{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:04:00Z","timestamp":1781885040325,"version":"3.54.5"},"reference-count":22,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"DAAD-Stiftung"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/lra.2024.3488402","type":"journal-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T17:58:22Z","timestamp":1730311102000},"page":"11353-11360","source":"Crossref","is-referenced-by-count":6,"title":["Safe Reinforcement Learning of Robot Trajectories in the Presence of Moving Obstacles"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8044-5111","authenticated-orcid":false,"given":"Jonas","family":"Kiemel","sequence":"first","affiliation":[{"name":"Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6458-9112","authenticated-orcid":false,"given":"Ludovic","family":"Righetti","sequence":"additional","affiliation":[{"name":"Tandon School of Engineering, New York University (NYU), Brooklyn, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Torsten","family":"Kr\u00f6ger","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4879-7680","authenticated-orcid":false,"given":"Tamim","family":"Asfour","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics (IAR), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460547"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1987.1087982"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109597"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids53995.2022.10000077"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982038"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref9","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5932"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref12","first-page":"784","article-title":"Model-free safe control for zero-violation reinforcement learning","volume-title":"Proc. 5th Annu. Conf. Robot Learn.","author":"Zhao","year":"2021"},{"key":"ref13","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"30","author":"Berkenkamp","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3299275"},{"key":"ref17","first-page":"143","article-title":"Safe exploration for reinforcement learning.","volume-title":"Proc. ESANN","author":"Hans","year":"2008"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363138"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-011-9264-x"},{"key":"ref20","article-title":"Learning to be safe: Deep rl with a safety critic","author":"Srinivasan"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561159"},{"key":"ref22","article-title":"Proximal policy optimization algorithms","author":"Schulman"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10726578\/10738380.pdf?arnumber=10738380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:38:32Z","timestamp":1734982712000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10738380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":22,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3488402","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}