{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T05:14:37Z","timestamp":1748409277472,"version":"3.40.3"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:00:00Z","timestamp":1730851200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:00:00Z","timestamp":1730851200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005856","name":"National Funds funded the paper through the Portuguese funding agency, FCT\u2014Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["UIDB\/50014\/2020"],"award-info":[{"award-number":["UIDB\/50014\/2020"]}],"id":[{"id":"10.13039\/501100005856","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,6]]},"DOI":"10.1109\/robot61475.2024.10796906","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:10:37Z","timestamp":1734981037000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Deep Reinforcement Learning Framework for UAV Indoor Navigation"],"prefix":"10.1109","author":[{"given":"Jo\u00e3o J.","family":"Martins","sequence":"first","affiliation":[{"name":"INESC TEC - Institute for Systems and Computer Engineering, Technology and Science,Porto,Portugal"}]},{"given":"Alexandre","family":"Amaral","sequence":"additional","affiliation":[{"name":"INESC TEC - Institute for Systems and Computer Engineering, Technology and Science,Porto,Portugal"}]},{"given":"Andr\u00e9","family":"Dias","sequence":"additional","affiliation":[{"name":"INESC TEC - Institute for Systems and Computer Engineering, Technology and Science,Porto,Portugal"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-59167-9_19"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANS47191.2022.9977308"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/s19081812"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/drones8050193"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1504\/IJBSR.2021.118776"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref8","article-title":"Actor-critic algorithms","author":"Konda","year":"1999","journal-title":"Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10090999"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890773"},{"journal-title":"Memory-based control with recurrent neural networks","year":"2015","author":"Heess","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS45731.2020.9181245"},{"journal-title":"Deterministic policy gradient algorithms","author":"Silver","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971780"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593706"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-021-01491-2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.108194"},{"key":"ref19","first-page":"2587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"35th International Conference on Machine Learning, ICML 2018","volume":"4","author":"Fujimoto"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS54063.2022.9859287"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"journal-title":"PX4\/PX4-autopilot: Stable release v1.14.0","key":"ref22"},{"key":"ref23","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"journal-title":"hector_quadrotor - ros wiki","key":"ref24"},{"journal-title":"tahsinkose\/sjtu-drone","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT61475.2024.10796935"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11235-015-0034-5"},{"journal-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"Abadi","key":"ref28"},{"journal-title":"Monitor wrapper \u2014 stable baselines3 2.2.1 documentation","key":"ref29"}],"event":{"name":"2024 7th Iberian Robotics Conference (ROBOT)","start":{"date-parts":[[2024,11,6]]},"location":"Madrid, Spain","end":{"date-parts":[[2024,11,8]]}},"container-title":["2024 7th Iberian Robotics Conference (ROBOT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10795802\/10796856\/10796906.pdf?arnumber=10796906","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T09:41:13Z","timestamp":1743846073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10796906\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/robot61475.2024.10796906","relation":{},"subject":[],"published":{"date-parts":[[2024,11,6]]}}}