{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:14:06Z","timestamp":1740100446615,"version":"3.37.3"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"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"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636362","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"7135-7142","source":"Crossref","is-referenced-by-count":1,"title":["DMotion: Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos"],"prefix":"10.1109","author":[{"given":"Haoqi","family":"Yuan","sequence":"first","affiliation":[]},{"given":"Ruihai","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Andrew","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Haipeng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zihan","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Dong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Relational neural expectation maximization: Unsupervised discovery of objects and their interactions","author":"van steenkiste","year":"2018","journal-title":"ICLRE"},{"article-title":"Monet: Unsupervised scene decomposition and representation","year":"2019","author":"burgess","key":"ref38"},{"key":"ref33","first-page":"6033","article-title":"Hierarchical long-term video prediction without supervision","author":"wichers","year":"2018","journal-title":"ICML"},{"article-title":"Stochastic adversarial video prediction","year":"2018","author":"lee","key":"ref32"},{"article-title":"Affordance learning for end-to-end visuomotor robot control","year":"2019","author":"h\u00e4m\u00e4l\u00e4inen","key":"ref31"},{"key":"ref30","first-page":"4739","article-title":"Universal planning networks: Learning generalizable representations for visuomotor control","author":"srinivas","year":"2018","journal-title":"ICML"},{"key":"ref37","article-title":"Learning to decompose and disentangle representations for video prediction","author":"hsieh","year":"2018","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.319"},{"key":"ref35","article-title":"Decomposing motion and content for natural video sequence prediction","author":"villegas","year":"2017","journal-title":"ICLRE"},{"key":"ref34","article-title":"Unsupervised learning of disentangled representations from video","author":"denton","year":"2017","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"article-title":"Learning a visuomotor controller for real world robotic grasping using simulated depth images","year":"2017","author":"viereck","key":"ref27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.020"},{"key":"ref2","article-title":"Unsupervised discovery of parts, structure, and dynamics","author":"xu","year":"2019","journal-title":"ICLRE"},{"key":"ref1","article-title":"Contrastive learning of structured world models","author":"kipf","year":"2019","journal-title":"ICLRE"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594448"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794006"},{"article-title":"Object-centric forward modeling for model predictive control","year":"2019","author":"ye","key":"ref21"},{"key":"ref24","article-title":"Self-supervised visual planning with temporal skip connections","author":"ebert","year":"2017","journal-title":"CoRL"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594519"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"article-title":"Learning what you can do before doing anything","year":"2018","author":"rybkin","key":"ref50"},{"key":"ref10","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"2016","journal-title":"NeurIPS"},{"key":"ref11","article-title":"Experience-embedded visual foresight","author":"yen-chen","year":"2019","journal-title":"CoRL"},{"key":"ref40","first-page":"6691","article-title":"Neural expectation maximization","author":"greff","year":"2017","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Internal physics models guide probabilistic judgments about object dynamics","volume":"2","author":"hamrick","year":"2011","journal-title":"Proceedings of the 33rd Annual Conference of the Cognitive Science Society"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1111\/j.0963-7214.2004.00281.x"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-7687.2007.00569.x"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2017.08.036"},{"key":"ref16","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"NeurIPS"},{"article-title":"Model predictive control theory and design","year":"1999","author":"mayne","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.128"},{"key":"ref19","article-title":"Decentralized reflective model predictive control of multiple flying robots in dynamic environment","author":"us","year":"2003","journal-title":"Proc 42nd IEEE Conf Decis Control"},{"key":"ref4","first-page":"700","article-title":"Unsupervised intuitive physics from visual observations","author":"ehrhardt","year":"2018","journal-title":"ACCV"},{"key":"ref3","first-page":"153","article-title":"Learning to see physics via visual de-animation","author":"wu","year":"2017","journal-title":"NeurIPS"},{"key":"ref6","article-title":"Reasoning about physical interactions with object-centric models","author":"janner","year":"2019","journal-title":"ICLRE"},{"key":"ref5","article-title":"Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks","author":"xue","year":"2016","journal-title":"NeurIPS"},{"key":"ref8","article-title":"Entity abstraction in visual modelbased reinforcement learning","author":"veerapaneni","year":"2019","journal-title":"CoRL"},{"article-title":"Cobra: Data-efficient model-based RL through unsupervised object discovery and curiosity-driven exploration","year":"2019","author":"watters","key":"ref7"},{"key":"ref49","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"ICLRE"},{"article-title":"Efficient model-based deep reinforcement learning with variational state tabulation","year":"2018","author":"corneil","key":"ref9"},{"key":"ref46","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010091220143"},{"key":"ref48","article-title":"World models","author":"ha","year":"2018","journal-title":"CoRR"},{"article-title":"Pyrep: Bringing v-rep to deep robot learning","year":"2019","author":"james","key":"ref47"},{"key":"ref42","first-page":"2424","article-title":"Multi-object representation learning with iterative variational inference","author":"greff","year":"2019","journal-title":"ICML"},{"key":"ref41","article-title":"The multi-entity variational autoencoder","author":"nash","year":"2017","journal-title":"NIPS Workshop"},{"key":"ref44","article-title":"Unsupervised learning of object keypoints for perception and control","author":"kulkarni","year":"2019","journal-title":"NeurIPS"},{"key":"ref43","article-title":"Unsupervised learning of object landmarks through conditional image generation","author":"jakab","year":"2018","journal-title":"NeurIPS"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2021,9,27]]},"location":"Prague, Czech Republic","end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636362.pdf?arnumber=9636362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:44Z","timestamp":1652201684000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636362\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636362","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}