{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T07:04:58Z","timestamp":1743750298945,"version":"3.37.3"},"reference-count":44,"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\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","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\/iros51168.2021.9636866","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"6794-6800","source":"Crossref","is-referenced-by-count":1,"title":["Policy Learning for Visually Conditioned Tactile Manipulation"],"prefix":"10.1109","author":[{"given":"Tarik","family":"Kelestemur","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taskin","family":"Padir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Platt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794378"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref33","first-page":"4694","article-title":"Qmdp-net: Deep learning for planning under partial observability","author":"karkus","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref32","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2019","journal-title":"International Conference on Machine Learning"},{"article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","year":"2018","author":"ebert","key":"ref31"},{"article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","year":"2018","author":"espeholt","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2932575"},{"key":"ref35","article-title":"Active neural localization","author":"chaplot","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref34","first-page":"1094","article-title":"Learning to achieve goals","author":"kaelbling","year":"1993","journal-title":"IJCAI"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197117"},{"key":"ref40","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2853652"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794048"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/s17122762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196712"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943123"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989460"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2139150"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139743"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","article-title":"Markov techniques for object localization with force-controlled robots","author":"gadeyne","year":"2001","journal-title":"10th Int’l Conf on Advanced Robotics"},{"article-title":"Deep recurrent q-learning for partially observable mdps","year":"2015","author":"hausknecht","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.364201"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1641793"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2005.1545286"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630818"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509194"},{"key":"ref2","first-page":"4","article-title":"Pomdps for robotic tasks with mixed observability","volume":"5","author":"ong","year":"2009","journal-title":"Robotics Science and Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989049"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341420"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/504729.504754"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.001"},{"key":"ref21","article-title":"End-to-end learnable histogram filters","author":"jonschkowski","year":"2016","journal-title":"NIPS workshop on Deep Learning for Action and Interaction"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref24","first-page":"4376","article-title":"Backprop kf: Learning discriminative deterministic state estimators","author":"haarnoja","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref41"},{"article-title":"Particle filter networks with application to visual localization","year":"2018","author":"karkus","key":"ref23"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225116"},{"key":"ref26","first-page":"2746","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"article-title":"Deep variational bayes filters: Unsupervised learning of state space models from raw data","year":"2016","author":"karl","key":"ref25"}],"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\/09636866.pdf?arnumber=9636866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:49Z","timestamp":1652201689000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636866\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636866","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}