{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T06:32:33Z","timestamp":1723271553511},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Samsung Research Funding & Incubation Center for Future Technology at Samsung Electronics","award":["SRFC-IT2002-02"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tro.2024.3400935","type":"journal-article","created":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T17:41:36Z","timestamp":1715708496000},"page":"2984-3003","source":"Crossref","is-referenced-by-count":2,"title":["Not Only Rewards but Also Constraints: Applications on Legged Robot Locomotion"],"prefix":"10.1109","volume":"40","author":[{"ORCID":"http:\/\/orcid.org\/0009-0001-4985-8118","authenticated-orcid":false,"given":"Yunho","family":"Kim","sequence":"first","affiliation":[{"name":"Robotics and Artificial Intelligence Lab, KAIST, Daejeon, South Korea"}]},{"ORCID":"http:\/\/orcid.org\/0009-0009-8907-3671","authenticated-orcid":false,"given":"Hyunsik","family":"Oh","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Lab, KAIST, Daejeon, South Korea"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-6598-2875","authenticated-orcid":false,"given":"Jeonghyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Lab, KAIST, Daejeon, South Korea"}]},{"ORCID":"http:\/\/orcid.org\/0009-0005-9489-0060","authenticated-orcid":false,"given":"Jinhyeok","family":"Choi","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Lab, KAIST, Daejeon, South Korea"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-6478-6426","authenticated-orcid":false,"given":"Gwanghyeon","family":"Ji","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Lab, KAIST, Daejeon, South Korea"}]},{"ORCID":"http:\/\/orcid.org\/0009-0003-7983-818X","authenticated-orcid":false,"given":"Moonkyu","family":"Jung","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Lab, KAIST, Daejeon, South Korea"}]},{"ORCID":"http:\/\/orcid.org\/0009-0003-8735-9373","authenticated-orcid":false,"given":"Donghoon","family":"Youm","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Lab, KAIST, Daejeon, South Korea"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-3444-8079","authenticated-orcid":false,"given":"Jemin","family":"Hwangbo","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Lab, KAIST, Daejeon, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.056"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3151396"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.ade2256"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2979656"},{"key":"ref11","article-title":"Evaluation of constrained reinforcement learning algorithms for legged locomotion","author":"Lee","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"ref13","first-page":"1101","article-title":"Deep dynamics models for learning dexterous manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Nagabandi","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.069"},{"key":"ref15","article-title":"Emergence of locomotion behaviours in rich environments","author":"Heess","year":"2017"},{"key":"ref16","first-page":"138","article-title":"Deep whole-body control: Learning a unified policy for manipulation and locomotion","volume-title":"Proc. Conf. Robot Learn.","author":"Fu","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2794620"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594448"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3186804"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3275384"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref22","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Rudin","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.011"},{"key":"ref25","first-page":"403","article-title":"Legged locomotion in challenging terrains using egocentric vision","volume-title":"Proc. Conf. Robot Learn.","author":"Agarwal","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3136645"},{"key":"ref28","article-title":"Learning multiple gaits of quadruped robot using hierarchical reinforcement learning","author":"Kim","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi9579"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161470"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981973"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3290509"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160562"},{"key":"ref35","first-page":"1893","article-title":"GenLoco: Generalized locomotion controllers for quadrupedal robots","volume-title":"Proc. Conf. Robot Learn.","author":"Feng","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"issue":"1","key":"ref37","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":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982038"},{"key":"ref39","article-title":"Conservative safety critics for exploration","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bharadhwaj","year":"2020"},{"issue":"1","key":"ref40","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref41","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tessler","year":"2018"},{"key":"ref42","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5932"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"key":"ref45","first-page":"11480","article-title":"CRPO: A new approach for safe reinforcement learning with convergence guarantee","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2021"},{"key":"ref46","article-title":"Projection-based constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2019"},{"key":"ref47","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"Ray","year":"2019"},{"key":"ref48","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref49","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref50","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14115"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201397"},{"key":"ref53","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013"},{"key":"ref54","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. Workshop Deep Learn.","author":"Chung","year":"2014"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2792536"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793865"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811755"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758092"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8860\/10365208\/10530429.pdf?arnumber=10530429","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T18:51:29Z","timestamp":1719600689000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10530429\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tro.2024.3400935","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}