{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:05:33Z","timestamp":1781712333399,"version":"3.54.5"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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":"publisher","award":["62373242"],"award-info":[{"award-number":["62373242"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92248303"],"award-info":[{"award-number":["92248303"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/lra.2025.3625514","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T18:06:17Z","timestamp":1761588377000},"page":"13169-13176","source":"Crossref","is-referenced-by-count":2,"title":["Anticipate Before Act: Prediction Based Constrained Reinforcement Learning Framework for Skiing Robot Control"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9370-0785","authenticated-orcid":false,"given":"Haoyang","family":"Li","sequence":"first","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8844-7391","authenticated-orcid":false,"given":"Xuekang","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4902-9415","authenticated-orcid":false,"given":"Jialing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2961-2997","authenticated-orcid":false,"given":"Zhanxiang","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6659-0756","authenticated-orcid":false,"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8901-9335","authenticated-orcid":false,"given":"Yue","family":"Gao","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence and AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574708004955"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s12541-020-00344-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/s22030816"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abq0785"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s12283-009-0018-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888916000163"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/app8122643"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-6495-6_40"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610200"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1123\/jab.28.1.41"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1520\/JAI102829"},{"issue":"1","key":"ref12","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garca","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"issue":"167","key":"ref14","first-page":"1","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref15","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Achiam","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5932"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982038"},{"key":"ref18","article-title":"Agile but safe: Learning collision-free high-speed legged locomotion","author":"He","year":"2024","journal-title":"Robot.: Sci. Syst. (RSS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3284378"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5599"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/acc63710.2025.11107610"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s12283-021-00340-7"},{"key":"ref23","first-page":"822","article-title":"Learning guidance rewards with trajectory-space smoothing","volume-title":"Proc. Adv. Neural Inf. Process Syst","volume":"33","author":"Gangwani","year":"2020"},{"key":"ref24","article-title":"Learning self-imitating diverse policies","author":"Gangwani","year":"2018"},{"key":"ref25","first-page":"13566","article-title":"Rudder: Return decomposition for delayed rewards","volume-title":"Proc. Adv Neural Inf Process Syst","volume":"32","author":"Arjona-Medina","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161144"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3375086"},{"key":"ref28","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Proc. Conf. Robot Learn.","author":"Margolis","year":"2023"},{"key":"ref29","article-title":"Brax - a differentiable physics engine for large scale rigid body simulation","author":"Freeman","year":"2021"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11215960\/11217163.pdf?arnumber=11217163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T19:02:17Z","timestamp":1764010937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11217163\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":29,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3625514","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}