{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:28:38Z","timestamp":1777652918345,"version":"3.51.4"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9635914","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T15:45:38Z","timestamp":1639669538000},"page":"5002-5008","source":"Crossref","is-referenced-by-count":26,"title":["PackerBot: Variable-Sized Product Packing with Heuristic Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Zifei","family":"Yang","sequence":"first","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Yang","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Song","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Song","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiyu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibin","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Tianshou","author":"weng","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.04.148"},{"key":"ref30","article-title":"Learn what not to learn: Action elimination with deep reinforcement learning","author":"zahavy","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1070.0250"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF00226291"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2012.07.036"},{"key":"ref11","article-title":"Optimization and coordinated autonomy in mobile fulfillment systems","author":"enright","year":"2011","journal-title":"AAAIW"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460699"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/027836499601500302"},{"key":"ref14","article-title":"Design of a multi-modal end-effector and grasping system: How integrated design helped win the amazon robotics challenge","author":"wade-mccue","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau4984"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.endm.2010.05.126"},{"key":"ref17","first-page":"46","article-title":"Approximation algorithms for bin packing: A survey","author":"man","year":"1996","journal-title":"Approximation Algorithms for NP-Hard Problems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(02)00134-0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.dam.2010.05.026"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793966"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461195"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062300"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TASE.2016.2600527","article-title":"Analysis and observations from the first amazon picking challenge","volume":"15","author":"correll","year":"2016","journal-title":"IEEE Trans Autom Sci Eng"},{"key":"ref6","article-title":"Online 3d bin packing with constrained deep reinforcement learning","author":"zhao","year":"2020"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1070.0250"},{"key":"ref7","article-title":"A generalized reinforcement learning algorithm for online 3d bin-packing","author":"verma","year":"2020","journal-title":"AAAI"},{"key":"ref2","article-title":"Solving a new 3d bin packing problem with deep reinforcement learning method","author":"hu","year":"2017"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1016\/j.ejor.2007.06.063","article-title":"Ts 2 pack : A two-level tabu search for the three-dimensional bin packing problem","volume":"195","author":"a","year":"2009","journal-title":"Eur J Oper Res"},{"key":"ref1","first-page":"1","article-title":"Robot packing with known items and nondeterministic arrival order","author":"wang","year":"2020","journal-title":"IEEE Trans Autom Sci Eng"},{"key":"ref20","article-title":"Neural combinatorial optimization with reinforcement learning","author":"bello","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN46459.2019.8956393"},{"key":"ref21","article-title":"Ranked reward: Enabling self-play reinforcement learning for combinatorial optimization","author":"laterre","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197508"},{"key":"ref23","first-page":"357","article-title":"One-shot visual imitation learning via meta-learning","author":"finn","year":"2017","journal-title":"CoRL"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00876"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460689"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09635914.pdf?arnumber=9635914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:13:44Z","timestamp":1756235624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9635914\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9635914","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}