{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T02:49:12Z","timestamp":1774147752916,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102700"],"award-info":[{"award-number":["2018AAA0102700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcds.2022.3209680","type":"journal-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T19:53:05Z","timestamp":1664308385000},"page":"1314-1322","source":"Crossref","is-referenced-by-count":6,"title":["A Reinforcement Learning Method for Rearranging Scattered Irregular Objects Inside a Crate"],"prefix":"10.1109","volume":"15","author":[{"given":"Liang","family":"Tang","sequence":"first","affiliation":[{"name":"Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9292-024X","authenticated-orcid":false,"given":"Hao","family":"Liu","sequence":"additional","affiliation":[{"name":"Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huang","family":"Huang","sequence":"additional","affiliation":[{"name":"Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinru","family":"Xie","sequence":"additional","affiliation":[{"name":"Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nailong","family":"Liu","sequence":"additional","affiliation":[{"name":"Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mou","family":"Li","sequence":"additional","affiliation":[{"name":"Systems Innovation Center, Beijing Institute of Control Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197508"},{"key":"ref35","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref15","first-page":"50","article-title":"Pick and place objects in a cluttered scene using deep reinforcement learning","volume":"20","author":"mohammed","year":"2020","journal-title":"Int J Mech Mechatronics Eng"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636280"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","first-page":"13","author":"bundy","year":"1984","journal-title":"Catalogue of Artificial Intelligence Tools"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060669"},{"key":"ref33","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"},{"key":"ref10","article-title":"Six-dimensional target pose estimation for robot autonomous manipulation: Methodology and verification","author":"wang","year":"2022","journal-title":"IEEE Trans Cogn Devel Syst"},{"key":"ref32","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3043168"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062250"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.06.007"},{"key":"ref16","article-title":"Hierarchical policy for non-prehensile multi-object rearrangement with deep reinforcement learning and Monte Carlo tree search","author":"bai","year":"2021","journal-title":"arXiv 2109 08973"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9306-z"},{"key":"ref18","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004255"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3092640"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341532"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2969680"},{"key":"ref20","article-title":"Learning to singulate objects using a push proposal network","author":"eitel","year":"2018","journal-title":"arXiv 1707 08101"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref21","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2018","journal-title":"arXiv 1707 01495"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794049"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967548"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103535"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3096239"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561409"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196740"},{"key":"ref4","year":"2021","journal-title":"Assessing perseverance’s first sample attempt—NASA Mars"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3093896"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2019.2921098"},{"key":"ref5","year":"2021","journal-title":"Update China’s Chang’e-5 retrieves 1 731 grams of moon samples"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10242607\/09904530.pdf?arnumber=9904530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:40:02Z","timestamp":1699904402000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9904530\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":35,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2022.3209680","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}