{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T11:37:20Z","timestamp":1777981040433,"version":"3.51.4"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T00:00:00Z","timestamp":1739404800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T00:00:00Z","timestamp":1739404800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"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"],"DOI":"10.1007\/s10846-024-02206-z","type":"journal-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T14:34:32Z","timestamp":1739457272000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Image-based Mapless Navigation of a Hybrid Aerial-Underwater Vehicle using Prioritized Deep Reinforcement Learning"],"prefix":"10.1007","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8819-1168","authenticated-orcid":false,"given":"Junior","family":"Costa\u00a0de\u00a0Jesus","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victor\u00a0Augusto","family":"Kich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alisson\u00a0Henrique","family":"Kolling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ricardo\u00a0Bedin","family":"Grando","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rodrigo","family":"da\u00a0Silva\u00a0Guerra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paulo\u00a0Lilles\u00a0Jorge","family":"Drews-Jr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,13]]},"reference":[{"key":"2206_CR1","unstructured":"Alves, S.F., Rosario, J.M., Ferasoli\u00a0Filho, H., Rincon, L., Yamasaki, R., Barrera, A.: Conceptual bases of robot navigation modeling, control and applications. Adv. Robot Navig. 26 (2011)"},{"key":"2206_CR2","doi-asserted-by":"publisher","unstructured":"Guth, F., Silveira, L., Botelho, S., Drews-Jr, P., Ballester, P.: Underwater slam: Challenges, state of the art, algorithms and a new biologically-inspired approach. In: IEEE RAS\/EMBS BioRob, pp. 981\u2013986 (2014). https:\/\/doi.org\/10.1109\/BIOROB.2014.6913908","DOI":"10.1109\/BIOROB.2014.6913908"},{"key":"2206_CR3","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D.: Continuous control with deep reinforcement learning. In: ICLR (2016)"},{"key":"2206_CR4","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: ICML, vol. 80, pp. 1861\u20131870 (2018)"},{"key":"2206_CR5","doi-asserted-by":"crossref","unstructured":"Grando, R.B., Jesus, J.C., Kich, V.A., Kolling, A.H., Pinheiro, P.M., Guerra, R.S., Drews-Jr, P.L.: Mapless navigation of a hybrid aerial underwater vehicle with deep reinforcement learning through environmental generalization. In: IEEE LARS\/SBR, pp. 1\u20136 (2022)","DOI":"10.1109\/LARS\/SBR\/WRE56824.2022.9995813"},{"key":"2206_CR6","doi-asserted-by":"crossref","unstructured":"Bonatti, R., Madaan, R., Vineet, V., Scherer, S., Kapoor, A.: Learning visuomotor policies for aerial navigation using cross-modal representations. In: IEEE\/RSJ IROS, pp. 1637\u20131644 (2020)","DOI":"10.1109\/IROS45743.2020.9341049"},{"key":"2206_CR7","doi-asserted-by":"crossref","unstructured":"Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. 40 (2017)","DOI":"10.1017\/S0140525X16001837"},{"key":"2206_CR8","doi-asserted-by":"crossref","unstructured":"Tai, L., Liu, M.: Towards cognitive exploration through deep reinforcement learning for mobile robots (2016). arXiv preprint arXiv:1610.01733","DOI":"10.1186\/s40638-016-0055-x"},{"issue":"2","key":"2206_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10846-021-01568-y","volume":"104","author":"RB Grando","year":"2022","unstructured":"Grando, R.B., Jesus, J.C., Kich, V.A., Kolling, A.H., Drews-Jr, P.L.J.: Double critic deep reinforcement learning for mapless 3d navigation of unmanned aerial vehicles. J. Intell. Robot. Syst. 104(2), 1\u201314 (2022)","journal-title":"J. Intell. Robot. Syst."},{"key":"2206_CR10","doi-asserted-by":"crossref","unstructured":"Grando, R.B., Jesus, J.C., Drews-Jr, P.L.: Deep reinforcement learning for mapless navigation of unmanned aerial vehicles. In: IEEE LARS\/SBR, pp. 1\u20136 (2020)","DOI":"10.1109\/LARS\/SBR\/WRE51543.2020.9307015"},{"key":"2206_CR11","doi-asserted-by":"crossref","unstructured":"Pinheiro, P.M., Neto, A.A., Grando, R.B., Silva, C.B.d., Aoki, V.M., Cardoso, D.S., Horn, A.C., Drews-Jr, P.L.: Trajectory planning for hybrid unmanned aerial underwater vehicles with smooth media transition. J. Intell. Robot. Syst. 104(3), 46 (2022)","DOI":"10.1007\/s10846-021-01567-z"},{"key":"2206_CR12","doi-asserted-by":"crossref","unstructured":"Rodriguez-Ramos, A., Sampedro, C., Bavle, H., Moreno, I.G., Campoy, P.: A 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":"2206_CR13","doi-asserted-by":"crossref","unstructured":"Sampedro, C., Rodriguez-Ramos, A., Bavle, H., Carrio, A., 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, 601\u2013627 (2019)","DOI":"10.1007\/s10846-018-0898-1"},{"key":"2206_CR14","doi-asserted-by":"crossref","unstructured":"He, L., Aouf, N., Whidborne, J.F., Song, B.: Integrated moment-based LGMD and deep reinforcement learning for UAV obstacle avoidance. In: IEEE ICRA, pp. 7491\u20137497 (2020)","DOI":"10.1109\/ICRA40945.2020.9197152"},{"issue":"22","key":"2206_CR15","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 Sensing 12(22), 3789 (2020)","journal-title":"Remote Sensing"},{"key":"2206_CR16","doi-asserted-by":"crossref","unstructured":"Jesus, J.C., Kich, V.A., Kolling, A.H., Grando, R.B., Cuadros, M.A.d.S.L., Gamarra, D.F.T.: Soft actor-critic for navigation of mobile robots. J. Intell. Robot. Syst. 102(2), 1\u201311 (2021)","DOI":"10.1007\/s10846-021-01367-5"},{"key":"2206_CR17","unstructured":"Thomas, D.-G., Olshanskyi, D., Krueger, K., Wongpiromsarn, T., Jannesari, A.: Interpretable uav collision avoidance using deep reinforcement learning (2021). arXiv preprint arXiv:2105.12254"},{"key":"2206_CR18","doi-asserted-by":"publisher","unstructured":"Grando, R.B., Jesus, J.C., Kich, V.A., Kolling, A.H., Bortoluzzi, N.P., Pinheiro, P.M., Alves\u00a0Neto, A., Drews-Jr, P.L.J.: Deep reinforcement learning for mapless navigation of a hybrid aerial underwater vehicle with medium transition. In: IEEE ICRA, pp. 1088\u20131094 (2021). https:\/\/doi.org\/10.1109\/ICRA48506.2021.9561188","DOI":"10.1109\/ICRA48506.2021.9561188"},{"key":"2206_CR19","unstructured":"Kaiser, L., Babaeizadeh, M., Milos, P., Osinski, B., Campbell, R.H., Czechowski, K., Erhan, D., Finn, C., Kozakowski, P., Levine, S., et al.: Model-based reinforcement learning for atari (2019). arXiv preprint arXiv:1903.00374"},{"key":"2206_CR20","unstructured":"Laskin, M., Srinivas, A., Abbeel, P.: Curl: Contrastive unsupervised representations for reinforcement learning. In: ICML, pp. 5639\u20135650 (2020)"},{"key":"2206_CR21","doi-asserted-by":"crossref","unstructured":"Jesus, J.C., Kich, V.A., Kolling, A.H., Grando, R.B., Guerra, R.S., Drews-Jr, P.L.: Depth-CUPRL: Depth-imaged contrastive unsupervised prioritized representations in reinforcement learning for mapless navigation of unmanned aerial vehicles. In: IEEE\/RSJ IROS, pp. 10579\u201310586 (2022)","DOI":"10.1109\/IROS47612.2022.9982161"},{"issue":"15","key":"2206_CR22","doi-asserted-by":"publisher","first-page":"5599","DOI":"10.3390\/s22155599","volume":"22","author":"M S\u00e1nchez","year":"2022","unstructured":"S\u00e1nchez, M., Morales, J., Mart\u00ednez, J.L., Fern\u00e1ndez-Lozano, J.J., Garc\u00eda-Cerezo, A.: Automatically annotated dataset of a ground mobile robot in natural environments via gazebo simulations. Sensors 22(15), 5599 (2022)","journal-title":"Sensors"},{"key":"2206_CR23","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3733\u20133742 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"issue":"4","key":"2206_CR24","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1137\/0330046","volume":"30","author":"BT Polyak","year":"1992","unstructured":"Polyak, B.T., Juditsky, A.B.: Acceleration of stochastic approximation by averaging. SICON 30(4), 838\u2013855 (1992)","journal-title":"SICON"},{"key":"2206_CR25","doi-asserted-by":"crossref","unstructured":"Roser, M., Dunbabin, M., Geiger, A.: Simultaneous underwater visibility assessment, enhancement and improved stereo. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 3840\u20133847 (2014). IEEE","DOI":"10.1109\/ICRA.2014.6907416"},{"key":"2206_CR26","doi-asserted-by":"crossref","unstructured":"Drews-Jr, P.L., Neto, A.A., Campos, M.F.: Hybrid unmanned aerial underwater vehicle: Modeling and simulation. In: IEEE\/RSJ IROS, pp. 4637\u20134642 (2014)","DOI":"10.1109\/IROS.2014.6943220"},{"key":"2206_CR27","doi-asserted-by":"publisher","unstructured":"Horn, A.C., Pinheiro, P.M., Grando, R.B., Silva, C.B., Neto, A.A., Drews-Jr, P.L.J.: A novel concept for hybrid unmanned aerial underwater vehicles focused on aquatic performance. In: IEEE LARS\/SBR, pp. 1\u20136 (2020). https:\/\/doi.org\/10.1109\/LARS\/SBR\/WRE51543.2020.9307110","DOI":"10.1109\/LARS\/SBR\/WRE51543.2020.9307110"}],"container-title":["Journal of Intelligent & Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-024-02206-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10846-024-02206-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-024-02206-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T21:19:09Z","timestamp":1743887949000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10846-024-02206-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,13]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["2206"],"URL":"https:\/\/doi.org\/10.1007\/s10846-024-02206-z","relation":{},"ISSN":["1573-0409"],"issn-type":[{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,13]]},"assertion":[{"value":"30 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The article has the approval of all the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All the authors gave their consent to participate in this article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"There are no conflicts of interest or competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest\/Competing interests"}}],"article-number":"27"}}