{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T22:22:32Z","timestamp":1780525352851,"version":"3.54.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1109\/lra.2021.3065271","type":"journal-article","created":{"date-parts":[[2021,3,11]],"date-time":"2021-03-11T20:51:55Z","timestamp":1615495915000},"page":"3918-3925","source":"Crossref","is-referenced-by-count":18,"title":["Uncertainty-Aware Contact-Safe Model-Based Reinforcement Learning"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3085-0343","authenticated-orcid":false,"given":"Cheng-Yu","family":"Kuo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Schaarschmidt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5539-4260","authenticated-orcid":false,"given":"Yunduan","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4879-7680","authenticated-orcid":false,"given":"Tamim","family":"Asfour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3545-4814","authenticated-orcid":false,"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","first-page":"1459","article-title":"Computationally efficient convolved multiple output gaussian processes","volume":"12","author":"\u00e1lvarez","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref31","first-page":"481","author":"bollini","year":"2013","journal-title":"Interpreting and Executing Recipes With a Cooking Robot"},{"key":"ref30","first-page":"1","article-title":"Data efficient reinforcement learning for legged robots","author":"yang","year":"0","journal-title":"Proc 3th Conf Robot Learn"},{"key":"ref10","first-page":"465","article-title":"Pilco: A. model-based and data-efficient approach to policy search","author":"deisenroth","year":"0","journal-title":"Proc 28th Int Conf Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-3834-2","author":"sch\u00e4ttler","year":"2012","journal-title":"Geometric Optimal Control-Theory Methods and Examples"},{"key":"ref12","first-page":"1701","article-title":"Data-efficient reinforcement learning with probabilistic model predictive control","volume":"84","author":"kamthe","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref13","author":"pontryagin","year":"1962","journal-title":"The Mathematical Theory of Optimal Processes"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197449"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968201"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010739"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref19","article-title":"Motion planner augmented reinforcement learning for robot manipulation in obstructed environments","author":"yamada","year":"0","journal-title":"Proc 4th Conf Robot Learn"},{"key":"ref28","author":"rasmussen","year":"2006","journal-title":"Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980200"},{"key":"ref27","first-page":"244","article-title":"Fastfood: Approximating kernel expansions in loglinear time","volume":"28","author":"le","year":"0","journal-title":"Proc 30th Int Conf Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095096"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2996067"},{"key":"ref29","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref5","first-page":"244","article-title":"Data-driven model predictive control for the contact-rich task of food cutting","author":"mitsioni","year":"0","journal-title":"Proc 19th IEEE-RAS Int Conf Humanoid Robots"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0549-y"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/S0005-1098(99)00214-9","article-title":"Constrained model predictive control: Stability and optimality","volume":"36","author":"mayne","year":"2000","journal-title":"Automatica"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.janxdis.2016.03.011"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref20","author":"deb","year":"2001","journal-title":"Multi-Objective Optimization Using Evolutionary Algorithms"},{"key":"ref22","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013915"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197125"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21990"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-5014-9_23"},{"key":"ref25","first-page":"9441","article-title":"Learning skills to patch plans based on inaccurate models","author":"lagrassa","year":"0","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9285111\/09376242.pdf?arnumber=9376242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:27Z","timestamp":1652194467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9376242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":32,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3065271","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]}}}