{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T09:43:46Z","timestamp":1775123026160,"version":"3.50.1"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201908080039"],"award-info":[{"award-number":["201908080039"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161548","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"9449-9456","source":"Crossref","is-referenced-by-count":16,"title":["Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction"],"prefix":"10.1109","author":[{"given":"Puze","family":"Liu","sequence":"first","affiliation":[{"name":"Technical University Darmstadt,Computer Science Department"}]},{"given":"Kuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Technical University Darmstadt,Computer Science Department"}]},{"given":"Davide","family":"Tateo","sequence":"additional","affiliation":[{"name":"Technical University Darmstadt,Computer Science Department"}]},{"given":"Snehal","family":"Jauhri","sequence":"additional","affiliation":[{"name":"Technical University Darmstadt,Computer Science Department"}]},{"given":"Zhiyuan","family":"Hu","sequence":"additional","affiliation":[{"name":"Technical University Darmstadt,Computer Science Department"}]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[{"name":"Technical University Darmstadt,Computer Science Department"}]},{"given":"Georgia","family":"Chalvatzaki","sequence":"additional","affiliation":[{"name":"Technical University Darmstadt,Computer Science Department"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref57","author":"lynch","year":"2017","journal-title":"Modern Robotics"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12103"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref15","article-title":"Constrained Policy Optimization","author":"achiam","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref59","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s001860050035"},{"key":"ref58","first-page":"1","article-title":"Mushroomrl: Simplifying reinforcement learning research","volume":"22","author":"d'eramo","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1115\/1.3169173"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1115\/1.3260800"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981456"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039601"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589439"},{"key":"ref17","article-title":"Provably Efficient Safe Exploration via Primal-Dual Policy Optimization","volume":"130","author":"ding","year":"2021","journal-title":"International Conference on Artificial Intelligence and Statistics (AIS-TATS)"},{"key":"ref16","article-title":"Responsive Safety in Rein-forcement Learning by PID Lagrangian Methods","author":"stooke","year":"2020","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5932"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06103-6"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196924"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982038"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460547"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794107"},{"key":"ref42","article-title":"Uncertainty-aware reinforcement learning for collision avoidance","author":"kahn","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811952"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2929996"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793611"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3177294"},{"key":"ref8","article-title":"Safe Ex-ploration for Reinforcement Learning","author":"hans","year":"2008","journal-title":"European Symposium on Artificial Neural Networks (ESANN)"},{"key":"ref7","article-title":"Safe Model-based Reinforcement Learning with Stability Guarantees","author":"berkenkamp","year":"2017","journal-title":"Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3761"},{"key":"ref4","author":"altman","year":"1999","journal-title":"Constrained Markov decision processes stochastic mod-eling Routledge"},{"key":"ref3","article-title":"Safe exploration for reinforcement learning in real unstructured environments","author":"pecka","year":"2015","journal-title":"Proc of the Computer Vision Winter Workshop"},{"key":"ref6","article-title":"Safe policy search for lifelong reinforcement learning with sublinear regret","author":"ammar","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref5","first-page":"1711","article-title":"Safe exploration in markov decision processes","author":"moldovan","year":"2012","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811698"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812238"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354295"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057055"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030133"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-090419-075625"},{"key":"ref30","first-page":"1357","article-title":"Robot reinforcement learning on the constraint manifold","author":"liu","year":"2022","journal-title":"Conference on Robot Learning"},{"key":"ref33","article-title":"Scalable safe exploration for global optimization of dynamical systems","author":"sukhija","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3063989"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981085"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN50785.2021.9515350"},{"key":"ref24","article-title":"A Lyapunov-based Approach to Safe Reinforcement Learning","author":"chow","year":"2018","journal-title":"Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref23","author":"berkenkamp","year":"2019","journal-title":"Safe exploration in reinforcement learning Theory and applications in robotics"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref25","article-title":"Lyapunov-based Safe Policy Optimization for Continuous Control","author":"chow","year":"2019","journal-title":"Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 36 th International Conference on Machine Learning"},{"key":"ref20","article-title":"Reward Constrained Policy Optimization","author":"tessler","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref22","article-title":"Saute rl: Almost surely safe reinforcement learning using state augmentation","author":"sootla","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref21","article-title":"Enhancing safe exploration using safety state augmentation","author":"sootla","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref28","first-page":"708","article-title":"Learning for safety-critical control with control barrier functions","author":"taylor","year":"2020","journal-title":"Learning for Dy-namics and Control"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref29","article-title":"Safe Exploration in Continuous Action Spaces","author":"dalal","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10161548.pdf?arnumber=10161548","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:34:05Z","timestamp":1690220045000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161548\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161548","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}