{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:01:58Z","timestamp":1781622118589,"version":"3.54.5"},"reference-count":46,"publisher":"Informa UK Limited","issue":"13","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673261"],"award-info":[{"award-number":["61673261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Advanced Robotics"],"published-print":{"date-parts":[[2020,7,2]]},"DOI":"10.1080\/01691864.2020.1757504","type":"journal-article","created":{"date-parts":[[2020,5,5]],"date-time":"2020-05-05T07:36:20Z","timestamp":1588664180000},"page":"873-887","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":12,"title":["Learning efficient push and grasp policy in a totebox from simulation"],"prefix":"10.1080","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4039-8637","authenticated-orcid":false,"given":"Peiyuan","family":"Ni","sequence":"first","affiliation":[{"name":"Intelligent Robot Laboratory of SJTU, Shanghai Jiao Tong University, Shanghai, People\u2019s Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenguang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Intelligent Robot Laboratory of SJTU, Shanghai Jiao Tong University, Shanghai, People\u2019s Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoruo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Intelligent Robot Laboratory of SJTU, Shanghai Jiao Tong University, Shanghai, People\u2019s Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qixin","family":"Cao","sequence":"additional","affiliation":[{"name":"Intelligent Robot Laboratory of SJTU, Shanghai Jiao Tong University, Shanghai, People\u2019s Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2020,5,5]]},"reference":[{"key":"CIT0001","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"CIT0002","unstructured":"Kalashnikov D, Irpan A, Pastor P, et al. QT-Opt: scalable deep reinforcement learning for vision-based robotic manipulation; 2018; arXiv preprint arXiv:1806.10293."},{"key":"CIT0003","unstructured":"Viereck U, Pas A, Saenko K, et al. Learning a visuomotor controller for real world robotic grasping using simulated depth images. Conference on Robot Learning; 2017."},{"key":"CIT0004","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.021"},{"key":"CIT0005","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"CIT0006","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139361"},{"key":"CIT0007","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759114"},{"key":"CIT0008","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"CIT0009","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"CIT0010","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461039"},{"key":"CIT0011","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"CIT0012","unstructured":"Breyer M, Furrer F, Novkovic T, et al. Flexible robotic grasping with sim-to-real transfer based reinforcement learning; 2018; arXiv preprint arXiv:1803.04996."},{"key":"CIT0013","unstructured":"Yan M, Frosio I, Tyree S, et al. Sim-to-real transfer of accurate grasping with eye-in-hand observations and continuous control; 2017; arXiv preprint arXiv:1712.03303."},{"key":"CIT0014","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461041"},{"key":"CIT0015","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759446"},{"key":"CIT0016","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202166"},{"key":"CIT0017","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68792-6_51"},{"key":"CIT0018","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2013.2289018"},{"key":"CIT0019","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2004.1371616"},{"key":"CIT0020","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917735594"},{"key":"CIT0021","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461044"},{"key":"CIT0022","unstructured":"Kumar S, Majumder A, Dutta S, et al. Design and development of an automated robotic pick & stow system for an e-commerce warehouse; 2017; arXiv preprint arXiv:1703.02340."},{"key":"CIT0023","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-018-0788-6"},{"key":"CIT0024","unstructured":"Coumans E, Bai Y, Hsu J. Pybullet physics engine, ed."},{"key":"CIT0025","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"CIT0026","unstructured":"Mahler J, Goldberg K. Learning deep policies for robot bin picking by simulating robust grasping sequences. Conference on Robot Learning; 2017. p. 515\u2013524."},{"key":"CIT0027","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"CIT0028","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"CIT0029","unstructured":"Ebert F, Finn C, Lee AX, et al. Self-supervised visual planning with temporal skip connections; 2017; arXiv preprint arXiv:1710.05268."},{"key":"CIT0030","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"CIT0031","doi-asserted-by":"crossref","unstructured":"Cosgun A, Hermans T, Emeli V, et al. Push planning for object placement on cluttered table surfaces. 2011 IEEE\/RSJ international conference on Intelligent Robots and Systems (IROS); 2011. p. 4627\u20134632.","DOI":"10.1109\/IROS.2011.6094737"},{"key":"CIT0032","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.009"},{"key":"CIT0033","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2012.VIII.008"},{"key":"CIT0034","unstructured":"Eitel A, Hauff N, Burgard W. Learning to singulate objects using a push proposal network; 2017; arXiv preprint arXiv:1707.08101."},{"key":"CIT0035","doi-asserted-by":"crossref","unstructured":"Boularias A, Bagnell JA, Stentz A. Learning to manipulate unknown objects in clutter by reinforcement. AAAI; 2015. p. 1336\u20131342.","DOI":"10.1609\/aaai.v29i1.9378"},{"key":"CIT0036","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2018.8560406"},{"key":"CIT0037","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225337"},{"key":"CIT0038","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68792-6_51"},{"key":"CIT0039","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/676"},{"key":"CIT0040","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"CIT0041","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"CIT0042","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"CIT0043","unstructured":"Schaul T, Quan J, Antonoglou I, et al. Prioritized experience replay; 2015; arXiv preprint arXiv:1511.05952."},{"key":"CIT0044","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2015.2448951"},{"key":"CIT0045","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980567"},{"key":"CIT0046","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"}],"container-title":["Advanced Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01691864.2020.1757504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T02:34:08Z","timestamp":1666492448000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01691864.2020.1757504"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,5]]},"references-count":46,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2020,7,2]]}},"alternative-id":["10.1080\/01691864.2020.1757504"],"URL":"https:\/\/doi.org\/10.1080\/01691864.2020.1757504","relation":{},"ISSN":["0169-1864","1568-5535"],"issn-type":[{"value":"0169-1864","type":"print"},{"value":"1568-5535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,5]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2019-05-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-02-03","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-04-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-05-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}