{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:20:16Z","timestamp":1783095616268,"version":"3.54.6"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["51922059"],"award-info":[{"award-number":["51922059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["51775305"],"award-info":[{"award-number":["51775305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JQ19010"],"award-info":[{"award-number":["JQ19010"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011429","name":"State Key Laboratory of Tribology","doi-asserted-by":"publisher","award":["SKLT2020D22"],"award-info":[{"award-number":["SKLT2020D22"]}],"id":[{"id":"10.13039\/501100011429","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Youth Talent Support Program"},{"DOI":"10.13039\/501100011415","name":"State Key Laboratory of Mechanical System and Vibration","doi-asserted-by":"publisher","award":["MSV202007"],"award-info":[{"award-number":["MSV202007"]}],"id":[{"id":"10.13039\/501100011415","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3077117","type":"journal-article","created":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T20:34:26Z","timestamp":1620074066000},"page":"68277-68288","source":"Crossref","is-referenced-by-count":9,"title":["Dynamics Learning With Object-Centric Interaction Networks for Robot Manipulation"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8367-258X","authenticated-orcid":false,"given":"Jiayu","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, State Key Laboratory of Tribology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3504-3065","authenticated-orcid":false,"given":"Chuxiong","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, State Key Laboratory of Tribology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9812-7709","authenticated-orcid":false,"given":"Yunan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, State Key Laboratory of Tribology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, State Key Laboratory of Tribology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917700714"},{"key":"ref38","article-title":"ShapeNet: An information-rich 3D model repository","author":"chang","year":"2015","journal-title":"arXiv 1512 03012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2956365"},{"key":"ref32","first-page":"373","article-title":"Dense object nets: Learning dense visual object descriptors by and for robotic manipulation","author":"florence","year":"2018","journal-title":"Proc Conf Robot Learn (CoRL)"},{"key":"ref31","article-title":"KPAM: KeyPoint affordances for category-level robotic manipulation","author":"manuelli","year":"2019","journal-title":"arXiv 1903 06684"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3026963"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010091220143"},{"key":"ref36","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013","journal-title":"arXiv 1312 6114"},{"key":"ref35","author":"wu","year":"2019","journal-title":"Detectron2"},{"key":"ref34","first-page":"100","article-title":"Object-centric forward modeling for model predictive control","author":"ye","year":"2019","journal-title":"Proc Conf Robot Learn (CoRL)"},{"key":"ref10","article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","author":"ebert","year":"2018","journal-title":"arXiv 1812 00568"},{"key":"ref11","article-title":"Hierarchical foresight: Self-supervised learning of long-horizon tasks via visual subgoal generation","author":"nair","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref13","article-title":"Stochastic adversarial video prediction","author":"lee","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref14","article-title":"Robustness via retrying: Closed-loop robotic manipulation with self-supervised learning","author":"ebert","year":"2018","journal-title":"Proc Conf Robot Learn (CoRL)"},{"key":"ref15","first-page":"5074","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","author":"agrawal","year":"2016","journal-title":"Proc Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197295"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2934174"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3001130"},{"key":"ref19","article-title":"Learning visual predictive models of physics for playing billiards","author":"fragkiadaki","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref28","first-page":"42","article-title":"Dynamics learning with cascaded variational inference for multi-step manipulation","author":"fang","year":"2019","journal-title":"Proc Conf Robot Learn (CoRL)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3027923"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2020.2975343"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2901898"},{"key":"ref29","first-page":"306","article-title":"Deep object pose estimation for semantic robotic grasping of household objects","volume":"87","author":"tremblay","year":"2018","journal-title":"Proc Conf Robot Learn (CoRL)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3013795"},{"key":"ref8","first-page":"1","article-title":"Reasoning about physical interactions with object-oriented prediction and planning","author":"janner","year":"2019","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref7","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.2991997"},{"key":"ref9","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"2016","journal-title":"Proc Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.024"},{"key":"ref22","article-title":"Learning 3D dynamic scene representations for robot manipulation","author":"xu","year":"2020","journal-title":"Proc Conf Robot Learn (CoRL)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.046"},{"key":"ref24","article-title":"Object and relation centric representations for push effect prediction","author":"tekden","year":"2021","journal-title":"arXiv 2102 02100"},{"key":"ref23","first-page":"4539","article-title":"Visual interaction networks: Learning a physics simulator from video","author":"watters","year":"2017","journal-title":"Proc Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref26","first-page":"91","article-title":"Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks","author":"xue","year":"2016","journal-title":"Proc Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197468"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09420758.pdf?arnumber=9420758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:44:51Z","timestamp":1741373091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9420758\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3077117","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}