{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T13:46:27Z","timestamp":1784036787733,"version":"3.55.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council Postgraduate Scholarship","doi-asserted-by":"publisher","award":["201806120019"],"award-info":[{"award-number":["201806120019"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3073711","type":"journal-article","created":{"date-parts":[[2021,4,16]],"date-time":"2021-04-16T20:15:19Z","timestamp":1618604119000},"page":"60175-60186","source":"Crossref","is-referenced-by-count":27,"title":["Hybrid Trajectory and Force Learning of Complex Assembly Tasks: A Combined Learning Framework"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9436-6262","authenticated-orcid":false,"given":"Yan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1134-009X","authenticated-orcid":false,"given":"Cristian C.","family":"Beltran-Hernandez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0058-2819","authenticated-orcid":false,"given":"Weiwei","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7576-756X","authenticated-orcid":false,"given":"Kensuke","family":"Harada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"2018","author":"haarnoja","year":"0","journal-title":"Int Conf Mach Learn"},{"key":"ref38","first-page":"1113","article-title":"Learning latent plans from play","volume":"100","author":"lynch","year":"2020","journal-title":"Proc Mach Learn Res (PMLR)"},{"key":"ref33","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref32","first-page":"661","article-title":"Efficient reductions for imitation learning","author":"ross","year":"2010","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref30","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"arXiv 1604 07316 [cs]"},{"key":"ref37","first-page":"1312","article-title":"Universal value function approximators","author":"schaul","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","first-page":"1094","article-title":"Learning to achieve goals","author":"kaelbling","year":"1993","journal-title":"Proc IJCAI"},{"key":"ref35","first-page":"1025","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","volume":"100","author":"gupta","year":"2020","journal-title":"Proc Mach Learn Res (PMLR)"},{"key":"ref34","first-page":"15298","article-title":"Goal-conditioned imitation learning","author":"ding","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-014-0329-9"},{"key":"ref40","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9435-2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2635479"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2018.8624968"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354134"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/0278364903022005002"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460696"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref19","first-page":"12","article-title":"Robot learning from demonstration","volume":"97","author":"atkeson","year":"1997","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010739"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1163\/016918611X558261"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/70.246048"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907080736"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8246961"},{"key":"ref29","first-page":"103","article-title":"A framework for behavioural cloning","volume":"15","author":"bain","year":"1995","journal-title":"Machine Intelligence"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/AIM.2016.7576815"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref7","first-page":"1852","article-title":"Assembly task learning and optimization through human’s demonstration and machine learning","author":"roveda","year":"2020","journal-title":"Proc IEEE Int Conf Syst Man Cybern (SMC)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1984.4788393"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref21","first-page":"849","article-title":"Policy search for motor primitives in robotics","author":"kober","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968201"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967995"},{"key":"ref23","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"vecerik","year":"2018","journal-title":"arXiv 1707 08817v2"},{"key":"ref26","article-title":"Robotic imitation of human assembly skills using hybrid trajectory and force learning","author":"wang","year":"2021","journal-title":"arXiv 2103 05912"},{"key":"ref43","author":"ota","year":"2020","journal-title":"Tf2rl"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09406007.pdf?arnumber=9406007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:39Z","timestamp":1639770939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9406007\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3073711","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}