{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:42:13Z","timestamp":1755801733174,"version":"3.44.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8968165","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"1025-1031","source":"Crossref","is-referenced-by-count":4,"title":["EARLY FUSION for Goal Directed Robotic Vision"],"prefix":"10.1109","author":[{"given":"Aaron","family":"Walsman","sequence":"first","affiliation":[{"name":"University of Washington,Paul G. Allen School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonatan","family":"Bisk","sequence":"additional","affiliation":[{"name":"University of Washington,Paul G. Allen School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saadia","family":"Gabriel","sequence":"additional","affiliation":[{"name":"University of Washington,Paul G. Allen School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dipendra","family":"Misra","sequence":"additional","affiliation":[{"name":"Cornell University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoav","family":"Artzi","sequence":"additional","affiliation":[{"name":"Cornell University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yejin","family":"Choi","sequence":"additional","affiliation":[{"name":"University of Washington,Paul G. Allen School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dieter","family":"Fox","sequence":"additional","affiliation":[{"name":"University of Washington,Paul G. Allen School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref33","article-title":"Tell me dave: Context-sensitive grounding of natural language to mobile manipulation instructions","author":"misra","year":"2014","journal-title":"Robotics Science and Systems RSS"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v25i1.7979","article-title":"Understanding natural language commands for robotic navigation and mobile manipulation","author":"tellex","year":"2011","journal-title":"Proceedings of the National Conference on Artificial Intelligence"},{"key":"ref31","article-title":"Following directions using statistical machine translation","author":"matuszek","year":"2010","journal-title":"Proceedings of the International Conference on Human-Robot Interaction"},{"key":"ref30","volume":"3","author":"gupta","year":"2017","journal-title":"Cognitive mapping and planning for visual navigation"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/676"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152466"},{"key":"ref35","article-title":"End-to-end training of deep visuomotor policies","author":"levin","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"ref34","article-title":"Mapping navigation instructions to continuous control actions with position visitation prediction","author":"blukis","year":"2018","journal-title":"Proc Conf Robot Learn"},{"key":"ref10","article-title":"A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning","author":"ross","year":"2011","journal-title":"14th International Conference of Artificial Intelligence and Statistics (AISTATS)"},{"key":"ref11","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.066"},{"key":"ref13","first-page":"4967","article-title":"A simple neural network module for relational reasoning","author":"santoro","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref15","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proceedings of the 32Nd International Conference on International Conference on Machine Learning"},{"key":"ref16","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference for Learning Representations"},{"key":"ref18","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017","journal-title":"31st Conference on Neural Information Processing Systems (NIPS 2017)"},{"key":"ref19","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"NIPS Deep Learning Workshop 2013"},{"key":"ref28","article-title":"End-to-end driving via conditional imitation learning","author":"codevilla","year":"2017","journal-title":"ICRA"},{"journal-title":"CHALET Cornell house agent learning environment","year":"2018","author":"yan","key":"ref4"},{"key":"ref27","article-title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","author":"anderson","year":"2017","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1287"},{"key":"ref6","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2015","journal-title":"ICLR 2015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref5","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"ICLR 2015"},{"key":"ref8","article-title":"Attention on attention: Architectures for visual question answering (vqa)","author":"singh","year":"2018","journal-title":"arXiv preprint arXiv 1803 07724"},{"key":"ref7","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"NIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1106"},{"key":"ref9","article-title":"An intriguing failing of convolutional neural networks and the coordconv solution","author":"liu","year":"2018","journal-title":"Proceedings of the 32Nd International Conference on Neural Information Processing Systems"},{"key":"ref1","article-title":"A system for multi-step mobile manipulation: Architecture, algorithms, and experiments","author":"srinivasa","year":"2016","journal-title":"International Symposium on Experimental Robotics"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3758\/BF03200774"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1658349.1658355"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(95)00025-9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/11550518_15"},{"journal-title":"Grounded language learning in a simulated 3d world","year":"2017","author":"hermann","key":"ref26"},{"key":"ref25","article-title":"Embodied Question Answering","author":"das","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2019,11,3]]},"location":"Macau, China","end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08968165.pdf?arnumber=8968165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:35:12Z","timestamp":1755714912000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8968165\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8968165","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}