{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:38:30Z","timestamp":1730255910015,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610080","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"7812-7818","source":"Crossref","is-referenced-by-count":0,"title":["6-DoF Closed-Loop Grasping with Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Sverre","family":"Herland","sequence":"first","affiliation":[{"name":"NTNU IDI,Norway"}]},{"given":"Kerstin","family":"Bach","sequence":"additional","affiliation":[{"name":"NTNU IDI,Norway"}]},{"given":"Ekrem","family":"Misimi","sequence":"additional","affiliation":[{"name":"SINTEF Ocean,Norway"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919859066"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197196"},{"key":"ref4","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conference on Robot Learning","author":"Kalashnikov"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919868017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00299"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197318"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004787"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104451"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2992195"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3226148"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adg1462"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1900533"},{"key":"ref17","first-page":"741","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","volume":"33","author":"Lee","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref19","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref20"},{"article-title":"Fast segment anything","year":"2023","author":"Zhao","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","year":"2021","author":"Makoviychuk","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917700714"},{"article-title":"Viola: Imitation learning for vision-based manipulation with object proposal priors","volume-title":"6th Annual Conference on Robot Learning","author":"Zhu","key":"ref25"},{"key":"ref26","article-title":"A general framework for grasping unknown objects by coupling vision-based drl, real-to-sim adaptation, and ibvs","author":"Sumskiy","year":"2023","journal-title":"International Journal of Robotics Research (IJRR)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2017.xiii.058"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3200138"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610080.pdf?arnumber=10610080","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:43:48Z","timestamp":1723268628000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610080\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610080","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}