{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T20:01:50Z","timestamp":1776110510484,"version":"3.50.1"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Robot"],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1007\/s10514-020-09951-8","type":"journal-article","created":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T04:02:36Z","timestamp":1603512156000},"page":"119-134","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Deep reinforcement learning for quadrotor path following with adaptive velocity"],"prefix":"10.1007","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8822-2681","authenticated-orcid":false,"given":"Bartomeu","family":"Rub\u00ed","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernardo","family":"Morcego","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ramon","family":"P\u00e9rez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,10,24]]},"reference":[{"issue":"8","key":"9951_CR1","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1109\/TAC.2007.902731","volume":"52","author":"AP Aguiar","year":"2007","unstructured":"Aguiar, A. P., & Hespanha, J. P. (2007). Trajectory-tracking and path-following of underactuated autonomous vehicles with parametric modeling uncertainty. IEEE Transactions on Automatic Control, 52(8), 1362\u20131379.","journal-title":"IEEE Transactions on Automatic Control"},{"issue":"3","key":"9951_CR2","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1016\/j.automatica.2007.06.030","volume":"44","author":"AP Aguiar","year":"2008","unstructured":"Aguiar, A. P., Hespanha, J. P., & Kokotovic, P. V. (2008). Performance limitations in reference tracking and path following for nonlinear systems. Automatica, 44(3), 598\u2013610.","journal-title":"Automatica"},{"key":"9951_CR3","doi-asserted-by":"crossref","unstructured":"Cabecinhas, D., Cunha, R., & Silvestre, C. (2009). Rotorcraft path following control for extended flight envelope coverage. In Proceedings of the 48th IEEE conference on decision and control, held jointly with the 28th Chinese control conference (CDC\/CCC), pp.\u00a03460\u20133465.","DOI":"10.1109\/CDC.2009.5400665"},{"key":"9951_CR4","doi-asserted-by":"crossref","unstructured":"Caicedo, J.\u00a0C., & Lazebnik, S. (2015). Active object localization with deep reinforcement learning. In 2015 IEEE international conference on computer vision (ICCV), pp.\u00a02488\u20132496, 12.","DOI":"10.1109\/ICCV.2015.286"},{"key":"9951_CR5","first-page":"595","volume-title":"RotorS\u2013A Modular Gazebo MAV Simulator Framework","author":"F Furrer","year":"2016","unstructured":"Furrer, F., Burri, M., Achtelik, M., & Siegwart, R. (2016). RotorS\u2013A Modular Gazebo MAV Simulator Framework (pp. 595\u2013625). Cham: Springer International Publishing."},{"issue":"1\u20132","key":"9951_CR6","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1163\/156855307779293715","volume":"21","author":"G Heredia","year":"2007","unstructured":"Heredia, G., & Ollero, A. (2007). Stability of autonomous vehicle path tracking with pure delays in the control loop. Advanced Robotics, 21(1\u20132), 23\u201350.","journal-title":"Advanced Robotics"},{"key":"9951_CR7","unstructured":"Ioffe, S., and Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv, vol. arXiv:1502.03167."},{"key":"9951_CR8","doi-asserted-by":"crossref","unstructured":"Kaminer, I., Yakimenko, O., Pascoal, A., and Ghabcheloo, R. (2006). Path generation, path following and coordinated control for time-critical missions of multiple UAVs. In 2006 American control conference, vol.\u00a01-12, pp.\u00a04906.","DOI":"10.1109\/ACC.2006.1657498"},{"key":"9951_CR9","doi-asserted-by":"crossref","unstructured":"Kang, K., Belkhale, S., Kahn, G., Abbeel, P., and Levine, S. (2019). Generalization through simulation: Integrating simulated and real data into deep reinforcement learning for vision-based autonomous flight. In 2019 international conference on robotics and automation (ICRA).","DOI":"10.1109\/ICRA.2019.8793735"},{"issue":"2","key":"9951_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3301273","volume":"3","author":"W Koch","year":"2019","unstructured":"Koch, W., Mancuso, R., West, R., & Bestavros, A. (2019). Reinforcement learning for uav attitude control. ACM Transaction on Cyber-Physical Systems, 3(2), 1\u201321.","journal-title":"ACM Transaction on Cyber-Physical Systems"},{"issue":"4","key":"9951_CR11","doi-asserted-by":"publisher","first-page":"4224","DOI":"10.1109\/LRA.2019.2930489","volume":"4","author":"NO Lambert","year":"2019","unstructured":"Lambert, N. O., Drew, D. S., Yaconelli, J., Calandra, R., Levine, S., & Pister, K. S. J. (2019). Low level control of a quadrotor with deep model-based reinforcement learning. IEEE Robotics and Automatic Letters, 4(4), 4224\u20134230.","journal-title":"IEEE Robotics and Automatic Letters"},{"key":"9951_CR12","unstructured":"Lillicrap, T.\u00a0P., Hunt, J.\u00a0J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D. (2016). Continuous control with deep reinforcement learning. In 2016 International conference on learning representations (ICLR)."},{"key":"9951_CR13","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1109\/JAS.2016.7508798","volume":"3","author":"L Li","year":"2016","unstructured":"Li, L., Lv, Y., & Wang, F. (2016). Traffic signal timing via deep reinforcement learning. IEEE\/CAA Journal of Automatica Sinica, 3, 247\u2013254, 7.","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"9951_CR14","doi-asserted-by":"crossref","unstructured":"Mittall, D., Kumar, K., Hashmi, S.\u00a0N., Kumar, P., Nanda, A., and Chandra, S. (2018). Performance comparison of deep and shallow network for quadcopter automation. In 2018 IEEE 13th international conference on industrial and information systems (ICIIS), pp.\u00a0143\u2013147.","DOI":"10.1109\/ICIINFS.2018.8721383"},{"key":"9951_CR15","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., et al. (2015). Human-level control through deep reinforcement learning. Nature, 518, 529\u2013533.","journal-title":"Nature"},{"key":"9951_CR16","doi-asserted-by":"crossref","unstructured":"Polvara, R., Patacchiola, M., Sharma, S., Wan, J., Manning, A., Sutton, R., and Cangelosi, A. (2018). Toward end-to-end control for uav autonomous landing via deep reinforcement learning. In 2018 International conference on unmanned aircraft systems (ICUAS), pp.\u00a0115\u2013123.","DOI":"10.1109\/ICUAS.2018.8453449"},{"key":"9951_CR17","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s10846-018-0891-8","volume":"93","author":"A Rodriguez-Ramos","year":"2019","unstructured":"Rodriguez-Ramos, A., Sampedro, C., Bavle, H., de la Puente, P., & Campoy, P. (2019). A deep reinforcement learning strategy for uav autonomous landing on a moving platform. Journal of Intelligent and Robotic Systems, 93, 351\u2013366, 2.","journal-title":"Journal of Intelligent and Robotic Systems"},{"key":"9951_CR18","doi-asserted-by":"crossref","unstructured":"Rub\u00ed, B., Morcego, B., and P\u00e9rez, R. (2020). A Deep Reinforcement Learning Approach for Path Following on a Quadrotor. In 2020 European control conference.","DOI":"10.23919\/ECC51009.2020.9143591"},{"key":"9951_CR19","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s10846-019-01085-z","volume":"98","author":"B Rub\u00ed","year":"2019","unstructured":"Rub\u00ed, B., P\u00e9rez, R., & Morcego, B. (2019). A survey of path following control strategies for UAVs focused on quadrotors. Journal of Intelligent and Robotic Systems, 98, 241\u2013265.","journal-title":"Journal of Intelligent and Robotic Systems"},{"key":"9951_CR20","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., and Riedmiller, M. (2014). Deterministic policy gradient algorithms. In Proceedings of the 31st international conference on international conference on machine learning-volume 32, pp.\u00a0I387\u2013I395, JMLR.org."},{"key":"9951_CR21","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., et al. (2016). Mastering the game of go with deep neural networks and tree search. Nature, 529, 484\u2013489.","journal-title":"Nature"},{"issue":"1","key":"9951_CR22","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/MCS.2013.2287568","volume":"34","author":"PB Sujit","year":"2014","unstructured":"Sujit, P. B., Saripalli, S., & Sousa, J. B. (2014). Unmanned aerial vehicle path following: A survey and analysis of algorithms for fixed-wing unmanned aerial vehicless. IEEE Control Systems, 34(1), 42\u201359.","journal-title":"IEEE Control Systems"},{"key":"9951_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3618-5","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1992","unstructured":"Sutton, R. S., & Barto, A. (1992). Reinforcement Learning: An Introduction. Cambridge: The MIT Press."},{"key":"9951_CR24","doi-asserted-by":"crossref","unstructured":"Tuyen, L.\u00a0P., and Chung, T. (2017). Controlling bicycle using deep deterministic policy gradient algorithm. In 2017 14th international conference on ubiquitous robots and ambient intelligence (URAI), pp.\u00a0413\u2013417, 6.","DOI":"10.1109\/URAI.2017.7992765"},{"key":"9951_CR25","doi-asserted-by":"crossref","unstructured":"Yu, R., Shi, Z., Huang, C., Li, T., and Ma, Q. (2017). Deep reinforcement learning based optimal trajectory tracking control of autonomous underwater vehicle. In 2017 36th Chinese control conference (CCC), pp.\u00a04958\u20134965, 7.","DOI":"10.23919\/ChiCC.2017.8028138"}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-020-09951-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10514-020-09951-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-020-09951-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T09:45:57Z","timestamp":1635241557000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10514-020-09951-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":25,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["9951"],"URL":"https:\/\/doi.org\/10.1007\/s10514-020-09951-8","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"value":"0929-5593","type":"print"},{"value":"1573-7527","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,24]]},"assertion":[{"value":"12 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 October 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}