{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:54:29Z","timestamp":1783457669524,"version":"3.55.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2016,3,1]],"date-time":"2016-03-01T00:00:00Z","timestamp":1456790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1208623"],"award-info":[{"award-number":["IIS-1208623"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of naval Research","doi-asserted-by":"publisher","award":["N00014-13-1-0562"],"award-info":[{"award-number":["N00014-13-1-0562"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Air Force Office of Scientific Research European Office of Aerospace Research and Development","award":["13-3055"],"award-info":[{"award-number":["13-3055"]}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-11-D-0001"],"award-info":[{"award-number":["W911NF-11-D-0001"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/tcyb.2015.2412554","type":"journal-article","created":{"date-parts":[[2015,3,24]],"date-time":"2015-03-24T16:44:35Z","timestamp":1427215475000},"page":"655-667","source":"Crossref","is-referenced-by-count":199,"title":["Optimized Assistive Human\u2013Robot Interaction Using Reinforcement Learning"],"prefix":"10.1109","volume":"46","author":[{"given":"Hamidreza","family":"Modares","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isura","family":"Ranatunga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank L.","family":"Lewis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan O.","family":"Popa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","author":"bertsekas","year":"2012","journal-title":"Dynamic Programming and Optimal Control Approximate Dynamic Programming"},{"key":"ref38","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1013431"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2011.2162501"},{"key":"ref31","article-title":"Engineering aspects of the human being as a servo-mechanism","author":"ragazzini","year":"0"},{"key":"ref30","first-page":"190","article-title":"The nature of the operator’s response in manual control and its implications for controller design","volume":"94","author":"tustin","year":"1947","journal-title":"J Inst Elec Eng II"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAS.2013.6704029"},{"key":"ref35","first-page":"1187","article-title":"Impedance control for multi-point human-robot interaction","author":"li","year":"2011","journal-title":"Proc 8th Asian Control Conf (ASCC)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICMECH.2011.5971211"},{"key":"ref28","first-page":"647","article-title":"Human adaptive mechatronics (HAM) for haptic system","volume":"1","author":"kurihara","year":"2004","journal-title":"Proc 30th IEEE Ind Elec Conf"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1987.1087743"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2005.1582887"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamcollsurg.2012.02.005"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912455366"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2012.2205924"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152664"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2005.850603"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2014.2309118"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2002.1045671"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CACSD-CCA-ISIC.2006.4776704"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1109\/TMECH.2013.2264533","article-title":"Human–robot collaboration based on motion intention estimation","volume":"19","author":"li","year":"2014","journal-title":"IEEE\/ASME Trans Mechatronics"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.03.008"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.096"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2276571"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.09.043"},{"key":"ref52","article-title":"Integral reinforcement learning for continuous-time input-affine nonlinear systems with simultaneous invariant explorations","author":"lee","year":"0","journal-title":"IEEE Trans Cybern"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1115\/1.3140702"},{"key":"ref11","first-page":"433","article-title":"Impedance control of robot manipulators using adaptive neural networks","volume":"2","author":"ge","year":"1998","journal-title":"Int J Intell Control Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2009.5410286"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISIC.2002.1157833"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980070"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2222374"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/41.679003"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(70)90052-X"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1155\/2012\/365067"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1152\/jn.01123.2011"},{"key":"ref4","author":"lewis","year":"1999","journal-title":"Neural Network Control of Robot Manipulators and Nonlinear Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1163\/016918611X607356"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/S026357470400075X"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2006.878297"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.03.015"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1142\/3774","author":"ge","year":"1998","journal-title":"Adaptive Neural Network Control of Robotic Manipulators"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-012-1186-9"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1201\/9780203026953","author":"lewis","year":"2003","journal-title":"Robot Manipulator Control Theory and Practice"},{"key":"ref45","first-page":"390","article-title":"Neural-network-based human intention estimation for physical human-robot interaction","author":"ge","year":"2011","journal-title":"Proc Int Conf Ubiquitous Robots and Ambient Intell"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2317301"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2384016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1049\/PBCE081E"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2012.2214134"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2010.2040202"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WHC.2009.4810835"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/7406788\/07066908.pdf?arnumber=7066908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:48:33Z","timestamp":1641988113000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7066908\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":54,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2015.2412554","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,3]]}}}