{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:44:04Z","timestamp":1777657444355,"version":"3.51.4"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"MOST","award":["2022ZD0114900"],"award-info":[{"award-number":["2022ZD0114900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006006"],"award-info":[{"award-number":["62006006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62136001"],"award-info":[{"award-number":["62136001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62061136001"],"award-info":[{"award-number":["62061136001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Qualcomm University Research Grant"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/lra.2023.3272518","type":"journal-article","created":{"date-parts":[[2023,5,2]],"date-time":"2023-05-02T22:11:48Z","timestamp":1683065508000},"page":"3900-3907","source":"Crossref","is-referenced-by-count":9,"title":["Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8222-7529","authenticated-orcid":false,"given":"Hongcheng","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0428-4552","authenticated-orcid":false,"given":"Fangwei","family":"Zhong","sequence":"additional","affiliation":[{"name":"National Key Laboratory of General Artificial Intelligence, School of Intelligence and Technology, BIGAI, Peking University,, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingdong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7856-5760","authenticated-orcid":false,"given":"Jianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"TAMS, Department of Informatics, Universität Hamburg, Hamburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9888-6409","authenticated-orcid":false,"given":"Yizhou","family":"Wang","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, Institute for Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7984-9909","authenticated-orcid":false,"given":"Hao","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref2","article-title":"Benchmarking classic and learned navigation in complex 3D environments","author":"Mishkin","year":"2019"},{"key":"ref3","article-title":"Decentralized distributed PPO: Solving pointgoal navigation","author":"Wijmans","year":"2019"},{"key":"ref4","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Chaplot","year":"2020"},{"key":"ref5","article-title":"Clip on wheels: Zero-shot object navigation as object localization and exploration","author":"Gadre","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neulet.2009.05.082"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neulet.2014.10.043"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3389\/fnint.2012.00077"},{"key":"ref9","volume-title":"Foundations of Behavioral Neuroscience","author":"Carlson","year":"2013"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_2"},{"key":"ref11","article-title":"Learning to set waypoints for audio-visual navigation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197008"},{"key":"ref13","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1053\/j.nainr.2008.10.010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2008.20014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2004.01.014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0378-5955(91)90148-3"},{"key":"ref18","first-page":"279","article-title":"Role of primate auditory cortex in hearing","volume":"2","author":"Heffner","year":"1990","journal-title":"Comp. Percep."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s00221-003-1616-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2015.09.026"},{"key":"ref21","first-page":"3165","article-title":"Learning neural acoustic fields","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Luo","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982431"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-87825-1_11"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01526"},{"key":"ref26","article-title":"Knowledge-driven scene priors for semantic audio-visual embodied navigation","author":"Tatiya","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v15i1.5222"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v15i1.5221"},{"key":"ref29","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Foerster","year":"2017"},{"key":"ref30","first-page":"1388","article-title":"A deep policy inference Q-network for multi-agent systems","volume-title":"Proc. 17th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Hong","year":"2018"},{"key":"ref31","article-title":"Return-based contrastive representation learning for reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2020"},{"key":"ref32","article-title":"Reinforcement learning with unsupervised auxiliary tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jaderberg","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3347450.3357659"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3011438"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1121\/1.399186"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.ps.42.020191.001031"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2013.12.008"},{"issue":"4","key":"ref38","first-page":"51","article-title":"Recent advances in the behavioral study of infant audition: The development of sound localization skills","volume":"14","author":"Morrongiello","year":"1990","journal-title":"J. Speech- Lang. Pathol. Audiol."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/dev.420270805"},{"key":"ref40","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Ganin","year":"2015"},{"key":"ref41","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref42","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_32"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054172"},{"key":"ref46","first-page":"12782","article-title":"Towards distraction-robust active visual tracking","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhong","year":"2021"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10102643\/10114576.pdf?arnumber=10114576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T18:38:33Z","timestamp":1723055913000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10114576\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":46,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3272518","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}