{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T07:58:46Z","timestamp":1773907126281,"version":"3.50.1"},"reference-count":52,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/iros.2018.8594193","type":"proceedings-article","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T02:33:30Z","timestamp":1548297210000},"page":"4606-4613","source":"Crossref","is-referenced-by-count":18,"title":["Learning Image-Conditioned Dynamics Models for Control of Underactuated Legged Millirobots"],"prefix":"10.1109","author":[{"given":"Anusha","family":"Nagabandi","sequence":"first","affiliation":[]},{"given":"Guangzhao","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Asmar","sequence":"additional","affiliation":[]},{"given":"Ravi","family":"Pandya","sequence":"additional","affiliation":[]},{"given":"Gregory","family":"Kahn","sequence":"additional","affiliation":[]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[]},{"given":"Ronald S.","family":"Fearing","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2806566"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2014.07.008"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6697168"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1109\/TRO.2014.2309194","article-title":"Model-less feedback control of continuum manipulators in constrained environments","author":"yip","year":"2014","journal-title":"IEEE Transactions on Robotics"},{"key":"ref31","article-title":"Sample-based information-theoretic stochastic optimal control","author":"lioutikov","year":"2014","journal-title":"IEEE Int Conf on Robotics and Automation"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00067-7"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385955"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4651188"},{"key":"ref34","article-title":"A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"ICML"},{"key":"ref28","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"ICML"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"ICLRE"},{"key":"ref29","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"2478","DOI":"10.1109\/IRDS.2002.1041641","article-title":"The intelligent asimo: System overview and integration","volume":"3","author":"sakagami","year":"2002","journal-title":"Intelligent Robots and Systems 2002 IEEE\/RSJ International Conference on"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758092"},{"key":"ref20","first-page":"1939","article-title":"Learning to walk in 20 minutes","volume":"95585","author":"tedrake","year":"2005","journal-title":"Proceedings of the Fourteenth Yale Workshop on Adaptive and Learning Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907117"},{"key":"ref21","first-page":"2562","article-title":"An evolutionary approach to gait learning for four-legged robots","volume":"3","author":"chernova","year":"2004","journal-title":"IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095076"},{"key":"ref23","first-page":"944","article-title":"Automatic gait optimization with gaussian process regression","volume":"7","author":"lizotte","year":"2007","journal-title":"IJCAI"},{"key":"ref26","article-title":"Memorybased control of active perception and action in minecraft","author":"oh","year":"2016","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631034"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543462"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref10","first-page":"94671s","article-title":"Dynamic legged locomotion for palm-size robots","author":"zarrouk","year":"2015","journal-title":"SPIE Defense"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.933183"},{"key":"ref40","author":"leffler","year":"2009","journal-title":"Perception-based generalization in model-based reinforcement learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364906069150"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/BIOROB.2010.5626034"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907526"},{"key":"ref15","first-page":"466","article-title":"A physical model for dynamical arthropod running on level ground","author":"komsuoglu","year":"2008","journal-title":"Departmental Papers (ESE)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28572-1_46"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/0278364904047390"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989397"},{"key":"ref19","author":"gay","year":"2013","journal-title":"Learning robot gait stability using neural networks as sensory feedback function for central pattern generators"},{"key":"ref4","author":"byl","year":"2008","journal-title":"Metastable legged-robot locomotion"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"10822","DOI":"10.3182\/20080706-5-KR-1001.01833","article-title":"Bigdog, the rough-terrain quadruped robot","volume":"41","author":"raibert","year":"2008","journal-title":"IFAC Proceedings Volumes"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509805"},{"key":"ref5","first-page":"769","article-title":"Hierarchical apprenticeship learning with application to quadruped locomotion","author":"kolter","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012426720699"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910392608"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref9","volume":"67","author":"mcclung","year":"2006","journal-title":"Techniques for Dynamic Maneuvering of Hexapedal Legged Robots"},{"key":"ref46","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref45","author":"nagabandi","year":"2017","journal-title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning"},{"key":"ref48","article-title":"A survey of numerical methods for optimal control","author":"rao","year":"2009","journal-title":"Advances in the Astronautical Sciences"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509309"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20147"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386243"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2524073"}],"event":{"name":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Madrid","start":{"date-parts":[[2018,10,1]]},"end":{"date-parts":[[2018,10,5]]}},"container-title":["2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8574473\/8593358\/08594193.pdf?arnumber=8594193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T04:07:08Z","timestamp":1598242028000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8594193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iros.2018.8594193","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}