{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T18:31:58Z","timestamp":1775673118123,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2020AAA0108902"],"award-info":[{"award-number":["2020AAA0108902"]}]},{"name":"Strategic Priority Research Program of Chinese Academy of Science","award":["XDB32050100"],"award-info":[{"award-number":["XDB32050100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206288"],"award-info":[{"award-number":["62206288"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/lra.2023.3320014","type":"journal-article","created":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T17:43:29Z","timestamp":1695836609000},"page":"7655-7662","source":"Crossref","is-referenced-by-count":13,"title":["Semantic Policy Network for Zero-Shot Object Goal Visual Navigation"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2521-7006","authenticated-orcid":false,"given":"Qianfan","family":"Zhao","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodel Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6240-5300","authenticated-orcid":false,"given":"Lu","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodel Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3193-6269","authenticated-orcid":false,"given":"Bin","family":"He","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2148-1846","authenticated-orcid":false,"given":"Zhiyong","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodel Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref2","first-page":"1","article-title":"Visual semantic navigation using scene priors","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Yang","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00691"},{"key":"ref4","first-page":"517","article-title":"Learning hierarchical relationships for object-goal navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Pal","year":"2021"},{"key":"ref5","first-page":"1","article-title":"VTNet: Visual transformer network for object goal navigation","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Du","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01441"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161289"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref9","first-page":"32340","article-title":"ZSON: Zero-shot object-goal navigation using multimodal goal embeddings","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Majumdar","year":"2022"},{"key":"ref10","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"Proc. 27th Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","author":"Mikolov","year":"2013"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref12","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"key":"ref13","first-page":"251","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","author":"Szot","year":"2021"},{"key":"ref14","article-title":"AI2-THOR: An interactive 3D environment for visual AI","author":"Kolve","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref16","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","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00323"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/70.88137"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008824626321"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968547"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238654"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282485"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282312"},{"key":"ref24","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"},{"key":"ref25","article-title":"Benchmarking classic and learned navigation in complex 3D environments","author":"Mishkin","year":"2019"},{"key":"ref26","article-title":"To learn or not to learn: Analyzing the role of learning for navigation in virtual environments","author":"Kojima","year":"2019"},{"key":"ref27","first-page":"3314","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fried","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref29","first-page":"11305","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Kipf","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00450"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20887-5_34"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69535-4_10"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1364\/OFC.2023.Tu2C.1"},{"key":"ref36","first-page":"468","article-title":"Zero-shot semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bucher","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00172"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref39","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","author":"Sohn","year":"2015"},{"key":"ref40","first-page":"42829","article-title":"ESC Exploration with soft commonsense constraints for zero-shot object navigation","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Zhou","year":"2023"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref46","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref47","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref48","article-title":"AllenAct: A framework for embodied AI research","author":"Weihs","year":"2020"},{"key":"ref49","first-page":"1","article-title":"DD-PPO: Learning near-perfect pointgoal navigators from 2.5 billion frames","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Wijmans","year":"2020"},{"key":"ref50","first-page":"1724","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Cho","year":"2014"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10254630\/10265178.pdf?arnumber=10265178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T07:03:24Z","timestamp":1709363004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10265178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":53,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3320014","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}