{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:03:38Z","timestamp":1781366618769,"version":"3.54.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004225","name":"Petrobras","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004225","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005639","name":"Universidade de S\u00e3o Paulo","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005639","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,29]]},"DOI":"10.1109\/lars69345.2025.11273007","type":"proceedings-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:37:25Z","timestamp":1764959845000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Autonomous UAV Flight Navigation in Confined Spaces: A Reinforcement Learning Approach"],"prefix":"10.1109","author":[{"given":"Marco S.","family":"Tayar","sequence":"first","affiliation":[{"name":"University of São Paulo,Department of Mechanical Engineering,São Carlos,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucas K.","family":"de Oliveira","sequence":"additional","affiliation":[{"name":"University of São Paulo,Department of Mechanical Engineering,São Carlos,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felipe Andrade G.","family":"Tommaselli","sequence":"additional","affiliation":[{"name":"University of São Paulo,Department of Mechanical Engineering,São Carlos,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juliano D.","family":"Negri","sequence":"additional","affiliation":[{"name":"University of São Paulo,Department of Mechanical Engineering,São Carlos,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thiago H.","family":"Segreto","sequence":"additional","affiliation":[{"name":"University of São Paulo,Department of Mechanical Engineering,São Carlos,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ricardo V.","family":"Godoy","sequence":"additional","affiliation":[{"name":"University of São Paulo,Department of Mechanical Engineering,São Carlos,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcelo","family":"Becker","sequence":"additional","affiliation":[{"name":"University of São Paulo,Department of Mechanical Engineering,São Carlos,Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s44182-025-00032-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2025.3548525"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2025.103608"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/drones8090516"},{"key":"ref6","first-page":"10","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","author":"Haarnoja"},{"key":"ref7","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv:1707.06347"},{"key":"ref8","article-title":"Reinforcement learning for unmanned aerial vehicle navigation: A survey","author":"Wu","year":"2023","journal-title":"Electronics"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105321"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref12","article-title":"Flightmare: A flexible quadrotor simulator","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv:2009.00563"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref14","article-title":"Sim-to-real transfer for rl in robotics: A review","author":"Muratore","year":"2021","journal-title":"arXiv preprint arXiv:2111.00956"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2942989"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-025-02219-2"},{"key":"ref17","volume-title":"Genesis: A generative and universal physics engine for robotics and beyond","author":"Authors","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adg1462"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3400838"},{"key":"ref20","volume-title":"Groundeffect-aware modeling and control for multicopters","author":"Yang","year":"2025"},{"key":"ref21","volume-title":"Learning to walk with less: a dyna-style approach to quadrupedal locomotion","author":"Affonso","year":"2025"},{"key":"ref22","article-title":"Benchmark survey of drl for uav navigation in cluttered environments","author":"Bakker","year":"2024","journal-title":"arXiv preprint arXiv:2410.14616"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2929993"},{"key":"ref24","article-title":"skrl: Modular and flexible library for reinforcement learning","author":"Serrano-Mu\u00f1oz","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2174\/1566524018666180611074856"},{"key":"ref26","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML), ser. Proceedings of Machine Learning Research","volume":"80","author":"Haarnoja"}],"event":{"name":"2025 Latin American Robotics Symposium (LARS)","location":"Monterrey, Mexico","start":{"date-parts":[[2025,10,29]]},"end":{"date-parts":[[2025,11,1]]}},"container-title":["2025 Latin American Robotics Symposium (LARS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11272988\/11272957\/11273007.pdf?arnumber=11273007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T06:15:49Z","timestamp":1765001749000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11273007\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/lars69345.2025.11273007","relation":{},"subject":[],"published":{"date-parts":[[2025,10,29]]}}}