{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T15:25:44Z","timestamp":1773329144261,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Impact Fund of the Hong Kong (HK) Research Grants Council","award":["R5017-18F"],"award-info":[{"award-number":["R5017-18F"]}]},{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Intra-Faculty Interdisciplinary Project under Grant ZVVR"},{"name":"PolyU under Grant G-UANS"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2024.3378915","type":"journal-article","created":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T19:44:56Z","timestamp":1711395896000},"page":"2349-2360","source":"Crossref","is-referenced-by-count":9,"title":["Safe Learning by Constraint-Aware Policy Optimization for Robotic Ultrasound Imaging"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9666-018X","authenticated-orcid":false,"given":"Anqing","family":"Duan","sequence":"first","affiliation":[{"name":"Faculty of Engineering, The Hong Kong Polytechnic University (PolyU), Hung Hom, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5255-5559","authenticated-orcid":false,"given":"Chenguang","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Liverpool, Liverpool, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1222-6651","authenticated-orcid":false,"given":"Jingyuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7652-8958","authenticated-orcid":false,"given":"Shengzeng","family":"Huo","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, The Hong Kong Polytechnic University (PolyU), Hung Hom, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7020-0943","authenticated-orcid":false,"given":"Peng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6535-0998","authenticated-orcid":false,"given":"Wanyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, The Hong Kong Polytechnic University (PolyU), Hung Hom, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3407-9226","authenticated-orcid":false,"given":"Yongping","family":"Zheng","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Research Institute for Smart Ageing, The Hong Kong Polytechnic University (PolyU), Hung Hom, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3426-6638","authenticated-orcid":false,"given":"David","family":"Navarro-Alarcon","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Research Institute for Smart Ageing, The Hong Kong Polytechnic University (PolyU), Hung Hom, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/technologies9010008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3109596"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.748246"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tmech.2024.3363699"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1049\/ccs.2020.0015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1186\/s13013-016-0074-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3186504"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3195069"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3025380"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3009069"},{"key":"ref11","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. ICML","author":"Schulman"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2023.3246089"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO54168.2021.9739464"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3131261"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3036215"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3189339"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3166204"},{"issue":"1","key":"ref18","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garcia","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref20","first-page":"1","article-title":"A Lyapunov-based approach to safe reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chow"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636468"},{"key":"ref22","first-page":"845","article-title":"Fast policy learning through imitation and reinforcement","volume-title":"Proc. 34th Conf. Uncertainty Artif. Intell.","author":"Cheng"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2018.8624934"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2021.3057022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3217468"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/app9091900"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref28","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kakade"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(67)90040-7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7727"},{"key":"ref33","first-page":"1","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Ho"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231204656"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3192049"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-0427(00)00433-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920985879"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3096966"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3390\/s21082858"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2012.07.005"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2390233"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2923241"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3218806"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8856\/10839176\/10478841.pdf?arnumber=10478841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T05:42:59Z","timestamp":1738820579000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10478841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3378915","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}