{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T06:22:24Z","timestamp":1767766944219,"version":"3.48.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF) Korean Government [Ministry of Science and ICT (MSIT)]","doi-asserted-by":"publisher","award":["RS-2025-24523431"],"award-info":[{"award-number":["RS-2025-24523431"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2025.3637854","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T19:00:42Z","timestamp":1764270042000},"page":"455-469","source":"Crossref","is-referenced-by-count":0,"title":["Practical Mixed Palletizing Manipulator System: Incorporating Practical Reinforcement Learning and Configuration-Space Motion Planning"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8261-8132","authenticated-orcid":false,"given":"Woo-Jin","family":"Ahn","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Inha University, Incheon, South Korea"}]},{"given":"Kyuwon","family":"Choi","sequence":"additional","affiliation":[{"name":"Roboligent, Austin, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7678-1841","authenticated-orcid":false,"given":"Seong-Woo","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea University, Seoul, South Korea"}]},{"given":"Cheol-Kyun","family":"Rho","sequence":"additional","affiliation":[{"name":"AgileSoDA, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1245-7318","authenticated-orcid":false,"given":"Dong-Sung","family":"Pae","sequence":"additional","affiliation":[{"name":"Department of Software, Sangmyung University, Cheonan, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2990-8066","authenticated-orcid":false,"given":"Myo-Taeg","family":"Lim","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea University, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2022.09.014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102360"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2519944"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3177422"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/su16031278"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04352-0"},{"key":"ref7","first-page":"1","article-title":"Optimizing three-dimensional bin packing through simulation","volume-title":"Proc. 6th IASTED Int. Conf. Model., Simul., Optim.","author":"Dube"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.4028\/www.scientific.net\/AMR.383-390.584"},{"issue":"12","key":"ref9","first-page":"231","article-title":"Palletizing application of a six-axis industrial robot","volume":"7","author":"Padhy","year":"2017","journal-title":"Int. J. Emerg. Technol. Adv. Eng."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70836-2_56"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICAL.2008.4636574"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196850"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2023.109814"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1108\/01445150410549746"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2024.02.007"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3348-6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2449\/1\/012040"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1111\/1475-3995.00400"},{"key":"ref19","article-title":"Solving a new 3D bin packing problem with deep reinforcement learning method","author":"Hu","year":"2017","journal-title":"arXiv:1708.05930"},{"key":"ref20","first-page":"1","article-title":"Learning efficient online 3D bin packing on packing configuration trees","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhao"},{"key":"ref21","first-page":"1136","article-title":"Towards online 3D bin packing: Learning synergies between packing and unpacking via DRL","volume-title":"Proc. Conf. Robot Learn.","author":"Song"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417796"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16155"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04604-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3468161"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440731"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref29","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref30","article-title":"Neural combinatorial optimization with reinforcement learning","author":"Bello","year":"2016","journal-title":"arXiv:1611.09940"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.04.053"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3235742"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.jestch.2023.101610"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2023.102028"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1049\/cth2.12432"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/235815.235821"},{"article-title":"Optimal bidirectional rapidly-exploring random trees","year":"2013","author":"Jordan","key":"ref37"},{"key":"ref38","article-title":"Machine learning for the multi-dimensional bin packing problem: Literature review and empirical evaluation","author":"Wu","year":"2023","journal-title":"arXiv:2312.08103"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03544-w"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55792-2_10"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794049"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30198-1_45"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/ICCAS52745.2021.9649790"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/UR57808.2023.10202516"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-023-00274-2"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460547"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/70.326569"},{"issue":"5","key":"ref48","first-page":"255","article-title":"Classic and heuristic approaches in robot motion planning\u2014A chronological review","volume":"1","author":"Masehian","year":"2007","journal-title":"Int. J. Mech. Mechatronics Eng."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.proeng.2014.12.098"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122814"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICIPS.1997.669198"},{"key":"ref53","first-page":"3728","article-title":"Basic pose control algorithm of 5-DOF hybrid robotic arm suitable for table tennis robot","volume-title":"Proc. 29th Chin. Control Conf.","author":"Zheng"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ECTICON.2009.5137019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-019-00103-5"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2019.00120"},{"key":"ref57","first-page":"355","article-title":"Learning obstacle representations for neural motion planning","volume-title":"Proc. Conf. Robot Learn.","author":"Strudel"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793889"},{"key":"ref59","first-page":"967","article-title":"Motion policy networks","volume-title":"Proc. Conf. Robot Learn.","author":"Fishman"},{"key":"ref60","article-title":"Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","author":"Fu","year":"2024","journal-title":"arXiv:2401.02117"},{"key":"ref61","first-page":"2327","article-title":"Deep imitation learning for bimanual robotic manipulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref62","article-title":"Learning and retrieval from prior data for skill-based imitation learning","author":"Nasiriany","year":"2022","journal-title":"arXiv:2210.11435"},{"key":"ref63","first-page":"630","article-title":"Guided imitation of task and motion planning","volume-title":"Proc. Conf. Robot Learn.","author":"McDonald"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref65","article-title":"Open X-embodiment: Robotic learning datasets and RT-X models","author":"O\u2019Neill","year":"2023","journal-title":"arXiv:2310.08864"},{"key":"ref66","first-page":"1199","article-title":"VIOLA: Imitation learning for vision-based manipulation with object proposal priors","volume-title":"Proc. Conf. Robot Learn.","author":"Zhu"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN60168.2024.10731447"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10609992"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13310"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980573"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/361237.361242"},{"key":"ref73","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref74","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Veli\u010dkovi\u0107"},{"volume-title":"Pybullet, a Python Module for Physics Simulation for Games, Robotics and Machine Learning","year":"2016","author":"Coumans","key":"ref75"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11270909.pdf?arnumber=11270909","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T06:17:53Z","timestamp":1767766673000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11270909\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3637854","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"type":"print","value":"1545-5955"},{"type":"electronic","value":"1558-3783"}],"subject":[],"published":{"date-parts":[[2026]]}}}