{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:33:00Z","timestamp":1730255580785,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561446","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"13716-13723","source":"Crossref","is-referenced-by-count":0,"title":["droidlet: modular, heterogenous, multi-modal agents"],"prefix":"10.1109","author":[{"given":"Anurag","family":"Pratik","sequence":"first","affiliation":[]},{"given":"Soumith","family":"Chintala","sequence":"additional","affiliation":[]},{"given":"Kavya","family":"Srinet","sequence":"additional","affiliation":[]},{"given":"Dhiraj","family":"Gandhi","sequence":"additional","affiliation":[]},{"given":"Rebecca","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Yuxuan","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Ryan","family":"Drew","sequence":"additional","affiliation":[]},{"given":"Sara","family":"Elkafrawy","sequence":"additional","affiliation":[]},{"given":"Anoushka","family":"Tiwari","sequence":"additional","affiliation":[]},{"given":"Tucker","family":"Hart","sequence":"additional","affiliation":[]},{"given":"Mary","family":"Williamson","sequence":"additional","affiliation":[]},{"given":"Abhinav","family":"Gupta","sequence":"additional","affiliation":[]},{"given":"Arthur","family":"Szlam","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Mmf: A multimodal framework for vision and language research","year":"2020","author":"singh","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"article-title":"Pyrobot: An open-source robotics framework for research and benchmarking","year":"2019","author":"murali","key":"ref33"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"1255","DOI":"10.1109\/TRO.2017.2705103","article-title":"ORB-SLAM2: an open-source SLAM system for monocular, stereo and RGB-D cameras","volume":"33","author":"mur-artal","year":"2017","journal-title":"IEEE Transactions on Robotics"},{"article-title":"Tensorflow modules","year":"2020","author":"modules","key":"ref31"},{"article-title":"Pytorch modules","year":"2020","author":"modules","key":"ref30"},{"article-title":"Recipes for building an open-domain chatbot","year":"2020","author":"roller","key":"ref37"},{"key":"ref36","first-page":"5","article-title":"ROS: an open-source robot operating system","volume":"3","author":"quigley","year":"2009","journal-title":"ICRA Workshop on Open Source Software"},{"article-title":"Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours","year":"2015","author":"pinto","key":"ref35"},{"key":"ref34","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref11"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.427"},{"article-title":"Openrave: A planning architecture for autonomous robotics","year":"2008","author":"diankov","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref14","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Multimodal end-user programming of web-based virtual assistant skills","year":"2020","author":"fischer","key":"ref15"},{"article-title":"Allennlp: A deep semantic natural language processing platform","year":"2017","author":"gardner","key":"ref16"},{"article-title":"Detectron","year":"2018","author":"girshick","key":"ref17"},{"article-title":"Craftassist: A framework for dialogue-enabled interactive agents","year":"2019","author":"gray","key":"ref18"},{"key":"ref19","article-title":"Robot learning in homes: Improving generalization and reducing dataset bias","author":"gupta","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref28","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"article-title":"A simple framework for contrastive learning of visual representations","year":"2020","author":"chen","key":"ref6"},{"key":"ref5","article-title":"A robust layered control system for a mobile robot","author":"brooks","year":"1985","journal-title":"AI Memo 864"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3191513"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2011.2181749"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.178"},{"article-title":"Learning to poke by poking: Experiential learning of intuitive physics","year":"2016","author":"agarwal","key":"ref2"},{"article-title":"Enforcing encoder-decoder modularity in sequenceto-sequence models","year":"2019","author":"dalmia","key":"ref9"},{"article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","year":"2016","author":"abadi","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1086"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.00975","article-title":"Momentum contrast for unsupervised visual representation learning","author":"he","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"article-title":"Model zoo","year":"2020","author":"koh","key":"ref24"},{"article-title":"Robotic frameworks, architectures and middleware comparison","year":"2017","author":"tsardoulias","key":"ref42"},{"key":"ref23","article-title":"Section 15.7: The copy demonstration","author":"horn","year":"1986","journal-title":"Robot Vision"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2012.2205651"},{"key":"ref26","article-title":"On the benefits of making robotic software frameworks thin","author":"makarenko","year":"2007","journal-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"article-title":"Tensorflow tutorial","year":"2020","author":"tutorial","key":"ref44"},{"key":"ref25","article-title":"Microsoft COCO: common objects in context","author":"lin","year":"2014","journal-title":"CoRR"},{"article-title":"Pytorch tutorial","year":"2020","author":"tutorial","key":"ref43"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561446.pdf?arnumber=9561446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:47:06Z","timestamp":1652197626000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561446","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}