{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:21:12Z","timestamp":1740108072293,"version":"3.37.3"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:00:00Z","timestamp":1731888000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:00:00Z","timestamp":1731888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61977019"],"award-info":[{"award-number":["61977019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017607","name":"Shenzhen Fundamental Research Program","doi-asserted-by":"publisher","award":["JCYJ20220818102415033","JSGG20201103093802006","KJZD20230923114222045"],"award-info":[{"award-number":["JCYJ20220818102415033","JSGG20201103093802006","KJZD20230923114222045"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s00521-024-10675-4","type":"journal-article","created":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T06:42:35Z","timestamp":1731912155000},"page":"1223-1240","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Aggressive and robust low-level control and trajectory tracking for quadrotors with deep reinforcement learning"],"prefix":"10.1007","volume":"37","author":[{"given":"Shiyu","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yanjie","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yunjiang","family":"Lou","sequence":"additional","affiliation":[]},{"given":"Ke","family":"Lin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,18]]},"reference":[{"issue":"2","key":"10675_CR1","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1007\/s10846-021-01527-7","volume":"104","author":"M Idrissi","year":"2022","unstructured":"Idrissi M, Salami M, Annaz F (2022) A review of quadrotor unmanned aerial vehicles: applications, architectural design and control algorithms. J Intell Robotic Syst 104(2):22. https:\/\/doi.org\/10.1007\/s10846-021-01527-7","journal-title":"J Intell Robotic Syst"},{"key":"10675_CR2","doi-asserted-by":"publisher","unstructured":"Gupte S, Mohandas PIT, Conrad JM (2012) A survey of quadrotor unmanned aerial vehicles. In: Proceedings of IEEE Southeastcon, IEEE, pp 1\u20136, https:\/\/doi.org\/10.1109\/SECon.2012.6196930","DOI":"10.1109\/SECon.2012.6196930"},{"key":"10675_CR3","first-page":"2","volume":"10","author":"K Choutri","year":"2020","unstructured":"Choutri K, Lagha M, Dala L (2020) A fully autonomous search and rescue system using quadrotor UAV. Int J Comput Digit Syst 10:2\u201312","journal-title":"Int J Comput Digit Syst"},{"issue":"8","key":"10675_CR4","doi-asserted-by":"publisher","first-page":"824","DOI":"10.3390\/rs9080824","volume":"9","author":"Y Zhang","year":"2017","unstructured":"Zhang Y, Yuan X, Li W et al (2017) Automatic power line inspection using UAV images. Remote Sens 9(8):824. https:\/\/doi.org\/10.3390\/rs9080824","journal-title":"Remote Sens"},{"key":"10675_CR5","doi-asserted-by":"publisher","unstructured":"Xing J, Cioffi G, Hidalgo-Carri\u00f3 J, et\u00a0al (2023) Autonomous power line inspection with drones via perception-aware MPC. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp 1086\u20131093, https:\/\/doi.org\/10.1109\/IROS55552.2023.10341871","DOI":"10.1109\/IROS55552.2023.10341871"},{"key":"10675_CR6","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/978-3-319-90893-9_43","volume":"42","author":"JP \u0160krinjar","year":"2019","unstructured":"\u0160krinjar JP, \u0160korput P, Furdi\u0107 M (2019) Application of unmanned aerial vehicles in logistic processes. Lecture Note Network and Syst 42:359\u2013366. https:\/\/doi.org\/10.1007\/978-3-319-90893-9_43","journal-title":"Lecture Note Network and Syst"},{"key":"10675_CR7","doi-asserted-by":"publisher","first-page":"307","DOI":"10.3303\/CET1544052","volume":"44","author":"DK Giles","year":"2015","unstructured":"Giles DK, Billing RC (2015) Deployment and performance of a UAV for crop spraying. Chem Eng Trans 44:307\u2013312. https:\/\/doi.org\/10.3303\/CET1544052","journal-title":"Chem Eng Trans"},{"issue":"2","key":"10675_CR8","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1016\/j.inpa.2022.02.002","volume":"10","author":"A Hafeez","year":"2023","unstructured":"Hafeez A, Husain MA, Singh SP et al (2023) Implementation of drone technology for farm monitoring & pesticide spraying: a review. Inform Process Agri 10(2):192\u2013203. https:\/\/doi.org\/10.1016\/j.inpa.2022.02.002","journal-title":"Inform Process Agri"},{"issue":"23","key":"10675_CR9","first-page":"3660","volume":"5","author":"AL Salih","year":"2010","unstructured":"Salih AL, Moghavvemi M, Mohamed HA et al (2010) Flight PID controller design for a UAV quadrotor. Sci. Res Essays 5(23):3660\u20133667","journal-title":"Sci. Res Essays"},{"key":"10675_CR10","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1007\/s10514-012-9280-5","volume":"33","author":"PEI Pounds","year":"2012","unstructured":"Pounds PEI, Bersak DR, Dollar A (2012) Stability of small-scale uav helicopters and quadrotors with added payload mass under pid control. Auton Robot 33:129\u2013142. https:\/\/doi.org\/10.1007\/s10514-012-9280-5","journal-title":"Auton Robot"},{"key":"10675_CR11","unstructured":"Koch WF, Bestavros A (2019) Flight controller synthesis via deep reinforcement learning. PhD thesis, Boston University, https:\/\/hdl.handle.net\/2144\/39552"},{"issue":"5","key":"10675_CR12","doi-asserted-by":"publisher","first-page":"3152","DOI":"10.1109\/TSMC.2022.3222857","volume":"53","author":"W Yang","year":"2023","unstructured":"Yang W, Jiang Y, He X et al (2023) Feasibility conditions-free prescribed performance decentralized fault-tolerant neural control of constrained large-scale systems. IEEE Trans Syst Man, Cyber: Syst 53(5):3152\u20133164. https:\/\/doi.org\/10.1109\/TSMC.2022.3222857","journal-title":"IEEE Trans Syst Man, Cyber: Syst"},{"issue":"2","key":"10675_CR13","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TNSE.2023.3325002","volume":"11","author":"H Shan","year":"2024","unstructured":"Shan H, Jiang Y, Liang H et al (2024) Fuzzy adaptive containment control for nonlinear multi-manipulator systems with actuator faults and predefined accuracy. IEEE Trans Netw Sci Eng 11(2):1510\u20131523. https:\/\/doi.org\/10.1109\/TNSE.2023.3325002","journal-title":"IEEE Trans Netw Sci Eng"},{"key":"10675_CR14","doi-asserted-by":"publisher","unstructured":"Goodarzi F, Lee D, Lee T (2013) Geometric nonlinear PID control of a quadrotor UAV on SE(3). In: European Control Conference. IEEE, pp 3845\u20133850, https:\/\/doi.org\/10.23919\/ECC.2013.6669644","DOI":"10.23919\/ECC.2013.6669644"},{"key":"10675_CR15","doi-asserted-by":"publisher","DOI":"10.3182\/20110828-6-IT-1002.02453","author":"GV Raffo","year":"2011","unstructured":"Raffo GV, Ortega MG, Rubio FR (2011) Nonlinear $$\\text{ H}_\\infty$$ controller for the quad-rotor helicopter with input coupling, vol 44. IFAC. https:\/\/doi.org\/10.3182\/20110828-6-IT-1002.02453","journal-title":"IFAC"},{"issue":"3","key":"10675_CR16","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1109\/TCST.2020.3001117","volume":"29","author":"E Tal","year":"2021","unstructured":"Tal E, Karaman S (2021) Accurate tracking of aggressive quadrotor trajectories using incremental nonlinear dynamic inversion and differential flatness. IEEE Trans Control Syst Technol 29(3):1203\u20131218. https:\/\/doi.org\/10.1109\/TCST.2020.3001117","journal-title":"IEEE Trans Control Syst Technol"},{"issue":"2","key":"10675_CR17","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1109\/LRA.2021.3131690","volume":"7","author":"D Hanover","year":"2022","unstructured":"Hanover D, Foehn P, Sun S et al (2022) Performance, precision, and payloads: adaptive nonlinear MPC for quadrotors. IEEE Robot Automat Lett 7(2):690\u2013697. https:\/\/doi.org\/10.1109\/LRA.2021.3131690","journal-title":"IEEE Robot Automat Lett"},{"issue":"2","key":"10675_CR18","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1109\/TASE.2017.2651109","volume":"15","author":"F Santoso","year":"2018","unstructured":"Santoso F, Garratt MA, Anavatti SG (2018) State-of-the-art intelligent flight control systems in unmanned aerial vehicles. IEEE Trans Automat Sci Eng 15(2):613\u2013627. https:\/\/doi.org\/10.1109\/TASE.2017.2651109","journal-title":"IEEE Trans Automat Sci Eng"},{"key":"10675_CR19","volume-title":"Reinforcement learning: An introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton RS, Barto AG (2018) Reinforcement learning: An introduction. MIT Press"},{"key":"10675_CR20","doi-asserted-by":"publisher","unstructured":"Li S, Liu T, Zhang C, et\u00a0al (2018) Learning unmanned aerial vehicle control for autonomous target following. In: International Joint Conference on Artificial Intelligence, vol 2018-July. IJCAI, pp 4936\u20134942, https:\/\/doi.org\/10.24963\/ijcai.2018\/685","DOI":"10.24963\/ijcai.2018\/685"},{"key":"10675_CR21","doi-asserted-by":"publisher","unstructured":"Polvara R, Patacchiola M, Sharma S, et\u00a0al (2017) Autonomous quadrotor landing using deep reinforcement learning. https:\/\/doi.org\/10.48550\/arXiv.1709.03339","DOI":"10.48550\/arXiv.1709.03339"},{"issue":"11","key":"10675_CR22","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober J, Bagnell JA, Peters J (2013) Reinforcement learning in robotics: a survey. Int J Robot Res 32(11):1238\u20131274. https:\/\/doi.org\/10.1177\/0278364913495721","journal-title":"Int J Robot Res"},{"issue":"3","key":"10675_CR23","doi-asserted-by":"publisher","first-page":"2271","DOI":"10.1109\/TIV.2022.3229723","volume":"8","author":"S Chen","year":"2023","unstructured":"Chen S, Li Y, Lou Y et al (2023) Learning real-time dynamic responsive gap-traversing policy for quadrotors with safety-aware exploration. IEEE Trans Intell Veh 8(3):2271\u20132284. https:\/\/doi.org\/10.1109\/TIV.2022.3229723","journal-title":"IEEE Trans Intell Veh"},{"key":"10675_CR24","doi-asserted-by":"publisher","unstructured":"Bauersfeld L, Kaufmann E, Scaramuzza D (2023) User-conditioned neural control policies for mobile robotics. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp 1342\u20131348, https:\/\/doi.org\/10.1109\/ICRA48891.2023.10160851","DOI":"10.1109\/ICRA48891.2023.10160851"},{"issue":"2","key":"10675_CR25","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 et al (2019) Reinforcement learning for UAV attitude control. ACM Trans Cyber-Physical Syst 3(2):1\u201321. https:\/\/doi.org\/10.1145\/3301273","journal-title":"ACM Trans Cyber-Physical Syst"},{"key":"10675_CR26","doi-asserted-by":"publisher","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, et\u00a0al (2015) Continuous control with deep reinforcement learning. https:\/\/doi.org\/10.48550\/arXiv.1509.02971","DOI":"10.48550\/arXiv.1509.02971"},{"key":"10675_CR27","unstructured":"Schulman J, Levine S, Moritz P, et\u00a0al (2015) Trust region policy optimization. In: International Conference on Machine Learning, vol\u00a037. PMLR, Lille, France, pp 1889\u20131897, https:\/\/proceedings.mlr.press\/v37\/schulman15.html"},{"key":"10675_CR28","doi-asserted-by":"publisher","unstructured":"Schulman J, Wolski F, Dhariwal P, et\u00a0al (2017) Proximal policy optimization algorithms. https:\/\/doi.org\/10.48550\/arXiv.1707.06347","DOI":"10.48550\/arXiv.1707.06347"},{"issue":"4","key":"10675_CR29","doi-asserted-by":"publisher","first-page":"2096","DOI":"10.1109\/LRA.2017.2720851","volume":"2","author":"J Hwangbo","year":"2017","unstructured":"Hwangbo J, Sa I, Siegwart R et al (2017) Control of a quadrotor with reinforcement learning. IEEE Robot Automat Lett 2(4):2096\u20132103. https:\/\/doi.org\/10.1109\/LRA.2017.2720851","journal-title":"IEEE Robot Automat Lett"},{"key":"10675_CR30","doi-asserted-by":"publisher","unstructured":"Lopes GC, Ferreira M, Da Silva Simoes A, et\u00a0al (2018) Intelligent control of a quadrotor with proximal policy optimization reinforcement learning. In: 2018 Latin American Robotic Symposium, 2018 Brazilian Symposium on Robotics (SBR) and 2018 Workshop on Robotics in Education (WRE). IEEE, pp 509\u2013514, https:\/\/doi.org\/10.1109\/LARS\/SBR\/WRE.2018.00094","DOI":"10.1109\/LARS\/SBR\/WRE.2018.00094"},{"key":"10675_CR31","unstructured":"Haarnoja T, Zhou A, Abbeel P, et\u00a0al (2018) Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, vol\u00a080. PMLR, pp 1861\u20131870, https:\/\/proceedings.mlr.press\/v80\/haarnoja18b.html"},{"key":"10675_CR32","doi-asserted-by":"publisher","unstructured":"Barros GM, Colombini EL (2020) Using soft actor-critic for low-Level UAV control. https:\/\/doi.org\/10.48550\/arXiv.2010.02293","DOI":"10.48550\/arXiv.2010.02293"},{"issue":"10","key":"10675_CR33","doi-asserted-by":"publisher","first-page":"3713","DOI":"10.1109\/TSMC.2018.2884725","volume":"50","author":"Y Wang","year":"2020","unstructured":"Wang Y, Sun J, He H et al (2020) Deterministic policy gradient with integral compensator for robust quadrotor control. IEEE Trans Syst Man Cybern Syst 50(10):3713\u20133725. https:\/\/doi.org\/10.1109\/TSMC.2018.2884725","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"10675_CR34","doi-asserted-by":"publisher","unstructured":"Li Y, Li H, Li Z, et\u00a0al (2019) Fast and accurate trajectory tracking for unmanned aerial vehicles based on deep reinforcement learning. In: International Conference on Embedded and Real-Time Computing Systems and Applications. IEEE, https:\/\/doi.org\/10.1109\/RTCSA.2019.8864571","DOI":"10.1109\/RTCSA.2019.8864571"},{"key":"10675_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2019.104222","volume":"95","author":"CH Pi","year":"2020","unstructured":"Pi CH, Hu KC, Cheng S et al (2020) Low-level autonomous control and tracking of quadrotor using reinforcement learning. Control Eng Pract 95:104222. https:\/\/doi.org\/10.1016\/j.conengprac.2019.104222","journal-title":"Control Eng Pract"},{"key":"10675_CR36","doi-asserted-by":"publisher","unstructured":"Puterman ML (2014) Markov decision processes.: Discrete stochastic dynamic programming. John Wiley Sons, https:\/\/doi.org\/10.1002\/9780470316887","DOI":"10.1002\/9780470316887"},{"key":"10675_CR37","doi-asserted-by":"publisher","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve Restricted Boltzmann machines. In: International Conference on Machine Learning, pp 807\u2013814, https:\/\/doi.org\/10.5555\/3104322.3104425","DOI":"10.5555\/3104322.3104425"},{"key":"10675_CR38","doi-asserted-by":"publisher","unstructured":"Kalman B, Kwasny S (1992) Why tanh: Choosing a sigmoidal function. In: International Joint Conference on Neural Networks, vol\u00a04. IEEE, pp 578\u2013581, https:\/\/doi.org\/10.1109\/IJCNN.1992.227257","DOI":"10.1109\/IJCNN.1992.227257"},{"key":"10675_CR39","doi-asserted-by":"publisher","unstructured":"Schulman J, Moritz P, Levine S, et\u00a0al (2016) High-dimensional continuous control using generalized advantage estimation. In: International Conference on Learning Representations, https:\/\/doi.org\/10.48550\/arXiv.1506.02438","DOI":"10.48550\/arXiv.1506.02438"},{"key":"10675_CR40","unstructured":"Murray RM, Rathinam M, Sluis W (1995) Differential flatness of mechanical control systems: A catalog of prototype systems. In: ASME international mechanical engineering congress and exposition, Citeseer, https:\/\/www.cds.caltech.edu\/~murray\/preprints\/mrs95-imece.pdf"},{"key":"10675_CR41","doi-asserted-by":"publisher","unstructured":"Mellinger D, Kumar V (2011) Minimum snap trajectory generation and control for quadrotors. In: IEEE International Conference on Robotics and Automation. IEEE, pp 2520\u20132525, https:\/\/doi.org\/10.1109\/ICRA.2011.5980409","DOI":"10.1109\/ICRA.2011.5980409"},{"issue":"2","key":"10675_CR42","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1109\/LRA.2017.2776353","volume":"3","author":"M Faessler","year":"2018","unstructured":"Faessler M, Franchi A, Scaramuzza D (2018) Differential flatness of quadrotor dynamics subject to rotor drag for accurate tracking of high-speed trajectories. IEEE Robot Automat Lett 3(2):620\u2013626. https:\/\/doi.org\/10.1109\/LRA.2017.2776353","journal-title":"IEEE Robot Automat Lett"},{"key":"10675_CR43","unstructured":"Song Y, Naji S, Kaufmann E, et\u00a0al (2021) Flightmare: A flexible quadrotor simulator. In: Conference on Robot Learning, vol 155. PMLR, pp 1147\u20131157, https:\/\/proceedings.mlr.press\/v155\/song21a"},{"key":"10675_CR44","unstructured":"Abadi M, Barham P, Chen J, et\u00a0al (2016) Tensorflow: A system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation. USENIX Association, Savannah, GA, pp 265\u2013283, https:\/\/www.usenix.org\/conference\/osdi16\/technical-sessions\/presentation\/abadi"},{"key":"10675_CR45","doi-asserted-by":"publisher","unstructured":"Sola J (2017) Quaternion kinematics for the error-state Kalman filter. https:\/\/doi.org\/10.48550\/arXiv.1711.02508","DOI":"10.48550\/arXiv.1711.02508"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10675-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10675-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10675-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T04:30:39Z","timestamp":1737693039000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10675-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,18]]},"references-count":45,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10675"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10675-4","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2024,11,18]]},"assertion":[{"value":"25 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2024","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 authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}