{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:00:37Z","timestamp":1783537237250,"version":"3.55.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1109\/lra.2021.3068106","type":"journal-article","created":{"date-parts":[[2021,3,23]],"date-time":"2021-03-23T20:05:55Z","timestamp":1616529955000},"page":"4345-4352","source":"Crossref","is-referenced-by-count":52,"title":["Visual Navigation in Real-World Indoor Environments Using End-to-End Deep Reinforcement Learning"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8437-3626","authenticated-orcid":false,"given":"Jonas","family":"Kulhanek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7588-7668","authenticated-orcid":false,"given":"Erik","family":"Derner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9578-8598","authenticated-orcid":false,"given":"Robert","family":"Babuska","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Stabilizing transformers for reinforcement learning","author":"parisotto","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/nature20101"},{"key":"ref33","article-title":"AI2-THOR: An interactive 3D environment for visual AI","author":"kolve","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref30","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref37","article-title":"From pixels to torques: Policy learning with deep dynamical models","author":"wahlstr\u00f6m","year":"2015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989366"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2496823"},{"key":"ref34","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","article-title":"FollowNet: Robot navigation by following natural language directions with deep reinforcement learning","author":"shah","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593720"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2994002"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.010"},{"key":"ref14","first-page":"2419","article-title":"Learning to navigate in cities without a map","author":"mirowski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref16","first-page":"325","article-title":"MaskRNN: Instance level video object segmentation","author":"hu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref18","article-title":"Quake 3 arena manual","author":"connors","year":"1999"},{"key":"ref19","article-title":"DeepMind lab","author":"beattie","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593706"},{"key":"ref4","article-title":"Building generalizable agents with a realistic and rich 3D environment","author":"wu","year":"2018"},{"key":"ref27","article-title":"On reward shaping for mobile robot navigation: A reinforcement learning and SLAM based approach","author":"botteghi","year":"2020"},{"key":"ref3","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2019.8870964"},{"key":"ref29","article-title":"Efficient parallel methods for deep reinforcement learning","author":"clemente","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00286"},{"key":"ref7","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2016"},{"key":"ref2","article-title":"Agent57: Outperforming the Atari human benchmark","author":"badia","year":"2020"},{"key":"ref9","article-title":"Visual semantic navigation using scene priors","author":"yang","year":"2018"},{"key":"ref1","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref21","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5121\/csit.2020.101117"},{"key":"ref23","article-title":"Playing doom with SLAM-augmented deep reinforcement learning","author":"bhatti","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2954952"},{"key":"ref25","article-title":"Towards monocular vision based obstacle avoidance through deep reinforcement learning","author":"xie","year":"2017"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9399748\/09384194.pdf?arnumber=9384194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:02Z","timestamp":1652194442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9384194\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":39,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3068106","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]}}}