{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:49:37Z","timestamp":1773154177008,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246933","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"15888-15894","source":"Crossref","is-referenced-by-count":1,"title":["Preference Aligned Diffusion Planner for Quadrupedal Locomotion Control"],"prefix":"10.1109","author":[{"given":"Xinyi","family":"Yuan","sequence":"first","affiliation":[{"name":"Osaka University,Graduate School of Engineering Science,Japan"}]},{"given":"Zhiwei","family":"Shang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou),Robotics and Autonomous Systems Thrust,China"}]},{"given":"Zifan","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou),Robotics and Autonomous Systems Thrust,China"}]},{"given":"Chenkai","family":"Wang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology,Department of Statistics and Data Science,China"}]},{"given":"Zhao","family":"Shan","sequence":"additional","affiliation":[{"name":"China Telecom,Institute of Artificial Intelligence (TeleAI),China"}]},{"given":"Meixin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Southeast University,School of Transportation,China"}]},{"given":"Chenjia","family":"Bai","sequence":"additional","affiliation":[{"name":"China Telecom,Institute of Artificial Intelligence (TeleAI),China"}]},{"given":"Weiwei","family":"Wan","sequence":"additional","affiliation":[{"name":"Osaka University,Graduate School of Engineering Science,Japan"}]},{"given":"Kensuke","family":"Harada","sequence":"additional","affiliation":[{"name":"Osaka University,Graduate School of Engineering Science,Japan"}]},{"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"China Telecom,Institute of Artificial Intelligence (TeleAI),China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Robot parkour learning","author":"Zhuang","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197312"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981973"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.011"},{"key":"ref6","first-page":"14810","article-title":"Data-efficient pipeline for offline reinforcement learning with limited data","volume":"35","author":"Nie","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref8","article-title":"Diffusion models for reinforcement learning: A survey","author":"Zhu","year":"2023"},{"key":"ref9","article-title":"Diffuseloco: Real-time legged locomotion control with diffusion from offline datasets","author":"Huang","year":"2024"},{"key":"ref10","article-title":"Mitigating covariate shift in imitation learning via offline data with partial coverage","volume-title":"Advances in Neural Information Processing Systems","author":"Chang","year":"2021"},{"key":"ref11","first-page":"70247","article-title":"Direct preference-based policy optimization without reward modeling","volume":"36","author":"An","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi9641"},{"key":"ref14","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Conference on Robot Learning","author":"Margolis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925881"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610137"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref18","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Rudin"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00861-3"},{"key":"ref21","article-title":"Offline reinforcement learning: Tutorial, review","volume":"5","author":"Levine","year":"2020","journal-title":"and Perspectives on Open Problems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610749"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3382529"},{"key":"ref26","article-title":"Is conditional generative modeling all you need for decisionmaking?","author":"Ajay","year":"2022"},{"key":"ref27","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022"},{"key":"ref28","article-title":"Imitating human behaviour with diffusion models","author":"Pearce","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref30","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref32","article-title":"Seabo: A simple search-based method for offline imitation learning","author":"Lyu","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i13.33576"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2757"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246933.pdf?arnumber=11246933","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:37:26Z","timestamp":1766061446000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246933\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246933","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}