{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:39:22Z","timestamp":1773931162364,"version":"3.50.1"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8793485","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"8943-8950","source":"Crossref","is-referenced-by-count":232,"title":["Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks"],"prefix":"10.1109","author":[{"given":"Michelle A.","family":"Lee","sequence":"first","affiliation":[]},{"given":"Yuke","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Krishnan","family":"Srinivasan","sequence":"additional","affiliation":[]},{"given":"Parth","family":"Shah","sequence":"additional","affiliation":[]},{"given":"Silvio","family":"Savarese","sequence":"additional","affiliation":[]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[]},{"given":"Animesh","family":"Garg","sequence":"additional","affiliation":[]},{"given":"Jeannette","family":"Bohg","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"arXiv preprint arXiv 1609 09861"},{"key":"ref38","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in atari games","author":"oh","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2991\/978-94-6239-133-8_25"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/027836499501400103"},{"key":"ref37","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref36","article-title":"Learning end-to-end multimodal sensor policies for autonomous navigation","author":"liu","year":"2017","journal-title":"arXiv preprint arXiv 1705 10422"},{"key":"ref35","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref34","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095096"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759578"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.044"},{"key":"ref2","first-page":"5074","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","author":"agrawal","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9435-2"},{"key":"ref20","article-title":"Fundamental limitations in performance and interpretability of common planar rigid-body contact models","author":"fazeli","year":"2017","journal-title":"ArXiv preprint arXiv 1710 04979"},{"key":"ref22","article-title":"Flownet: Learning optical ow with convolutional networks","volume":"abs 1504 6852","author":"fischer","year":"2015","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref24","article-title":"Experimental studies of contact space model for multi-surface collisions in articulated rigid-body systems","author":"ganguly","year":"2018","journal-title":"International Symposium on Experimental Robotics"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759592"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2645124"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487176"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363558"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989326"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.538"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1177\/027836498700600101"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1115\/1.3149634"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354090"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363524"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2819658"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800101"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1989.100031"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852779"},{"key":"ref14","article-title":"The feeling of success: Does touch sensing help predict grasp outcomes?","author":"calandra","year":"2017","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989384"},{"key":"ref16","first-page":"496","article-title":"The chai libraries","author":"conti","year":"2003","journal-title":"Proceedings of Eurohaptics 2003"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28872-7_16"},{"key":"ref18","author":"edelman","year":"1987","journal-title":"Neural darwinism The theory of neuronal group selection Basic books"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914559753"},{"key":"ref4","article-title":"Stochastic variational video prediction","author":"babaeizadeh","year":"2017","journal-title":"arXiv preprint arXiv 1710 11252"},{"key":"ref3","article-title":"Learning dexterous in-hand manipulation","author":"andrychowicz","year":"2018","journal-title":"arXiv preprint arXiv 1808 02194"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630999"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094878"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1111\/j.0956-7976.2004.00691.x"},{"key":"ref7","article-title":"Integrated tactile sensing for gripper ngers","author":"bicchi","year":"1988","journal-title":"Int Conf on Robot Vision and Sensory Control"},{"key":"ref49","first-page":"2222","article-title":"Multimodal learning with deep boltzmann machines","author":"srivastava","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2721939"},{"key":"ref46","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2162271"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943202"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907696"},{"key":"ref42","first-page":"842","author":"ponton","year":"2016","journal-title":"A convex model of humanoid momentum dynamics for multi-contact motion generation"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-013-9365-9"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913506757"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2019,5,20]]},"end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08793485.pdf?arnumber=8793485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:15:10Z","timestamp":1657854910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8793485\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8793485","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}