{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T11:17:35Z","timestamp":1767093455284,"version":"3.27.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":[[2024,7,1]]},"DOI":"10.1109\/codit62066.2024.10708345","type":"proceedings-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T17:27:18Z","timestamp":1729272438000},"page":"2917-2923","source":"Crossref","is-referenced-by-count":3,"title":["Safety-Driven Deep Reinforcement Learning Framework for Cobots: A Sim2Real Approach"],"prefix":"10.1109","volume":"16","author":[{"given":"Ammar N.","family":"Abbas","sequence":"first","affiliation":[{"name":"Software Competence Center,Data Science,Hagenberg,Austria"}]},{"given":"Shakra","family":"Mehak","sequence":"additional","affiliation":[{"name":"Software Competence Center,Data Science,Hagenberg,Austria"}]},{"given":"Georgios C.","family":"Chasparis","sequence":"additional","affiliation":[{"name":"Pilz,Industrial Automation,Cork,Ireland"}]},{"given":"John D.","family":"Kelleher","sequence":"additional","affiliation":[{"name":"Trinity College Dublin,Computer Science,Dublin,Ireland"}]},{"given":"Michael","family":"Guilfoyle","sequence":"additional","affiliation":[{"name":"Pilz,Industrial Automation,Cork,Ireland"}]},{"given":"Maria Chiara","family":"Leva","sequence":"additional","affiliation":[{"name":"Technological University Dublin,Food Science and Environmental Health,Dublin,Ireland"}]},{"given":"Aswin K","family":"Ramasubramanian","sequence":"additional","affiliation":[{"name":"Irish Manufacturing Research,Robotics and Automation,Mullingar,Ireland"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2024.03.015"},{"issue":"1","key":"ref2","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u0131a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2014.7090732"},{"journal-title":"Standard DIN EN ISO 10218\u20131","article-title":"Robots and robotic devices-safety requirements for industrial robots-part 1: Robots","year":"2012","key":"ref5"},{"journal-title":"Standard DIN EN 61508\u20131","article-title":"Functional safety of electrical\/electronic\/programmable electronic safety-related systems part 1: General requirements","year":"2016","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1051\/matecconf\/201710002011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISPCE-TW.2017.8626833"},{"key":"ref9","article-title":"Provably safe reinforcement learning: Conceptual analysis, survey, and benchmarking","author":"Krasowski","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-443-13812-6.00011-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20737"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812181"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3063989"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3351797"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196924"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3002852"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3173039"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561384"},{"key":"ref21","first-page":"13 859","article-title":"Safe reinforcement learning by imagining the near future","volume":"34","author":"Thomas","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3447928.3456653"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161548"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.6585"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"article-title":"Safe reinforcement learning using probabilistic shields","volume-title":"31st International Conference on Concurrency Theory (CONCUR 2020)","author":"Jansen","key":"ref26"},{"article-title":"Benchmarking safe exploration in deep reinforcement learning","year":"2019","author":"Ray","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06187-8"},{"article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","year":"2018","author":"Plappert","key":"ref29"},{"key":"ref30","article-title":"Safety gymnasium: A unified safe reinforcement learning benchmark","volume":"36","author":"Ji","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5220\/0006849302930300"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54927-9"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/app13020680"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2021.11.287"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.cirp.2022.04.054"},{"article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","year":"2018","author":"Plappert","key":"ref36"},{"article-title":"Accelerating robot learning of contact-rich manipulations: A curriculum learning study","year":"2022","author":"Beltran-Hernandez","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.71"},{"article-title":"ammar-n-abbas\/sim2real-ur-gym-gazebo: v1.0.0","year":"2024","author":"Abbas","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCECE51280.2021.9342134"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/s20030939"},{"article-title":"Gymnasium robotics","year":"2023","author":"de Lazcano","key":"ref42"},{"key":"ref43","first-page":"5556","article-title":"Controlling overestimation bias with truncated mixture of continuous distributional quantile critics","volume-title":"International Conference on Machine Learning","author":"Kuznetsov"}],"event":{"name":"2024 10th International Conference on Control, Decision and Information Technologies (CoDIT)","start":{"date-parts":[[2024,7,1]]},"location":"Vallette, Malta","end":{"date-parts":[[2024,7,4]]}},"container-title":["2024 10th International Conference on Control, Decision and Information Technologies (CoDIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10708054\/10708053\/10708345.pdf?arnumber=10708345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T04:49:38Z","timestamp":1729313378000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10708345\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,1]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/codit62066.2024.10708345","relation":{},"subject":[],"published":{"date-parts":[[2024,7,1]]}}}