{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T03:39:56Z","timestamp":1783827596116,"version":"3.55.0"},"reference-count":126,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council-Cardiff University Scholarship","doi-asserted-by":"publisher","award":["CSC202006120013"],"award-info":[{"award-number":["CSC202006120013"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2024.3378010","type":"journal-article","created":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T18:39:37Z","timestamp":1710873577000},"page":"2292-2308","source":"Crossref","is-referenced-by-count":29,"title":["A Survey of Object Goal Navigation"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3644-7424","authenticated-orcid":false,"given":"Jingwen","family":"Sun","sequence":"first","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-9861","authenticated-orcid":false,"given":"Jing","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8968-9902","authenticated-orcid":false,"given":"Ze","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Engineering, Cardiff University, Cardiff, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2094-5680","authenticated-orcid":false,"given":"Yu-Kun","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3260099"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3081406"},{"key":"ref3","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018","journal-title":"arXiv:1807.06757"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"ref6","article-title":"ObjectNav revisited: On evaluation of embodied agents navigating to objects","author":"Batra","year":"2020","journal-title":"arXiv:2006.13171"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793493"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207265"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00297"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967677"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_24"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9898026"},{"key":"ref14","article-title":"Visual semantic navigation using scene priors","author":"Yang","year":"2018","journal-title":"arXiv:1810.06543"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/KSE.2019.8919366"},{"key":"ref16","first-page":"517","article-title":"Learning hierarchical relationships for object-goal navigation","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Pal"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LARS\/SBR\/WRE51543.2020.9307029"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SWC50871.2021.00027"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93046-2_7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01485"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01662"},{"key":"ref22","first-page":"1","article-title":"VTNet: Visual transformer network for object goal navigation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Du"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812027"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547852"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00691"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068906"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01509"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01581"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00346"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00511"},{"key":"ref31","article-title":"A general purpose supervisory signal for embodied agents","author":"Pratap Singh","year":"2022","journal-title":"arXiv:2212.01186"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00758"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01716"},{"key":"ref34","first-page":"1","article-title":"Offline visual representation learning for embodied navigation","volume-title":"Proc. Workshop Reincarnating Reinforcement Learn. ICLR","author":"Yadav"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-023-11190-8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.084"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-022-00902-7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01214"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00252"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01039"},{"key":"ref41","article-title":"Multiple thinking achieving meta-ability decoupling for object navigation","author":"Dang","year":"2023","journal-title":"arXiv:2302.01520"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IRCE59430.2023.10255036"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/robotics12040104"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3243618"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612100"},{"key":"ref46","article-title":"Learning to terminate in object navigation","author":"Song","year":"2023","journal-title":"arXiv:2309.16164"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref48","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Chaplot"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981646"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160473"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00645"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560925"},{"key":"ref53","first-page":"1","article-title":"Learning to map for active semantic goal navigation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Georgakis"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981766"},{"key":"ref56","article-title":"Predicting dense and context-aware cost maps for semantic robot navigation","author":"Goel","year":"2022","journal-title":"arXiv:2210.08952"},{"key":"ref57","article-title":"Self-supervised object goal navigation with in-situ finetuning","author":"Yeon Min","year":"2022","journal-title":"arXiv:2212.05923"},{"key":"ref58","first-page":"4283","article-title":"Semantic visual navigation by watching YouTube videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Chang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN50785.2021.9515530"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49997.2022.9926534"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3182803"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01445"},{"key":"ref63","article-title":"ReVoLT: Relational reasoning and Voronoi local graph planning for target-driven navigation","author":"Liu","year":"2023","journal-title":"arXiv:2301.02382"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.075"},{"key":"ref65","article-title":"CoWs on pasture: Baselines and benchmarks for language-driven zero-shot object navigation","author":"Yitzhak Gadre","year":"2022","journal-title":"arXiv:2203. 10421"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01441"},{"key":"ref67","first-page":"32340","article-title":"ZSON: Zero-shot object-goal navigation using multimodal goal embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Majumdar"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01652"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161289"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_18"},{"key":"ref71","article-title":"Zero-shot object searching using large-scale object relationship prior","author":"Chen","year":"2023","journal-title":"arXiv:2303.06228"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3320014"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3346800"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"ref75","article-title":"ESC: Exploration with soft commonsense constraints for zero-shot object navigation","author":"Zhou","year":"2023","journal-title":"arXiv:2301.13166"},{"key":"ref76","article-title":"Co-NavGPT: Multi-robot cooperative visual semantic navigation using large language models","author":"Yu","year":"2023","journal-title":"arXiv:2310.07937"},{"key":"ref77","article-title":"Bridging zero-shot object navigation and foundation models through pixel-guided navigation skill","author":"Cai","year":"2023","journal-title":"arXiv:2309.10309"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3577164.3577178"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA57826.2023.10215817"},{"key":"ref80","article-title":"The development of LLMs for embodied navigation","author":"Lin","year":"2023","journal-title":"arXiv:2311.00530"},{"key":"ref81","article-title":"From seeing to moving: A survey on learning for visual indoor navigation (VIN)","author":"Ye","year":"2020","journal-title":"arXiv:2002.11310"},{"key":"ref82","article-title":"Deep learning for embodied vision navigation: A survey","author":"Zhu","year":"2021","journal-title":"arXiv:2108.04097"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105036"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref85","article-title":"AI2-THOR: An interactive 3D environment for visual AI","author":"Kolve","year":"2017","journal-title":"arXiv:1712.05474"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref88","first-page":"251","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Szot"},{"key":"ref89","first-page":"1","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Ramakrishnan"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00477"},{"key":"ref91","first-page":"5982","article-title":"ProcTHOR: Large-scale embodied AI using procedural generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Deitke"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989164"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref98","article-title":"Building generalizable agents with a realistic and rich 3D environment","author":"Wu","year":"2018","journal-title":"arXiv:1801.02209"},{"key":"ref99","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref100","first-page":"1","article-title":"DD-PPO: Learning near-perfect pointgoal navigators from 2.5 billion frames","volume-title":"Proc. Int. Conf. Learn. Representat. (ICLR)","author":"Wijmans"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00076"},{"key":"ref102","first-page":"16221","article-title":"Ask4Help: Learning to leverage an expert for embodied tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Singh"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/UR57808.2023.10202397"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.93.4.1591"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref107","first-page":"1","article-title":"Learning to explore using active neural SLAM","volume-title":"Proc. Int. Conf. Learn. Representa. (ICLR)","author":"Chaplot"},{"key":"ref108","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref110","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref111","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","year":"2023"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref113","article-title":"DeBERTaV3: Improving DeBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing","author":"He","year":"2021","journal-title":"arXiv:2111.09543"},{"key":"ref114","first-page":"9700","article-title":"MultiON: Benchmarking semantic map memory using multi-object navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Wani"},{"key":"ref115","article-title":"SGoLAM: Simultaneous goal localization and mapping for multi-object goal navigation","author":"Kim","year":"2021","journal-title":"arXiv:2110.07171"},{"key":"ref116","first-page":"28670","article-title":"Learning active camera for multi-object navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Chen"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982216"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01010"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25555-7_5"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636667"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475575"},{"key":"ref122","first-page":"1652","article-title":"The focussed D algorithm for real-time replanning","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Stentz"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvc773wg"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00617"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adf6991"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8856\/10839176\/10475904.pdf?arnumber=10475904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T06:00:20Z","timestamp":1738821620000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10475904\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":126,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3378010","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}