{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:03:05Z","timestamp":1760608985976,"version":"3.40.3"},"publisher-location":"Boston, MA","reference-count":31,"publisher":"Springer US","isbn-type":[{"type":"print","value":"9781489976857"},{"type":"electronic","value":"9781489976871"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-1-4899-7687-1_16","type":"book-chapter","created":{"date-parts":[[2017,4,13]],"date-time":"2017-04-13T12:32:22Z","timestamp":1492086742000},"page":"75-85","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Autonomous Helicopter Flight Using Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Adam","family":"Coates","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew Y.","family":"Ng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,4,14]]},"reference":[{"key":"16_CR1335","doi-asserted-by":"crossref","unstructured":"Abbeel P, Coates A, Hunter T, Ng AY (2008) Autonomous autorotation of an rc helicopter. In: ISER 11, Athens","DOI":"10.1007\/978-3-642-00196-3_45"},{"key":"16_CR1336","doi-asserted-by":"crossref","unstructured":"Abbeel P, Coates A, Quigley M, Ng AY (2007) An application of reinforcement learning to aerobatic helicopter flight. In: NIPS 19, Vancouver, pp\u00a01\u20138","DOI":"10.7551\/mitpress\/7503.003.0006"},{"key":"16_CR1337","unstructured":"Abbeel P, Ganapathi V, Ng AY (2006) Learning vehicular dynamics with application to modeling helicopters. In: NIPS 18, Vancouver"},{"key":"16_CR1338","series-title":"Proceedings of the international conference on machine learning, Banff. ACM, New York","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430","volume-title":"Apprenticeship learning via inverse reinforcement learning","author":"P Abbeel","year":"2004","unstructured":"Abbeel P, Ng AY (2004) Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the international conference on machine learning, Banff. ACM, New York"},{"key":"16_CR1339","series-title":"Proceedings of the international conference on machine learning, Bonn. ACM, New York","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102352","volume-title":"Exploration and apprenticeship learning in reinforcement learning","author":"P Abbeel","year":"2005","unstructured":"Abbeel P, Ng AY (2005a) Exploration and apprenticeship learning in reinforcement learning. In: Proceedings of the international conference on machine learning, Bonn. ACM, New York"},{"key":"16_CR1340","unstructured":"Abbeel P, Ng AY (2005b) Learning first order Markov models for control. In: NIPS 18, Vancouver"},{"key":"16_CR1341","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1143844.1143845","volume-title":"ICML \u201906: proceedings of the 23rd international conference on machine learning","author":"P Abbeel","year":"2006","unstructured":"Abbeel P, Quigley M, Ng AY (2006) Using inaccurate models in reinforcement learning. In: ICML \u201906: proceedings of the 23rd international conference on machine learning, Pittsburgh. ACM, New York, pp\u00a01\u20138"},{"key":"16_CR1342","volume-title":"Optimal control: linear quadratic methods","author":"B Anderson","year":"1989","unstructured":"Anderson B, Moore J (1989) Optimal control: linear quadratic methods. Prentice-Hall, Princeton"},{"key":"16_CR1343","series-title":"International conference on robotics and automation, Seoul. IEEE, Canada","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932842","volume-title":"Autonomous helicopter control using reinforcement learning policy search methods","author":"J Bagnell","year":"2001","unstructured":"Bagnell J, Schneider J (2001) Autonomous helicopter control using reinforcement learning policy search methods. In: International conference on robotics and automation, Seoul. IEEE, Canada"},{"key":"16_CR1344","first-page":"213","volume":"3","author":"RI Brafman","year":"2002","unstructured":"Brafman RI, Tennenholtz M (2002) R-max, a general polynomial time algorithm for near-optimal reinforcement learning. J Mach Learn Res 3: 213\u2013231","journal-title":"J Mach Learn Res"},{"key":"16_CR1345","doi-asserted-by":"crossref","unstructured":"Coates A, Abbeel P, Ng AY (2008) Learning for control from multiple demonstrations. In: Proceedings of the 25th international conference on machine learning (ICML \u201908), Helsinki","DOI":"10.1145\/1390156.1390175"},{"issue":"1","key":"16_CR1346","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc 39(1):1\u201338","journal-title":"J R Stat Soc"},{"key":"16_CR1347","first-page":"3609","volume":"4","author":"M Dunbabin","year":"2004","unstructured":"Dunbabin M, Brosnan S, Roberts J, Corke P (2004) Vibration isolation for autonomous helicopter flight. In: Proceedings of the IEEE international conference on robotics and automation, New Orleans, vol\u00a04, pp\u00a03609\u20133615","journal-title":"Proceedings of the IEEE international conference on robotics and automation, New Orleans"},{"key":"16_CR1348","series-title":"AIAA guidance, navigation and control conference, Monterey. Massachusetts Institute of Technology, Cambridge","doi-asserted-by":"publisher","DOI":"10.2514\/6.2002-4834","volume-title":"Control logic for automated aerobatic flight of miniature helicopter","author":"V Gavrilets","year":"2002","unstructured":"Gavrilets V, Martinos I, Mettler B, Feron E (2002a) Control logic for automated aerobatic flight of miniature helicopter. In: AIAA guidance, navigation and control conference, Monterey. Massachusetts Institute of Technology, Cambridge"},{"key":"16_CR1349","series-title":"AIAA\/IEEE digital avionics systems conference, Irvine","doi-asserted-by":"publisher","DOI":"10.1109\/DASC.2002.1052943","volume-title":"Flight test and simulation results for an autonomous aerobatic helicopter","author":"V Gavrilets","year":"2002","unstructured":"Gavrilets V, Martinos I, Mettler B, Feron E (2002b) Flight test and simulation results for an autonomous aerobatic helicopter. In: AIAA\/IEEE digital avionics systems conference, Irvine"},{"key":"16_CR1350","series-title":"AIAA guidance, navigation and control conference, Montreal","first-page":"1593","volume-title":"Nonlinear model for a small-size acrobatic helicopter","author":"V Gavrilets","year":"2001","unstructured":"Gavrilets V, Mettler B, Feron E (2001) Nonlinear model for a small-size acrobatic helicopter. In: AIAA guidance, navigation and control conference, Montreal, pp\u00a01593\u20131600"},{"key":"16_CR1351","volume-title":"Differential dynamic programming","author":"DH Jacobson","year":"1970","unstructured":"Jacobson DH, Mayne DQ (1970) Differential dynamic programming. Elsevier, New York"},{"key":"16_CR1352","series-title":"Proceedings of the international conference on machine learning, Washington, DC","volume-title":"Exploration in metric state spaces","author":"S Kakade","year":"2003","unstructured":"Kakade S, Kearns M, Langford J (2003) Exploration in metric state spaces. In: Proceedings of the international conference on machine learning, Washington, DC"},{"key":"16_CR1353","unstructured":"Kearns M, Koller D (1999) Efficient reinforcement learning in factored MDPs. In: Proceedings of the 16th international joint conference on artificial intelligence, Stockholm. Morgan Kaufmann, San Francisco"},{"issue":"2\u20133","key":"16_CR1354","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1023\/A:1017984413808","volume":"49","author":"M Kearns","year":"2002","unstructured":"Kearns M, Singh S (2002) Near-optimal reinforcement learning in polynomial time. Mach Learn J 49(2\u20133):209\u2013232","journal-title":"Mach Learn J"},{"key":"16_CR1355","unstructured":"La Civita M (2003) Integrated modeling and robust control for full-envelope flight of robotic helicopters. PhD thesis, Carnegie Mellon University, Pittsburgh"},{"issue":"2","key":"16_CR1356","doi-asserted-by":"publisher","first-page":"485","DOI":"10.2514\/1.15796","volume":"29","author":"M La Civita","year":"2006","unstructured":"La Civita M, Papageorgiou G, Messner WC, Kanade T (2006) Design and flight testing of a high-bandwidth $$\\mathcal{H}_{\\infty }$$ loop shaping controller for a robotic helicopter. J Guid Control Dyn 29(2):485\u2013494","journal-title":"J Guid Control Dyn"},{"key":"16_CR1357","volume-title":"Principles of helicopter aerodynamics","author":"J Leishman","year":"2000","unstructured":"Leishman J (2000) Principles of helicopter aerodynamics. Cambridge University Press, Cambridge"},{"key":"16_CR1358","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1093\/comjnl\/7.4.308","volume":"7","author":"JA Nelder","year":"1964","unstructured":"Nelder JA, Mead R (1964) A simplex method for function minimization. Comput J 7:308\u2013313","journal-title":"Comput J"},{"key":"16_CR1359","series-title":"International symposium on experimental robotics, Singapore. Springer, Berlin","volume-title":"Autonomous inverted helicopter flight via reinforcement learning","author":"AY Ng","year":"2004","unstructured":"Ng AY, Coates A, Diel M, Ganapathi V, Schulte J, Tse B et al (2004) Autonomous inverted helicopter flight via reinforcement learning. In: International symposium on experimental robotics, Singapore. Springer, Berlin"},{"key":"16_CR1360","unstructured":"Ng AY, Jordan M (2000) Pegasus: a policy search method for large MDPs and POMDPs. In: Proceedings of the uncertainty in artificial intelligence 16th conference, Stanford. Morgan Kaufmann, San Francisco"},{"key":"16_CR1361","unstructured":"Ng AY, Kim HJ, Jordan M, Sastry S (2004) Autonomous helicopter flight via reinforcement learning. In: NIPS 16, Vancouver"},{"key":"16_CR1362","first-page":"663","volume-title":"Proceedings of the 17th international conference on machine learning","author":"AY Ng","year":"2000","unstructured":"Ng AY, Russell S (2000) Algorithms for inverse reinforcement learning. In: Proceedings of the 17th international conference on machine learning, San Francisco. Morgan Kaufmann, San Francisco, pp\u00a0663\u2013670"},{"issue":"3","key":"16_CR1363","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1109\/TRA.2003.810239","volume":"19","author":"S Saripalli","year":"2003","unstructured":"Saripalli S, Montgomery JF, Sukhatme GS (2003) Visually-guided landing of an unmanned aerial vehicle. IEEE Trans Robot Auton Syst 19(3):371\u2013380","journal-title":"IEEE Trans Robot Auton Syst"},{"key":"16_CR1364","series-title":"AIAA education series","volume-title":"Basic helicopter aerodynamics","author":"J Seddon","year":"1990","unstructured":"Seddon J (1990) Basic helicopter aerodynamics. AIAA education series. America Institute of Aeronautics and Astronautics, El Segundo"},{"key":"16_CR1365","doi-asserted-by":"publisher","first-page":"3","DOI":"10.4050\/JAHS.37.3","volume":"37","author":"MB Tischler","year":"1992","unstructured":"Tischler MB, Cauffman MG (1992) Frequency response method for rotorcraft system identification: flight application to BO-105 couple rotor\/fuselage dynamics. J Am Helicopter Soc 37:3\u201317","journal-title":"J Am Helicopter Soc"}],"container-title":["Encyclopedia of Machine Learning and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-4899-7687-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T15:29:46Z","timestamp":1719156586000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-1-4899-7687-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9781489976857","9781489976871"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-1-4899-7687-1_16","relation":{},"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"14 April 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}