{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:29:05Z","timestamp":1785511745041,"version":"3.56.0"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Wallenberg AI, Autonomous Systems and Software Program"},{"DOI":"10.13039\/501100004063","name":"Knut och Alice Wallenbergs Stiftelse","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1109\/lra.2021.3111962","type":"journal-article","created":{"date-parts":[[2021,9,13]],"date-time":"2021-09-13T20:35:50Z","timestamp":1631565350000},"page":"8583-8590","source":"Crossref","is-referenced-by-count":17,"title":["Learning Deep Energy Shaping Policies for Stability-Guaranteed Manipulation"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0443-7982","authenticated-orcid":false,"given":"Shahbaz Abdul","family":"Khader","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3599-440X","authenticated-orcid":false,"given":"Hang","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1133-0884","authenticated-orcid":false,"given":"Pietro","family":"Falco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2965-2953","authenticated-orcid":false,"given":"Danica","family":"Kragic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref31","article-title":"Garage: A toolkit for reproducible reinforcement learning research","author":"contributors","year":"2019"},{"key":"ref30","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref34","first-page":"949","article-title":"Natural evolution strategies","volume":"15","author":"wierstra","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref10","article-title":"Learning stable normalizing-flow control for robotic manipulation","author":"khader","year":"2020"},{"key":"ref11","first-page":"146","article-title":"Input convex neural networks","author":"amos","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","author":"rubinstein","year":"2004","journal-title":"The Cross Entropy Method A Unified Approach to Combinatorial Optimization Monte-Carlo Simulation (Information Science and Statistics)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3011351"},{"key":"ref14","article-title":"Deep lagrangian networks: Using physics as model prior for deep learning","author":"lutter","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","article-title":"Unsupervised learning of lagrangian dynamics from images for prediction and control","volume":"33","author":"zhong","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"15 379","article-title":"Hamiltonian neural networks","volume":"32","author":"greydanus","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref17","article-title":"Hamiltonian generative networks","author":"toth","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2343194"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9528-y"},{"key":"ref28","first-page":"1647","article-title":"Compliant manipulation for peg-in-hole: Is passive compliance a key to learn contact motion","author":"yun","year":"0","journal-title":"Proc IEEE Int Conf Robot Automat"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.088"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/00207178808906161"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2996067"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref5","first-page":"1141","article-title":"Control regularization for reduced variance reinforcement learning","author":"cheng","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref8","author":"slotine","year":"1991","journal-title":"Applied nonlinear control"},{"key":"ref7","author":"siciliano","year":"2010","journal-title":"Robotics Modelling Planning and Control"},{"key":"ref2","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"berkenkamp","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3028529"},{"key":"ref1","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref20","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87481-2_16"},{"key":"ref21","article-title":"Parameter space noise for exploration","author":"matthias","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/37.915398"},{"key":"ref23","first-page":"512","article-title":"The cross entropy method for fast policy search","author":"mannor","year":"2003","journal-title":"Proc 20th Int Conf Mach Learn"},{"key":"ref26","first-page":"375","article-title":"Impedance and interaction control","author":"hogan","year":"2018","journal-title":"Handbook on Robotics and Automation"},{"key":"ref25","first-page":"11 128","article-title":"Learning stable deep dynamics models","author":"kolter","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9475905\/09536404.pdf?arnumber=9536404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:07Z","timestamp":1652194447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9536404\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":34,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3111962","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10]]}}}