{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T16:38:20Z","timestamp":1784997500135,"version":"3.55.0"},"reference-count":134,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AME Programmatic Funding Scheme","award":["#A18A2b0046"],"award-info":[{"award-number":["#A18A2b0046"]}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NRFISF Joint Call","award":["NRF2015-NRF-ISF001-2541"],"award-info":[{"award-number":["NRF2015-NRF-ISF001-2541"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1109\/tetci.2022.3141105","type":"journal-article","created":{"date-parts":[[2022,1,21]],"date-time":"2022-01-21T21:35:43Z","timestamp":1642800943000},"page":"230-244","source":"Crossref","is-referenced-by-count":327,"title":["A Survey of Embodied AI: From Simulators to Research Tasks"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4551-2424","authenticated-orcid":false,"given":"Jiafei","family":"Duan","sequence":"first","affiliation":[{"name":"Nanyang Technological University of Singapore, School of Electrical and Electronics Engineering, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samson","family":"Yu","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3012-9222","authenticated-orcid":false,"given":"Hui Li","family":"Tan","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheston","family":"Tan","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/1064546053278973"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191324"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-27833-7_1"},{"key":"ref5","author":"Haugeland","year":"1985","journal-title":"Artificial Intelligence: The Very Idea."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3585.001.0001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref11","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"},{"key":"ref12","article-title":"Deepmind lab","author":"Beattie","year":"2016"},{"key":"ref13","article-title":"Ai2-thor: An interactive 3D environment for visual AI","author":"Kolve","year":"2017"},{"key":"ref14","article-title":"Chalet: Cornell house agent learning environment","author":"Yan","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"ref16","article-title":"Vrkitchen: An interactive 3D virtual environment for task-oriented learning","author":"Gao","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965078"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref20","article-title":"Threedworld: A platform for interactive multi-modal physical simulation","author":"Gan","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01437-z"},{"key":"ref23","article-title":"From seeing to moving: A survey on learning for visual indoor navigation (VIN","author":"Ye","year":"2020"},{"key":"ref24","article-title":"Learning exploration policies for navigation","author":"Chen","year":"2019"},{"key":"ref25","article-title":"Semi-parametric topological memory for navigation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Savinov","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013848"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref30","article-title":"Embodied AI workshop","year":"2021"},{"key":"ref31","article-title":"Allenact: A framework for embodied AI research","author":"Weihs","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref36","article-title":"Are we making real progress in simulated environments? Measuring the sim2real gap in embodied visual navigation","author":"Kadian","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00323"},{"key":"ref38","article-title":"Objectnav revisited: On evaluation of embodied agents navigating to objects","author":"Batra","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_28"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00685"},{"key":"ref41","article-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00685"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_19"},{"key":"ref44","article-title":"Learning to explore using active neural SLAM","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chaplot","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_24"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_30"},{"key":"ref47","article-title":"DD-PPO: Learning near-perfect pointgoal navigators from 2.5 billion frames","author":"Wijmans","year":"2019"},{"key":"ref48","article-title":"Simultaneous mapping and target driven navigation","author":"Georgakis","year":"2019"},{"key":"ref49","article-title":"Auxiliary tasks speed up learning pointgoal navigation","author":"Ye","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560893"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00691"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_24"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_2"},{"key":"ref54","article-title":"Object goal navigation using goal-oriented semantic exploration","author":"Chaplot","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636667"},{"key":"ref56","article-title":"Learning object-conditioned exploration using distributed soft actor critic","author":"Wahid","year":"2020"},{"key":"ref57","article-title":"Visual semantic navigation using scene priors","author":"Yang","year":"2018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01074"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00279"},{"key":"ref62","first-page":"53","article-title":"Neural modular control for embodied question answering","volume-title":"Proc. Conf. Robot Learn.","author":"Das","year":"2018"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00647"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_39"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-021-00703-z"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_2"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref69","article-title":"Unifying map and landmark based representations for visual navigation","author":"Gupta","year":"2017"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00884"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00063"},{"key":"ref73","article-title":"Learning to visually navigate in photorealistic environments without any supervision","author":"Mezghani","year":"2020"},{"key":"ref74","article-title":"Benchmarking classic and learned navigation in complex 3D environments","author":"Mishkin","year":"2019"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2624754"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw6326"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/BF02055574"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref79","article-title":"Large-scale study of curiosity-driven learning","author":"Burda","year":"2018"},{"key":"ref80","first-page":"1109","article-title":"VIME: Variational information maximizing exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Houthooft","year":"2016"},{"key":"ref81","first-page":"5062","article-title":"Self-supervised exploration via disagreement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pathak","year":"2019"},{"key":"ref82","article-title":"Exploration by random network distillation","author":"Burda","year":"2018"},{"key":"ref83","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_26"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00405"},{"key":"ref86","article-title":"Episodic curiosity through reachability","author":"Savinov","year":"2018"},{"key":"ref87","first-page":"8388","article-title":"Learning to play with intrinsically-motivated, self-aware agents","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Haber","year":"2018"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01289"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-008-9235-4"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9365-8"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/70.508439"},{"key":"ref93","first-page":"293","article-title":"Rapidly-exploring random trees: Progress and prospects","volume":"5","author":"LaValle","year":"2001","journal-title":"Algorithmic Comput. Robot., New Directions"},{"key":"ref94","article-title":"Learning to act by predicting the future","author":"Dosovitskiy","year":"2016"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.4.613"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.60"},{"key":"ref97","first-page":"4055","article-title":"Successor features for transfer in reinforcement learning","volume":"30","author":"Barreto","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00111"},{"key":"ref99","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793493"},{"key":"ref101","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref102","article-title":"Neural predictive belief representations","author":"Guo","year":"2018"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197008"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref105","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Thomason","year":"2019"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref107","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150855"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"ref113","article-title":"Physion: Evaluating physical prediction from vision in humans and machines","author":"Bear","year":"2021"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00233"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_24"},{"key":"ref116","article-title":"Learning affordance landscapes for interaction exploration in 3D environments","volume":"33","author":"Nagarajan","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459864"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459795"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3166687"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref121","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","author":"Ramakrishnan","year":"2021"},{"key":"ref122","article-title":"Joint 2D-3D-semantic data for indoor scene understanding","author":"Armeni","year":"2017"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1046\/j.0031-868x.2003.024_01.x"},{"key":"ref124","article-title":"Blender - A 3D modelling and rendering package, Alicevision","author":"Alicevision","year":"2018"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01381"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.011"},{"key":"ref129","article-title":"Learning about objects by learning to interact with them","volume":"33","author":"Lohmann","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref130","article-title":"Reskin: Versatile, replaceable, lasting tactile skins","volume-title":"CoRL","author":"Bhirangi","year":"2021"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417768"},{"key":"ref132","first-page":"103","article-title":"Audio-visual embodied navigation","volume":"97","author":"Chen","year":"2019","journal-title":"Environment"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-2631-2"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197364"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/9741092\/09687596.pdf?arnumber=9687596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:21:12Z","timestamp":1705184472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687596\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4]]},"references-count":134,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2022.3141105","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4]]}}}