{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T05:47:49Z","timestamp":1771048069650,"version":"3.50.1"},"reference-count":53,"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":[{"DOI":"10.13039\/501100019356","name":"Guangxi Power Grid Company\u2019s 2023 Science and Technology Innovation Project","doi-asserted-by":"publisher","award":["GXKJXM20230169"],"award-info":[{"award-number":["GXKJXM20230169"]}],"id":[{"id":"10.13039\/501100019356","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","award":["2025JH6\/101000028"],"award-info":[{"award-number":["2025JH6\/101000028"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3620908","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T17:42:50Z","timestamp":1760463770000},"page":"23352-23365","source":"Crossref","is-referenced-by-count":1,"title":["Residual Policy Optimization With Trust Region Constraints: A Learning Framework for Stable and Agile Wheel-Legged Locomotion"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3646-1899","authenticated-orcid":false,"given":"Naifeng","family":"He","sequence":"first","affiliation":[{"name":"College of Automation, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}]},{"given":"Zhong","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Automation, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6577-8632","authenticated-orcid":false,"given":"Xiaoliang","family":"Fan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"}]},{"given":"Wenqiang","family":"Que","sequence":"additional","affiliation":[{"name":"College of Automation, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}]},{"given":"Siyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"given":"Hongyu","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Automation, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3880-1175","authenticated-orcid":false,"given":"Chunguang","family":"Bu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8001-002X","authenticated-orcid":false,"given":"Bi","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi9641"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.060"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3345876"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/rob.22450"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3503277"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981091"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/02783649221102473"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3504132"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2014.2305792"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3071530"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3275384"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3412111"},{"key":"ref14","first-page":"2594","article-title":"Curiosity-driven learning of joint locomotion and manipulation tasks","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Schwarke"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160751"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15226-9_14"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802062"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610200"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801648"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161144"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801909"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3455788"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-021-05811-4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3326334"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610069"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128166"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adh5401"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3185055"},{"key":"ref33","article-title":"SATA: Safe and adaptive torque-based locomotion policies inspired by animal learning","author":"Li","year":"2025","journal-title":"arXiv:2502.12674"},{"key":"ref34","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinto"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610528"},{"key":"ref36","first-page":"66328","article-title":"Seeing is not believing: Robust reinforcement learning against spurious correlation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref37","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"33","author":"Zhang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29139"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2024.104799"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi8022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.059"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982038"},{"key":"ref45","first-page":"8378","article-title":"Natural policy gradient primal-dual method for constrained Markov decision processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ding"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3400935"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20737"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3572427"},{"key":"ref49","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3522773"},{"key":"ref52","first-page":"1","article-title":"SoloParkour: Constrained reinforcement learning for visual locomotion from privileged experience","volume-title":"Proc. Conf. Robot Learn.","author":"Chane-Sane"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802334"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/11202537.pdf?arnumber=11202537","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:51:38Z","timestamp":1762800698000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11202537\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3620908","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}