{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:02:23Z","timestamp":1789718543699,"version":"4.0.1"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371737","type":"print"},{"value":"9783032371744","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37174-4_14","type":"book-chapter","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:10:13Z","timestamp":1789715413000},"page":"233-250","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical 3D Scene Graph Construction and\u00a0Belief-Based Planning for\u00a0Semantic Navigation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6175-3944","authenticated-orcid":false,"given":"Bing","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7344-1101","authenticated-orcid":false,"given":"Zuyao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-234X","authenticated-orcid":false,"given":"Changwen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,19]]},"reference":[{"key":"14_CR1","unstructured":"Anderson, P., et al.: On evaluation of embodied navigation agents. arXiv preprint arXiv:1807.06757 (2018)"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Armeni, I., et al.: 3D scene graph: a structure for unified semantics, 3D space, and camera. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5664\u20135673 (2019)","DOI":"10.1109\/ICCV.2019.00576"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Y., et al.: CogNav: cognitive process modeling for object goal navigation with LLMs. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9550\u20139560 (2025)","DOI":"10.1109\/ICCV51701.2025.00891"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: Proceedings of the 2017 International Conference on 3D Vision (3DV), pp. 667\u2013676. IEEE Computer Society (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"14_CR5","unstructured":"Chang, M., et\u00a0al.: GOAT: Go to any thing. arXiv preprint arXiv:2311.06430 (2023)"},{"key":"14_CR6","unstructured":"Chaplot, D.S., Gandhi, D.P., Gupta, A., Salakhutdinov, R.R.: Object goal navigation using goal-oriented semantic exploration. In: Proceedings of the Advances in Neural Information Processing Systems, vol. 33, pp. 4247\u20134258 (2020)"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Gadre, S.Y., Wortsman, M., Ilharco, G., Schmidt, L., Song, S.: CoWs on pasture: Baselines and benchmarks for language-driven zero-shot object navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23171\u201323181 (2023)","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Gu, Q., et al.: ConceptGraphs: open-vocabulary 3D scene graphs for perception and planning. In: Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 5021\u20135028. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Hughes, N., et al.: Foundations of spatial perception for robotics: hierarchical representations and real-time systems. Int. J. Robot. Res. 43(10), 1457\u2013 1505 (2024)","DOI":"10.1177\/02783649241229725"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Isler, S., Sabzevari, R., Delmerico, J., Scaramuzza, D.: An information gain formulation for active volumetric 3D reconstruction. In: Proceedings of the 2016 IEEE international conference on robotics and automation (ICRA), pp. 3477\u20133484. IEEE (2016)","DOI":"10.1109\/ICRA.2016.7487527"},{"issue":"2","key":"14_CR11","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.robot.2007.01.009","volume":"57","author":"N Kalra","year":"2009","unstructured":"Kalra, N., Ferguson, D., Stentz, A.: Incremental reconstruction of generalized Voronoi diagrams on grids. Robot. Auton. Syst. 57(2), 123\u2013128 (2009)","journal-title":"Robot. Auton. Syst."},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Khanna, M., et al.: Habitat synthetic scenes dataset (HSSD-200): an analysis of 3D scene scale and realism tradeoffs for Object Goal navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16384\u201316393 (2024)","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Koch, S., Vaskevicius, N., Colosi, M., Hermosilla, P., Ropinski, T.: Open3DSG: open-vocabulary 3D scene graphs from point clouds with queryable objects and open-set relationships. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14183\u201314193 (2024)","DOI":"10.1109\/CVPR52733.2024.01345"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Kuang, Y., Lin, H., Jiang, M.: OpenFMNav: Towards open-set zero-shot object navigation via vision-language foundation models. arXiv preprint arXiv:2402.10670 (2024)","DOI":"10.18653\/v1\/2024.findings-naacl.24"},{"key":"14_CR15","unstructured":"Long, Y., Cai, W., Wang, H., Zhan, G., Dong, H.: InstructNav: zero-shot system for generic instruction navigation in unexplored environment. In: Proceedings of the Conference on Robot Learning, pp. 2049\u20132060. PMLR (2025)"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Majumdar, A., Aggarwal, G., Devnani, B., Hoffman, J., Batra, D.: ZSON: zero-shot object-goal navigation using multimodal goal embeddings. In: PRoceedings of the Advances in Neural Information Processing Systems, vol. 35, pp. 32340\u201332352 (2022)","DOI":"10.52202\/068431-2343"},{"key":"14_CR17","unstructured":"Puig, X., et al.: Habitat 3.0: a co-habitat for humans, avatars and robots. arXiv preprint arXiv:2310.13724 (2023)"},{"key":"14_CR18","unstructured":"Ramakrishnan, S.K., et al.: Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI. arXiv preprint arXiv:2109.08238 (2021)"},{"key":"14_CR19","unstructured":"Rana, K., Het al.: SayPlan: grounding large language models using 3D scene graphs for scalable robot task planning. In: Proceedings of the Conference on Robot Learning, pp. 23\u201372. PMLR (2023)"},{"issue":"12\u201314","key":"14_CR20","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."},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Sethian, J.A.: A fast marching level set method for monotonically advancing fronts. Proc. National Acad. Sci. 93(4), 1591\u20131595 (1996)","DOI":"10.1073\/pnas.93.4.1591"},{"key":"14_CR22","unstructured":"Silver, D., Veness, J.: Monte-carlo planning in large POMDPs. In: Advances in neural information processing systems, vol. 23, (2010)"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Sun, X., Liu, L., Zhi, H., Qiu, R., Liang, J.: Prioritized semantic learning for zero-shot instance navigation. In: Proceedings of the European Conference on Computer Vision, pp. 161\u2013178. Springer (2024)","DOI":"10.1007\/978-3-031-73254-6_10"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Wang, A., Liu, L., Chen, H., Lin, Z., Han, J., Ding, G.: YOLOE: real-time seeing anything. arXiv preprint arXiv:2503.07465 (2025)","DOI":"10.1109\/ICCV51701.2025.02280"},{"key":"14_CR25","unstructured":"Wang, S., et al.: VLingNav: embodied navigation with adaptive reasoning and visual-assisted linguistic memory. arXiv preprint arXiv:2601.08665 (2026)"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhao, X., Cai, W., Sun, C.: ImagineNav++: prompting vision-language models as embodied navigator through scene imagination. arXiv preprint arXiv:2512.17435 (2025)","DOI":"10.1109\/TPAMI.2026.3688692"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Werby, A., Huang, C., B\u00fcchner, M., Valada, A., Burgard, W.: Hierarchical open-vocabulary 3D scene graphs for language-grounded robot navigation. In: Proceedings of the Robotics: Science and Systems,, Delft, Netherlands (2024)","DOI":"10.15607\/RSS.2024.XX.077"},{"key":"14_CR28","unstructured":"Wu, P., et al.: VoroNav: Voronoi-based zero-shot object navigation with large language model. In: Proceedings of the International Conference on Machine Learning, pp. 53757\u201353775. PMLR (2024)"},{"key":"14_CR29","unstructured":"Xie, J., et al.: TravelPlanner: a benchmark for real-world planning with language agents. In: Proceedings of the 41st International Conference on Machine Learning, pp. 54590\u201354613 (2024)"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Yadav, K., et al.: Habitat-Matterport 3D semantics dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4927\u20134936 (2023)","DOI":"10.1109\/CVPR52729.2023.00477"},{"key":"14_CR31","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Yin, H., Xu, X., Wu, Z., Zhou, J., Lu, J.: SG-Nav: online 3D scene graph prompting for LLM-based zero-shot object navigation. In: Proceedings of the Advances in neural information processing systems, vol. 37, pp. 5285\u20135307 (2024)","DOI":"10.52202\/079017-0171"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Yin, H., et al.: UniGoal: towards universal zero-shot goal-oriented navigation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 19057\u201319066 (2025)","DOI":"10.1109\/CVPR52734.2025.01775"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Yokoyama, N., Ha, S., Batra, D., Wang, J., Bucher, B.: VLFM: vision-language frontier maps for zero-shot semantic navigation. In: Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 42\u201348. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Yu, B., Kasaei, H., Cao, M.: L3MVN: Leveraging large language models for visual target navigation. In: Proceedings of the 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3554\u20133560. IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Uni-NaVid: a video-based Vision-language-Action model for unifying embodied navigation tasks. arXiv preprint arXiv:2412.06224 (2024)","DOI":"10.15607\/RSS.2025.XXI.013"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, M., et al.: ApexNav: an adaptive exploration strategy for zero-shot object navigation with target-centric semantic fusion. IEEE Robot. Autom. Lett. (2025)","DOI":"10.1109\/LRA.2025.3606388"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, S., Yu, X., Song, X., Wang, Y., Jiang, S.: Function-centric Bayesian network for zero-shot object goal navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19535\u201319545 (2025)","DOI":"10.1109\/ICCV51701.2025.01816"},{"key":"14_CR39","unstructured":"Zhao, X., Cai, W., Tang, L., Wang, T.: ImagineNav: prompting vision-language models as embodied navigator through scene imagination. arXiv preprint arXiv:2410.09874 (2024)"},{"issue":"2","key":"14_CR40","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1109\/LRA.2021.3051563","volume":"6","author":"B Zhou","year":"2021","unstructured":"Zhou, B., Zhang, Y., Chen, X., Shen, S.: FUEL: fast UAV exploration using incremental frontier structure and hierarchical planning. IEEE Robot. Autom. Lett. 6(2), 779\u2013786 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"14_CR41","unstructured":"Zhou, K., et al.: ESC: exploration with soft commonsense constraints for zero-shot object navigation. In: Proceedings of the International Conference on Machine Learning, pp. 42829\u201342842. PMLR (2023)"},{"key":"14_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Hu, Y., Zhang, L., Li, Z., Chen, S.: BeliefMapNav: 3D voxel-based belief map for zero-shot object navigation. arXiv preprint arXiv:2506.06487 (2025)","DOI":"10.52202\/085713-2782"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Zivkovic, Z., Bakker, B., Krose, B.: Hierarchical map building and planning based on graph partitioning. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pp. 803\u2013809 (2006)","DOI":"10.1109\/ROBOT.2006.1641808"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37174-4_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:10:31Z","timestamp":1789715431000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37174-4_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371737","9783032371744"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37174-4_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"19 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}