{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T23:17:35Z","timestamp":1783207055228,"version":"3.54.6"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2035"],"award-info":[{"award-number":["U22A2035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011319","name":"Jianghan University","doi-asserted-by":"publisher","award":["2022XKZX12"],"award-info":[{"award-number":["2022XKZX12"]}],"id":[{"id":"10.13039\/501100011319","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134157","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:05:39Z","timestamp":1781107539000},"page":"134157","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Visual and multi-modal knowledge graph grounding model for visual navigation"],"prefix":"10.1016","volume":"698","author":[{"given":"Jin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zengkai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4177-7188","authenticated-orcid":false,"given":"Kang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134157_bib0005","series-title":"Conference on Robot Learning","first-page":"46","article-title":"Taskography: evaluating robot task planning over large 3D scene graphs","author":"Agia","year":"2022"},{"key":"10.1016\/j.neucom.2026.134157_bib0010","author":"Anderson"},{"key":"10.1016\/j.neucom.2026.134157_bib0015","series-title":"Conference on Robot Learning","first-page":"287","article-title":"Do as i can, not as i say: grounding language in robotic affordances","author":"Brohan","year":"2023"},{"key":"10.1016\/j.neucom.2026.134157_bib0020","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.neucom.2026.134157_bib0025","author":"Chaplot"},{"key":"10.1016\/j.neucom.2026.134157_bib0030","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume":"33","author":"Chaplot","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134157_bib0035","article-title":"Neural topological SLAM for visual navigation","author":"Chaplot","year":"2020","journal-title":"IEEE"},{"key":"10.1016\/j.neucom.2026.134157_bib0040","author":"Chen"},{"key":"10.1016\/j.neucom.2026.134157_bib0045","author":"Chiang"},{"key":"10.1016\/j.neucom.2026.134157_bib0050","series-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023","article-title":"InstructBLIP: towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"10.1016\/j.neucom.2026.134157_bib0055","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"3617","article-title":"Unbiased directed object attention graph for object navigation","author":"Dang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134157_bib0060","doi-asserted-by":"crossref","first-page":"4083","DOI":"10.1109\/LRA.2023.3346800","article-title":"Can an embodied agent find your \u201ccat-shaped mug\u201d? LLM-based zero-shot object navigation","volume":"9","author":"Dorbala","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.134157_bib0065","unstructured":"D. Driess, F. Xia, M.S. Sajjadi, C. Lynch, A. Chowdhery, A. Wahid, J. Tompson, Q. Vuong, T. Yu, W. Huang, et al., Palm-e: an embodied multimodal language model, 2023."},{"key":"10.1016\/j.neucom.2026.134157_bib0070","first-page":"1","article-title":"Visual object search by learning spatial context","volume":"PP","author":"Druon","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.134157_bib0075","series-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021","article-title":"VTNet: visual transformer network for object goal navigation","author":"Du","year":"2021"},{"key":"10.1016\/j.neucom.2026.134157_bib0080","series-title":"European Conference on Computer Vision","first-page":"834","article-title":"LSD-SLAM: large-scale direct monocular SLAM","author":"Engel","year":"2014"},{"key":"10.1016\/j.neucom.2026.134157_bib0085","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"23171","article-title":"Cows on pasture: baselines and benchmarks for language-driven zero-shot object navigation","author":"Gadre","year":"2023"},{"key":"10.1016\/j.neucom.2026.134157_bib0090","series-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"5021","article-title":"Conceptgraphs: open-vocabulary 3D scene graphs for perception and planning","author":"Gu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134157_bib0095","author":"Guan"},{"key":"10.1016\/j.neucom.2026.134157_bib0100","series-title":"2023 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"10608","article-title":"Visual language maps for robot navigation","author":"Huang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134157_bib0105","author":"Kolve"},{"key":"10.1016\/j.neucom.2026.134157_bib0110","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-016-0981-7","article-title":"Visual genome: connecting language and vision using crowdsourced dense image annotations","volume":"123","author":"Krishna","year":"2017","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134157_bib0115","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"15890","article-title":"Visual graph memory with unsupervised representation for visual navigation","author":"Kwon","year":"2021"},{"key":"10.1016\/j.neucom.2026.134157_bib0120","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1002\/rob.21831","article-title":"RTAB-map as an open-source LiDAR and visual simultaneous localization and mapping library for large-scale and long-term online operation","volume":"36","author":"Labb\u00e9","year":"2019","journal-title":"J. Field Robot."},{"key":"10.1016\/j.neucom.2026.134157_bib0125","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"848","article-title":"Deep variation-structured reinforcement learning for visual relationship and attribute detection","author":"Liang","year":"2017"},{"key":"10.1016\/j.neucom.2026.134157_bib0130","author":"Lin"},{"key":"10.1016\/j.neucom.2026.134157_bib0135","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134157_bib0140","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102678","article-title":"Learning multimodal adaptive relation graph and action boost memory for visual navigation","volume":"62","author":"Luo","year":"2024","journal-title":"Adv. Eng. Inform."},{"key":"10.1016\/j.neucom.2026.134157_bib0145","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2024.3497718","article-title":"NavTr: object-goal navigation with learnable transformer queries","author":"Mao","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.134157_bib0150","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2025.3546860","article-title":"Context-aware graph inference and generative adversarial imitation learning for object-goal navigation in unfamiliar environment","author":"Meng","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.134157_bib0155","series-title":"European Conference on Computer Vision","first-page":"728","article-title":"Simple open-vocabulary object detection","author":"Minderer","year":"2022"},{"key":"10.1016\/j.neucom.2026.134157_bib0160","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"147","article-title":"Lava: label-efficient visual learning and adaptation","author":"Nassar","year":"2023"},{"key":"10.1016\/j.neucom.2026.134157_bib0165","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"13765","article-title":"Grid: scene-graph-based instruction-driven robotic task planning","author":"Ni","year":"2024"},{"key":"10.1016\/j.neucom.2026.134157_bib0170","series-title":"Conference on Robot Learning","first-page":"517","article-title":"Learning hierarchical relationships for object-goal navigation","author":"Pal","year":"2021"},{"key":"10.1016\/j.neucom.2026.134157_bib0175","series-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1532","article-title":"Glove: global vectors for word representation","author":"Pennington","year":"2014"},{"key":"10.1016\/j.neucom.2026.134157_bib0180","author":"Qiao"},{"key":"10.1016\/j.neucom.2026.134157_bib0185","author":"Rajvanshi"},{"key":"10.1016\/j.neucom.2026.134157_bib0190","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18890","article-title":"Poni: potential functions for objectgoal navigation with interaction-free learning","author":"Ramakrishnan","year":"2022"},{"key":"10.1016\/j.neucom.2026.134157_bib0195","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"17896","article-title":"Pirlnav: pretraining with imitation and RL finetuning for objectnav","author":"Ramrakhya","year":"2023"},{"key":"10.1016\/j.neucom.2026.134157_bib0200","series-title":"7th Annual Conference on Robot Learning","article-title":"Sayplan: grounding large language models using 3D scene graphs for scalable robot task planning","author":"Rana","year":"2023"},{"key":"10.1016\/j.neucom.2026.134157_bib0205","series-title":"Conference on Robot Learning","first-page":"492","article-title":"LM-NAV: robotic navigation with large pre-trained models of language, vision, and action","author":"Shah","year":"2023"},{"key":"10.1016\/j.neucom.2026.134157_bib0210","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10740","article-title":"Alfred: a benchmark for interpreting grounded instructions for everyday tasks","author":"Shridhar","year":"2020"},{"key":"10.1016\/j.neucom.2026.134157_bib0215","author":"Touvron"},{"key":"10.1016\/j.neucom.2026.134157_bib0220","author":"Tsai"},{"key":"10.1016\/j.neucom.2026.134157_bib0225","author":"Wei"},{"key":"10.1016\/j.neucom.2026.134157_bib0230","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6750","article-title":"Learning to learn how to learn: self-adaptive visual navigation using meta-learning","author":"Wortsman","year":"2019"},{"key":"10.1016\/j.neucom.2026.134157_bib0235","author":"Wu"},{"key":"10.1016\/j.neucom.2026.134157_bib0240","series-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"5214","article-title":"Aligning knowledge graph with visual perception for object-goal navigation","author":"Xu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134157_bib0245","series-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"3554","article-title":"L3mvn: leveraging large language models for visual target navigation","author":"Yu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134157_bib0250","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"15130","article-title":"Hierarchical object-to-zone graph for object navigation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134157_bib0255","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"7641","article-title":"Navgpt: explicit reasoning in vision-and-language navigation with large language models","author":"Zhou","year":"2024"},{"key":"10.1016\/j.neucom.2026.134157_bib0260","series-title":"International Conference on Machine Learning","first-page":"42829","article-title":"Esc: exploration with soft commonsense constraints for zero-shot object navigation","author":"Zhou","year":"2023"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226015559?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226015559?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T22:35:48Z","timestamp":1783204548000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226015559"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":52,"alternative-id":["S0925231226015559"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134157","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Visual and multi-modal knowledge graph grounding model for visual navigation","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134157","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134157"}}