{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:36:05Z","timestamp":1730302565015,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T00:00:00Z","timestamp":1626048000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T00:00:00Z","timestamp":1626048000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,12]]},"DOI":"10.1109\/ur52253.2021.9494631","type":"proceedings-article","created":{"date-parts":[[2021,7,30]],"date-time":"2021-07-30T21:22:36Z","timestamp":1627680156000},"page":"464-470","source":"Crossref","is-referenced-by-count":1,"title":["A Deep Reinforcement Learning-based Application Framework for Conveyor Belt-based Pick-and-Place Systems using 6-axis Manipulators under Uncertainty and Real-time Constraints"],"prefix":"10.1109","author":[{"given":"Tuyen P.","family":"Le","sequence":"first","affiliation":[{"name":"AgileSoDA Company,South Korea"}]},{"given":"DongHyun","family":"Lee","sequence":"additional","affiliation":[{"name":"AgileSoDA Company,South Korea"}]},{"given":"DaeWoo","family":"Choi","sequence":"additional","affiliation":[{"name":"Hankuk University of Foreign Studies,Department of Statistics,South Korea"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2012.2205651"},{"key":"ref11","first-page":"995","article-title":"Rrt-connect: An efficient approach to single-query path planning","volume":"2","author":"kuffner","year":"2000","journal-title":"Proceedings 2000 ICRA Millennium Conference IEEE International Conference on Robotics and Automation Symposia Proceedings (Cat No 00CH37065)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/7426913"},{"journal-title":"Niryo one","year":"2021","key":"ref13"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2854283"},{"key":"ref17","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"99","author":"sutton","year":"1999","journal-title":"NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-017-9579-x"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICSEngT.2012.6339325"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2011.12.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0736-5845(99)00041-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SVR.2019.00049"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1287\/opre.16.3.687","article-title":"Letter to the editor—a proof of the optimality of the shortest remaining processing time discipline","volume":"16","author":"schrage","year":"1968","journal-title":"Operations Research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2018.00012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref1","volume":"44","author":"buchholz","year":"2015","journal-title":"Bin-Picking New Approaches for a Classical Problem"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"schulman","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/7426913"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2011.2181749"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/MRA.2012.2205651","article-title":"The open motion planning library","volume":"19","author":"sucan","year":"2012","journal-title":"IEEE Robotics & Automation Magazine"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref26"},{"article-title":"Deep recurrent q-learning for partially observable mdps","year":"2015","author":"hausknecht","key":"ref25"}],"event":{"name":"2021 18th International Conference on Ubiquitous Robots (UR)","start":{"date-parts":[[2021,7,12]]},"location":"Gangneung, Korea (South)","end":{"date-parts":[[2021,7,14]]}},"container-title":["2021 18th International Conference on Ubiquitous Robots (UR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9494626\/9494628\/09494631.pdf?arnumber=9494631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:17:27Z","timestamp":1659485847000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9494631\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,12]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ur52253.2021.9494631","relation":{},"subject":[],"published":{"date-parts":[[2021,7,12]]}}}