{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T21:53:31Z","timestamp":1757541211082,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561937","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"2768-2774","source":"Crossref","is-referenced-by-count":4,"title":["End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning"],"prefix":"10.1109","author":[{"given":"Mohammadreza","family":"Sharif","sequence":"first","affiliation":[{"name":"Northeastern University,Electrical and Computer Engineering Department,Boston,MA,USA,02115"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deniz","family":"Erdogmus","sequence":"additional","affiliation":[{"name":"Northeastern University,Electrical and Computer Engineering Department,Boston,MA,USA,02115"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Amato","sequence":"additional","affiliation":[{"name":"Northeastern University,Khoury College of Computer Sciences,Boston,MA,USA,02115"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taskin","family":"Padir","sequence":"additional","affiliation":[{"name":"Northeastern University,Electrical and Computer Engineering Department,Boston,MA,USA,02115"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"CAD2RL: Real Single-Image flight without a single real image","year":"2016","author":"sadeghi","key":"ref39"},{"article-title":"Bebionic prosthetic design","year":"2011","author":"medynski","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5979561"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593707"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref31"},{"article-title":"Soft Actor-Critic: Off-Policy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"haarnoja","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363441"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref35","first-page":"8024","article-title":"PyTorch: An imperative style, HighPerformance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"article-title":"Digideep: A DeepRL pipeline for developers","year":"2019","author":"sharif","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2010.2100828"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinbiomech.2010.02.011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2018.00001"},{"article-title":"SOLAR: Deep structured representations for Model-Based reinforcement learning","year":"2018","author":"zhang","key":"ref13"},{"key":"ref14","article-title":"Deep reinforcement learning for robotic manipulation with asynchronous Off-Policy updates","author":"gu","year":"2016","journal-title":"Robotics and Automation"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2011.5975338"},{"article-title":"A reduction of imitation learning and structured prediction to No-Regret online learning","year":"2010","author":"ross","key":"ref16"},{"article-title":"Reinforcement learning from imperfect demonstrations","year":"2018","author":"gao","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2017.8009453"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aao4900"},{"key":"ref28","volume":"2","author":"dam","year":"1998","journal-title":"Quaternions Interpolation and Animation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2016.00007"},{"article-title":"DeepMind control suite","year":"2018","author":"tassa","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0186318"},{"article-title":"Visual cues to improve myoelectric control of upper limb prostheses","year":"2017","author":"gigli","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1080\/00222895.1993.9942048"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/1743-0003-7-42"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0093-5"},{"key":"ref7","first-page":"25","article-title":"Particle filters vs hidden markov models for prosthetic robot hand grasp selection","volume":"1","author":"sharif","year":"2019","journal-title":"International journal of Computer and Robotics"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2015.02.009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1152\/jn.1998.79.3.1307"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2013.2282898"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/BioRob49111.2020.9224380"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2909824.3020252"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(95)00103-4"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2018.2884719"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref26","first-page":"27836491771031","article-title":"Learning Hand-Eye coordination for robotic grasping with deep learning and Large-Scale data collection","author":"levine","year":"2016","journal-title":"The Int’ l J of Robotics Research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64816-3_8"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561937.pdf?arnumber=9561937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T19:08:59Z","timestamp":1674241739000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561937\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561937","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}