{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:40:12Z","timestamp":1735198812062,"version":"3.32.0"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802625","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"5168-5175","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion-PbD: Generalizable Robot Programming by Demonstration with Diffusion Features"],"prefix":"10.1109","author":[{"given":"Michael","family":"Murray","sequence":"first","affiliation":[{"name":"University of Washington,Paul G. Allen School of Computer Science & Engineering,Seattle,WA,USA,98195"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Entong","family":"Su","sequence":"additional","affiliation":[{"name":"University of Washington,Paul G. Allen School of Computer Science & Engineering,Seattle,WA,USA,98195"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maya","family":"Cakmak","sequence":"additional","affiliation":[{"name":"University of Washington,Paul G. Allen School of Computer Science & Engineering,Seattle,WA,USA,98195"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Survey: Robot programming by demonstration","volume-title":"Springrer, Tech. Rep.","author":"Billard","year":"2008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/00222890109601915"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/713755872"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/02640410600946860"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.tins.2021.01.007"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1049\/ccs2.12005"},{"article-title":"Viola: Imitation learning for vision-based manipulation with object proposal priors","volume-title":"6th Annual Conference on Robot Learning (CoRL)","author":"Zhu","key":"ref8"},{"article-title":"Learning generalizable manipulation policies with object-centric 3d representations","volume-title":"7th Annual Conference on Robot Learning","author":"Zhu","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1983.12681"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.2006703"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157815"},{"key":"ref13","first-page":"72","article-title":"Towards integrating learning by demonstration and learning by instruction in a multimodal robot","volume-title":"Proceedings of the IROS-2003 Workshop on Robot Learning by Demonstration","author":"Wermter"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139462"},{"key":"ref15","first-page":"13 139","article-title":"Language-conditioned imitation learning for robot manipulation tasks","volume":"33","author":"Stepputtis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968543"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.026"},{"key":"ref19","first-page":"3536","article-title":"Xskill: Cross embodiment skill discovery","volume-title":"Conference on Robot Learning","author":"Xu"},{"article-title":"Roboclip: one demonstration is enough to learn robot policies","year":"2023","author":"Sontakke","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2007.4415177"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v2i1.13164"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.048"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2017.8172448"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.002"},{"key":"ref26","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref27","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref28","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"article-title":"Imagen video: High definition video generation with diffusion models","year":"2022","author":"Ho","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref33","first-page":"2905","article-title":"Generative skill chaining: Long-horizon skill planning with diffusion models","volume-title":"Conference on Robot Learning","author":"Mishra"},{"article-title":"Octo: An open-source generalist robot policy","year":"2023","author":"Ghosh","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610665"},{"article-title":"Planning as in-painting: A diffusion-based embodied task plan ning framework for environments under uncertainty","year":"2023","author":"Yang","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.014"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3330663"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.027"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.010"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611277"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611293"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3272516"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610792"},{"article-title":"Emergent correspondence from image diffusion","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Tang","key":"ref45"},{"key":"ref46","article-title":"Diffusion hyperfeatures: Searching through time and space for semantic correspondence","author":"Luo","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"What does stable diffusion know about the 3d scene?","year":"2023","author":"Zhan","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref50","article-title":"Mediapipe: A framework for perceiving and processing reality","volume-title":"Third workshop on computer vision for AR\/VR at IEEE computer vision and pattern recognition (CVPR)","volume":"2019","author":"Lugaresi"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.494"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160765"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811922"},{"key":"ref55","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"article-title":"Dinov2: Learning robust visual features without supervision","year":"2023","author":"Oquab","key":"ref56"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802625.pdf?arnumber=10802625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:01:43Z","timestamp":1735196503000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802625\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802625","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}