{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:45:22Z","timestamp":1785717922972,"version":"3.56.0"},"reference-count":150,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":71,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62461002"],"award-info":[{"award-number":["62461002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-53024-2","type":"journal-article","created":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T13:02:31Z","timestamp":1779627751000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Task-oriented visual SLAM: a comprehensive map classification framework for dynamic indoor robot manipulation"],"prefix":"10.1038","volume":"16","author":[{"given":"Xuerou","family":"Shen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingzhang","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,24]]},"reference":[{"issue":"6","key":"53024_CR1","doi-asserted-by":"publisher","first-page":"5767","DOI":"10.1109\/LRA.2024.3396057","volume":"9","author":"M Kim","year":"2024","unstructured":"Kim, M., Kwon, Y., Lee, S. B. & Yoon, S. E. CCTV-informed human-aware robot navigation in crowded indoor environments. IEEE Robot. Autom. Lett. 9(6), 5767\u20135774 (2024).","journal-title":"IEEE Robot. Autom. Lett."},{"key":"53024_CR2","doi-asserted-by":"crossref","unstructured":"R\u00fcnz, M., Buffier, M. & Agapito, L. (eds) MaskFusion: Real-time recognition, tracking and reconstruction of multiple moving objects. In 17th IEEE International Symposium on Mixed and Augmented Reality (ISMAR); 2018 Oct 16\u201320; Munich, Germany (2018).","DOI":"10.1109\/ISMAR.2018.00024"},{"key":"53024_CR3","doi-asserted-by":"crossref","unstructured":"Ren, Y. F., Xu, B. B., Choi, C. L., Leutenegger, S. & IEEE (eds) Visual-inertial multi-instance dynamic SLAM with object-level relocalisation. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS); 2022 Oct 23\u201327; Kyoto, Japan (2022).","DOI":"10.1109\/IROS47612.2022.9981795"},{"issue":"12","key":"53024_CR4","doi-asserted-by":"publisher","first-page":"14239","DOI":"10.1109\/TII.2024.3441661","volume":"20","author":"TL Jin","year":"2024","unstructured":"Jin, T. L. et al. Whole-body inverse kinematics and operation-oriented motion planning for robot mobile manipulation. IEEE Trans. Industr. Inf. 20(12), 14239\u201314248 (2024).","journal-title":"IEEE Trans. Industr. Inf."},{"key":"53024_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117734","author":"IA Kazerouni","year":"2022","unstructured":"Kazerouni, I. A., Fitzgerald, L., Dooly, G. & Toal, D. A survey of state-of-the-art on visual SLAM. Expert Syst. Appl. https:\/\/doi.org\/10.1016\/j.eswa.2022.117734 (2022).","journal-title":"Expert Syst. Appl."},{"key":"53024_CR6","unstructured":"Qing, Y. & Yu, H. (eds) A review of visual SLAM algorithms for fusion of point-line features. In 13th International Conference on Computer Engineering and Networks (CENet); 2023 2024 Nov 03\u201305; Wuxi, Peoples R China (2024)."},{"key":"53024_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z. J., Sheng, W. H., Yang, G. C., Su, Z. D., Liang, B. J. & IEEE (eds) Comparison and analysis of feature method and direct method in visual SLAM technology for social robots. In 13th World Congress on Intelligent Control and Automation (WCICA); 2018 Jul 04\u201308; Changsha, Peoples R China (2018).","DOI":"10.1109\/WCICA.2018.8630714"},{"issue":"6","key":"53024_CR8","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1007\/s12559-018-9591-8","volume":"10","author":"R Li","year":"2018","unstructured":"Li, R., Wang, S. & Gu, D. Ongoing evolution of visual SLAM from geometry to deep learning: Challenges and opportunities. Cogn. Comput. 10(6), 875\u2013889 (2018).","journal-title":"Cogn. Comput."},{"key":"53024_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2022.102298","author":"SP Li","year":"2022","unstructured":"Li, S. P. et al. Overview of deep learning application on visual SLAM. Displays https:\/\/doi.org\/10.1016\/j.displa.2022.102298 (2022).","journal-title":"Displays"},{"key":"53024_CR10","doi-asserted-by":"publisher","DOI":"10.3390\/s21041243","author":"S Arshad","year":"2021","unstructured":"Arshad, S. & Kim, G. W. Role of deep learning in loop closure detection for visual and Lidar SLAM: A survey. Sensors https:\/\/doi.org\/10.3390\/s21041243 (2021).","journal-title":"Sensors"},{"issue":"6","key":"53024_CR11","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1109\/TRO.2016.2624754","volume":"32","author":"C Cadena","year":"2016","unstructured":"Cadena, C. et al. Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age. IEEE Trans. Robot. 32(6), 1309\u20131332 (2016).","journal-title":"IEEE Trans. Robot."},{"issue":"9","key":"53024_CR12","doi-asserted-by":"publisher","first-page":"5696","DOI":"10.1109\/LRA.2023.3300227","volume":"8","author":"H Min","year":"2023","unstructured":"Min, H., Han, K. M. & Kim, Y. J. OctoMap-RT: Fast probabilistic volumetric mapping using ray-tracing GPUs. IEEE Robot. Autom. Lett. 8(9), 5696\u20135703 (2023).","journal-title":"IEEE Robot. Autom. Lett."},{"key":"53024_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111571","author":"XH Wang","year":"2024","unstructured":"Wang, X. H., Yin, Z. Y., Zhang, F. Q., Feng, D. & Wang, Z. S. MP-NeRF: More refined deblurred neural radiance field for 3D reconstruction of blurred images. Knowl. Based Syst. https:\/\/doi.org\/10.1016\/j.knosys.2024.111571 (2024).","journal-title":"Knowl. Based Syst."},{"key":"53024_CR14","doi-asserted-by":"crossref","unstructured":"Hedman, P., Srinivasan, P. P., Mildenhall, B., Barron, J. T., Debevec, P. & IEEE (eds) Baking neural radiance fields for real-time view synthesis. In 18th IEEE\/CVF International Conference on Computer Vision (ICCV); 2021 Oct 11\u201317; Electrical Network (2021).","DOI":"10.1109\/ICCV48922.2021.00582"},{"key":"53024_CR15","doi-asserted-by":"crossref","unstructured":"Reiser, C., Peng, S. Y., Liao, Y. Y., Geiger, A. & IEEE (eds) KiloNeRF: Speeding up neural radiance fields with thousands of tiny MLPs. In 18th IEEE\/CVF International Conference on Computer Vision (ICCV); 2021 Oct 11\u201317; Electrical Network (2021).","DOI":"10.1109\/ICCV48922.2021.01407"},{"key":"53024_CR16","doi-asserted-by":"crossref","unstructured":"Kurz, A., Neff, T., Lv, Z. Y., Zollh\u00f6fer, M. & Steinberger, M. (eds) AdaNeRF: Adaptive sampling for real-time rendering of neural radiance fields. In 17th European Conference on Computer Vision (ECCV); 2022 Oct 23\u201327; Tel Aviv, Israel (2022).","DOI":"10.1007\/978-3-031-19790-1_16"},{"key":"53024_CR17","doi-asserted-by":"crossref","unstructured":"Xu, D. J., Jiang, Y. F., Wang, P. H., Fan, Z. W., Shi, H., Wang, Z. Y. (eds) SinNeRF: Training neural radiance fields on complex scenes from a single image. In 17th European Conference on Computer Vision (ECCV); 2022 Oct 23\u201327; Tel Aviv, Israel (2022).","DOI":"10.1007\/978-3-031-20047-2_42"},{"key":"53024_CR18","unstructured":"Tang, J. X., Chen, X. K., Wang, J. B. & Zeng, G. (eds) Compressible-composable NeRF via rank-residual decomposition. In 36th Conference on Neural Information Processing Systems (NeurIPS); 2022 Nov 28\u2013Dec 09; Electrical Network (2022)."},{"key":"53024_CR19","doi-asserted-by":"crossref","unstructured":"Han, Y., Yu, T., Yu, X., Xu, D., Zheng, B., Dai, Z. et al. Super-NeRF: View-consistent detail generation for NeRF super-resolution. IEEE Trans. Vis. Comput. Graph. (2024).","DOI":"10.1109\/TVCG.2024.3490840"},{"key":"53024_CR20","doi-asserted-by":"crossref","unstructured":"Verbin, D., Hedman, P., Mildenhall, B., Zickler, T., Barron, J. T. & Srinivasan, P. P. Ref-NeRF: Structured view-dependent appearance for neural radiance fields. IEEE Trans. Pattern Anal. Mach. Intell. (2024).","DOI":"10.1109\/TPAMI.2024.3360018"},{"key":"53024_CR21","doi-asserted-by":"crossref","unstructured":"Zhan, Y. F., Li, Z. X., Niu, M. Y., Zhong, Z. H., Nobuhara, S., Nishino, K. et al. (eds) KFD-NeRF: Rethinking dynamic NeRF with Kalman filter. In 18th European Conference on Computer Vision (ECCV); 2024 Sep 29\u2013Oct 04 2025; Milan, Italy (2025).","DOI":"10.1007\/978-3-031-72995-9_1"},{"key":"53024_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129653","author":"JX Liu","year":"2025","unstructured":"Liu, J. X., Cheng, H., Wang, S., Zhao, F. & Li, M. NeRF dynamic scene reconstruction based on motion, semantic information and inpainting. Neurocomputing https:\/\/doi.org\/10.1016\/j.neucom.2025.129653 (2025).","journal-title":"Neurocomputing"},{"issue":"8","key":"53024_CR23","doi-asserted-by":"publisher","first-page":"4429","DOI":"10.1109\/TVCG.2024.3397828","volume":"31","author":"B Fei","year":"2025","unstructured":"Fei, B. et al. 3D Gaussian Splatting as a new era: A survey. IEEE Trans. Vis. Comput. Graph. 31(8), 4429\u20134449 (2025).","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"53024_CR24","doi-asserted-by":"publisher","DOI":"10.1145\/3592433","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T. & Drettakis, G. 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. https:\/\/doi.org\/10.1145\/3592433 (2023).","journal-title":"ACM Trans. Graph."},{"key":"53024_CR25","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3549551","author":"D Li","year":"2025","unstructured":"Li, D., Huang, S.-S. & Huang, H. MPGS: Multi-plane Gaussian splatting for compact scenes rendering. IEEE Trans. Vis. Comput. Graph. https:\/\/doi.org\/10.1109\/TVCG.2025.3549551 (2025).","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"53024_CR26","doi-asserted-by":"crossref","unstructured":"Yang, Z. Y., Gao, X. Y., Zhou, W., Jiao, S. H., Zhang, Y. Q., Jin, X. G. et al. (eds) Deformable 3D Gaussians for high-fidelity monocular dynamic scene reconstruction. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2024 Jun 16\u201322; Seattle, WA (2024).","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"53024_CR27","doi-asserted-by":"crossref","unstructured":"Huang, L. T., Bai, J. Y., Guo, J., Li, Y. Q. & Guo, Y. W. (eds) On the error analysis of 3D Gaussian splatting and an optimal projection strategy. In 18th European Conference on Computer Vision (ECCV); 2024 Sep 29-Oct 04; Milan, Italy (2025).","DOI":"10.1007\/978-3-031-72643-9_15"},{"key":"53024_CR28","unstructured":"Cheng, K., Long, X. X., Yang, K. Z., Yao, Y., Yin, W., Ma, Y. X. et al. (eds) GaussianPro: 3D Gaussian splatting with progressive propagation. In 41st International Conference on Machine Learning (ICML); 2024 Jul 21\u201327; Vienna, Austria (2024)."},{"key":"53024_CR29","doi-asserted-by":"crossref","unstructured":"Fang, G. C. & Wang, B. (eds) Mini-splatting: Representing scenes with a constrained number of Gaussians. In 18th European Conference on Computer Vision (ECCV); 2024 Sep 29-Oct 04; Milan, Italy (2024).","DOI":"10.1007\/978-3-031-72980-5_10"},{"key":"53024_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, J. H., Zhan, F. N., Xu, M. Y., Lu, S. J., Xing, E. & IEEE (eds) FreGS: 3D Gaussian splatting with progressive frequency regularization. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2024 Jun 16\u201322; Seattle, WA (2024).","DOI":"10.1109\/CVPR52733.2024.02024"},{"key":"53024_CR31","doi-asserted-by":"crossref","unstructured":"Hamdi, A., Melas-Kyriazi, L., Mai, J. J., Qian, G. C., Liu, R. S., Vondrick, C. et al. (eds) GES: Generalized exponential splatting for efficient radiance field rendering. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2024 Jun 16\u201322; Seattle, WA (2024).","DOI":"10.1109\/CVPR52733.2024.01873"},{"key":"53024_CR32","doi-asserted-by":"crossref","unstructured":"Liu, X., Zhan, X. H., Tang, J. X., Shan, Y., Zeng, G., Lin, D. H. et al. (eds) HumanGaussian: Text-driven 3D human generation with Gaussian splatting. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2024 Jun 16\u201322; Seattle, WA (2024).","DOI":"10.1109\/CVPR52733.2024.00635"},{"key":"53024_CR33","doi-asserted-by":"crossref","unstructured":"Huang, Q. Q., Leonard, J. J. & IEEE (eds) GAPSLAM: Blending Gaussian approximation and particle filters for real-time non-Gaussian SLAM. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS); 2023 Oct 01\u201305; Detroit, MI (2023).","DOI":"10.1109\/IROS55552.2023.10341889"},{"key":"53024_CR34","doi-asserted-by":"crossref","unstructured":"Hu, J. R., Chen, X. H., Feng, B. Y., Li, G. L., Yang, L. J., Bao, H. et al. (eds) CG-SLAM: Efficient dense RGB-D SLAM in a consistent uncertainty-aware 3D Gaussian field. In 18th European Conference on Computer Vision (ECCV); 2024 Sep 29-Oct 04; Milan, Italy (2025).","DOI":"10.1007\/978-3-031-72698-9_6"},{"issue":"10","key":"53024_CR35","doi-asserted-by":"publisher","first-page":"8778","DOI":"10.1109\/LRA.2024.3451390","volume":"9","author":"YM Ji","year":"2024","unstructured":"Ji, Y. M. et al. NEDS-SLAM: A neural explicit dense semantic SLAM framework using 3D Gaussian Splatting. IEEE Robot. Autom. Lett. 9(10), 8778\u20138785 (2024).","journal-title":"IEEE Robot. Autom. Lett."},{"key":"53024_CR36","doi-asserted-by":"crossref","unstructured":"Li, M. R., Liu, S. H., Zhou, H., Zhu, G. H., Cheng, N., Deng, T. C., et al. (eds) SGS-SLAM: Semantic Gaussian splatting for neural dense SLAM. In 18th European Conference on Computer Vision (ECCV); 2024 Sep 29-Oct 04; Milan, Italy (2025).","DOI":"10.1007\/978-3-031-72751-1_10"},{"issue":"12","key":"53024_CR37","doi-asserted-by":"publisher","first-page":"11794","DOI":"10.1109\/LRA.2024.3498773","volume":"9","author":"SM Jiao","year":"2024","unstructured":"Jiao, S. M., Li, Y. & Shan, Z. W. DFS-SLAM: A visual SLAM algorithm for deep fusion of semantic information. IEEE Robot. Autom. Lett. 9(12), 11794\u201311801 (2024).","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"6","key":"53024_CR38","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","volume":"37","author":"C Campos","year":"2021","unstructured":"Campos, C., Elvira, R., Rodriguez, J. J. G., Montiel, J. M. M. & Tardos, J. D. ORB-SLAM3: An accurate open-source library for visual, visual-inertial, and multimap SLAM. IEEE Trans. Robot. 37(6), 1874\u20131890 (2021).","journal-title":"IEEE Trans. Robot."},{"key":"53024_CR39","doi-asserted-by":"crossref","unstructured":"Withey, D. J., Matebese, B. T. & IEEE (eds) An OctoMap-based 3D CostMap. In 22nd Annual International Conference of the Rapid-Product-Development-Association-of-South-Africa (RAPDASA) \/ Robotics and Mechatronics Conference (RobMech)\/Conference of Pattern-Recognition-Association-of-South-Africa (PRASA); 2021 Nov 03\u201305; CSIR Natl Laser Centre, Pretoria, South Africa (2022).","DOI":"10.1109\/RAPDASA-RobMech-PRAS53819.2021.9829092"},{"key":"53024_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Y. C., Hu, B. R., Huang, J. K., Tai, Y. W., Tang, C. K. & IEEE (eds) Instance neural radiance field. In IEEE\/CVF International Conference on Computer Vision (ICCV); 2023 Oct 02\u201306; Paris, France (2023).","DOI":"10.1109\/ICCV51070.2023.00079"},{"key":"53024_CR41","doi-asserted-by":"crossref","unstructured":"Mitroudas, T., Balaska, V., Psomoulis, A., Gasteratos, A. & IEEE (eds) Light-weight approach for safe landing in populated areas. In IEEE International Conference on Robotics and Automation (ICRA); 2024 May 13\u201317; Yokohama, Japan (2024).","DOI":"10.1109\/ICRA57147.2024.10611639"},{"key":"53024_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110582","author":"PG Wang","year":"2025","unstructured":"Wang, P. G. et al. Real-time semantic SLAM-based 3D reconstruction robot for greenhouse vegetables. Comput. Electron. Agric. https:\/\/doi.org\/10.1016\/j.compag.2025.110582 (2025).","journal-title":"Comput. Electron. Agric."},{"issue":"5","key":"53024_CR43","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J. M. M. & Tard\u00f3s, J. D. ORB-SLAM: A versatile and accurate monocular SLAM system. IEEE Trans. Robot. 31(5), 1147\u20131163 (2015).","journal-title":"IEEE Trans. Robot."},{"key":"53024_CR44","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2197","author":"DM Kim","year":"2024","unstructured":"Kim, D. M. et al. Real-time reconstruction of pipes using RGB-D cameras. Comput. Anim. Virtual Worlds https:\/\/doi.org\/10.1002\/cav.2197 (2024).","journal-title":"Comput. Anim. Virtual Worlds"},{"issue":"1","key":"53024_CR45","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/TNNLS.2022.3175775","volume":"35","author":"A Karambakhsh","year":"2024","unstructured":"Karambakhsh, A. et al. SparseVoxNet: 3-D object recognition with sparsely aggregation of 3-D dense blocks. IEEE Trans. Neural Netw. Learn. Syst. 35(1), 532\u2013546 (2024).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"2","key":"53024_CR46","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1109\/TPAMI.2022.3164083","volume":"45","author":"YH Li","year":"2023","unstructured":"Li, Y. H., Yao, T., Pan, Y. W. & Mei, T. Contextual transformer networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 1489\u20131500 (2023).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"53024_CR47","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2201","author":"XQ Zhu","year":"2024","unstructured":"Zhu, X. Q. et al. TMSDNet: Transformer with multi-scale dense network for single and multi-view 3D reconstruction. Comput. Anim. Virtual Worlds https:\/\/doi.org\/10.1002\/cav.2201 (2024).","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"53024_CR48","doi-asserted-by":"publisher","first-page":"4380","DOI":"10.1109\/TRO.2025.3584559","volume":"41","author":"J Michaux","year":"2025","unstructured":"Michaux, J. et al. Let us make a splan: Risk-aware trajectory optimization in a normalized Gaussian splat. IEEE Trans. Robot. 41, 4380\u20134397 (2025).","journal-title":"IEEE Trans. Robot."},{"key":"53024_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111503","author":"M G\u00f6k","year":"2024","unstructured":"G\u00f6k, M. Dynamic path planning via dueling double deep Q-network (D3QN) with prioritized experience replay. Appl. Soft Comput. https:\/\/doi.org\/10.1016\/j.asoc.2024.111503 (2024).","journal-title":"Appl. Soft Comput."},{"issue":"3","key":"53024_CR50","first-page":"2621","volume":"137","author":"J Xin","year":"2023","unstructured":"Xin, J., Du, K. N., Feng, J. L. & Shan, M. An improved high precision 3D semantic mapping of indoor scenes from RGB-D images. Comput. Model. Eng. Sci. 137(3), 2621\u20132640 (2023).","journal-title":"Comput. Model. Eng. Sci."},{"key":"53024_CR51","doi-asserted-by":"crossref","unstructured":"Millane, A., Oleynikova, H., Wirbelt, E., Steinert, R., Ramasamy, V., Tingdahl, D. et al. (eds) nvblox: GPU-accelerated incremental signed distance field mapping. In IEEE International Conference on Robotics and Automation (ICRA); 2024 May 13\u201317; Yokohama, Japan (2024).","DOI":"10.1109\/ICRA57147.2024.10611532"},{"key":"53024_CR52","doi-asserted-by":"crossref","unstructured":"Bai, Y. L., Miao, Z. Q., Wang, X. K., Liu, Y., Wang, H. S., Wang, Y. N. et al. (eds) VDBblox: Accurate and efficient distance fields for path planning and mesh reconstruction. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS); 2023 Oct 01\u201305; Detroit, MI (2023).","DOI":"10.1109\/IROS55552.2023.10342123"},{"key":"53024_CR53","doi-asserted-by":"crossref","unstructured":"Pan, Y., Kompis, Y., Bartolomei, L., Mascaro, R., Stachniss, C., Chli, M. et al. (eds) Voxfield: Non-projective signed distance fields for online planning and 3D reconstruction. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS); 2022 Oct 23\u201327; Kyoto, Japan (2022).","DOI":"10.1109\/IROS47612.2022.9981318"},{"key":"53024_CR54","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3198724","author":"LL Xia","year":"2022","unstructured":"Xia, L. L., Meng, D. A., Zhang, J. J., Zhang, D. C. & Hu, Z. Q. Visual-inertial simultaneous localization and mapping: Dynamically fused point-line feature extraction and engineered robotic applications. IEEE Trans. Instrum. Meas. https:\/\/doi.org\/10.1109\/TIM.2022.3198724 (2022).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"53024_CR55","doi-asserted-by":"publisher","first-page":"52906","DOI":"10.1109\/ACCESS.2020.2981648","volume":"8","author":"CB Tao","year":"2020","unstructured":"Tao, C. B., Gao, Z., Yan, J. L., Li, C. G. & Cui, G. Z. Indoor 3D semantic robot VSLAM based on mask regional convolutional neural network. IEEE Access 8, 52906\u201352916 (2020).","journal-title":"IEEE Access"},{"issue":"2","key":"53024_CR56","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1109\/TBDATA.2022.3187413","volume":"9","author":"XL Bi","year":"2023","unstructured":"Bi, X. L., Hu, J. W., Xiao, B., Li, W. S. & Gao, X. B. IEMask R-CNN: Information-enhanced Mask R-CNN. IEEE Trans. Big Data 9(2), 688\u2013700 (2023).","journal-title":"IEEE Trans. Big Data"},{"key":"53024_CR57","doi-asserted-by":"publisher","first-page":"126525","DOI":"10.1109\/ACCESS.2022.3226212","volume":"10","author":"XG Zhang","year":"2022","unstructured":"Zhang, X. G., Wang, X. K. & Zhang, R. D. Dynamic semantics SLAM based on improved Mask R-CNN. IEEE Access 10, 126525\u2013126535 (2022).","journal-title":"IEEE Access"},{"key":"53024_CR58","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1016\/j.neucom.2021.06.072","volume":"459","author":"DW Yi","year":"2021","unstructured":"Yi, D. W., Su, J. Y. & Chen, W. H. Probabilistic faster R-CNN with stochastic region proposing: Towards object detection and recognition in remote sensing imagery. Neurocomputing 459, 290\u2013301 (2021).","journal-title":"Neurocomputing"},{"key":"53024_CR59","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104317","author":"EH Chai","year":"2021","unstructured":"Chai, E. H., Ta, L., Ma, Z. F. & Zhi, M. ERF-YOLO: A YOLO algorithm compatible with fewer parameters and higher accuracy. Image Vis. Comput. https:\/\/doi.org\/10.1016\/j.imavis.2021.104317 (2021).","journal-title":"Image Vis. Comput."},{"key":"53024_CR60","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126655","author":"G Oreski","year":"2023","unstructured":"Oreski, G. YOLO*C\u2014Adding context improves YOLO performance. Neurocomputing https:\/\/doi.org\/10.1016\/j.neucom.2023.126655 (2023).","journal-title":"Neurocomputing"},{"key":"53024_CR61","doi-asserted-by":"crossref","unstructured":"Xu, J. L., Pan, F., Han, X. H., Wang, L. Z., Wang, Y. H., Li, W. X. et al. (eds) EdgeTrim-YOLO: Improved trim YOLO framework tailored for deployment on edge devices. In 4th International Conference on Computer Communication and Artificial Intelligence (CCAI); 2024 May 24\u201326; Xian, Peoples R China (2024).","DOI":"10.1109\/CCAI61966.2024.10602964"},{"key":"53024_CR62","doi-asserted-by":"crossref","unstructured":"Nawal, M., Brahmanage, G., Leung, H. & IEEE (eds) RGB-PD SLAM: Scale consistent monocular SLAM using predicted depth. In 11th IEEE International Conference on Consumer Electronics\u2014Taiwan (ICCE-Taiwan)\u2014Empower of Innovative Consumer Technology; 2024 Jul 09\u201311; Taichung, Taiwan (2024).","DOI":"10.1109\/ICCE-Taiwan62264.2024.10674415"},{"issue":"8","key":"53024_CR63","doi-asserted-by":"publisher","first-page":"11882","DOI":"10.1109\/TVT.2025.3552541","volume":"74","author":"Y He","year":"2025","unstructured":"He, Y. et al. MD-SLAM: A multi-task deep-learning-based visual SLAM system in dynamic environments. IEEE Trans. Veh. Technol. 74(8), 11882\u201311893 (2025).","journal-title":"IEEE Trans. Veh. Technol."},{"key":"53024_CR64","doi-asserted-by":"crossref","unstructured":"Li, B. N., Meng, X. W. & IEEE (eds) CP-SLAM: Real-time visual SLAM based on continuous probability map. In 2nd Asia-Pacific Computer Technologies Conference (APCT); 2023 Jan 06\u201308; Electrical Network (2023).","DOI":"10.1109\/APCT58752.2023.00012"},{"issue":"7","key":"53024_CR65","doi-asserted-by":"publisher","first-page":"10878","DOI":"10.1109\/JSEN.2024.3365822","volume":"24","author":"HX Zhang","year":"2024","unstructured":"Zhang, H. X., Wang, D. Y. & Huo, J. Real-time dynamic SLAM using moving probability based on IMU and segmentation. IEEE Sens. J. 24(7), 10878\u201310891 (2024).","journal-title":"IEEE Sens. J."},{"issue":"10","key":"53024_CR66","doi-asserted-by":"publisher","first-page":"7053","DOI":"10.1007\/s11760-024-03375-y","volume":"18","author":"Q Sun","year":"2024","unstructured":"Sun, Q., Liu, W., Zou, J. J., Xu, Z. Q. & Li, Y. B. GGC-SLAM: A VSLAM system based on predicted static probability of feature points in dynamic environments. Signal Image Video Process. 18(10), 7053\u20137064 (2024).","journal-title":"Signal Image Video Process."},{"key":"53024_CR67","doi-asserted-by":"crossref","unstructured":"Yu, C., Liu, Z. X., Liu, X. J., Xie, F. G., Yang, Y., Wei, Q. et al. (eds) DS-SLAM: A semantic visual SLAM towards dynamic environments. In 25th IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS); 2018 Oct 01\u201305; Madrid, Spain (2018).","DOI":"10.1109\/IROS.2018.8593691"},{"issue":"9","key":"53024_CR68","doi-asserted-by":"publisher","first-page":"14596","DOI":"10.1109\/JSEN.2024.3373892","volume":"24","author":"ZH Lin","year":"2024","unstructured":"Lin, Z. H., Zhang, Q., Tian, Z., Yu, P. Z. & Lan, J. L. DPL-SLAM: Enhancing dynamic point-line SLAM through dense semantic methods. IEEE Sens. J. 24(9), 14596\u201314607 (2024).","journal-title":"IEEE Sens. J."},{"key":"53024_CR69","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2026.115424","author":"RJ Li","year":"2026","unstructured":"Li, R. J., Chen, H., Ma, Y. C., Nie, F. P. & Huang, Y. X. MIARS: Mutual information-guided feature selection with angle reconstruction and semantic alignment for multi-label learning. Knowl. Based Syst. https:\/\/doi.org\/10.1016\/j.knosys.2026.115424 (2026).","journal-title":"Knowl. Based Syst."},{"key":"53024_CR70","doi-asserted-by":"publisher","DOI":"10.1016\/j.fss.2025.109368","author":"LZ Chen","year":"2025","unstructured":"Chen, L. Z., Cai, M. J. & Li, Q. G. Multi-label feature selection with high-level semantic label relationships based on fuzzy rough sets. Fuzzy Sets Syst. https:\/\/doi.org\/10.1016\/j.fss.2025.109368 (2025).","journal-title":"Fuzzy Sets Syst."},{"key":"53024_CR71","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111335","author":"ZL Lin","year":"2025","unstructured":"Lin, Z. L., Lin, Y. J., Zhang, Y. & Zhao, H. Hierarchical feature selection driven by inter-category relevance and semantic independence. Pattern Recogn. https:\/\/doi.org\/10.1016\/j.patcog.2024.111335 (2025).","journal-title":"Pattern Recogn."},{"key":"53024_CR72","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130993","author":"S Dhali","year":"2025","unstructured":"Dhali, S. & Dasgupta, B. Trifocal SLAM: A dynamic SLAM based on three frame views. Neurocomputing https:\/\/doi.org\/10.1016\/j.neucom.2025.130993 (2025).","journal-title":"Neurocomputing"},{"key":"53024_CR73","doi-asserted-by":"publisher","DOI":"10.3390\/s25216641","author":"TY Yang","year":"2025","unstructured":"Yang, T. Y., Wei, S. F., Nan, J. X., Li, M. Y. & Li, M. R. BDGS-SLAM: A probabilistic 3D Gaussian splatting framework for robust SLAM in dynamic environments. Sensors (Basel) https:\/\/doi.org\/10.3390\/s25216641 (2025).","journal-title":"Sensors (Basel)"},{"key":"53024_CR74","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1109\/TRO.2024.3502508","volume":"41","author":"GR Li","year":"2025","unstructured":"Li, G. R., Liu, X. Y. & Loianno, G. Human-aware physical human-robot collaborative transportation and manipulation with multiple aerial robots. IEEE Trans. Robot. 41, 762\u2013781 (2025).","journal-title":"IEEE Trans. Robot."},{"key":"53024_CR75","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2024.102845","author":"C Zheng","year":"2025","unstructured":"Zheng, C. et al. Semantic map construction approach for human-robot collaborative manufacturing. Robot. Comput. Integr. Manuf. https:\/\/doi.org\/10.1016\/j.rcim.2024.102845 (2025).","journal-title":"Robot. Comput. Integr. Manuf."},{"key":"53024_CR76","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.131281","author":"MH Lv","year":"2025","unstructured":"Lv, M. H. et al. Si-CA MobileNet: A lightweight and efficient convolutional neural network for distracted driver detection. Neurocomputing https:\/\/doi.org\/10.1016\/j.neucom.2025.131281 (2025).","journal-title":"Neurocomputing"},{"key":"53024_CR77","doi-asserted-by":"crossref","unstructured":"Li, Y. Y., Hu, J., Wen, Y., Evangelidis, G., Salahi, K., Wang, Y. Z. et al. (eds) Rethinking vision transformers for MobileNet size and speed. In IEEE\/CVF International Conference on Computer Vision (ICCV); 2023 Oct 02\u201306 2023; Paris, France (2023).","DOI":"10.1109\/ICCV51070.2023.01549"},{"key":"53024_CR78","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2024.100636","author":"SE Mathe","year":"2024","unstructured":"Mathe, S. E., Kondaveeti, H. K., Vappangi, S., Vanambathina, S. D. & Kumaravelu, N. K. A comprehensive review on applications of Raspberry Pi. Comput. Sci. Rev. https:\/\/doi.org\/10.1016\/j.cosrev.2024.100636 (2024).","journal-title":"Comput. Sci. Rev."},{"key":"53024_CR79","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105057","author":"M Kang","year":"2024","unstructured":"Kang, M., Ting, C. M., Ting, F. F. & Phan, R. C. W. ASF-YOLO: A novel YOLO model with attentional scale sequence fusion for cell instance segmentation. Image Vis. Comput. https:\/\/doi.org\/10.1016\/j.imavis.2024.105057 (2024).","journal-title":"Image Vis. Comput."},{"key":"53024_CR80","doi-asserted-by":"crossref","unstructured":"Zins, M., Simon, G., Berger, M. O. & IEEE (eds) OA-SLAM: Leveraging objects for camera relocalization in visual SLAM. In 21st IEEE International Symposium on Mixed and Augmented Reality (ISMAR); 2022 Oct 17\u201322; Singapore, Singapore (2022).","DOI":"10.1109\/ISMAR55827.2022.00090"},{"key":"53024_CR81","doi-asserted-by":"crossref","unstructured":"Song, S. F., Zhao, J. Q., Feng, T. T., Ye, C., Xiong, L. & IEEE (eds) Scale estimation with dual quadrics for monocular object SLAM. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS); 2022 Oct 23\u201327; Kyoto, Japan (2022).","DOI":"10.1109\/IROS47612.2022.9981554"},{"issue":"9","key":"53024_CR82","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1080\/0951192X.2021.1946853","volume":"34","author":"ZT Wang","year":"2021","unstructured":"Wang, Z. T. et al. Instance segmentation of point cloud captured by RGB-D sensor based on deep learning. Int. J. Comput. Integr. Manuf. 34(9), 950\u2013963 (2021).","journal-title":"Int. J. Comput. Integr. Manuf."},{"key":"53024_CR83","unstructured":"Zhou, C. Yolact++ Better Real-Time Instance Segmentation (2020)."},{"key":"53024_CR84","doi-asserted-by":"publisher","DOI":"10.3390\/rs16040663","author":"YQ Li","year":"2024","unstructured":"Li, Y. Q. et al. Classification of typical static objects in road scenes based on LO-Net. Remote Sens. https:\/\/doi.org\/10.3390\/rs16040663 (2024).","journal-title":"Remote Sens."},{"key":"53024_CR85","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.103955","author":"DS Hong","year":"2020","unstructured":"Hong, D. S., Chen, H. H., Hsiao, P. Y., Fu, L. C. & Siao, S. M. CrossFusion net: Deep 3D object detection based on RGB images and point clouds in autonomous driving. Image Vis. Comput. https:\/\/doi.org\/10.1016\/j.imavis.2020.103955 (2020).","journal-title":"Image Vis. Comput."},{"key":"53024_CR86","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2024.105376","author":"M Mahmoud","year":"2024","unstructured":"Mahmoud, M., Chen, W., Yang, Y. & Li, Y. X. Automated BIM generation for large-scale indoor complex environments based on deep learning. Autom. Constr. https:\/\/doi.org\/10.1016\/j.autcon.2024.105376 (2024).","journal-title":"Autom. Constr."},{"key":"53024_CR87","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3336651","author":"XY Qiang","year":"2023","unstructured":"Qiang, X. Y., He, W. B., Chen, S. Y., Lv, Q. Z. & Huang, F. Hierarchical point cloud transformer: A unified vegetation semantic segmentation model for multisource point clouds based on deep learning. IEEE Trans. Geosci. Remote Sens. https:\/\/doi.org\/10.1109\/TGRS.2023.3336651 (2023).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"3","key":"53024_CR88","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1109\/TCSVT.2022.3207789","volume":"33","author":"XT Wang","year":"2023","unstructured":"Wang, X. T., Fan, X. P. & Zhao, D. B. PointFilterNet: A filtering network for point cloud denoising. IEEE Trans. Circuits Syst. Video Technol. 33(3), 1276\u20131290 (2023).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"53024_CR89","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2023.103539","author":"ZY Chen","year":"2024","unstructured":"Chen, Z. Y. et al. Local aggressive and physically realizable adversarial attacks on 3D point cloud. Comput. Secur. https:\/\/doi.org\/10.1016\/j.cose.2023.103539 (2024).","journal-title":"Comput. Secur."},{"key":"53024_CR90","doi-asserted-by":"crossref","unstructured":"Sinha, D. & El-Sharkawy, M. (eds) Thin MobileNet: An enhanced MobileNet architecture. In IEEE 10th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON); 2019 Oct 10\u201312; Columbia Univ, New York, NY (2019).","DOI":"10.1109\/UEMCON47517.2019.8993089"},{"key":"53024_CR91","doi-asserted-by":"crossref","unstructured":"Bouguezzi, S., Faiedh, H., Souani, C. & IEEE (eds) Slim MobileNet: An enhanced deep convolutional neural network. In 18th International Multi-conference on Systems, Signals & Devices (SSD); 2021 Mar 22\u201325; Monastir, Tunisia (2021).","DOI":"10.1109\/SSD52085.2021.9429519"},{"key":"53024_CR92","doi-asserted-by":"crossref","unstructured":"Huynh, V. T., Nguyen, T. T., Nguyen, T. V. & Tran, M. T. (eds) MobileNet-SA: Lightweight CNN with self attention for sketch classification. In 11th Pacific-Rim Symposium on Image and Video Technology (PSIVT); 2023 Nov 22\u201324; Auckland University Technology, City Campus, Auckland, New Zealand (2024).","DOI":"10.1007\/978-981-97-0376-0_9"},{"key":"53024_CR93","doi-asserted-by":"crossref","unstructured":"Sucar, E., Wada, K., Davison, A. & IEEE (eds) NodeSLAM: Neural object descriptors for multi-view shape reconstruction. In 8th International Conference on 3D Vision (3DV); 2020 Nov 25\u201328; Electrical Network (2020).","DOI":"10.1109\/3DV50981.2020.00105"},{"issue":"11","key":"53024_CR94","doi-asserted-by":"publisher","first-page":"17234","DOI":"10.1109\/TITS.2024.3418949","volume":"25","author":"R Tian","year":"2024","unstructured":"Tian, R. et al. DynaQuadric: Dynamic quadric SLAM for quadric initialization, mapping, and tracking. IEEE Trans. Intell. Transp. Syst. 25(11), 17234\u201317246 (2024).","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"53024_CR95","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3378264","author":"XM Wu","year":"2024","unstructured":"Wu, X. M., Liu, Z. M., Tian, Y. X., Liu, Z. & Chen, W. H. KN-SLAM: Keypoints and neural implicit encoding SLAM. IEEE Trans. Instrum. Meas. https:\/\/doi.org\/10.1109\/TIM.2024.3378264 (2024).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"53024_CR96","unstructured":"Gao, R. H., Chang, Y. Y., Mall, S., Li, F. F. & Wu, J. J. (eds) OBJECTFOLDER: A dataset of objects with implicit visual, auditory, and tactile representations. In 5th Conference on Robot Learning (CoRL); 2021 Nov 08\u201311; London, England (2021)."},{"key":"53024_CR97","doi-asserted-by":"crossref","unstructured":"Gao, R. H., Si, Z. L., Chang, Y. Y., Clarke, S., Bohg, J., Li, F. F. et al. (eds) OBJECTFOLDER 2.0: A multisensory object dataset for Sim2Real transfer. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2022 Jun 18\u201324; New Orleans, LA (2022).","DOI":"10.1109\/CVPR52688.2022.01034"},{"key":"53024_CR98","doi-asserted-by":"publisher","DOI":"10.3390\/s23187921","author":"YM Chang","year":"2023","unstructured":"Chang, Y. M., Hu, J. & Xu, S. Y. OTE-SLAM: An object tracking enhanced visual SLAM system for dynamic environments. Sensors https:\/\/doi.org\/10.3390\/s23187921 (2023).","journal-title":"Sensors"},{"key":"53024_CR99","doi-asserted-by":"crossref","unstructured":"Henein, M., Abello, M., Ila, V. & Mahony, R. (eds) Exploring the effect of meta-structural information on the global consistency of SLAM. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)\/Workshop on Machine Learning Methods for High-Level Cognitive Capabilities in Robotics; 2017 Sep 24\u201328; Vancouver, Canada (2017).","DOI":"10.1109\/IROS.2017.8205970"},{"issue":"1","key":"53024_CR100","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","volume":"109","author":"FZ Zhuang","year":"2021","unstructured":"Zhuang, F. Z. et al. A comprehensive survey on transfer learning. Proc. IEEE 109(1), 43\u201376 (2021).","journal-title":"Proc. IEEE"},{"key":"53024_CR101","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108488","author":"XG Li","year":"2024","unstructured":"Li, X. G., Ji, W. T. & Huang, J. D. Local instance-based transfer learning for reinforcement learning. Eng. Appl. Artif. Intell. https:\/\/doi.org\/10.1016\/j.engappai.2024.108488 (2024).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"53024_CR102","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1016\/j.isprsjprs.2022.11.013","volume":"195","author":"W Huang","year":"2023","unstructured":"Huang, W., Shi, Y. L., Xiong, Z. T., Wang, Q. & Zhu, X. X. Semi-supervised bidirectional alignment for remote sensing cross-domain scene classification. ISPRS J. Photogramm. Remote Sens. 195, 192\u2013203 (2023).","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"53024_CR103","doi-asserted-by":"publisher","first-page":"17160","DOI":"10.1109\/TASE.2025.3575097","volume":"22","author":"QX Zhao","year":"2025","unstructured":"Zhao, Q. X., Zheng, M. H., Li, Z. X., Huang, S. C. & Shi, W. Robot dexterous grasping in cluttered scenes based on single-view point cloud. IEEE Trans. Autom. Sci. Eng. 22, 17160\u201317169 (2025).","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"53024_CR104","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.131.223602","author":"CH Lee","year":"2023","unstructured":"Lee, C. H. et al. Coherent two-photon LIDAR with incoherent light. Phys. Rev. Lett. https:\/\/doi.org\/10.1103\/PhysRevLett.131.223602 (2023).","journal-title":"Phys. Rev. Lett."},{"issue":"1","key":"53024_CR105","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0921-8890(03)00006-X","volume":"44","author":"N Tomatis","year":"2003","unstructured":"Tomatis, N., Nourbakhsh, I. & Siegwart, R. Hybrid simultaneous localization and map building: A natural integration of topological and metric. Robot. Auton. Syst. 44(1), 3\u201314 (2003).","journal-title":"Robot. Auton. Syst."},{"key":"53024_CR106","doi-asserted-by":"crossref","unstructured":"Sim, R., Little, J. J. & IEEE (eds) Autonomous vision-based exploration and mapping using hybrid maps and Rao-Blackwellised particle filters. In IEEE\/RSJ International Conference on Intelligent Robots and Systems; 2006 Oct 09\u201313; Beijing, Peoples R China (2006).","DOI":"10.1109\/IROS.2006.282485"},{"key":"53024_CR107","doi-asserted-by":"crossref","unstructured":"Konolige, K., Marder-Eppstein, E., Marthi, B. & IEEE (eds) Navigation in hybrid metric-topological maps. In IEEE International Conference on Robotics and Automation (ICRA); 2011 May 09\u201313; Shanghai, Peoples R China (2011).","DOI":"10.1109\/ICRA.2011.5980074"},{"key":"53024_CR108","doi-asserted-by":"crossref","unstructured":"Choi, J. & IEEE (eds) Hybrid map-based SLAM using a Velodyne laser scanner. In IEEE 17th International Conference on Intelligent Transportation Systems (ITSC); 2014 Oct 08\u201311; Qingdao, Peoples R China (2014).","DOI":"10.1109\/ITSC.2014.6958185"},{"key":"53024_CR109","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3209726","author":"YM Ding","year":"2022","unstructured":"Ding, Y. M., Xiong, Z., Xiong, J., Cui, Y. & Cao, Z. G. OGI-SLAM2: A hybrid map SLAM framework grounded in inertial-based SLAM. IEEE Trans. Instrum. Meas. https:\/\/doi.org\/10.1109\/TIM.2022.3209726 (2022).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"53024_CR110","doi-asserted-by":"crossref","unstructured":"Abate, M., Chang, Y., Hughes, N., Carlone, L. (eds) Kimera2: Robust and accurate metric-semantic SLAM in the real world. In 18th International Conference on Experimental Robotics (ISER); 2023 Nov 26\u201330; Chiangmai, Thailand (2024).","DOI":"10.1007\/978-3-031-63596-0_8"},{"issue":"12\u201314","key":"53024_CR111","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1177\/02783649211056674","volume":"40","author":"A Rosinol","year":"2021","unstructured":"Rosinol, A. et al. Kimera: From SLAM to spatial perception with 3D dynamic scene graphs. Int. J. Robot. Res. 40(12\u201314), 1510\u20131546 (2021).","journal-title":"Int. J. Robot. Res."},{"issue":"5","key":"53024_CR112","doi-asserted-by":"publisher","first-page":"2009","DOI":"10.1109\/TKDE.2023.3312358","volume":"36","author":"CX Wang","year":"2024","unstructured":"Wang, C. X. et al. GTCAlign: Global topology consistency-based graph alignment. IEEE Trans. Knowl. Data Eng. 36(5), 2009\u20132025 (2024).","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"53024_CR113","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2024.104729","author":"G Younes","year":"2024","unstructured":"Younes, G., Khalil, D., Zelek, J. & Asmar, D. H-SLAM: Hybrid direct-indirect visual SLAM. Robot. Auton. Syst. https:\/\/doi.org\/10.1016\/j.robot.2024.104729 (2024).","journal-title":"Robot. Auton. Syst."},{"key":"53024_CR114","doi-asserted-by":"publisher","first-page":"2682","DOI":"10.1109\/TASE.2024.3382770","volume":"22","author":"HC Jiang","year":"2025","unstructured":"Jiang, H. C., Qian, R., Du, L., Pu, J. & Feng, J. F. UL-SLAM: A universal monocular line-based SLAM via unifying structural and non-structural constraints. IEEE Trans. Autom. Sci. Eng. 22, 2682\u20132699 (2025).","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"issue":"1","key":"53024_CR115","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1109\/TRO.2022.3199087","volume":"39","author":"HS Yin","year":"2023","unstructured":"Yin, H. S., Li, S. M., Tao, Y., Guo, J. L. & Huang, B. Dynam-SLAM: An accurate, robust stereo visual-inertial SLAM method in dynamic environments. IEEE Trans. Robot. 39(1), 289\u2013308 (2023).","journal-title":"IEEE Trans. Robot."},{"key":"53024_CR116","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2022.111001","author":"X Gao","year":"2022","unstructured":"Gao, X., Zhang, G. Y. & Xiong, Y. J. Multi-scale multi-modal fusion for object detection in autonomous driving based on selective kernel. Measurement https:\/\/doi.org\/10.1016\/j.measurement.2022.111001 (2022).","journal-title":"Measurement"},{"key":"53024_CR117","doi-asserted-by":"publisher","DOI":"10.3390\/rs14020420","author":"GQ Qi","year":"2022","unstructured":"Qi, G. Q. et al. Small object detection method based on adaptive spatial parallel convolution and fast multi-scale fusion. Remote Sens. https:\/\/doi.org\/10.3390\/rs14020420 (2022).","journal-title":"Remote Sens."},{"key":"53024_CR118","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3449944","author":"YM Xu","year":"2024","unstructured":"Xu, Y. M., Li, B. L., Wang, Y. & Cui, Y. H. Filter fusion: Camera-LiDAR filter fusion for 3-D object detection with a robust fused head. IEEE Trans. Instrum. Meas. https:\/\/doi.org\/10.1109\/TIM.2024.3449944 (2024).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"53024_CR119","doi-asserted-by":"crossref","unstructured":"Li, B. Y., Zou, D. P., Sartori, D., Pei, L., Yu, W. X. & IEEE (eds) TextSLAM: Visual SLAM with planar text features. In IEEE International Conference on Robotics and Automation (ICRA); 2020 May 31\u2013Jun 15; Electrical Network (2020).","DOI":"10.1109\/ICRA40945.2020.9197233"},{"key":"53024_CR120","doi-asserted-by":"crossref","unstructured":"Johari, M. M., Carta, C., Fleuret, F. & IEEE (eds) ESLAM: Efficient dense SLAM system based on hybrid representation of signed distance fields. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2023 Jun 17\u201324; Vancouver, Canada (2023).","DOI":"10.1109\/CVPR52729.2023.01670"},{"key":"53024_CR121","doi-asserted-by":"crossref","unstructured":"Huang, C. G., Mees, O., Zeng, A. & Burgard, W. (eds) Audio visual language maps for robot navigation. In 18th International Conference on Experimental Robotics (ISER); 2023 Nov 26\u201330; Chiangmai, Thailand (2024).","DOI":"10.1007\/978-3-031-63596-0_10"},{"key":"53024_CR122","doi-asserted-by":"crossref","unstructured":"Xin, Z., Yue, Y. F., Zhang, L. J., Wu, C. M. & IEEE (eds) HERO-SLAM: Hybrid enhanced robust optimization of neural SLAM. In IEEE International Conference on Robotics and Automation (ICRA); 2024 May 13\u201317; Yokohama, Japan (2024).","DOI":"10.1109\/ICRA57147.2024.10610000"},{"key":"53024_CR123","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3432336","author":"W Wang","year":"2024","unstructured":"Wang, W. et al. HVL-SLAM: Hybrid vision and LiDAR fusion for SLAM. IEEE Trans. Geosci. Remote Sens. https:\/\/doi.org\/10.1109\/TGRS.2024.3432336 (2024).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"53024_CR124","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3316258","author":"XW Ji","year":"2023","unstructured":"Ji, X. W. et al. Object SLAM based on spatial layout and semantic consistency. IEEE Trans. Instrum. Meas. https:\/\/doi.org\/10.1109\/TIM.2023.3316258 (2023).","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"3","key":"53024_CR125","doi-asserted-by":"publisher","first-page":"5361","DOI":"10.1109\/JSEN.2024.3515137","volume":"25","author":"RL Zeng","year":"2025","unstructured":"Zeng, R. L., Zheng, Z. X., Pan, Z. H. & Yu, L. Multimodal sensors fusion SLAM based on local control and multiscale distance analysis. IEEE Sens. J. 25(3), 5361\u20135369 (2025).","journal-title":"IEEE Sens. J."},{"issue":"10","key":"53024_CR126","doi-asserted-by":"publisher","first-page":"10564","DOI":"10.1109\/TII.2023.3240578","volume":"19","author":"D Kong","year":"2023","unstructured":"Kong, D. et al. Explicit points-of-interest driven Siamese transformer for 3D LiDAR place recognition in outdoor challenging environments. IEEE Trans. Ind. Inf. 19(10), 10564\u201310577 (2023).","journal-title":"IEEE Trans. Ind. Inf."},{"key":"53024_CR127","doi-asserted-by":"publisher","first-page":"3078","DOI":"10.1109\/TRO.2025.3562440","volume":"41","author":"WB Zhu","year":"2025","unstructured":"Zhu, W. B., Yuan, J., Zhang, X. B. & Chen, F. Bridging the gap between semantics and geometry in SLAM: A semantic-geometric tight-coupling monocular visual object SLAM system. IEEE Trans. Robot. 41, 3078\u20133098 (2025).","journal-title":"IEEE Trans. Robot."},{"key":"53024_CR128","doi-asserted-by":"publisher","DOI":"10.3390\/rs17101691","author":"JL Fan","year":"2025","unstructured":"Fan, J. L. et al. EMS-SLAM: Dynamic RGB-D SLAM with semantic-geometric constraints for GNSS-denied environments. Remote Sens. https:\/\/doi.org\/10.3390\/rs17101691 (2025).","journal-title":"Remote Sens."},{"key":"53024_CR129","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3228006","author":"SH Cheng","year":"2023","unstructured":"Cheng, S. H., Sun, C. H., Zhang, S. J. & Zhang, D. F. SG-SLAM: A real-time RGB-D visual SLAM toward dynamic scenes with semantic and geometric information. IEEE Trans. Instrum. Meas. https:\/\/doi.org\/10.1109\/TIM.2022.3228006 (2023).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"53024_CR130","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111054","author":"ZH Lin","year":"2025","unstructured":"Lin, Z. H. et al. SLAM2: Simultaneous localization and multimode mapping for indoor dynamic environments. Pattern Recogn. https:\/\/doi.org\/10.1016\/j.patcog.2024.111054 (2025).","journal-title":"Pattern Recogn."},{"key":"53024_CR131","doi-asserted-by":"crossref","unstructured":"Cai, Y. C., Gao, J. F., Pohl, C., Asfour, T. & IEEE (eds) Visual imitation learning of task-oriented object grasping and rearrangement. In 2024 International Conference on Intelligent Robots and Systems; 2024 Oct 14\u201318 2024; Abu Dhabi, United Arab Emirates (2024).","DOI":"10.1109\/IROS58592.2024.10801466"},{"key":"53024_CR132","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102247","author":"X Wang","year":"2024","unstructured":"Wang, X., Sun, Z. J., Chehri, A., Jeon, G. & Song, Y. C. Deep learning and multi-modal fusion for real-time multi-object tracking: Algorithms, challenges, datasets, and comparative study. Inf. Fusion https:\/\/doi.org\/10.1016\/j.inffus.2024.102247 (2024).","journal-title":"Inf. Fusion"},{"key":"53024_CR133","doi-asserted-by":"crossref","unstructured":"Chappuis, C., Zermatten, V., Lobry, S., Le Saux, B., Tuia, D. & IEEE (eds) Prompt-RSVQA: Prompting visual context to a language model for Remote Sensing Visual Question Answering. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2022 Jun 18\u201324; New Orleans, LA (2022).","DOI":"10.1109\/CVPRW56347.2022.00143"},{"key":"53024_CR134","doi-asserted-by":"crossref","unstructured":"Tong, S. B., Liu, Z., Zhai, Y. X., Ma, Y., Lecun, Y., Xie, S. N. et al. (eds) Eyes wide shut? Exploring the visual shortcomings of multimodal LLMs. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2024 Jun 16\u201322; Seattle, WA (2024).","DOI":"10.1109\/CVPR52733.2024.00914"},{"issue":"10","key":"53024_CR135","doi-asserted-by":"publisher","first-page":"13311","DOI":"10.1109\/JIOT.2025.3532494","volume":"12","author":"Y Weng","year":"2025","unstructured":"Weng, Y., Yang, K. Y., Liu, Z., He, W. B. & Tang, X. Y. LGVLM-mIoT: A lightweight generative visual-language model for multilingual IoT applications. IEEE Internet Things J. 12(10), 13311\u201313326 (2025).","journal-title":"IEEE Internet Things J."},{"key":"53024_CR136","doi-asserted-by":"publisher","first-page":"2765","DOI":"10.1109\/TRO.2025.3552348","volume":"41","author":"T Chen","year":"2025","unstructured":"Chen, T. et al. Splat-Nav: Safe real-time robot navigation in Gaussian splatting maps. IEEE Trans. Robot. 41, 2765\u20132784 (2025).","journal-title":"IEEE Trans. Robot."},{"key":"53024_CR137","doi-asserted-by":"crossref","unstructured":"Gao, X. J., Li, X. Y., Zhuang, Y. Y., Zhang, Q., Hu, W. B., Zhang, C. P. et al. (eds) Mani-GS: Gaussian splatting manipulation with triangular mesh. In 2025 Conference on Computer Vision and Pattern Recognition-CVPR-Annual; 2025 Jun 10\u201317 2025; Nashville, TN (2025).","DOI":"10.1109\/CVPR52734.2025.01993"},{"key":"53024_CR138","doi-asserted-by":"crossref","unstructured":"Shen, S. Y., Shao, T. J., Zhou, K., Jiang, C. F. F., Yang, Y. & IEEE Computer SOC (eds) EnliveningGS: Active locomotion of 3DGS. In 2025 Conference on Computer Vision and Pattern Recognition-CVPR-Annual; 2025 Jun 10\u201317 2025; Nashville, TN (2025).","DOI":"10.1109\/CVPR52734.2025.00092"},{"key":"53024_CR139","doi-asserted-by":"publisher","DOI":"10.3390\/s24196258","author":"ZH Lin","year":"2024","unstructured":"Lin, Z. H., Tian, Z., Zhang, Q., Zhuang, H. Y. & Lan, J. L. Enhanced visual SLAM for collision-free driving with lightweight autonomous cars. Sensors https:\/\/doi.org\/10.3390\/s24196258 (2024).","journal-title":"Sensors"},{"key":"53024_CR140","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110329","author":"YS Guo","year":"2024","unstructured":"Guo, Y. S. et al. DSCA: A dual semantic correlation alignment method for domain adaptation object detection. Pattern Recogn. https:\/\/doi.org\/10.1016\/j.patcog.2024.110329 (2024).","journal-title":"Pattern Recogn."},{"issue":"13","key":"53024_CR141","doi-asserted-by":"publisher","first-page":"23","DOI":"10.54254\/2755-2721\/2025.18471","volume":"60","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Tian, Q. & Tang, C. Review of object detection based on event cameras. Comput. Eng. Appl. 60(13), 23\u201335 (2024).","journal-title":"Comput. Eng. Appl."},{"issue":"1","key":"53024_CR142","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","volume":"44","author":"G Gallego","year":"2022","unstructured":"Gallego, G. et al. Event-based vision: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 44(1), 154\u2013180 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"53024_CR143","doi-asserted-by":"crossref","unstructured":"Sundar, V., Dutson, M., Ardelean, A., Bruschini, C., Charbon, E., Gupta, M. et al. (eds) Generalized event cameras. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2024 Jun 16\u201322; Seattle, WA (2024).","DOI":"10.1109\/CVPR52733.2024.02362"},{"issue":"9","key":"53024_CR144","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"KY Zhou","year":"2022","unstructured":"Zhou, K. Y., Yang, J. K., Loy, C. C. & Liu, Z. W. Learning to prompt for vision-language models. Int. J. Comput. Vis. 130(9), 2337\u20132348 (2022).","journal-title":"Int. J. Comput. Vis."},{"key":"53024_CR145","doi-asserted-by":"crossref","unstructured":"Zhou, K. Y., Yang, J. K., Loy, C. C., Liu, Z. W. & IEEE Comp SOC (eds) Conditional prompt learning for vision-language models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2022 Jun 18\u201324 2022; New Orleans, LA (2022).","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"3","key":"53024_CR146","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.1109\/TPAMI.2024.3507000","volume":"47","author":"P Xu","year":"2025","unstructured":"Xu, P. et al. LVLM-EHub: A comprehensive evaluation benchmark for large vision-language models. IEEE Trans. Pattern Anal. Mach. Intell. 47(3), 1877\u20131893 (2025).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"8","key":"53024_CR147","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","volume":"46","author":"JY Zhang","year":"2024","unstructured":"Zhang, J. Y., Huang, J. X., Jin, S. & Lu, S. J. Vision-language models for vision tasks: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(8), 5625\u20135644 (2024).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"53024_CR148","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3704435","volume":"57","author":"YJ Qin","year":"2025","unstructured":"Qin, Y. J. et al. Tool learning with foundation models. ACM Comput. Surv. 57(4), 1\u201340 (2025).","journal-title":"ACM Comput. Surv."},{"issue":"6","key":"53024_CR149","doi-asserted-by":"publisher","first-page":"5146","DOI":"10.1109\/TCSVT.2023.3332814","volume":"34","author":"MQ Yang","year":"2024","unstructured":"Yang, M. Q., Gao, Y. J., Tang, L. Z., Hou, J. & Hu, B. Wearable eye-tracking system for synchronized multimodal data acquisition. IEEE Trans. Circuits Syst. Video Technol. 34(6), 5146\u20135159 (2024).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"53024_CR150","doi-asserted-by":"publisher","first-page":"2027","DOI":"10.1109\/TMM.2023.3291503","volume":"26","author":"DH Chen","year":"2024","unstructured":"Chen, D. H. & Zhang, R. T. Building multimodal knowledge bases with multimodal computational sequences and generative adversarial networks. IEEE Trans. Multimedia 26, 2027\u20132040 (2024).","journal-title":"IEEE Trans. Multimedia"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53024-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53024-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53024-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:03:42Z","timestamp":1785715422000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53024-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,24]]},"references-count":150,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["53024"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-53024-2","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,24]]},"assertion":[{"value":"7 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"23756"}}