{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T00:54:24Z","timestamp":1772931264616,"version":"3.50.1"},"reference-count":65,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B6002"],"award-info":[{"award-number":["U21B6002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Scientific and Technological Innovation 2030 of China","doi-asserted-by":"publisher","award":["2021ZD0110900"],"award-info":[{"award-number":["2021ZD0110900"]}],"id":[{"id":"10.13039\/501100001809","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.2025.3578326","type":"journal-article","created":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T17:55:46Z","timestamp":1749578146000},"page":"16572-16590","source":"Crossref","is-referenced-by-count":3,"title":["Confidence-Aware Robust Dynamical Distance Constrained Reinforcement Learning for Social Robot Navigation"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1272-4295","authenticated-orcid":false,"given":"Kai","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7499-6160","authenticated-orcid":false,"given":"Tao","family":"Xue","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2980-6281","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3583741"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630866"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5654369"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2021.9010012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341519"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3222989"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340705"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561595"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160660"},{"issue":"1","key":"ref17","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u0131a","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/614"},{"key":"ref20","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"Ray","year":"2019","journal-title":"arXiv:1910.01708"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.113.238701"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3071954"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3387010"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3161699"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3346049"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3257549"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636102"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00868"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01240"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3138547"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3144501"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811776"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561843"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919859436"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"issue":"167","key":"ref36","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":"ref37","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref38","first-page":"1","article-title":"Projection-based constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref39","first-page":"11795","article-title":"Accelerating safe reinforcement learning with constraint-mismatched baseline policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/763"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref42","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018","journal-title":"arXiv:1801.08757"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-104941"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8263977"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794107"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.077"},{"key":"ref48","first-page":"25636","article-title":"Reachability constrained reinforcement learning","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Yu"},{"key":"ref49","first-page":"38561","article-title":"Iterative reachability estimation for safe reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ganai"},{"key":"ref50","article-title":"Uncertainty-aware reinforcement learning for collision avoidance","author":"Kahn","year":"2017","journal-title":"arXiv:1702.01182"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793611"},{"key":"ref52","first-page":"7193","article-title":"Online robust reinforcement learning with model uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref53","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinto"},{"key":"ref54","first-page":"10571","article-title":"Robust multi-agent reinforcement learning with model uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhang"},{"key":"ref55","first-page":"1","article-title":"Robust multi-agent reinforcement learning with state uncertainty","volume":"21","author":"He","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref56","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1190"},{"key":"ref58","first-page":"11085","article-title":"Dynamical distance learning for semi-supervised and unsupervised skill discovery","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hartikainen"},{"key":"ref59","first-page":"11003","article-title":"Towards better Laplacian representation in reinforcement learning with generalized graph drawing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref60","first-page":"36670","article-title":"Reachability-aware Laplacian representation in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561672"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636139"},{"key":"ref63","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341689"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05732-2"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/11029302.pdf?arnumber=11029302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:29:47Z","timestamp":1750746587000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11029302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3578326","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}