{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T04:20:22Z","timestamp":1779164422679,"version":"3.51.4"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T00:00:00Z","timestamp":1643587200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T00:00:00Z","timestamp":1643587200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Robot Syst"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s10846-021-01568-y","type":"journal-article","created":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T07:05:01Z","timestamp":1643612701000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["Double Critic Deep Reinforcement Learning for Mapless 3D Navigation of Unmanned Aerial Vehicles"],"prefix":"10.1007","volume":"104","author":[{"given":"Ricardo Bedin","family":"Grando","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junior Costa","family":"de Jesus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victor Augusto","family":"Kich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alisson Henrique","family":"Kolling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paulo Lilles Jorge","family":"Drews-Jr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,31]]},"reference":[{"key":"1568_CR1","unstructured":"Dulac-Arnold, G., Evans, R., van Hasselt, H., Sunehag, P., Lillicrap, T., Hunt, J., Mann, T., Weber, T., Degris, T. , Coppin, B.: \u201cDeep reinforcement learning in large discrete action spaces, arXiv:1512.07679 (2015)"},{"key":"1568_CR2","unstructured":"Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D.: \u201cContinuous control with deep reinforcement learning. In: ICLR (2015)"},{"key":"1568_CR3","unstructured":"Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P.: \u201cBenchmarking deep reinforcement learning for continuous control. In: International conference on machine learning. PMLR, pp 1329\u20131338 (2016)"},{"key":"1568_CR4","doi-asserted-by":"crossref","unstructured":"Drews-Jr, P.L.J. , Hern\u00e1ndez, E., Elfes, A., Nascimento, E.R., Campos, M.F.M.: \u201cReal-time monocular obstacle avoidance using underwater dark channel prior\u201d. In: IEEE\/RSJ IROS, pp 4672\u20134677 (2016)","DOI":"10.1109\/IROS.2016.7759687"},{"key":"1568_CR5","first-page":"09829","volume":"1706","author":"L Xie","year":"2017","unstructured":"Xie, L., Wang, S.: A. markham, and. N. Trigoni, \u201cTowards monocular vision based obstacle avoidance through deep reinforcement learning,\u201d arXiv preprint arXiv 1706, 09829 (2017)","journal-title":"N. Trigoni, \u201cTowards monocular vision based obstacle avoidance through deep reinforcement learning,\u201d arXiv preprint arXiv"},{"key":"1568_CR6","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Mottaghi, R., Kolve, E., Lim, J.J., Gupta, A., Fei-fei, L., Farhadi, A.: \u201cTarget-driven visual navigation in indoor scenes using deep reinforcement learning\u201d. In: IEEE ICRA, pp 3357\u20133364 (2017)","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"1568_CR7","doi-asserted-by":"crossref","unstructured":"Tai, L., Paolo, G., Liu, M: \u201cVirtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation\u201d. In: IEEE\/RSJ IROS, pp 31\u201336 (2017)","DOI":"10.1109\/IROS.2017.8202134"},{"key":"1568_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y.F., Everett, M., Liu, M., How, J.P.: \u201cSocially aware motion planning with deep reinforcement learning\u201d. In: IEEE\/RSJ IROS, pp 1343\u20131350 (2017)","DOI":"10.1109\/IROS.2017.8202312"},{"key":"1568_CR9","doi-asserted-by":"crossref","unstructured":"Jesus, J.C., Bottega, J.A., Cuadros, M.A., Gamarra, D.F. : \u201cDeep deterministic policy gradient for navigation of mobile robots in simulated environments\u201d. In: ICAR, pp 362\u2013367 (2019)","DOI":"10.1109\/ICAR46387.2019.8981638"},{"issue":"2","key":"1568_CR10","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/s10846-018-0898-1","volume":"95","author":"C Sampedro","year":"2019","unstructured":"Sampedro, C., Rodriguez-Ramos, A., Bavle, H., Carrio, A., de la Puente, P., Campoy, P.: A fully-autonomous aerial robot for search and rescue applications in indoor environments using learning-based techniques. Journal of Intelligent & Robotic Systems 95(2), 601\u2013627 (2019)","journal-title":"Journal of Intelligent & Robotic Systems"},{"key":"1568_CR11","doi-asserted-by":"crossref","unstructured":"Kang, K., Belkhale, S., Kahn, G., Abbeel, P., Levine, S.: \u201cGeneralization through simulation: Integrating simulated and real data into deep reinforcement learning for vision-based autonomous flight\u201d. In: IEEE ICRA, pp 6008\u20136014 (2019)","DOI":"10.1109\/ICRA.2019.8793735"},{"key":"1568_CR12","doi-asserted-by":"crossref","unstructured":"Grando, R.B., de Jesus, J.C., Drews-Jr, P.L.: \u201cDeep reinforcement learning for mapless navigation of unmanned aerial vehicles\u201d. In: 2020 Latin American Robotics Symposium (LARS), 2020 Brazilian Symposium on Robotics (SBR) and 2020 Workshop on Robotics in Education (WRE). IEEE, pp 1\u20136 (2020)","DOI":"10.1109\/LARS\/SBR\/WRE51543.2020.9307015"},{"key":"1568_CR13","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: \u201cAddressing function approximation error in actor-critic methods\u201d. In: International Conference on Machine Learning. PMLR, pp 1587\u20131596 (2018)"},{"key":"1568_CR14","doi-asserted-by":"crossref","unstructured":"Marino, R., Mastrogiovanni, F., Sgorbissa, A., Zaccaria, R.: \u201cA minimalistic quadrotor navigation strategy for indoor multi-floor scenarios\u201d. In: Intelligent Autonomous Systems 13. Springer, pp 1561\u20131570 (2016)","DOI":"10.1007\/978-3-319-08338-4_112"},{"key":"1568_CR15","doi-asserted-by":"crossref","unstructured":"Grando, R.B., Costa de Jesus, J., Kich, V.A., Kolling, A.H. , Bortoluzzi, P.N., Pinheiro, P.M., Neto, A.A., Drews-Jr, P.L.J: \u201cDeep reinforcement learning for mapless navigation of a hybrid aerial underwater vehicle with medium transition\u201d, IEEE International Conference on Robotics and Automation (ICRA), pp arXiv:2103 (2021)","DOI":"10.1109\/ICRA48506.2021.9561188"},{"issue":"11","key":"1568_CR16","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. The International Journal of Robotics Research 32(11), 1238\u20131274 (2013)","journal-title":"The International Journal of Robotics Research"},{"issue":"3","key":"1568_CR17","doi-asserted-by":"publisher","first-page":"122","DOI":"10.3390\/robotics2030122","volume":"2","author":"P Kormushev","year":"2013","unstructured":"Kormushev, P., Calinon, S., Caldwell, D.G.: Reinforcement learning in robotics: Applications and real-world challenges. Robotics 2(3), 122\u2013148 (2013)","journal-title":"Robotics"},{"key":"1568_CR18","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: \u201cDomain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp 23\u201330 (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"1568_CR19","doi-asserted-by":"crossref","unstructured":"Ota, K., Sasaki, Y., Jha, D. K., Yoshiyasu, Y., Kanezaki, A.: \u201cEfficient exploration in constrained environments with goal-oriented reference path. In: IEEE\/RSJ IROS (2020)","DOI":"10.1109\/IROS45743.2020.9341620"},{"key":"1568_CR20","doi-asserted-by":"crossref","unstructured":"Rodriguez-Ramos, A., Sampedro, C., Bavle, H., Moreno, I.G., Bavle, H., Campoy, P.: \u201cA deep reinforcement learning technique for vision-based autonomous multirotor landing on a moving platform. In: IEEE\/RSJ IROS, pp 1010\u20131017 (2018)","DOI":"10.1109\/IROS.2018.8594472"},{"key":"1568_CR21","doi-asserted-by":"crossref","unstructured":"Furrer, F., Burri, M., Achtelik, M., Siegwart, R.: \u201cRotorS \u2013 modular gazebo MAV simulator framework. In: Robot Operating System (ROS), pp 595\u2013625 (2016)","DOI":"10.1007\/978-3-319-26054-9_23"},{"key":"1568_CR22","unstructured":"He, L., Aouf, N., Whidborne, J.F., Song, B: \u201cDeep reinforcement learning based local planner for uav obstacle avoidance using demonstration data, arXiv:2008.02521 (2020)"},{"issue":"22","key":"1568_CR23","doi-asserted-by":"publisher","first-page":"3789","DOI":"10.3390\/rs12223789","volume":"12","author":"B Li","year":"2020","unstructured":"Li, B., Gan, Z., Chen, D., Sergey Aleksandrovich, D.: Uav maneuvering target tracking in uncertain environments based on deep reinforcement learning and meta-learning. Remote Sens. 12(22), 3789 (2020)","journal-title":"Remote Sens."},{"key":"1568_CR24","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., Chintala, S.: \u201cPytorch: An imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett, Eds., vol. 32. Curran Associates, Inc. [Online]. Available: https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf (2019)"},{"key":"1568_CR25","doi-asserted-by":"crossref","unstructured":"Rukhovich, D., Sofiiuk, K., Galeev, D., Barinova, O., Konushin, A.: \u201cIterdet, Iterative scheme for object detection in crowded environments\u201d (2021)","DOI":"10.1007\/978-3-030-73973-7_33"},{"key":"1568_CR26","unstructured":"Tao, A., Sapra, K., Catanzaro, B.: Hierarchical multi-scale attention for semantic segmentation, vol. arXiv:2005.10821 (2020)"},{"key":"1568_CR27","unstructured":"Shoeybi, M., Patwary, M., Puri, R., LeGresley, P., Casper, J., Catanzaro, B: \u201cMegatron-lm: Training multi-billion parameter language models using model parallelism\u201d (2020)"},{"key":"1568_CR28","unstructured":"Quigley, M., Conley, K., Gerkey, B., Faust, J., Foote, T., Leibs, J., Wheeler, R., Ng, A.Y.: \u201cROS: an open-source robot operating system. In: IEEE ICRA - Workshop on open source software. Kobe, Japan, vol. 3, p 5 (2009)"},{"key":"1568_CR29","doi-asserted-by":"crossref","unstructured":"Drews-Jr, P.L.J., Neto, A.A., Campos, M.F.M.: \u201cHybrid unmanned aerial underwater vehicle: Modeling and simulation. pp. 4637\u20134642 (2014)","DOI":"10.1109\/IROS.2014.6943220"},{"key":"1568_CR30","doi-asserted-by":"crossref","unstructured":"Neto, A.A., Mozelli, L.A., Drews-Jr, P.L.J., Campos, M.F.M.: \u201cAttitude control for an hybrid unmanned aerial underwater vehicle: A robust switched strategy with global stability. In: IEEE ICRA, pp 395\u2013400 (2015)","DOI":"10.1109\/ICRA.2015.7139029"},{"key":"1568_CR31","doi-asserted-by":"crossref","unstructured":"Horn, A.C., Pinheiro, P.M., Silva, C.B., Neto, A.A., Drews-Jr, P.L.J.: \u201cA study on configuration of propellers for multirotor-like hybrid aerial-aquatic vehicles. In: ICAR, pp 173\u2013178 (2019)","DOI":"10.1109\/ICAR46387.2019.8981667"},{"key":"1568_CR32","doi-asserted-by":"crossref","unstructured":"Horn, A.C., Pinheiro, P.M., Grando, R.B., da Silva, C. B., Neto, A.A., Drews, P.L.: \u201cA novel concept for hybrid unmanned aerial underwater vehicles focused on aquatic performance\u201d, pp. 1\u20136 (2020)","DOI":"10.1109\/LARS\/SBR\/WRE51543.2020.9307110"},{"key":"1568_CR33","unstructured":"Bedin Grando, R., Drews Jr, P.L.J., Alves Neto, A.: Ardupilot and ros-based control system concept for a hybrid unmanned aerial underwater vehicle. In: II Brazilian Humanoid Robot Workshop and III Brazilian Workshop on Service Robotics, pp 26\u201329 (2019)"},{"key":"1568_CR34","doi-asserted-by":"crossref","unstructured":"Grando, R.B., Pinheiro, P.M., Bortoluzzi, N.P., da Silva, C.B., Zauk, O.F., Pi\u00f1eiro, M.O., Aoki, M.V., Kelbouscas, A.L., Lima, Y.B., Drews, P.L., Neto, A.A.: \u201cVisual-based autonomous unmanned aerial vehicle for inspection in indoor environments,\u201d pp. 1\u20136 (2020)","DOI":"10.1109\/LARS\/SBR\/WRE51543.2020.9307024"},{"key":"1568_CR35","doi-asserted-by":"crossref","unstructured":"Koenig, N., A Howard, A.: \u201cDesign and use paradigms for gazebo, an open-source multi-robot simulator\u201d. In: IEEE\/RSJ IROS, vol. 3, pp 2149\u20132154 (2004)","DOI":"10.1109\/IROS.2004.1389727"}],"container-title":["Journal of Intelligent &amp; Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-021-01568-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10846-021-01568-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-021-01568-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T16:47:45Z","timestamp":1726591665000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10846-021-01568-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,31]]},"references-count":35,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["1568"],"URL":"https:\/\/doi.org\/10.1007\/s10846-021-01568-y","relation":{},"ISSN":["0921-0296","1573-0409"],"issn-type":[{"value":"0921-0296","type":"print"},{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,31]]},"assertion":[{"value":"8 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 December 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors have ethcally approved this work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"This paper can be published, the permission was approved by the author and the all the coauthors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Consent for Publication"}},{"value":"The authors inform this work present no competing interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Competing interests"}}],"article-number":"29"}}