{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:47:37Z","timestamp":1777502857118,"version":"3.51.4"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127225","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"5482-5488","source":"Crossref","is-referenced-by-count":5,"title":["Certificated Actor-Critic: Hierarchical Reinforcement Learning with Control Barrier Functions for Safe Navigation"],"prefix":"10.1109","author":[{"given":"Junjun","family":"Xie","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering and Automation, Harbin Institute of Technology,Department of Automation,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhao","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering and Automation, Harbin Institute of Technology,Department of Automation,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering and Automation, Harbin Institute of Technology,Department of Automation,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huijun","family":"Gao","sequence":"additional","affiliation":[{"name":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3047728"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3100142"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160671"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610210"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3152313"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811772"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340823"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341626"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2017.xiii.073"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/AIM52237.2022.9863392"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160857"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3322088"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160991"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA55696.2022.00045"},{"key":"ref15","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning.","author":"Achiam","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3216996"},{"key":"ref18","first-page":"708","article-title":"Learning for safetycritical control with control barrier functions","author":"Taylor","year":"2020","journal-title":"Learning for Dynamics and Control. PMLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5132"},{"key":"ref20","article-title":"Barrier functions inspired reward shaping for reinforcement learning","author":"Ranjan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","volume-title":"Reinforcement learning: An introduction.","author":"Sutton","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040372"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483029"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426229"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2299335"},{"key":"ref28","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning.","author":"Haarnoja","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref30","volume-title":"Gymnasium","author":"Towers","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812353"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127225.pdf?arnumber=11127225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:48:46Z","timestamp":1756882126000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127225\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127225","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}