{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T04:52:07Z","timestamp":1761367927938,"version":"build-2065373602"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,30]]},"DOI":"10.1109\/humanoids65713.2025.11203112","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:50Z","timestamp":1761326150000},"page":"736-743","source":"Crossref","is-referenced-by-count":0,"title":["Bipedalism for Quadrupedal Robots: Versatile Loco-Manipulation Through Risk-Adaptive Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yuyou","family":"Zhang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Department of Mechanical Engineering,Pittsburgh,PA,USA,15213"}]},{"given":"Radu","family":"Corcodel","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Labs (MERL),Cambridge,MA,USA,02139"}]},{"given":"Ding","family":"Zhao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Department of Mechanical Engineering,Pittsburgh,PA,USA,15213"}]}],"member":"263","reference":[{"key":"ref1","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning. PMLR","author":"Rudin","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"key":"ref4","article-title":"Hybrid internal model: Learning agile legged locomotion with simulated robot response","volume-title":"The Twelfth International Conference on Learning Representations","author":"Long","year":"2024"},{"key":"ref5","article-title":"Soloparkour: Constrained reinforcement learning for visual locomotion from privileged experience","volume-title":"8th Annual Conference on Robot Learning","author":"Chane-Sane","year":"2024"},{"key":"ref6","article-title":"SLR: Learning quadruped locomotion without privileged information","volume-title":"8th Annual Conference on Robot Learning","author":"Chen","year":"2024"},{"key":"ref7","article-title":"Learning h-infinity locomotion control","volume-title":"8th Annual Conference on Robot Learning","author":"Long","year":"2024"},{"key":"ref8","article-title":"Gaitor: Learning a unified representation across gaits for real-world quadruped locomotion","volume-title":"8th Annual Conference on Robot Learning","author":"Mitchell","year":"2024"},{"key":"ref9","article-title":"TOP-nav: Legged navigation integrating terrain, obstacle and proprioception estimation","volume-title":"8th Annual Conference on Robot Learning","author":"Ren","year":"2024"},{"key":"ref10","article-title":"Robotkeyframing: Learning locomotion with high-level objectives via mixture of dense and sparse rewards","volume-title":"8th Annual Conference on Robot Learning","author":"Zargarbashi","year":"2024"},{"key":"ref11","article-title":"Generalized animal imitator: Agile locomotion with versatile motion prior","volume-title":"8 th Annual Conference on Robot Learning","author":"Yang","year":"2024"},{"key":"ref12","article-title":"UMI-on-legs: Making manipulation policies mobile with a manipulation-centric whole-body controller","volume-title":"8th Annual Conference on Robot Learning","author":"Ha","year":"2024"},{"key":"ref13","article-title":"Guided reinforcement learning for robust multi-contact loco-manipulation","volume-title":"8th Annual Conference on Robot Learning","author":"Sleiman","year":"2024"},{"key":"ref14","article-title":"Continuously improving mobile manipulation with autonomous real-world RL","volume-title":"8th Annual Conference on Robot Learning","author":"Mendonca","year":"2024"},{"key":"ref15","article-title":"Learning to open and traverse doors with a legged manipulator","volume-title":"8 th Annual Conference on Robot Learning","author":"Zhang","year":"2024"},{"key":"ref16","article-title":"A versatile planner for learning dexterous and whole-body manipulation","volume-title":"8 th Annual Conference on Robot Learning","author":"Bruedigam","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981984"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160325"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161392"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341936"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adg5014"},{"key":"ref22","first-page":"138","article-title":"Deep whole-body control: learning a unified policy for manipulation and locomotion","volume-title":"Conference on Robot Learning. PMLR","author":"Fu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801980"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1006\/jhev.1994.1011"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.04.021"},{"key":"ref26","article-title":"Risk-aware robotics: Tail risk measures in planning, control, and verification","author":"Akella","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Efficient exploration via epistemic-risk-seeking policy optimization","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"O\u2019Donoghue","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794273"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068908"},{"key":"ref31","article-title":"Visual whole-body control for legged loco-manipulation","volume-title":"8th Annual Conference on Robot Learning","author":"Liu","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3336109"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611066"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143567"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610125"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802742"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802517"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611307"},{"key":"ref39","article-title":"Visual manipulation with legs","volume-title":"8th Annual Conference on Robot Learning","author":"He","year":"2024"},{"key":"ref40","article-title":"Longhorizon locomotion and manipulation on a quadrupedal robot with large language models","author":"Ouyang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161470"},{"key":"ref42","article-title":"Learning agile bipedal motions on a quadrupedal robot","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802439"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160324"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610137"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3349934"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610086"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3125047"},{"key":"ref49","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"International conference on machine learning. PMLR","author":"Bellemare","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref51","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"International conference on machine learning. PMLR","author":"Dabney","year":"2018"},{"key":"ref52","first-page":"32639","article-title":"Efficient risk-averse reinforcement learning","volume":"35","author":"Greenberg","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref53","article-title":"Estimating risk and uncertainty in deep reinforcement learning","author":"Clements","year":"2019","journal-title":"arXiv preprint"},{"key":"ref54","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Conference on Robot Learning. PMLR","author":"Margolis","year":"2023"},{"key":"ref55","article-title":"Highdimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.2307\/253675"},{"key":"ref57","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)","start":{"date-parts":[[2025,9,30]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2025,10,2]]}},"container-title":["2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11202977\/11203009\/11203112.pdf?arnumber=11203112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T04:46:32Z","timestamp":1761367592000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11203112\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/humanoids65713.2025.11203112","relation":{},"subject":[],"published":{"date-parts":[[2025,9,30]]}}}