{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:48:55Z","timestamp":1777567735461,"version":"3.51.4"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611125","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"6973-6980","source":"Crossref","is-referenced-by-count":9,"title":["Universal Visual Decomposer: Long-Horizon Manipulation Made Easy"],"prefix":"10.1109","author":[{"given":"Zichen","family":"Zhang","sequence":"first","affiliation":[{"name":"Allen Institute for AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunshuang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Osbert","family":"Bastani","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhishek","family":"Gupta","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinesh","family":"Jayaraman","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yecheng Jason","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Weihs","sequence":"additional","affiliation":[{"name":"Allen Institute for AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref2","article-title":"Option discovery using deep skill chaining","volume-title":"International Conference on Learning Representations","author":"Bagaria"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811889"},{"key":"ref4","first-page":"1430","article-title":"Goal-conditioned reinforcement learning with imagined subgoals","volume-title":"International Conference on Machine Learning","author":"Chane-Sane"},{"key":"ref5","first-page":"1009","article-title":"Self-consistent trajectory autoencoder: Hierarchical reinforcement learning with trajectory embeddings","volume-title":"International conference on machine learning","author":"Co-Reyes"},{"key":"ref6","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Damen"},{"key":"ref7","first-page":"3161","article-title":"Robothor: An open simulation-to-real embodied AI platform","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Deitke"},{"key":"ref8","article-title":"Goal-conditioned imitation learning","volume":"32","author":"Ding","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","volume":"32","author":"Eysenbach","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981999"},{"key":"ref11","first-page":"106","article-title":"Generalization with lossy affordances: Leveraging broad offline data for learning visuomotor tasks","volume-title":"Conference on Robot Learning","author":"Fang"},{"key":"ref12","article-title":"Learning to reach goals via iterated supervised learning","author":"Ghosh","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref14","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","author":"Gupta","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.041"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00876"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140817"},{"key":"ref18","article-title":"Time-agnostic prediction: Predicting predictable video frames","author":"Jayaraman","year":"2019","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01441"},{"key":"ref20","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560986"},{"key":"ref22","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Conference on robot learning","author":"Lynch"},{"key":"ref23","article-title":"Liv: Language-image representations and rewards for robotic control","author":"Ma","year":"2023"},{"key":"ref24","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022"},{"key":"ref25","article-title":"Where are we in the search for an artificial visual cortex for embodied intelligence?","author":"Majumdar","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.061"},{"key":"ref27","article-title":"Near-optimal representation learning for hierarchical reinforcement learning","author":"Nachum","year":"2018"},{"key":"ref28","article-title":"Data-efficient hierarchical reinforcement learning","volume":"31","author":"Nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"Hierarchical foresight: Self-supervised learning of long-horizon tasks via visual subgoal generation","author":"Nair","year":"2019"},{"key":"ref30","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref31","article-title":"Planning with goal-conditioned policies","volume":"32","author":"Nasiriany","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref33","article-title":"The unsurprising effectiveness of pre-trained vision models for control","author":"Parisi","year":"2022"},{"key":"ref34","first-page":"17321","article-title":"Long-horizon visual planning with goal-conditioned hierarchical predictors","volume":"33","author":"Pertsch","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref36","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref37","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref39","article-title":"Waypoint-based imitation learning for robotic manipulation","author":"Shi","year":"2023"},{"key":"ref40","first-page":"4654","article-title":"Taco: Learning task decomposition via temporal alignment for control","volume-title":"International Conference on Machine Learning","author":"Shiarlis"},{"key":"ref41","first-page":"785","article-title":"Perceiver-actor: A multitask transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref43","first-page":"5922","article-title":"Visual room rearrangement","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021","author":"Weihs"},{"key":"ref44","article-title":"DD-PPO: learning near-perfect pointgoal navigators from 2.5 billion frames","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Wijmans"},{"key":"ref45","article-title":"Masked visual pretraining for motor control","author":"Xiao","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460689"},{"key":"ref47","first-page":"12611","article-title":"World model as a graph: Learning latent landmarks for planning","volume-title":"International Conference on Machine Learning","author":"Zhang"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611125.pdf?arnumber=10611125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:14:38Z","timestamp":1723349678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611125\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611125","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}