{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:48:47Z","timestamp":1773193727177,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"European Union’s Horizon Europe Framework Programme","award":["101070596"],"award-info":[{"award-number":["101070596"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/lra.2026.3665075","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:08:52Z","timestamp":1771276132000},"page":"4985-4992","source":"Crossref","is-referenced-by-count":0,"title":["Preference Aligned Visuomotor Diffusion Policies for Deformable Object Manipulation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5700-684X","authenticated-orcid":false,"given":"Marco","family":"Moletta","sequence":"first","affiliation":[{"name":"Robotics, Perception and Learning Lab, EECS, KTH Royal Institute of Technology, Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3827-3824","authenticated-orcid":false,"given":"Michael C.","family":"Welle","sequence":"additional","affiliation":[{"name":"Robotics, Perception and Learning Lab, EECS, KTH Royal Institute of Technology, Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2965-2953","authenticated-orcid":false,"given":"Danica","family":"Kragic","sequence":"additional","affiliation":[{"name":"Robotics, Perception and Learning Lab, EECS, KTH Royal Institute of Technology, Stockholm, Sweden"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9737-2"},{"key":"ref2","first-page":"420","article-title":"Preference learning in assistive robotics: Observational repeated inverse reinforcement learning","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Woodworth","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2022.3147415"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-022723-033252"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5821\/dissertation-2117-330728"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375184"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.447"},{"key":"ref10","first-page":"53728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Rafailov","year":"2023"},{"key":"ref11","article-title":"Diffusion-RPO: Aligning diffusion models through relative preference optimization","author":"Gu","year":"2024"},{"key":"ref12","first-page":"24897","article-title":"Aligning diffusion models by optimizing human utility","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Li","year":"2024"},{"key":"ref13","article-title":"Adapting to variations in textile properties for robotic manipulation","author":"Longhini","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN60168.2024.10731242"},{"key":"ref16","article-title":"Imitating task and motion planning with visuomotor transformers","author":"Dalal","year":"2023"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3272516"},{"key":"ref20","first-page":"2905","article-title":"Generative skill chaining: Long-horizon skill planning with diffusion models","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Mishra","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.028"},{"key":"ref22","article-title":"Imitating human behaviour with diffusion models","author":"Pearce","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14125-6_4"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.053"},{"issue":"136","key":"ref25","first-page":"1","article-title":"A survey of preference-based reinforcement learning methods","volume":"18","author":"Wirth","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23780-5_30"},{"key":"ref27","first-page":"1142","article-title":"A Bayesian approach for policy learning from trajectory preference queries","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2012","author":"Wilson"},{"key":"ref28","article-title":"Relative preference optimization: Enhancing LLM alignment through contrasting responses across identical and diverse prompts","author":"Yin","year":"2024"},{"key":"ref29","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.17541"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801806"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206206"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094735"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915581193"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11246933"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127926"},{"key":"ref38","article-title":"The crucial role of samplers in online direct preference optimization","author":"Shi","year":"2024"},{"key":"ref39","article-title":"Real-time operator takeover for visuomotor diffusion policy training","author":"Ingelhag","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abd8803"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965891"},{"key":"ref42","article-title":"Quest2ROS: An app to facilitate teleoperating robots","volume-title":"Proc. 7th Int. Workshop Virtual, Augmented, Mixed-Reality Hum.-Robot Interact.","author":"Welle","year":"2024"},{"key":"ref43","article-title":"Robot learning as an empirical science: Best practices for policy evaluation","author":"Kress-Gazit","year":"2024"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11400564\/11397166.pdf?arnumber=11397166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:22:42Z","timestamp":1773120162000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":43,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3665075","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}