{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:40:42Z","timestamp":1780317642905,"version":"3.54.1"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T00:00:00Z","timestamp":1645488000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T00:00:00Z","timestamp":1645488000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"national natural science foundation of china","doi-asserted-by":"publisher","award":["No. 61803009"],"award-info":[{"award-number":["No. 61803009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"fundamental research funds for the central universities","doi-asserted-by":"publisher","award":["YWF-21-BJ-541"],"award-info":[{"award-number":["YWF-21-BJ-541"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004750","name":"aeronautical science foundation of china","doi-asserted-by":"publisher","award":["No. 20175851032"],"award-info":[{"award-number":["No. 20175851032"]}],"id":[{"id":"10.13039\/501100004750","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":[[2022,7]]},"DOI":"10.1007\/s00521-022-07033-7","type":"journal-article","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T16:02:47Z","timestamp":1645545767000},"page":"11141-11161","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Disturbance rejection and high dynamic quadrotor control based on reinforcement learning and supervised learning"],"prefix":"10.1007","volume":"34","author":[{"given":"Mingjun","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihao","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingxun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,2,22]]},"reference":[{"key":"7033_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-05906-x","author":"S MahmoudZadeh","year":"2021","unstructured":"MahmoudZadeh S, Yazdani A, Elmi A, Abbasi A, Ghanooni P (2021) Exploiting a fleet of UAVs for monitoring and data acquisition of a distributed sensor network. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-021-05906-x","journal-title":"Neural Comput Appl"},{"key":"7033_CR2","doi-asserted-by":"publisher","unstructured":"Geng L, Zhang YF, Wang JJ, Fuh JYH, Teo SH (2013) Mission planning of autonomous UAVs for urban surveillance with evolutionary algorithms. In:10th IEEE international conference on control and automation (ICCA), pp 828\u2013833. https:\/\/doi.org\/10.1109\/ICCA.2013.6564992","DOI":"10.1109\/ICCA.2013.6564992"},{"issue":"9","key":"7033_CR3","doi-asserted-by":"publisher","first-page":"5431","DOI":"10.1007\/s00521-018-3373-9","volume":"31","author":"Y Khosiawan","year":"2018","unstructured":"Khosiawan Y, Park Y, Moon I, Nilakantan JM, Nielsen I (2018) Task scheduling system for UAV operations in indoor environment. Neural Comput Appl 31(9):5431\u20135459. https:\/\/doi.org\/10.1007\/s00521-018-3373-9","journal-title":"Neural Comput Appl"},{"issue":"3","key":"7033_CR4","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1109\/TGRS.2008.2010314","volume":"47","author":"M Nagai","year":"2009","unstructured":"Nagai M, Chen T, Shibasaki R, Kumagai H, Ahmed A (2009) UAV-borne 3-D mapping system by multisensor integration. IEEE T Geosci Remote 47(3):701\u2013708. https:\/\/doi.org\/10.1109\/TGRS.2008.2010314","journal-title":"IEEE T Geosci Remote"},{"key":"7033_CR5","doi-asserted-by":"crossref","unstructured":"Waharte S, Trigoni N (2010) Supporting search and rescue operations with UAVs. In: International conference on emerging security technologies (EST), Canterbury, UK, 6\u20137 Sept 2010, pp 142\u2013147","DOI":"10.1109\/EST.2010.31"},{"key":"7033_CR6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989679","author":"D Falanga","year":"2017","unstructured":"Falanga D, Mueggler E, Faessler M, Scaramuzza D (2017) Aggressive quadrotor flight through narrow gaps with onboard sensing and computing using active vision. IEEE ICRA. https:\/\/doi.org\/10.1109\/ICRA.2017.7989679","journal-title":"IEEE ICRA"},{"key":"7033_CR7","doi-asserted-by":"publisher","unstructured":"Maleki KN, Ashenayi K, Hook LR, Fuller JG, Hutchins N (2016) A reliable system design for nondeterministic adaptive controllers in small UAV autopilots. In: IEEE\/AIAA 35th digital avionics systems conference (DASC). https:\/\/doi.org\/10.1109\/DASC.2016.7778103","DOI":"10.1109\/DASC.2016.7778103"},{"issue":"3","key":"7033_CR8","doi-asserted-by":"publisher","first-page":"1176","DOI":"10.1109\/TLA.2016.7459596","volume":"14","author":"JP Ortiz","year":"2016","unstructured":"Ortiz JP, Minchala LI, Reinoso MJ (2016) Nonlinear robust H-Infinity PID controller for the multivariable system quadrotor. IEEE Lat Am T 14(3):1176\u20131183. https:\/\/doi.org\/10.1109\/TLA.2016.7459596","journal-title":"IEEE Lat Am T"},{"key":"7033_CR9","doi-asserted-by":"publisher","unstructured":"Bouabdallah S, Siegwart R (2005) Backstepping and sliding-mode techniques applied to an indoor micro quadrotor. In: IEEE international conference on robotics and automation, pp 2247\u20132252. https:\/\/doi.org\/10.1109\/ROBOT.2005.1570447","DOI":"10.1109\/ROBOT.2005.1570447"},{"key":"7033_CR10","doi-asserted-by":"publisher","unstructured":"Lu P, Kampen EJV (2015) Active fault-tolerant control for quadrotors subjected to a complete rotor failure. In: IEEE\/RSJ international conference on intelligent robots & systems, pp 4698\u20134703.https:\/\/doi.org\/10.1109\/IROS.2015.7354046","DOI":"10.1109\/IROS.2015.7354046"},{"issue":"2","key":"7033_CR11","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1109\/TASE.2017.2651109","volume":"15","author":"F Santoso","year":"2017","unstructured":"Santoso F, Garratt MA, Anavatti SG (2017) State-of-the-art intelligent flight control systems in unmanned aerial vehicles. IEEE Trans Autom Sci Eng 15(2):613\u2013627. https:\/\/doi.org\/10.1109\/TASE.2017.2651109","journal-title":"IEEE Trans Autom Sci Eng"},{"issue":"4","key":"7033_CR12","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1162\/artl.1995.2.4.417","volume":"2","author":"O Miglino","year":"1995","unstructured":"Miglino O, Lund HH, Nolfi S (1995) Evolving mobile robots in simulated and real environments. Artif Life 2(4):417\u2013434. https:\/\/doi.org\/10.1162\/artl.1995.2.4.417","journal-title":"Artif Life"},{"key":"7033_CR13","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.neunet.2019.01.011","volume":"113","author":"O Sigaud","year":"2019","unstructured":"Sigaud O, Stulp F (2019) Policy search in continuous action domains: an overview. Neural Netw 113:28\u201340. https:\/\/doi.org\/10.1016\/j.neunet.2019.01.011","journal-title":"Neural Netw"},{"key":"7033_CR14","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872","author":"J Hwangbo","year":"2019","unstructured":"Hwangbo J, Lee J, Dosovitskiy A et al (2019) Learning agile and dynamic motor skills for legged robots. Sci Robot. https:\/\/doi.org\/10.1126\/scirobotics.aau5872","journal-title":"Sci Robot"},{"key":"7033_CR15","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1007\/11552246_35","volume":"16","author":"AY Ng","year":"2003","unstructured":"Ng AY, Kim HJ, Jordan MI, Sastry S (2003) Autonomous helicopter flight via reinforcement learning. Adv Neur In 16:799\u2013806. https:\/\/doi.org\/10.1007\/11552246_35","journal-title":"Adv Neur In"},{"issue":"13","key":"7033_CR16","doi-asserted-by":"publisher","first-page":"1608","DOI":"10.1177\/0278364910371999","volume":"29","author":"P Abbeel","year":"2010","unstructured":"Abbeel P, Coates A, Ng AY (2010) Autonomous helicopter aerobatics through apprenticeship learning. Int J Robotics Res 29(13):1608\u20131639. https:\/\/doi.org\/10.1177\/0278364910371999","journal-title":"Int J Robotics Res"},{"issue":"4","key":"7033_CR17","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, Hutter M (2017) Control of a quadrotor With reinforcement learning. IEEE Robot Autom Let 2(4):2096\u20132103. https:\/\/doi.org\/10.1109\/LRA.2017.2720851","journal-title":"IEEE Robot Autom Let"},{"issue":"2","key":"7033_CR18","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 Trans Cyber-Phys Syst 3(2):1\u201321. https:\/\/doi.org\/10.1145\/3301273","journal-title":"ACM Trans Cyber-Phys Syst"},{"key":"7033_CR19","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison CJ et al (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529:484\u2013489. https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"key":"7033_CR20","volume-title":"Reinforcement learning: an introduction","author":"S Richard","year":"2018","unstructured":"Richard S, Andrew G (2018) Reinforcement learning: an introduction, 2nd edn. The MIT Press, Cambridge, MA","edition":"2"},{"key":"7033_CR21","unstructured":"Schulman J, Levine S, Abbeel P et al (2015) Trust region policy optimization. In: Proceedings of the international conference on machine learning, pp 1889\u20131897. arXiv:1502.05477"},{"issue":"6","key":"7033_CR22","doi-asserted-by":"publisher","first-page":"A187","DOI":"10.1016\/S1098-3015(10)67722-4","volume":"8","author":"TP Lillicrap","year":"2015","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A et al (2015) Continuous control with deep reinforcement learning. Comput Sci 8(6):A187. https:\/\/doi.org\/10.1016\/S1098-3015(10)67722-4","journal-title":"Comput Sci"},{"key":"7033_CR23","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv preprint. arXiv:1707.06347"},{"key":"7033_CR24","unstructured":"Achiam J, Abbeel P (2020) Proximal policy optimization. https:\/\/spinningup.openai.com\/en\/latest\/algorithms\/ppo.html. Accessed 26 July 2021"},{"key":"7033_CR25","unstructured":"Schulman J, Moritz P et al (2015) High-dimensional continuous control using generalized advantage estimation. arXiv preprint. arXiv:1506.02438"},{"key":"7033_CR26","unstructured":"Abadi M, Barham P, Chen JM et al (2016) TensorFlow: a system for large-scale machine learning. In: Proc 12th USENIX conf on operating systems design and implementation, pp 265\u2013283. arXiv:1605.08695v2"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07033-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-07033-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07033-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,25]],"date-time":"2022-06-25T09:12:51Z","timestamp":1656148371000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-07033-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,22]]},"references-count":26,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["7033"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-07033-7","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,22]]},"assertion":[{"value":"4 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 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":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}