{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T06:15:38Z","timestamp":1778307338787,"version":"3.51.4"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62473213"],"award-info":[{"award-number":["62473213"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Sustainable Development Science and Technology Special Project of Shenzhen","award":["KCXFZ20230731100900002"],"award-info":[{"award-number":["KCXFZ20230731100900002"]}]},{"name":"Shenzhen Science and Technology Program","award":["KQTD20210811090143060"],"award-info":[{"award-number":["KQTD20210811090143060"]}]},{"name":"Beijing Tianjin Hebei Basic Research Cooperation Special Project","award":["24JCZXJC00060"],"award-info":[{"award-number":["24JCZXJC00060"]}]},{"name":"Hong Kong Research Grants Council General Research Fund","award":["PolyU-15235424"],"award-info":[{"award-number":["PolyU-15235424"]}]},{"name":"Research Institute for Artificial Intelligence of Things"},{"name":"Hong Kong Polytechnic University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/lra.2026.3685452","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T20:06:17Z","timestamp":1776715577000},"page":"7588-7595","source":"Crossref","is-referenced-by-count":0,"title":["Semantic-Aware Behavior Optimization With Safety Reinforcement Feedback for Language-Conditioned Manipulation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2642-9329","authenticated-orcid":false,"given":"Xiuxiu","family":"Qi","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2725-2529","authenticated-orcid":false,"given":"Jiannong","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9786-7257","authenticated-orcid":false,"given":"Julie A.","family":"McCann","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chongshan","family":"Fan","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4512-5494","authenticated-orcid":false,"given":"Hanqian","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4488-1375","authenticated-orcid":false,"given":"Hongpeng","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3265893"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abd9461"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2979656"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01716"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3468770"},{"key":"ref7","first-page":"4085","article-title":"A policy-guided imitation approach for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Xu","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3457538"},{"key":"ref9","first-page":"6002","article-title":"Feasibility consistent representation learning for safe reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cen","year":"2024"},{"key":"ref10","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127531"},{"key":"ref12","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Liang","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.055"},{"key":"ref15","first-page":"2914","article-title":"Toward the fundamental limits of imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Rajaraman","year":"2020"},{"key":"ref16","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Zitkovich","year":"2023"},{"key":"ref17","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Driess","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref19","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Proc. Conf. Robot Learn.","author":"Brohan","year":"2023"},{"key":"ref20","first-page":"15338","article-title":"First order constrained optimization in policy space","volume-title":"Proc. Adv Neural Inf. Process. Syst.","volume":"33","author":"Zhang","year":"2020"},{"key":"ref21","first-page":"9133","article-title":"Responsive safety in reinforcement learning by PID Lagrangian methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stooke","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965392"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref24","first-page":"1949","article-title":"3D diffuser actor: Policy diffusion with 3D scene representations","volume-title":"Proc. Conf. Robot Learn.","author":"Ke","year":"2024"},{"key":"ref25","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","first-page":"25636","article-title":"Reachability constrained reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu","year":"2022"},{"key":"ref28","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref31","first-page":"3949","article-title":"Act3D: 3D feature field transformers for multi-task robotic manipulation","volume-title":"Proc. Conf. Robot Learn. Proc. Mach. Learn. Res.","author":"Gervet","year":"2023"},{"key":"ref32","first-page":"991","article-title":"BC-Z: Zero-shot task generalization with robotic imitation learning","volume-title":"Proc. 5th Conf. Robot Learn.","author":"Jang","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref34","first-page":"2195","article-title":"Waypoint-based imitation learning for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shi","year":"2023"},{"key":"ref35","first-page":"284","article-title":"GNFactor: Multi-task real robot learning with generalizable neural feature fields","volume-title":"Proc. 5th Conf. Robot Learn.","author":"Ze","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0831"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11481819\/11487962.pdf?arnumber=11487962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T06:06:56Z","timestamp":1778306816000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11487962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":37,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3685452","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}