2024 IEEE 25th China Conference on System Simulation Technology and Its Application","first-page":"346","article-title":"Dyn-darkslam: YOLO-based visual SLAM in low-light conditions","author":"Wu","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b163","series-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.robot.2026.105535_b164","series-title":"Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding","author":"Kendall","year":"2015"},{"key":"10.1016\/j.robot.2026.105535_b165","doi-asserted-by":"crossref","unstructured":"H. Zhao, J. Shi, X. Qi, X. Wang, J. Jia, Pyramid scene parsing network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2881\u20132890.","DOI":"10.1109\/CVPR.2017.660"},{"key":"10.1016\/j.robot.2026.105535_b166","doi-asserted-by":"crossref","unstructured":"L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, H. Adam, Encoder-decoder with atrous separable convolution for semantic image segmentation, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"10.1016\/j.robot.2026.105535_b167","doi-asserted-by":"crossref","unstructured":"D. Bolya, C. Zhou, F. Xiao, Y.J. Lee, Yolact: Real-time instance segmentation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 9157\u20139166.","DOI":"10.1109\/ICCV.2019.00925"},{"key":"10.1016\/j.robot.2026.105535_b168","doi-asserted-by":"crossref","unstructured":"S. Liu, L. Qi, H. Qin, J. Shi, J. Jia, Path aggregation network for instance segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8759\u20138768.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"10.1016\/j.robot.2026.105535_b169","doi-asserted-by":"crossref","unstructured":"K. Chen, J. Pang, J. Wang, Y. Xiong, X. Li, S. Sun, W. Feng, Z. Liu, J. Shi, W. Ouyang, et al., Hybrid task cascade for instance segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4974\u20134983.","DOI":"10.1109\/CVPR.2019.00511"},{"key":"10.1016\/j.robot.2026.105535_b170","doi-asserted-by":"crossref","unstructured":"B. Cheng, I. Misra, A.G. Schwing, A. Kirillov, R. Girdhar, Masked-attention mask transformer for universal image segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 1290\u20131299.","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"10.1016\/j.robot.2026.105535_b171","doi-asserted-by":"crossref","unstructured":"Y. Fang, S. Yang, X. Wang, Y. Li, C. Fang, Y. Shan, B. Feng, W. Liu, Instances as queries, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 6910\u20136919.","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"10.1016\/j.robot.2026.105535_b172","series-title":"2019 International Conference on Robotics and Automation","first-page":"5231","article-title":"Mid-fusion: Octree-based object-level multi-instance dynamic slam","author":"Xu","year":"2019"},{"key":"10.1016\/j.robot.2026.105535_b173","series-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1366","article-title":"Voxblox: Incremental 3d euclidean signed distance fields for on-board mav planning","author":"Oleynikova","year":"2017"},{"key":"10.1016\/j.robot.2026.105535_b174","doi-asserted-by":"crossref","unstructured":"L. Jiang, H. Zhao, S. Shi, S. Liu, C.-W. Fu, J. Jia, Pointgroup: Dual-set point grouping for 3d instance segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 4867\u20134876.","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"10.1016\/j.robot.2026.105535_b175","doi-asserted-by":"crossref","unstructured":"J. Hou, A. Dai, M. Nie\u00dfner, 3d-sis: 3d semantic instance segmentation of rgb-d scans, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4421\u20134430.","DOI":"10.1109\/CVPR.2019.00455"},{"issue":"1","key":"10.1016\/j.robot.2026.105535_b176","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1109\/TCSVT.2021.3056726","article-title":"RGB-d semantic segmentation and label-oriented voxelgrid fusion for accurate 3D semantic mapping","volume":"32","author":"Shi","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"5","key":"10.1016\/j.robot.2026.105535_b177","doi-asserted-by":"crossref","first-page":"1551","DOI":"10.1007\/s11263-021-01445-z","article-title":"Efficientps: Efficient panoptic segmentation","volume":"129","author":"Mohan","year":"2021","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b178","doi-asserted-by":"crossref","first-page":"1742","DOI":"10.1109\/LRA.2020.2969919","article-title":"Fast panoptic segmentation network","volume":"5","author":"De Geus","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b179","series-title":"2024 21st International Conference on Ubiquitous Robots","first-page":"01","article-title":"Panoptic-SLAM: Visual SLAM in dynamic environments using panoptic segmentation","author":"Abati","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b180","article-title":"PS-SLAM: A visual SLAM for semantic mapping in dynamic outdoor environment using panoptic segmentation","author":"Li","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.robot.2026.105535_b181","series-title":"2016 IEEE International Conference on Robotics and Automation","first-page":"5729","article-title":"Place categorization and semantic mapping on a mobile robot","author":"S\u00fcnderhauf","year":"2016"},{"key":"10.1016\/j.robot.2026.105535_b182","series-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"6863","article-title":"Improving condition-and environment-invariant place recognition with semantic place categorization","author":"Garg","year":"2017"},{"key":"10.1016\/j.robot.2026.105535_b183","series-title":"2023 IEEE 26th International Conference on Intelligent Transportation Systems","first-page":"2151","article-title":"Visem: A visual and semantic information fusion based place recognition for long term autonomous navigation","author":"Arshad","year":"2023"},{"key":"10.1016\/j.robot.2026.105535_b184","series-title":"Context-based visual-language place recognition","author":"Woo","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b185","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.robot.2026.105535_b186","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.robot.2026.105535_b187","doi-asserted-by":"crossref","unstructured":"C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, Going deeper with convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10.1016\/j.robot.2026.105535_b188","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.robot.2026.105535_b189","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"issue":"6","key":"10.1016\/j.robot.2026.105535_b190","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","article-title":"Places: A 10 million image database for scene recognition","volume":"40","author":"Zhou","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.robot.2026.105535_b191","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/s11263-013-0695-z","article-title":"The sun attribute database: Beyond categories for deeper scene understanding","volume":"108","author":"Patterson","year":"2014","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.robot.2026.105535_b192","doi-asserted-by":"crossref","unstructured":"R. Arandjelovic, P. Gronat, A. Torii, T. Pajdla, J. Sivic, NetVLAD: CNN architecture for weakly supervised place recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 5297\u20135307.","DOI":"10.1109\/CVPR.2016.572"},{"key":"10.1016\/j.robot.2026.105535_b193","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b194","doi-asserted-by":"crossref","unstructured":"R. Wang, Y. Shen, W. Zuo, S. Zhou, N. Zheng, Transvpr: Transformer-based place recognition with multi-level attention aggregation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 13648\u201313657.","DOI":"10.1109\/CVPR52688.2022.01328"},{"key":"10.1016\/j.robot.2026.105535_b195","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.eswa.2016.10.014","article-title":"Semantic maps from multiple visual cues","volume":"68","author":"Kostavelis","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.robot.2026.105535_b196","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/s10514-017-9638-9","article-title":"Topological map construction and scene recognition for vehicle localization","volume":"42","author":"Lin","year":"2018","journal-title":"Auton. Robots"},{"issue":"1","key":"10.1016\/j.robot.2026.105535_b197","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1109\/LRA.2022.3223556","article-title":"Long-term localization using semantic cues in floor plan maps","volume":"8","author":"Zimmerman","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b198","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"5205","article-title":"Placenav: Topological navigation through place recognition","author":"Suomela","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b199","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2025.3541454","article-title":"PRISM-TopoMap: online topological mapping with place recognition and scan matching","author":"Muravyev","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b200","doi-asserted-by":"crossref","first-page":"214685","DOI":"10.1109\/ACCESS.2020.3041038","article-title":"Pspnet-SLAM: A semantic SLAM detect dynamic object by pyramid scene parsing network","volume":"8","author":"Long","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.robot.2026.105535_b201","unstructured":"H. Zhou, J. Fang, L. Zhang, Y. Xu, Y. Liu, Semantic scene completion from a single depth image, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 1746\u20131754."},{"key":"10.1016\/j.robot.2026.105535_b202","series-title":"2011 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1277","article-title":"Towards semantic SLAM using a monocular camera","author":"Civera","year":"2011"},{"issue":"6","key":"10.1016\/j.robot.2026.105535_b203","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1016\/j.robot.2008.03.005","article-title":"Bayesian space conceptualization and place classification for semantic maps in mobile robotics","volume":"56","author":"Vasudevan","year":"2008","journal-title":"Robot. Auton. Syst."},{"key":"10.1016\/j.robot.2026.105535_b204","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"8216","article-title":"Semantic graph based place recognition for 3d point clouds","author":"Kong","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b205","series-title":"Open-set semantic uncertainty aware metric-semantic graph matching","author":"Singh","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b206","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1139\/dsa-2022-0045","article-title":"Factor graph localization for mobile robots using google indoor street view and CNN-based place recognition","volume":"11","author":"Tennakoon","year":"2023","journal-title":"Drone Syst. Appl."},{"key":"10.1016\/j.robot.2026.105535_b207","series-title":"ISR 2018; 50th International Symposium on Robotics","first-page":"1","article-title":"Semantic segmentation guided slam using vision and lidar","author":"Patel","year":"2018"},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b208","doi-asserted-by":"crossref","first-page":"1745","DOI":"10.1109\/TVCG.2020.3028218","article-title":"Accurate dynamic SLAM using CRF-based long-term consistency","volume":"28","author":"Du","year":"2020","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"10.1016\/j.robot.2026.105535_b209","series-title":"2022 22nd International Conference on Control, Automation and Systems","first-page":"129","article-title":"RGB-d visual SLAM algorithm using scene flow and conditional random field in dynamic environments","author":"Jeon","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b210","series-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"755","article-title":"Learning deep generative spatial models for mobile robots","author":"Pronobis","year":"2017"},{"key":"10.1016\/j.robot.2026.105535_b211","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"13787","article-title":"Active semantic mapping and pose graph spectral analysis for robot exploration","author":"Zhang","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b212","doi-asserted-by":"crossref","first-page":"60704","DOI":"10.1109\/ACCESS.2020.2983121","article-title":"VPS-SLAM: Visual planar semantic SLAM for aerial robotic systems","volume":"8","author":"Bavle","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.robot.2026.105535_b213","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"5939","article-title":"Avp-slam: Semantic visual mapping and localization for autonomous vehicles in the parking lot","author":"Qin","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b214","series-title":"2022 International Conference on Robotics and Automation","first-page":"4121","article-title":"Robust semantic mapping and localization on a free-flying robot in microgravity","author":"Miller","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b215","series-title":"2019 IEEE International Conference on Image Processing","first-page":"2566","article-title":"Visual odometry based on semantic supervision","author":"Liu","year":"2019"},{"key":"10.1016\/j.robot.2026.105535_b216","doi-asserted-by":"crossref","first-page":"166528","DOI":"10.1109\/ACCESS.2019.2952161","article-title":"SOF-SLAM: A semantic visual SLAM for dynamic environments","volume":"7","author":"Cui","year":"2019","journal-title":"IEEE Access"},{"issue":"5","key":"10.1016\/j.robot.2026.105535_b217","doi-asserted-by":"crossref","DOI":"10.1177\/1729881417735667","article-title":"Semantic segmentation\u2013aided visual odometry for urban autonomous driving","volume":"14","author":"An","year":"2017","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"10.1016\/j.robot.2026.105535_b218","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"4930","article-title":"Sad-slam: A visual slam based on semantic and depth information","author":"Yuan","year":"2020"},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b219","doi-asserted-by":"crossref","first-page":"795","DOI":"10.3390\/rs14030795","article-title":"Dgs-slam: A fast and robust rgbd slam in dynamic environments combined by geometric and semantic information","volume":"14","author":"Yan","year":"2022","journal-title":"Remote. Sens."},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b220","doi-asserted-by":"crossref","first-page":"1467","DOI":"10.3390\/app10041467","article-title":"Dynamic-DSO: direct sparse odometry using objects semantic information for dynamic environments","volume":"10","author":"Sheng","year":"2020","journal-title":"Appl. Sci."},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b221","article-title":"Dystslam: an efficient stereo vision SLAM system in dynamic environment","volume":"34","author":"Li","year":"2022","journal-title":"Meas. Sci. Technol."},{"issue":"11","key":"10.1016\/j.robot.2026.105535_b222","doi-asserted-by":"crossref","first-page":"10818","DOI":"10.1109\/JSEN.2022.3169340","article-title":"WF-SLAM: A robust VSLAM for dynamic scenarios via weighted features","volume":"22","author":"Zhong","year":"2022","journal-title":"IEEE Sensors J."},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b223","doi-asserted-by":"crossref","first-page":"163","DOI":"10.3390\/ijgi10030163","article-title":"PLD-SLAM: A new RGB-d SLAM method with point and line features for indoor dynamic scene","volume":"10","author":"Zhang","year":"2021","journal-title":"ISPRS Int. J. Geo-Information"},{"issue":"21","key":"10.1016\/j.robot.2026.105535_b224","doi-asserted-by":"crossref","first-page":"8561","DOI":"10.3390\/s22218561","article-title":"YPD-SLAM: A real-time VSLAM system for handling dynamic indoor environments","volume":"22","author":"Wang","year":"2022","journal-title":"Sensors"},{"issue":"7","key":"10.1016\/j.robot.2026.105535_b225","doi-asserted-by":"crossref","first-page":"1893","DOI":"10.3390\/rs15071893","article-title":"PLDS-SLAM: point and line features SLAM in dynamic environment","volume":"15","author":"Yuan","year":"2023","journal-title":"Remote. Sens."},{"issue":"12","key":"10.1016\/j.robot.2026.105535_b226","doi-asserted-by":"crossref","first-page":"4252","DOI":"10.3390\/app10124252","article-title":"DM-SLAM: Monocular SLAM in dynamic environments","volume":"10","author":"Lu","year":"2020","journal-title":"Appl. Sci."},{"key":"10.1016\/j.robot.2026.105535_b227","series-title":"2021 IEEE International Conference on Robotics and Automation","first-page":"11175","article-title":"Towards real-time semantic rgb-d slam in dynamic environments","author":"Ji","year":"2021"},{"key":"10.1016\/j.robot.2026.105535_b228","series-title":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"4399","article-title":"CFP-SLAM: A real-time visual SLAM based on coarse-to-fine probability in dynamic environments","author":"Hu","year":"2022"},{"issue":"24","key":"10.1016\/j.robot.2026.105535_b229","doi-asserted-by":"crossref","first-page":"30009","DOI":"10.1007\/s10489-023-05070-w","article-title":"DO-SLAM: research and application of semantic SLAM system towards dynamic environments based on object detection","volume":"53","author":"Wei","year":"2023","journal-title":"Appl. Intell."},{"issue":"12","key":"10.1016\/j.robot.2026.105535_b230","doi-asserted-by":"crossref","first-page":"13210","DOI":"10.1109\/JSEN.2023.3270534","article-title":"OVD-SLAM: An online visual SLAM for dynamic environments","volume":"23","author":"He","year":"2023","journal-title":"IEEE Sensors J."},{"issue":"1","key":"10.1016\/j.robot.2026.105535_b231","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1002\/rob.22248","article-title":"MVS-SLAM: Enhanced multiview geometry for improved semantic RGBD slam in dynamic environment","volume":"41","author":"Islam","year":"2024","journal-title":"J. Field Robot."},{"key":"10.1016\/j.robot.2026.105535_b232","series-title":"2018 IEEE Winter Conference on Applications of Computer Vision","first-page":"1001","article-title":"Detect-SLAM: Making object detection and SLAM mutually beneficial","author":"Zhong","year":"2018"},{"key":"10.1016\/j.robot.2026.105535_b233","article-title":"DynaNav-SVO: Dynamic stereo visual odometry with semantic-aware perception for autonomous navigation","author":"Contreras","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.robot.2026.105535_b234","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2023.3326234","article-title":"SG-SLAM: A real-time RGB-d visual SLAM toward dynamic scenes with semantic and geometric information","volume":"72","author":"Cheng","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.robot.2026.105535_b235","series-title":"2025 IEEE International Conference on Real-Time Computing and Robotics","first-page":"1","article-title":"Adaptive prior scene-object SLAM for dynamic environments","author":"Zhang","year":"2025"},{"key":"10.1016\/j.robot.2026.105535_b236","series-title":"2023 38th Youth Academic Annual Conference of Chinese Association of Automation","first-page":"132","article-title":"A visual SLAM algorithm based on instance segmentation and background inpainting in dynamic scenes","author":"Qian","year":"2023"},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b237","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1109\/TRO.2020.3031267","article-title":"Empty cities: A dynamic-object-invariant space for visual SLAM","volume":"37","author":"Bescos","year":"2020","journal-title":"IEEE Trans. Robot."},{"issue":"11","key":"10.1016\/j.robot.2026.105535_b238","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b239","doi-asserted-by":"crossref","first-page":"5191","DOI":"10.1109\/LRA.2021.3068640","article-title":"Dynaslam II: Tightly-coupled multi-object tracking and SLAM","volume":"6","author":"Bescos","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b240","series-title":"2021 IEEE International Conference on Robotics and Automation","first-page":"11705","article-title":"DOT: Dynamic object tracking for visual SLAM","author":"Ballester","year":"2021"},{"issue":"5","key":"10.1016\/j.robot.2026.105535_b241","doi-asserted-by":"crossref","first-page":"2645","DOI":"10.1109\/LRA.2023.3256919","article-title":"Pointslot: Real-time simultaneous localization and object tracking for dynamic environment","volume":"8","author":"Zhou","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b242","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"5017","article-title":"Robust ego and object 6-dof motion estimation and tracking","author":"Zhang","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b243","series-title":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"4865","article-title":"MOTSLAM: MOT-assisted monocular dynamic SLAM using single-view depth estimation","author":"Zhang","year":"2022"},{"issue":"5","key":"10.1016\/j.robot.2026.105535_b244","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1002\/rob.22062","article-title":"DE-SLAM: SLAM for highly dynamic environment","volume":"39","author":"Xing","year":"2022","journal-title":"J. Field Robot."},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b245","doi-asserted-by":"crossref","first-page":"6846","DOI":"10.1109\/LRA.2022.3178150","article-title":"Twistslam: Constrained slam in dynamic environment","volume":"7","author":"Gonzalez","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b246","doi-asserted-by":"crossref","unstructured":"M. Schorghuber, D. Steininger, Y. Cabon, M. Humenberger, M. Gelautz, SLAMANTIC-leveraging semantics to improve VSLAM in dynamic environments, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, 2019.","DOI":"10.1109\/ICCVW.2019.00468"},{"key":"10.1016\/j.robot.2026.105535_b247","series-title":"VDO-SLAM: A visual dynamic object-aware SLAM system","author":"Zhang","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b248","doi-asserted-by":"crossref","unstructured":"J. Huang, S. Yang, T.-J. Mu, S.-M. Hu, ClusterVO: Clustering moving instances and estimating visual odometry for self and surroundings, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 2168\u20132177.","DOI":"10.1109\/CVPR42600.2020.00224"},{"issue":"18","key":"10.1016\/j.robot.2026.105535_b249","doi-asserted-by":"crossref","first-page":"7921","DOI":"10.3390\/s23187921","article-title":"OTE-SLAM: An object tracking enhanced visual SLAM system for dynamic environments","volume":"23","author":"Chang","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.robot.2026.105535_b250","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"Bytetrack: Multi-object tracking by associating every detection box","author":"Zhang","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b251","series-title":"2018 IEEE International Conference on Robotics and Automation","first-page":"7510","article-title":"Robust dense mapping for large-scale dynamic environments","author":"B\u00e2rsan","year":"2018"},{"issue":"14","key":"10.1016\/j.robot.2026.105535_b252","doi-asserted-by":"crossref","first-page":"1697","DOI":"10.1177\/0278364916669237","article-title":"ElasticFusion: Real-time dense SLAM and light source estimation","volume":"35","author":"Whelan","year":"2016","journal-title":"Int. J. Robot. Res."},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b253","doi-asserted-by":"crossref","first-page":"3037","DOI":"10.1109\/LRA.2019.2923960","article-title":"Volumetric instance-aware semantic mapping and 3D object discovery","volume":"4","author":"Grinvald","year":"2019","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"10","key":"10.1016\/j.robot.2026.105535_b254","doi-asserted-by":"crossref","first-page":"2494","DOI":"10.1109\/TPAMI.2019.2947048","article-title":"Surfelmeshing: Online surfel-based mesh reconstruction","volume":"42","author":"Sch\u00f6ps","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.robot.2026.105535_b255","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"13311","article-title":"QueSTMaps: Queryable semantic topological maps for 3D scene understanding","author":"Mehan","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b256","article-title":"Scene representations for robotic spatial perception","volume":"8","author":"Mascaro","year":"2024","journal-title":"Annu. Rev. Control. Robot. Auton. Syst."},{"key":"10.1016\/j.robot.2026.105535_b257","series-title":"2021 IEEE International Conference on Robotics and Automation","first-page":"11626","article-title":"Compositional and scalable object slam","author":"Sharma","year":"2021"},{"key":"10.1016\/j.robot.2026.105535_b258","series-title":"2019 International Conference on Robotics and Automation","first-page":"7123","article-title":"Real-time monocular object-model aware sparse SLAM","author":"Hosseinzadeh","year":"2019"},{"issue":"12","key":"10.1016\/j.robot.2026.105535_b259","doi-asserted-by":"crossref","first-page":"25169","DOI":"10.1109\/TITS.2021.3136918","article-title":"Accurate object association and pose updating for semantic SLAM","volume":"23","author":"Chen","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.robot.2026.105535_b260","series-title":"2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1785","article-title":"Scene flow propagation for semantic mapping and object discovery in dynamic street scenes","author":"Kochanov","year":"2016"},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b261","doi-asserted-by":"crossref","first-page":"3531","DOI":"10.1109\/LRA.2022.3146502","article-title":"Volumetric instance-level semantic mapping via multi-view 2D-to-3D label diffusion","volume":"7","author":"Mascaro","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b262","series-title":"Multi-level map construction for dynamic scenes","author":"Hu","year":"2023"},{"key":"10.1016\/j.robot.2026.105535_b263","series-title":"2020 IEEE International Conference on Robotics and Automation","first-page":"2102","article-title":"Textslam: Visual slam with planar text features","author":"Li","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b264","series-title":"2021 IEEE International Conference on Robotics and Automation","first-page":"14192","article-title":"Tsdf++: A multi-object formulation for dynamic object tracking and reconstruction","author":"Grinvald","year":"2021"},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b265","doi-asserted-by":"crossref","first-page":"1910","DOI":"10.1109\/TRO.2023.3245986","article-title":"Semantic octree mapping and shannon mutual information computation for robot exploration","volume":"39","author":"Asgharivaskasi","year":"2023","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.robot.2026.105535_b266","series-title":"2022 IEEE\/ASME International Conference on Advanced Intelligent Mechatronics","first-page":"374","article-title":"Volumetric instance-level semantic mapping via blendmask","author":"Sun","year":"2022"},{"issue":"18","key":"10.1016\/j.robot.2026.105535_b267","doi-asserted-by":"crossref","first-page":"20657","DOI":"10.1109\/JSEN.2021.3099511","article-title":"RS-SLAM: A robust semantic SLAM in dynamic environments based on RGB-d sensor","volume":"21","author":"Ran","year":"2021","journal-title":"IEEE Sensors J."},{"key":"10.1016\/j.robot.2026.105535_b268","series-title":"2018 IEEE Intelligent Vehicles Symposium","first-page":"965","article-title":"Dense 3D semantic SLAM of traffic environment based on stereo vision","author":"Li","year":"2018"},{"key":"10.1016\/j.robot.2026.105535_b269","series-title":"Pocd: Probabilistic object-level change detection and volumetric mapping in semi-static scenes","author":"Qian","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b270","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1007\/s11554-013-0379-5","article-title":"Dense real-time mapping of object-class semantics from RGB-d video","volume":"10","author":"St\u00fcckler","year":"2015","journal-title":"J. Real-Time Image Process."},{"key":"10.1016\/j.robot.2026.105535_b271","series-title":"2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1897","article-title":"Dynamic body vslam with semantic constraints","author":"Reddy","year":"2015"},{"key":"10.1016\/j.robot.2026.105535_b272","series-title":"2019 International Conference on Robotics and Automation","first-page":"6891","article-title":"Dense 3D visual mapping via semantic simplification","author":"Morreale","year":"2019"},{"key":"10.1016\/j.robot.2026.105535_b273","series-title":"2022 International Joint Conference on Neural Networks","first-page":"1","article-title":"Efficient multi-task rgb-d scene analysis for indoor environments","author":"Seichter","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b274","series-title":"Infinitam v3: A framework for large-scale 3d reconstruction with loop closure","author":"Prisacariu","year":"2017"},{"key":"10.1016\/j.robot.2026.105535_b275","series-title":"2019 IEEE Winter Conference on Applications of Computer Vision","first-page":"1089","article-title":"Real-time progressive 3D semantic segmentation for indoor scenes","author":"Pham","year":"2019"},{"key":"10.1016\/j.robot.2026.105535_b276","series-title":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1094","article-title":"Tupper-map: Temporal and unified panoptic perception for 3d metric-semantic mapping","author":"Yang","year":"2021"},{"key":"10.1016\/j.robot.2026.105535_b277","doi-asserted-by":"crossref","unstructured":"Y. Xiong, R. Liao, H. Zhao, R. Hu, M. Bai, E. Yumer, R. Urtasun, Upsnet: A unified panoptic segmentation network, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 8818\u20138826.","DOI":"10.1109\/CVPR.2019.00902"},{"key":"10.1016\/j.robot.2026.105535_b278","doi-asserted-by":"crossref","unstructured":"D. Kim, S. Woo, J.-Y. Lee, I.S. Kweon, Video panoptic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9859\u20139868.","DOI":"10.1109\/CVPR42600.2020.00988"},{"key":"10.1016\/j.robot.2026.105535_b279","series-title":"2022 International Conference on Robotics and Automation","first-page":"8018","article-title":"Panoptic multi-tsdfs: a flexible representation for online multi-resolution volumetric mapping and long-term dynamic scene consistency","author":"Schmid","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b280","series-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"7233","article-title":"Panopticndt: Efficient and robust panoptic mapping","author":"Seichter","year":"2023"},{"key":"10.1016\/j.robot.2026.105535_b281","doi-asserted-by":"crossref","unstructured":"D. Wu, Z. Yan, H. Zha, Panorecon: Real-time panoptic 3d reconstruction from monocular video, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 21507\u201321518.","DOI":"10.1109\/CVPR52733.2024.02032"},{"key":"10.1016\/j.robot.2026.105535_b282","series-title":"2022 International Conference on Robotics and Automation","article-title":"Eprecon: An efficient framework for real-time panoptic 3D reconstruction from monocular video","author":"Zhou","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b283","doi-asserted-by":"crossref","unstructured":"F. Bernuy, J. Ruiz del Solar, Semantic mapping of large-scale outdoor scenes for autonomous off-road driving, in: Proceedings of the IEEE International Conference on Computer Vision Workshops, 2015, pp. 35\u201341.","DOI":"10.1109\/ICCVW.2015.26"},{"key":"10.1016\/j.robot.2026.105535_b284","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s10846-017-0744-x","article-title":"Topological semantic mapping and localization in urban road scenarios","volume":"92","author":"Bernuy","year":"2018","journal-title":"J. Intell. Robot. Syst."},{"key":"10.1016\/j.robot.2026.105535_b285","article-title":"Vision-based mapping of lane semantics and topology for intelligent vehicles","volume":"111","author":"Tian","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.robot.2026.105535_b286","series-title":"2018 IEEE International Conference on Real-Time Computing and Robotics","first-page":"520","article-title":"Indoor environment semantic topological mapping based on deep learning","author":"Zhao","year":"2018"},{"key":"10.1016\/j.robot.2026.105535_b287","series-title":"2018 IEEE International Conference on Robotics and Automation","first-page":"3818","article-title":"Topomap: Topological mapping and navigation based on visual slam maps","author":"Blochliger","year":"2018"},{"key":"10.1016\/j.robot.2026.105535_b288","series-title":"International Conference on Intelligent Robotics and Applications","first-page":"337","article-title":"Topological and semantic map generation for mobile robot indoor navigation","author":"Chen","year":"2021"},{"key":"10.1016\/j.robot.2026.105535_b289","series-title":"Conference on Robot Learning","first-page":"393","article-title":"Topological semantic graph memory for image-goal navigation","author":"Kim","year":"2023"},{"key":"10.1016\/j.robot.2026.105535_b290","doi-asserted-by":"crossref","unstructured":"I. Armeni, Z.-Y. He, J. Gwak, A.R. Zamir, M. Fischer, J. Malik, S. Savarese, 3d scene graph: A structure for unified semantics, 3d space, and camera, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 5664\u20135673.","DOI":"10.1109\/ICCV.2019.00576"},{"issue":"12","key":"10.1016\/j.robot.2026.105535_b291","doi-asserted-by":"crossref","first-page":"4921","DOI":"10.1109\/TCYB.2019.2931042","article-title":"3-d scene graph: A sparse and semantic representation of physical environments for intelligent agents","volume":"50","author":"Kim","year":"2019","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.robot.2026.105535_b292","unstructured":"S.-C. Wu, J. Wald, K. Tateno, N. Navab, F. Tombari, Scenegraphfusion: Incremental 3d scene graph prediction from rgb-d sequences, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 7515\u20137525."},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b293","doi-asserted-by":"crossref","first-page":"4110","DOI":"10.1109\/LRA.2022.3149572","article-title":"Topological semantic mapping by consolidation of deep visual features","volume":"7","author":"Sousa","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b294","doi-asserted-by":"crossref","first-page":"7809","DOI":"10.1109\/JSTARS.2022.3205746","article-title":"Automated semantics and topology representation of residential-building space using floor-plan raster maps","volume":"15","author":"Yang","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"10.1016\/j.robot.2026.105535_b295","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"9761","article-title":"A context-enhanced full-resolution floor plan segmentation network for topological semantic mapping","author":"Cao","year":"2024"},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b296","doi-asserted-by":"crossref","first-page":"9251","DOI":"10.1016\/j.ifacol.2023.10.007","article-title":"Semantic and topological mapping using intersection identification","volume":"56","author":"Fredriksson","year":"2023","journal-title":"IFAC-PapersOnLine"},{"key":"10.1016\/j.robot.2026.105535_b297","series-title":"ICRA 2025 Workshop on Foundation Models and Neuro-Symbolic AI for Robotics","article-title":"SENT map-semantically enhanced topological maps with foundation models","author":"Kathirvel","year":"2025"},{"issue":"1","key":"10.1016\/j.robot.2026.105535_b298","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/S0921-8890(03)00006-X","article-title":"Hybrid simultaneous localization and map building: a natural integration of topological and metric","volume":"44","author":"Tomatis","year":"2003","journal-title":"Robot. Auton. Syst."},{"key":"10.1016\/j.robot.2026.105535_b299","first-page":"4845","article-title":"Local metrical and global topological maps in the hybrid spatial semantic hierarchy","volume":"vol. 5","author":"Kuipers","year":"2004"},{"key":"10.1016\/j.robot.2026.105535_b300","series-title":"2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"5109","article-title":"Hybrid metric-topological-semantic mapping in dynamic environments","author":"Drouilly","year":"2015"},{"key":"10.1016\/j.robot.2026.105535_b301","series-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"590","article-title":"Semantic 3D occupancy mapping through efficient high order CRFs","author":"Yang","year":"2017"},{"key":"10.1016\/j.robot.2026.105535_b302","series-title":"2007 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1","article-title":"P3 & beyond: Solving energies with higher order cliques","author":"Kohli","year":"2007"},{"issue":"8","key":"10.1016\/j.robot.2026.105535_b303","doi-asserted-by":"crossref","first-page":"2391","DOI":"10.1109\/TCSVT.2018.2863027","article-title":"Hybrid modeling of non-rigid scenes from RGBD cameras","volume":"29","author":"Malleson","year":"2018","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.robot.2026.105535_b304","doi-asserted-by":"crossref","first-page":"61287","DOI":"10.1109\/ACCESS.2018.2873597","article-title":"Hierarchical semantic mapping using convolutional neural networks for intelligent service robotics","volume":"6","author":"Luo","year":"2018","journal-title":"IEEE Access"},{"issue":"12","key":"10.1016\/j.robot.2026.105535_b305","doi-asserted-by":"crossref","first-page":"16057","DOI":"10.1109\/TVT.2020.3041852","article-title":"Hybrid semi-dense 3D semantic-topological mapping from stereo visual-inertial odometry SLAM with loop closure detection","volume":"69","author":"Wen","year":"2020","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.robot.2026.105535_b306","series-title":"2020 IEEE International Conference on Robotics and Automation","first-page":"9659","article-title":"A hierarchical framework for collaborative probabilistic semantic mapping","author":"Yue","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b307","series-title":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"2417","article-title":"Hd-ccsom: Hierarchical and dense collaborative continuous semantic occupancy mapping through label diffusion","author":"Deng","year":"2022"},{"issue":"12\u201314","key":"10.1016\/j.robot.2026.105535_b308","doi-asserted-by":"crossref","first-page":"1510","DOI":"10.1177\/02783649211056674","article-title":"Kimera: From SLAM to spatial perception with 3D dynamic scene graphs","volume":"40","author":"Rosinol","year":"2021","journal-title":"Int. J. Robot. Res."},{"issue":"7","key":"10.1016\/j.robot.2026.105535_b309","doi-asserted-by":"crossref","first-page":"7076","DOI":"10.1109\/TIE.2021.3095812","article-title":"Building metric-topological map to efficient object search for mobile robot","volume":"69","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"10","key":"10.1016\/j.robot.2026.105535_b310","doi-asserted-by":"crossref","first-page":"1457","DOI":"10.1177\/02783649241229725","article-title":"Foundations of spatial perception for robotics: Hierarchical representations and real-time systems","volume":"43","author":"Hughes","year":"2024","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.robot.2026.105535_b311","doi-asserted-by":"crossref","unstructured":"J. Wald, H. Dhamo, N. Navab, F. Tombari, Learning 3d semantic scene graphs from 3d indoor reconstructions, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 3961\u20133970.","DOI":"10.1109\/CVPR42600.2020.00402"},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b312","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1109\/LRA.2020.2965893","article-title":"Graduated non-convexity for robust spatial perception: From non-minimal solvers to global outlier rejection","volume":"5","author":"Yang","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b313","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2024.3451395","article-title":"Clio: Real-time task-driven open-set 3d scene graphs","author":"Maggio","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b314","series-title":"Fast segment anything","author":"Zhao","year":"2023"},{"key":"10.1016\/j.robot.2026.105535_b315","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.robot.2026.105535_b316","doi-asserted-by":"crossref","DOI":"10.1016\/j.robot.2020.103632","article-title":"Object-RPE: Dense 3D reconstruction and pose estimation with convolutional neural networks","volume":"133","author":"Hoang","year":"2020","journal-title":"Robot. Auton. Syst."},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b317","doi-asserted-by":"crossref","first-page":"1975","DOI":"10.1109\/LRA.2023.3242872","article-title":"Towards long-term retrieval-based visual localization in indoor environments with changes","volume":"8","author":"Kabalar","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b318","series-title":"2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance","first-page":"1","article-title":"High-speed tracking-by-detection without using image information","author":"Bochinski","year":"2017"},{"key":"10.1016\/j.robot.2026.105535_b319","series-title":"2018 IEEE International Conference on Robotics and Automation","first-page":"1855","article-title":"Multi-view 3D entangled forest for semantic segmentation and mapping","author":"Antonello","year":"2018"},{"key":"10.1016\/j.robot.2026.105535_b320","series-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"385","article-title":"Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation","author":"Nakajima","year":"2018"},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b321","doi-asserted-by":"crossref","first-page":"3838","DOI":"10.1109\/LRA.2024.3371873","article-title":"Semantics-aware receding horizon planner for object-centric active mapping","volume":"9","author":"Lu","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b322","doi-asserted-by":"crossref","first-page":"6718","DOI":"10.1109\/LRA.2022.3176799","article-title":"Semantic-direct visual odometry","volume":"7","author":"Bao","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b323","series-title":"European Conference on Computer Vision","first-page":"834","article-title":"LSD-SLAM: Large-scale direct monocular SLAM","author":"Engel","year":"2014"},{"issue":"1","key":"10.1016\/j.robot.2026.105535_b324","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1109\/TPAMI.2023.3324320","article-title":"Textslam: Visual SLAM with semantic planar text features","volume":"46","author":"Li","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.robot.2026.105535_b325","series-title":"2011 10th IEEE International Symposium on Mixed and Augmented Reality","first-page":"127","article-title":"Kinectfusion: Real-time dense surface mapping and tracking","author":"Newcombe","year":"2011"},{"key":"10.1016\/j.robot.2026.105535_b326","series-title":"2019 International Conference on Robotics and Automation","first-page":"7108","article-title":"Semantic mapping for view-invariant relocalization","author":"Li","year":"2019"},{"issue":"1\u20132","key":"10.1016\/j.robot.2026.105535_b327","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1002\/nav.3800020109","article-title":"The hungarian method for the assignment problem","volume":"2","author":"Kuhn","year":"1955","journal-title":"Nav. Res. Logist. Q."},{"key":"10.1016\/j.robot.2026.105535_b328","series-title":"2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"4602","article-title":"SLAM with objects using a nonparametric pose graph","author":"Mu","year":"2016"},{"issue":"11","key":"10.1016\/j.robot.2026.105535_b329","doi-asserted-by":"crossref","first-page":"3069","DOI":"10.1007\/s11263-021-01513-4","article-title":"Fairmot: On the fairness of detection and re-identification in multiple object tracking","volume":"129","author":"Zhang","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.robot.2026.105535_b330","series-title":"Encyclopedia of Biometrics","first-page":"827","article-title":"Gaussian mixture models","author":"Reynolds","year":"2015"},{"key":"10.1016\/j.robot.2026.105535_b331","series-title":"2021 International Conference on 3D Vision (3DV)","first-page":"1362","article-title":"DSP-SLAM: Object oriented SLAM with deep shape priors","author":"Wang","year":"2021"},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b332","doi-asserted-by":"crossref","first-page":"2912","DOI":"10.1109\/TRO.2023.3273180","article-title":"An object slam framework for association, mapping, and high-level tasks","volume":"39","author":"Wu","year":"2023","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.robot.2026.105535_b333","doi-asserted-by":"crossref","unstructured":"M. Strecke, J. Stuckler, Em-fusion: Dynamic object-level slam with probabilistic data association, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 5865\u20135874.","DOI":"10.1109\/ICCV.2019.00596"},{"key":"10.1016\/j.robot.2026.105535_b334","first-page":"2","article-title":"Semantic iterative closest point through expectation-maximization.","volume":"vol. 1","author":"Parkison","year":"2018"},{"issue":"11","key":"10.1016\/j.robot.2026.105535_b335","doi-asserted-by":"crossref","first-page":"3052","DOI":"10.1109\/TVCG.2019.2932216","article-title":"Hierarchical topic model based object association for semantic SLAM","volume":"25","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"10.1016\/j.robot.2026.105535_b336","series-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"161","article-title":"Localization of classified objects in slam using nonparametric statistics and clustering","author":"Iqbal","year":"2018"},{"key":"10.1016\/j.robot.2026.105535_b337","series-title":"2012 10th IAPR International Workshop on Document Analysis Systems","first-page":"297","article-title":"Word image retrieval using bag of visual words","author":"Shekhar","year":"2012"},{"key":"10.1016\/j.robot.2026.105535_b338","doi-asserted-by":"crossref","unstructured":"G. Berton, C. Masone, B. Caputo, Rethinking visual geo-localization for large-scale applications, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4878\u20134888.","DOI":"10.1109\/CVPR52688.2022.00483"},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b339","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1109\/LRA.2018.2801879","article-title":"X-view: Graph-based semantic multi-view localization","volume":"3","author":"Gawel","year":"2018","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b340","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1109\/TRO.2018.2853729","article-title":"Vins-mono: A robust and versatile monocular visual-inertial state estimator","volume":"34","author":"Qin","year":"2018","journal-title":"IEEE Trans. Robot."},{"issue":"72","key":"10.1016\/j.robot.2026.105535_b341","first-page":"8","article-title":"Ceres solver: Tutorial & reference","volume":"2","author":"Agarwal","year":"2012","journal-title":"Google Inc"},{"key":"10.1016\/j.robot.2026.105535_b342","first-page":"216","article-title":"iSAM2: Incremental smoothing and mapping using the Bayes tree","volume":"vol. 31","author":"Kaess","year":"2012"},{"key":"10.1016\/j.robot.2026.105535_b343","series-title":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"4554","article-title":"CALC2. 0: Combining appearance, semantic and geometric information for robust and efficient visual loop closure","author":"Merrill","year":"2019"},{"key":"10.1016\/j.robot.2026.105535_b344","series-title":"2019 Chinese Control Conference","first-page":"4136","article-title":"Loop closure detection for visual SLAM fusing semantic information","author":"Hu","year":"2019"},{"key":"10.1016\/j.robot.2026.105535_b345","series-title":"2021 IEEE 6th International Conference on Signal and Image Processing","first-page":"245","article-title":"SV-loop: Semantic-visual loop closure detection with panoptic segmentation","author":"Yuan","year":"2021"},{"key":"10.1016\/j.robot.2026.105535_b346","series-title":"International Conference on Robotics in Alpe-Adria Danube Region","first-page":"580","article-title":"Seqslam with bag of visual words for appearance based loop closure detection","author":"Tsintotas","year":"2018"},{"key":"10.1016\/j.robot.2026.105535_b347","series-title":"2023 IEEE International Conference on Imaging Systems and Techniques","first-page":"1","article-title":"Semantic-based visual vocabulary for loop closure detection","author":"Papapetros","year":"2023"},{"issue":"10","key":"10.1016\/j.robot.2026.105535_b348","doi-asserted-by":"crossref","first-page":"4395","DOI":"10.1109\/TIV.2023.3298608","article-title":"Semantic loop closure detection for intelligent vehicles using panoramas","volume":"8","author":"Xiao","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.robot.2026.105535_b349","series-title":"2025 22nd International Conference on Ubiquitous Robots","first-page":"34","article-title":"Semantic loop closure for reducing false matches in SLAM","author":"Kim","year":"2025"},{"key":"10.1016\/j.robot.2026.105535_b350","series-title":"2021 IEEE International Intelligent Transportation Systems Conference","first-page":"2909","article-title":"Hierarchical loop closure detection for long-term visual SLAM with semantic-geometric descriptors","author":"Singh","year":"2021"},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b351","doi-asserted-by":"crossref","first-page":"2030","DOI":"10.1109\/TII.2020.3010580","article-title":"Semantic loop closure detection with instance-level inconsistency removal in dynamic industrial scenes","volume":"17","author":"Chen","year":"2021","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.robot.2026.105535_b352","article-title":"PRIOR-SLAM: Enabling visual SLAM for loop closure under large viewpoint variations","author":"Wang","year":"2025","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.robot.2026.105535_b353","series-title":"2022 30th Mediterranean Conference on Control and Automation","first-page":"731","article-title":"SLAM and map learning using hybrid semantic graph optimization","author":"Agrawal","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b354","first-page":"1281","article-title":"D3VO: Deep depth, deep pose and deep uncertainty for monocular visual odometry","author":"Yang","year":"2020","journal-title":"Proc. the IEEE\/CVF Conf. Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.robot.2026.105535_b355","doi-asserted-by":"crossref","unstructured":"F. Wimbauer, N. Yang, L. Von Stumberg, N. Zeller, D. Cremers, MonoRec: Semi-supervised dense reconstruction in dynamic environments from a single moving camera, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 6112\u20136122.","DOI":"10.1109\/CVPR46437.2021.00605"},{"issue":"4","key":"10.1016\/j.robot.2026.105535_b356","doi-asserted-by":"crossref","first-page":"4407","DOI":"10.1109\/LRA.2018.2869640","article-title":"Vlocnet++: Deep multitask learning for semantic visual localization and odometry","volume":"3","author":"Radwan","year":"2018","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"1","key":"10.1016\/j.robot.2026.105535_b357","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1109\/TPAMI.2020.3007546","article-title":"Simvodis: Simultaneous visual odometry, object detection, and instance segmentation","volume":"44","author":"Kim","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b358","doi-asserted-by":"crossref","first-page":"4244","DOI":"10.1109\/LRA.2022.3150854","article-title":"Simvodis++: Neural semantic visual odometry in dynamic environments","volume":"7","author":"Kim","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b359","series-title":"FindAnything: Open-vocabulary and object-centric mapping for robot exploration in any environment","author":"Laina","year":"2025"},{"key":"10.1016\/j.robot.2026.105535_b360","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"6657","article-title":"Resolving loop closure confusion in repetitive environments for visual slam through ai foundation models assistance","author":"Li","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b361","series-title":"How nerfs and 3d gaussian splatting are reshaping slam: a survey","first-page":"1","author":"Tosi","year":"2024"},{"issue":"1","key":"10.1016\/j.robot.2026.105535_b362","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1145\/3503250","article-title":"Nerf: Representing scenes as neural radiance fields for view synthesis","volume":"65","author":"Mildenhall","year":"2021","journal-title":"Commun. ACM"},{"issue":"2","key":"10.1016\/j.robot.2026.105535_b363","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1109\/LRA.2020.2965415","article-title":"Deepfactors: Real-time probabilistic dense monocular slam","volume":"5","author":"Czarnowski","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b364","doi-asserted-by":"crossref","unstructured":"X. Kong, S. Liu, M. Taher, A.J. Davison, vmap: Vectorised object mapping for neural field slam, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 952\u2013961.","DOI":"10.1109\/CVPR52729.2023.00098"},{"issue":"9","key":"10.1016\/j.robot.2026.105535_b365","doi-asserted-by":"crossref","first-page":"5950","DOI":"10.1109\/LRA.2023.3302176","article-title":"Ro-map: Real-time multi-object mapping with neural radiance fields","volume":"8","author":"Han","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b366","series-title":"2022 IEEE International Conference on Systems, Man, and Cybernetics","first-page":"430","article-title":"Meslam: Memory efficient slam based on neural fields","author":"Kruzhkov","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b367","doi-asserted-by":"crossref","unstructured":"H. Wang, J. Wang, L. Agapito, Co-slam: Joint coordinate and sparse parametric encodings for neural real-time slam, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 13293\u201313302.","DOI":"10.1109\/CVPR52729.2023.01277"},{"key":"10.1016\/j.robot.2026.105535_b368","doi-asserted-by":"crossref","unstructured":"M.M. Johari, C. Carta, F. Fleuret, Eslam: Efficient dense slam system based on hybrid representation of signed distance fields, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 17408\u201317419.","DOI":"10.1109\/CVPR52729.2023.01670"},{"issue":"8","key":"10.1016\/j.robot.2026.105535_b369","doi-asserted-by":"crossref","first-page":"4761","DOI":"10.1109\/LRA.2023.3289152","article-title":"Nisb-map: Scalable mapping with neural implicit spatial block","volume":"8","author":"Xiang","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b370","series-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"3437","article-title":"Nerf-slam: Real-time dense monocular slam with neural radiance fields","author":"Rosinol","year":"2023"},{"key":"10.1016\/j.robot.2026.105535_b371","series-title":"2023 IEEE International Conference on Robotics and Automation","first-page":"4171","article-title":"Imode: Real-time incremental monocular dense mapping using neural field","author":"Matsuki","year":"2023"},{"key":"10.1016\/j.robot.2026.105535_b372","series-title":"2024 International Conference on 3D Vision (3DV)","first-page":"42","article-title":"Nicer-slam: Neural implicit scene encoding for rgb slam","author":"Zhu","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b373","doi-asserted-by":"crossref","unstructured":"L. Liso, E. Sandstr\u00f6m, V. Yugay, L. Van Gool, M.R. Oswald, Loopy-slam: Dense neural slam with loop closures, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 20363\u201320373.","DOI":"10.1109\/CVPR52733.2024.01925"},{"key":"10.1016\/j.robot.2026.105535_b374","doi-asserted-by":"crossref","unstructured":"L. Li, L. Zhang, Z. Wang, Y. Shen, Gs3lam: Gaussian semantic splatting slam, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 3019\u20133027.","DOI":"10.1145\/3664647.3680739"},{"key":"10.1016\/j.robot.2026.105535_b375","article-title":"SDD-SLAM: Semantic-driven dynamic SLAM with Gaussian splatting","author":"Liu","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b376","series-title":"Large-scale Gaussian splatting SLAM","author":"Xin","year":"2025"},{"key":"10.1016\/j.robot.2026.105535_b377","series-title":"Gaussian mapping for evolving scenes","author":"Yugay","year":"2025"},{"issue":"21","key":"10.1016\/j.robot.2026.105535_b378","doi-asserted-by":"crossref","first-page":"6919","DOI":"10.3390\/s24216919","article-title":"Neural surfel reconstruction: Addressing loop closure challenges in large-scale 3D neural scene mapping","volume":"24","author":"Cui","year":"2024","journal-title":"Sensors (Basel, Switzerland)"},{"key":"10.1016\/j.robot.2026.105535_b379","unstructured":"D.S. Chaplot, R. Salakhutdinov, A. Gupta, S. Gupta, Neural topological slam for visual navigation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 12875\u201312884."},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b380","doi-asserted-by":"crossref","first-page":"4649","DOI":"10.1109\/LRA.2020.3003275","article-title":"Distributed consistent multi-robot semantic localization and mapping","volume":"5","author":"Tchuiev","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b381","series-title":"2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting","first-page":"1","article-title":"Cosar: Multi-robot collaborative semantic mapping over wireless networks","author":"Hu","year":"2023"},{"key":"10.1016\/j.robot.2026.105535_b382","series-title":"Active metric-semantic mapping by multiple aerial robots","author":"Liu","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b383","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1109\/TRO.2025.3526295","article-title":"Riemannian Optimization for Active Mapping With Robot Teams","volume":"41","author":"Asgharivaskasi","year":"2025","journal-title":"IEEE Trans. Robot."},{"issue":"76","key":"10.1016\/j.robot.2026.105535_b384","doi-asserted-by":"crossref","first-page":"166","DOI":"10.4114\/intartif.vol28iss76pp166-185","article-title":"Multi-robot exploration and semantic map building: Heterogeneous terrestrial robots and a drone","volume":"28","author":"Aguilar","year":"2025","journal-title":"Intel. Artif."},{"key":"10.1016\/j.robot.2026.105535_b385","doi-asserted-by":"crossref","unstructured":"A. Dai, A.X. Chang, M. Savva, M. Halber, T. Funkhouser, M. Nie\u00dfner, Scannet: Richly-annotated 3d reconstructions of indoor scenes, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 5828\u20135839.","DOI":"10.1109\/CVPR.2017.261"},{"key":"10.1016\/j.robot.2026.105535_b386","article-title":"Matterport3D: Learning from RGB-d data in indoor environments","author":"Chang","year":"2017","journal-title":"Int. Conf. 3D Vis. (3DV)"},{"key":"10.1016\/j.robot.2026.105535_b387","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"2127","article-title":"Active vision dataset benchmark","author":"Ammirato","year":"2018"},{"key":"10.1016\/j.robot.2026.105535_b388","doi-asserted-by":"crossref","unstructured":"A. Geiger, P. Lenz, R. Urtasun, Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite, in: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, CVPR, 2012, pp. 3354\u20133361.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"10.1016\/j.robot.2026.105535_b389","doi-asserted-by":"crossref","unstructured":"M. Menze, A. Geiger, Object Scene Flow for Autonomous Vehicles, in: Conference on Computer Vision and Pattern Recognition, CVPR, 2015.","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"10.1016\/j.robot.2026.105535_b390","article-title":"KITTI-360: A novel dataset and benchmarks for urban scene understanding in 2D and 3D","author":"Liao","year":"2022","journal-title":"Pattern Anal. Mach. Intell. (PAMI)"},{"key":"10.1016\/j.robot.2026.105535_b391","doi-asserted-by":"crossref","unstructured":"H. Caesar, V. Bankiti, A.H. Lang, S. Vora, V.E. Liong, Q. Xu, A. Krishnan, Y. Pan, G. Baldan, O. Beijbom, nuscenes: A multimodal dataset for autonomous driving, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11621\u201311631.","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"10.1016\/j.robot.2026.105535_b392","series-title":"Active metric-semantic mapping by multiple aerial robots","author":"Liu","year":"2023"},{"issue":"3","key":"10.1016\/j.robot.2026.105535_b393","doi-asserted-by":"crossref","first-page":"2989","DOI":"10.1109\/LRA.2024.3363542","article-title":"3D active metric-semantic slam","volume":"9","author":"Tao","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105535_b394","series-title":"Learning to map for active semantic goal navigation","author":"Georgakis","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b395","series-title":"2024 International Joint Conference on Neural Networks","first-page":"1","article-title":"RASLS: Reinforcement learning active SLAM approach with layout semantic","author":"Tian","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b396","series-title":"2022 International Conference on Robotics and Automation","first-page":"9272","article-title":"Hierarchical representations and explicit memory: Learning effective navigation policies on 3d scene graphs using graph neural networks","author":"Ravichandran","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b397","series-title":"Toward robust active semantic SLAM via Max-Mixtures","author":"Baxter","year":"2020"},{"key":"10.1016\/j.robot.2026.105535_b398","series-title":"The International Symposium of Robotics Research","first-page":"19","article-title":"Continual slam: Beyond lifelong simultaneous localization and mapping through continual learning","author":"V\u00f6disch","year":"2022"},{"key":"10.1016\/j.robot.2026.105535_b399","series-title":"European Conference on Computer Vision","first-page":"41","article-title":"Learn to memorize and to forget: A continual learning perspective of dynamic slam","author":"Li","year":"2024"},{"key":"10.1016\/j.robot.2026.105535_b400","doi-asserted-by":"crossref","unstructured":"N. V\u00f6disch, D. Cattaneo, W. Burgard, A. Valada, Covio: Online continual learning for visual-inertial odometry, in: Proceedings of the Ieee\/Cvf Conference on Computer Vision and Pattern Recognition, 2023, pp. 2464\u20132473.","DOI":"10.1109\/CVPRW59228.2023.00245"},{"key":"10.1016\/j.robot.2026.105535_b401","article-title":"BYE: Build your encoder with one sequence of exploration data for long-term dynamic scene understanding","author":"Huang","year":"2025","journal-title":"IEEE Robot. Autom. Lett."}],"container-title":["Robotics and Autonomous Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0921889026002071?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0921889026002071?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T15:01:21Z","timestamp":1781103681000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0921889026002071"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":401,"alternative-id":["S0921889026002071"],"URL":"https:\/\/doi.org\/10.1016\/j.robot.2026.105535","relation":{},"ISSN":["0921-8890"],"issn-type":[{"value":"0921-8890","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Semantic Visual Simultaneous Localization and Mapping: A survey on state of the art, challenges, and future directions","name":"articletitle","label":"Article Title"},{"value":"Robotics and Autonomous Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.robot.2026.105535","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"105535"}}