{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T08:15:36Z","timestamp":1775808936903,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Foundation for Science and Technology (FCT), in the context of Ph.D. Scholarship","doi-asserted-by":"publisher","award":["2022.10977.BD"],"award-info":[{"award-number":["2022.10977.BD"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"National Funds through the FCT","doi-asserted-by":"publisher","award":["UIDB\/00127\/2020"],"award-info":[{"award-number":["UIDB\/00127\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tase.2023.3342419","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T20:10:24Z","timestamp":1702930224000},"page":"7427-7435","source":"Crossref","is-referenced-by-count":13,"title":["RLAD: Reinforcement Learning From Pixels for Autonomous Driving in Urban Environments"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5743-7663","authenticated-orcid":false,"given":"Daniel","family":"Coelho","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, and the Intelligent System Associate Laboratory (LASI), Institute of Electronics and Informatics Engineering of Aveiro (IEETA), University of Aveiro, Aveiro, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9288-5058","authenticated-orcid":false,"given":"Miguel","family":"Oliveira","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, and the Intelligent System Associate Laboratory (LASI), Institute of Electronics and Informatics Engineering of Aveiro (IEETA), University of Aveiro, Aveiro, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1283-7388","authenticated-orcid":false,"given":"V\u00edtor","family":"Santos","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, and the Intelligent System Associate Laboratory (LASI), Institute of Electronics and Informatics Engineering of Aveiro (IEETA), University of Aveiro, Aveiro, Portugal"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3192019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3116063"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01550"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101834","article-title":"Multi-modal policy fusion for end-to-end autonomous driving","volume":"98","author":"Huang","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3115235"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564412"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2022.05.017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/robotics12050127"},{"key":"ref10","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"Kostrikov","year":"2020","journal-title":"arXiv:2004.13649"},{"key":"ref11","first-page":"2784","article-title":"Stabilizing off-policy deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cetin"},{"key":"ref12","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref14","article-title":"Learning invariant representations for reinforcement learning without reconstruction","author":"Zhang","year":"2020","journal-title":"arXiv:2006.10742"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20259"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3109284"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref18","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"Hessel","year":"2017","journal-title":"arXiv:1710.02298"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref20","article-title":"Loss is its own reward: Self-supervision for reinforcement learning","author":"Shelhamer","year":"2016","journal-title":"arXiv:1612.07307"},{"key":"ref21","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016","journal-title":"arXiv:1602.01783"},{"key":"ref22","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref24","article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","author":"Yarats","year":"2021","journal-title":"arXiv:2107.09645"},{"key":"ref25","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref26","article-title":"CARLA: An open urban driving simulator","author":"Dosovitskiy","year":"2017","journal-title":"arXiv:1711.03938"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01494"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref30","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","author":"Espeholt","year":"2018","journal-title":"arXiv:1802.01561"},{"key":"ref31","article-title":"Deep learning using rectified linear units (ReLU)","author":"Fred Agarap","year":"2018","journal-title":"arXiv:1803.08375"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2994027"},{"key":"ref33","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Ziebart"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref36","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref38","first-page":"1","article-title":"Trans-Fuser: Imitation with transformer-based sensor fusion for autonomous driving","author":"Chitta","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref39","article-title":"Safety-enhanced autonomous driving using interpretable sensor fusion transformer","author":"Shao","year":"2022","journal-title":"arXiv:2207.14024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01671"},{"key":"ref41","article-title":"DeepMind control suite","author":"Tassa","year":"2018","journal-title":"arXiv:1801.00690"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8856\/10718645\/10364974.pdf?arnumber=10364974","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T17:27:46Z","timestamp":1729531666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10364974\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":41,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tase.2023.3342419","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}