{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T02:12:48Z","timestamp":1778638368214,"version":"3.51.4"},"reference-count":134,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611477","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"6892-6903","source":"Crossref","is-referenced-by-count":136,"title":["Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration<sup>0<\/sup>"],"prefix":"10.1109","author":[{"given":"Abby","family":"O\u2019Neill","sequence":"first","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Abdul","family":"Rehman","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}]},{"given":"Abhiram","family":"Maddukuri","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}]},{"given":"Abhishek","family":"Gupta","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Abhishek","family":"Padalkar","sequence":"additional","affiliation":[{"name":"German Aerospace Center"}]},{"given":"Abraham","family":"Lee","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Acorn","family":"Pooley","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Agrim","family":"Gupta","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Ajay","family":"Mandlekar","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Ajinkya","family":"Jain","sequence":"additional","affiliation":[{"name":"Intrinsic LLC"}]},{"given":"Albert","family":"Tung","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Alex","family":"Bewley","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Alex","family":"Herzog","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Alex","family":"Irpan","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Alexander","family":"Khazatsky","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Anant","family":"Rai","sequence":"additional","affiliation":[{"name":"New York University"}]},{"given":"Anchit","family":"Gupta","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Andrew","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Anikait","family":"Singh","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Animesh","family":"Garg","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Aniruddha","family":"Kembhavi","sequence":"additional","affiliation":[{"name":"Allen Institute for AI"}]},{"given":"Annie","family":"Xie","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Anthony","family":"Brohan","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Antonin","family":"Raffin","sequence":"additional","affiliation":[{"name":"German Aerospace Center"}]},{"given":"Archit","family":"Sharma","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Arefeh","family":"Yavary","sequence":"additional","affiliation":[{"name":"University of California,Davis"}]},{"given":"Arhan","family":"Jain","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Ashwin","family":"Balakrishna","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}]},{"given":"Ayzaan","family":"Wahid","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Ben","family":"Burgess-Limerick","sequence":"additional","affiliation":[{"name":"Queensland University of Technology"}]},{"given":"Beomjoon","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology"}]},{"given":"Bernhard","family":"Sch\u00f6lkopf","sequence":"additional","affiliation":[{"name":"Max Planck Institute"}]},{"given":"Blake","family":"Wulfe","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}]},{"given":"Brian","family":"Ichter","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Cewu","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Charles","family":"Xu","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Charlotte","family":"Le","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Chelsea","family":"Finn","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Chenfeng","family":"Xu","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Cheng","family":"Chi","sequence":"additional","affiliation":[{"name":"Columbia University"}]},{"given":"Chenguang","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Freiburg"}]},{"given":"Christine","family":"Chan","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Christopher","family":"Agia","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Chuer","family":"Pan","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Chuyuan","family":"Fu","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Coline","family":"Devin","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Danfei","family":"Xu","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Daniel","family":"Morton","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Danny","family":"Driess","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Daphne","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Deepak","family":"Pathak","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Dhruv","family":"Shah","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Dieter","family":"B\u00fcchler","sequence":"additional","affiliation":[{"name":"Max Planck Institute"}]},{"given":"Dinesh","family":"Jayaraman","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}]},{"given":"Dmitry","family":"Kalashnikov","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Dorsa","family":"Sadigh","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Edward","family":"Johns","sequence":"additional","affiliation":[{"name":"Imperial College London"}]},{"given":"Ethan","family":"Foster","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Fangchen","family":"Liu","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Federico","family":"Ceola","sequence":"additional","affiliation":[{"name":"Istituto Italiano di Tecnologia"}]},{"given":"Fei","family":"Xia","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Feiyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"IO-AI TECH"}]},{"given":"Freek","family":"Stulp","sequence":"additional","affiliation":[{"name":"German Aerospace Center"}]},{"given":"Gaoyue","family":"Zhou","sequence":"additional","affiliation":[{"name":"New York University"}]},{"given":"Gaurav S.","family":"Sukhatme","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Gautam","family":"Salhotra","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Ge","family":"Yan","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}]},{"given":"Gilbert","family":"Feng","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Giulio","family":"Schiavi","sequence":"additional","affiliation":[{"name":"ETH Z&#x00FC;rich"}]},{"given":"Glen","family":"Berseth","sequence":"additional","affiliation":[{"name":"University of Montreal"}]},{"given":"Gregory","family":"Kahn","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Guanzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"California Institute of Technology"}]},{"given":"Hao","family":"Su","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}]},{"given":"Hao-Shu","family":"Fang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Haochen","family":"Shi","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Henghui","family":"Bao","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Heni","family":"Ben Amor","sequence":"additional","affiliation":[{"name":"Arizona State University"}]},{"given":"Henrik I","family":"Christensen","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}]},{"given":"Hiroki","family":"Furuta","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Homer","family":"Walke","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Hongjie","family":"Fang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Huy","family":"Ha","sequence":"additional","affiliation":[{"name":"Columbia University"}]},{"given":"Igor","family":"Mordatch","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Ilija","family":"Radosavovic","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Isabel","family":"Leal","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Jacky","family":"Liang","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Jad","family":"Abou-Chakra","sequence":"additional","affiliation":[{"name":"Queensland University of Technology"}]},{"given":"Jaehyung","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology"}]},{"given":"Jaimyn","family":"Drake","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[{"name":"Technische Universit&#x00E4;t Darmstadt"}]},{"given":"Jan","family":"Schneider","sequence":"additional","affiliation":[{"name":"Max Planck Institute"}]},{"given":"Jasmine","family":"Hsu","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Jeannette","family":"Bohg","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Jeffrey","family":"Bingham","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Jeffrey","family":"Wu","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Jensen","family":"Gao","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Jiaheng","family":"Hu","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}]},{"given":"Jiajun","family":"Wu","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Jialin","family":"Wu","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Jiankai","family":"Sun","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Jianlan","family":"Luo","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Jiayuan","family":"Gu","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}]},{"given":"Jie","family":"Tan","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Jihoon","family":"Oh","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Jimmy","family":"Wu","sequence":"additional","affiliation":[{"name":"Princeton University"}]},{"given":"Jingpei","family":"Lu","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}]},{"given":"Jingyun","family":"Yang","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Jitendra","family":"Malik","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Jo\u00e3o","family":"Silv\u00e9rio","sequence":"additional","affiliation":[{"name":"German Aerospace Center"}]},{"given":"Joey","family":"Hejna","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Jonathan","family":"Booher","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Jonathan","family":"Tompson","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Jonathan","family":"Yang","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Jordi","family":"Salvador","sequence":"additional","affiliation":[{"name":"Allen Institute for AI"}]},{"given":"Joseph J.","family":"Lim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology"}]},{"given":"Junhyek","family":"Han","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology"}]},{"given":"Kaiyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}]},{"given":"Kanishka","family":"Rao","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Karl","family":"Pertsch","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Karol","family":"Hausman","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Keegan","family":"Go","sequence":"additional","affiliation":[{"name":"Intrinsic LLC"}]},{"given":"Keerthana","family":"Gopalakrishnan","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Ken","family":"Goldberg","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Kendra","family":"Byrne","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Kenneth","family":"Oslund","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Kento","family":"Kawaharazuka","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Kevin","family":"Black","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Kevin","family":"Lin","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Kevin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Kiana","family":"Ehsani","sequence":"additional","affiliation":[{"name":"Allen Institute for AI"}]},{"given":"Kiran","family":"Lekkala","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Kirsty","family":"Ellis","sequence":"additional","affiliation":[{"name":"University of Montreal"}]},{"given":"Krishan","family":"Rana","sequence":"additional","affiliation":[{"name":"Queensland University of Technology"}]},{"given":"Krishnan","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Kuan","family":"Fang","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Kunal Pratap","family":"Singh","sequence":"additional","affiliation":[{"name":"EPFL"}]},{"given":"Kuo-Hao","family":"Zeng","sequence":"additional","affiliation":[{"name":"Allen Institute for AI"}]},{"given":"Kyle","family":"Hatch","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}]},{"given":"Kyle","family":"Hsu","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Laurent","family":"Itti","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Lawrence Yunliang","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Lerrel","family":"Pinto","sequence":"additional","affiliation":[{"name":"New York University"}]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Liam","family":"Tan","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Linxi Jim","family":"Fan","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Lionel","family":"Ott","sequence":"additional","affiliation":[{"name":"ETH Z&#x00FC;rich"}]},{"given":"Lisa","family":"Lee","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Luca","family":"Weihs","sequence":"additional","affiliation":[{"name":"Allen Institute for AI"}]},{"given":"Magnum","family":"Chen","sequence":"additional","affiliation":[{"name":"IO-AI TECH"}]},{"given":"Marion","family":"Lepert","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Marius","family":"Memmel","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Masha","family":"Itkina","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}]},{"given":"Mateo Guaman","family":"Castro","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Max","family":"Spero","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Maximilian","family":"Du","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Michael","family":"Ahn","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Michael C.","family":"Yip","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}]},{"given":"Mingtong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}]},{"given":"Mingyu","family":"Ding","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Minho","family":"Heo","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology"}]},{"given":"Mohan Kumar","family":"Srirama","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Mohit","family":"Sharma","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Moo Jin","family":"Kim","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Naoaki","family":"Kanazawa","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Nicklas","family":"Hansen","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}]},{"given":"Nicolas","family":"Heess","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Nikhil J","family":"Joshi","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Niko","family":"Suenderhauf","sequence":"additional","affiliation":[{"name":"Queensland University of Technology"}]},{"given":"Ning","family":"Liu","sequence":"additional","affiliation":[{"name":"IO-AI TECH"}]},{"given":"Norman","family":"Di Palo","sequence":"additional","affiliation":[{"name":"Imperial College London"}]},{"given":"Nur Muhammad Mahi","family":"Shafiullah","sequence":"additional","affiliation":[{"name":"New York University"}]},{"given":"Oier","family":"Mees","sequence":"additional","affiliation":[{"name":"University of Freiburg"}]},{"given":"Oliver","family":"Kroemer","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Osbert","family":"Bastani","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}]},{"given":"Pannag R","family":"Sanketi","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Patrick Tree","family":"Miller","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}]},{"given":"Patrick","family":"Yin","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Paul","family":"Wohlhart","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Peng","family":"Xu","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Peter David","family":"Fagan","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}]},{"given":"Peter","family":"Mitrano","sequence":"additional","affiliation":[{"name":"University of Michigan"}]},{"given":"Pierre","family":"Sermanet","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Priya","family":"Sundaresan","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Qiuyu","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Quan","family":"Vuong","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Rafael","family":"Rafailov","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Ran","family":"Tian","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Ria","family":"Doshi","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Roberto","family":"Mart\u00edn-Mart\u00edn","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}]},{"given":"Rohan","family":"Baijal","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Rosario","family":"Scalise","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Rose","family":"Hendrix","sequence":"additional","affiliation":[{"name":"Allen Institute for AI"}]},{"given":"Roy","family":"Lin","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Runjia","family":"Qian","sequence":"additional","affiliation":[{"name":"IO-AI TECH"}]},{"given":"Ruohan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Russell","family":"Mendonca","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Rutav","family":"Shah","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}]},{"given":"Ryan","family":"Hoque","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Ryan","family":"Julian","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Samuel","family":"Bustamante","sequence":"additional","affiliation":[{"name":"German Aerospace Center"}]},{"given":"Sean","family":"Kirmani","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Shan","family":"Lin","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}]},{"given":"Sherry","family":"Moore","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Shikhar","family":"Bahl","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Shivin","family":"Dass","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Shubham","family":"Sonawani","sequence":"additional","affiliation":[{"name":"Arizona State University"}]},{"given":"Shuran","family":"Song","sequence":"additional","affiliation":[{"name":"Columbia University"}]},{"given":"Sichun","family":"Xu","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Siddhant","family":"Haldar","sequence":"additional","affiliation":[{"name":"New York University"}]},{"given":"Siddharth","family":"Karamcheti","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Simeon","family":"Adebola","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Simon","family":"Guist","sequence":"additional","affiliation":[{"name":"Max Planck Institute"}]},{"given":"Soroush","family":"Nasiriany","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}]},{"given":"Stefan","family":"Schaal","sequence":"additional","affiliation":[{"name":"Intrinsic LLC"}]},{"given":"Stefan","family":"Welker","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Stephen","family":"Tian","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Subramanian","family":"Ramamoorthy","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}]},{"given":"Sudeep","family":"Dasari","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Suneel","family":"Belkhale","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Sungjae","family":"Park","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology"}]},{"given":"Suraj","family":"Nair","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}]},{"given":"Suvir","family":"Mirchandani","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Takayuki","family":"Osa","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Tanmay","family":"Gupta","sequence":"additional","affiliation":[{"name":"Allen Institute for AI"}]},{"given":"Tatsuya","family":"Harada","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Tatsuya","family":"Matsushima","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Ted","family":"Xiao","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Thomas","family":"Kollar","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}]},{"given":"Tianhe","family":"Yu","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Tianli","family":"Ding","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Todor","family":"Davchev","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Tony Z.","family":"Zhao","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Travis","family":"Armstrong","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Trinity","family":"Chung","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Vidhi","family":"Jain","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Vincent","family":"Vanhoucke","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Wei","family":"Zhan","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Wenxuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Wolfram","family":"Burgard","sequence":"additional","affiliation":[{"name":"University of Technology,Nuremberg"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Xiaolong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}]},{"given":"Xinghao","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Xinyang","family":"Geng","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Xiyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"IO-AI TECH"}]},{"given":"Xu","family":"Liangwei","sequence":"additional","affiliation":[{"name":"IO-AI TECH"}]},{"given":"Xuanlin","family":"Li","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}]},{"given":"Yao","family":"Lu","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Yecheng Jason","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}]},{"given":"Yejin","family":"Kim","sequence":"additional","affiliation":[{"name":"Allen Institute for AI"}]},{"given":"Yevgen","family":"Chebotar","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Yifan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Arizona State University"}]},{"given":"Yifeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}]},{"given":"Yilin","family":"Wu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Ying","family":"Xu","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Yixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}]},{"given":"Yonatan","family":"Bisk","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Yoonyoung","family":"Cho","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology"}]},{"given":"Youngwoon","family":"Lee","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Yuchen","family":"Cui","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Yue","family":"Cao","sequence":"additional","affiliation":[{"name":"IO-AI TECH"}]},{"given":"Yueh-Hua","family":"Wu","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}]},{"given":"Yujin","family":"Tang","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Yuke","family":"Zhu","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}]},{"given":"Yunchu","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Yunfan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Yunshuang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}]},{"given":"Yunzhu","family":"Li","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}]},{"given":"Yusuke","family":"Iwasawa","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Yutaka","family":"Matsuo","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Zehan","family":"Ma","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Zhuo","family":"Xu","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Zichen Jeff","family":"Cui","sequence":"additional","affiliation":[{"name":"New York University"}]},{"given":"Zichen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Allen Institute for AI"}]},{"given":"Zipeng","family":"Lin","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref2","volume-title":"GPT-4 technical report","year":"2023"},{"key":"ref3","article-title":"PaLM 2 technical report","author":"Anil","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00265"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2956775"},{"issue":"2","key":"ref6","first-page":"167","article-title":"DBpedia - a large-scale, multilingual knowledge base extracted from wikipedia","volume-title":"Semantic Web","volume":"6","author":"Lehmann","year":"2015"},{"key":"ref7","first-page":"133","article-title":"Web data commons-extracting structured data from two large web corpora","volume-title":"LDOW","volume":"937","author":"M\u00fchleisen"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref9","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref11","first-page":"9355","article-title":"Hardware conditioned policies for multi-robot transfer learning","author":"Chen","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","first-page":"4470","article-title":"Graph networks as learnable physics engines for inference and control","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Sanchez-Gonzalez"},{"key":"ref13","article-title":"Learning to control self-assembling morphologies: a study of generalization via modularity","volume":"32","author":"Pathak","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968201"},{"key":"ref15","article-title":"One policy to control them all: Shared modular policies for agent-agnostic control","volume-title":"ICML","author":"Huang"},{"key":"ref16","article-title":"My body is a cage: the role of morphology in graph-based incompatible control","author":"Kurin","year":"2020"},{"key":"ref17","article-title":"XIRL: Cross-embodiment inverse reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Zakka"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636628"},{"key":"ref19","article-title":"Metamorph: Learning universal controllers with transformers","volume-title":"International Conference on Learning Representations","author":"Gupta"},{"key":"ref20","article-title":"A generalist dynamics model for control","author":"Schubert","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161227"},{"key":"ref22","first-page":"1684","article-title":"Modularity through attention: Efficient training and transfer of language-conditioned policies for robot manipulation","volume-title":"Proceedings of The 6th Conference on Robot Learning","volume":"205","author":"Zhou"},{"key":"ref23","first-page":"885","article-title":"RoboNet: Large-scale multi-robot learning","volume-title":"Conference on Robot Learning (CoRL)","volume":"100","author":"Dasari"},{"key":"ref24","article-title":"Know thyself: Transferable visual control policies through robot-awareness","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref25","article-title":"RoboCat: A self-improving foundation agent for robotic manipulation","author":"Bousmalis","year":"2023"},{"key":"ref26","article-title":"Polybot: Training one policy across robots while embracing variability","author":"Yang","year":"2023"},{"key":"ref27","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref28","article-title":"Bridging action space mismatch in learning from demonstrations","author":"Salhotra","year":"2023"},{"key":"ref29","article-title":"Robot learning with sensorimotor pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969946"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560833"},{"key":"ref32","article-title":"ViNT: A Foundation Model for Visual Navigation","volume-title":"7th Annual Conference on Robot Learning (CoRL)","author":"Shah"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.002"},{"key":"ref35","article-title":"Third-person visual imitation learning via decoupled hierarchical controller","volume":"32","author":"Sharma","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2977835"},{"key":"ref38","first-page":"339","article-title":"Reinforcement learning with videos: Combining offline observations with interaction","volume-title":"Conference on Robot Learning","author":"Schmeckpeper"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636080"},{"key":"ref40","first-page":"991","article-title":"BC-Z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Jang"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.026"},{"key":"ref42","first-page":"1743","article-title":"Embodied concept learner: Self-supervised learning of concepts and mapping through instruction following","volume-title":"Conference on Robot Learning","author":"Ding"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2017.xiii.050"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.082"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.012"},{"key":"ref47","first-page":"55","article-title":"Graph inverse reinforcement learning from diverse videos","volume-title":"Conference on Robot Learning","author":"Kumar"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161178"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.002"},{"key":"ref50","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","volume-title":"Conference on Robot Learning","author":"Wang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_42"},{"key":"ref52","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022","journal-title":"CoRL"},{"key":"ref53","article-title":"Masked visual pre-training for motor control","author":"Xiao","year":"2022"},{"key":"ref54","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic"},{"key":"ref55","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022"},{"key":"ref56","article-title":"Where are we in the search for an artificial visual cortex for embodied intelligence?","author":"Majumdar","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.032"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00648"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980145"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139793"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2017.xiii.058"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593950"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref66","article-title":"QT-Opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"Kalashnikov","year":"2018"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00891"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560844"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref71","article-title":"Fanuc manipulation: A dataset for learning-based manipulation with fanuc mate 200iD robot","author":"Zhu","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758091"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref74","article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","author":"Ebert","year":"2018"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/SMI.2004.1314504"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225116"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912445831"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906903"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2015.2448951"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref81","first-page":"160","article-title":"Object-Net3D: A large scale database for 3d object recognition","volume-title":"European Conference on Computer Vision (ECCV)","author":"Xiang"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2992195"},{"key":"ref83","first-page":"466","article-title":"ObjectFolder: A dataset of objects with implicit visual, auditory, and tactile representations","volume-title":"Conference on Robot Learning","author":"Gao"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref85","article-title":"MT-Opt: Continuous multi-task robotic reinforcement learning at scale","author":"Kalashnikov","year":"2021"},{"key":"ref86","article-title":"RoboTurk: A crowdsourcing platform for robotic skill learning through imitation","volume-title":"CoRR","author":"Mandlekar","year":"2018"},{"key":"ref87","first-page":"906","article-title":"Multiple interactions made easy (MIME): Large scale demonstrations data for imitation","volume-title":"Conference on robot learning","author":"Sharma"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968114"},{"key":"ref89","article-title":"Bridge data: Boosting generalization of robotic skills with cross-domain datasets","volume-title":"Robotics: Science and Systems (RSS) XVIII","author":"Ebert"},{"key":"ref90","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"Mandlekar","year":"2021"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3295255"},{"key":"ref92","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA57147.2024.10611615","article-title":"RH20T: A robotic dataset for learning diverse skills in one-shot","volume-title":"RSS 2023 Workshop on Learning for Task and Motion Planning","author":"Fang"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611293"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.041"},{"key":"ref95","article-title":"Bridgedata v2: A dataset for robot learning at scale","author":"Walke","year":"2023"},{"issue":"1","key":"ref96","first-page":"1","article-title":"Understanding natural language","volume-title":"Cognitive Psychology","volume":"3","author":"Winograd","year":"1972"},{"key":"ref97","article-title":"Walk the talk: Connecting language, knowledge, and action in route instructions","volume-title":"Proceedings of the Twenty-First AAAI Conference on Artificial Intelligence","author":"MacMahon"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2010.5453186"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7974"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23778-7_25"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/880"},{"key":"ref102","first-page":"13 139","article-title":"Language-conditioned imitation learning for robot manipulation tasks","volume":"33","author":"Stepputtis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref103","first-page":"1303","article-title":"Learning language-conditioned robot behavior from offline data and crowd-sourced annotation","volume-title":"Conference on Robot Learning","author":"Nair"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196123"},{"key":"ref106","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Shridhar"},{"key":"ref107","article-title":"Human instruction-following with deep reinforcement learning via transfer-learning from text","author":"Hill","year":"2020"},{"key":"ref108","article-title":"Grounding language in play","volume-title":"Robotics: Science and Systems (RSS)","author":"Lynch"},{"key":"ref109","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning (CoRL)","author":"Ahn"},{"key":"ref110","article-title":"VIMA: General robot manipulation with multimodal prompts","volume-title":"International Conference on Machine Learning (ICML)","author":"Jiang"},{"key":"ref111","first-page":"20","article-title":"ChatGPT for robotics: Design principles and model abilities","volume":"2","author":"Vemprala","year":"2023","journal-title":"Microsoft Auton. Syst. Robot. Res"},{"key":"ref112","article-title":"VoxPoser: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023"},{"key":"ref113","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref114","article-title":"Open-world object manipulation using pre-trained vision-language models","author":"Stone","year":"2023"},{"key":"ref115","article-title":"EmbodiedGPT: Vision-language pre-training via embodied chain of thought","author":"Mu","year":"2023"},{"key":"ref116","article-title":"Film: Visual reasoning with a general conditioning layer","author":"Perez","year":"2017"},{"key":"ref117","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref119","article-title":"RLDS: an ecosystem to generate, share and use datasets in reinforcement learning","author":"Ramos","year":"2021"},{"key":"ref120","article-title":"Universal sentence encoder","author":"Cer","year":"2018"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.2307\/jj.1823137.10"},{"key":"ref122","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022"},{"key":"ref123","article-title":"PaLM-E: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref124","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"ref125","article-title":"UL2: Unifying language learning paradigms","author":"Tay","year":"2023"},{"key":"ref126","article-title":"Latent plans for task agnostic offline reinforcement learning","volume-title":"Proceedings of the 6th Conference on Robot Learning (CoRL)","author":"Rosete-Beas"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160396"},{"key":"ref128","article-title":"CLVR jaco play dataset","author":"Dass","year":"2023"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2024.3353075\/mm1"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.010"},{"key":"ref131","article-title":"Viola: Imitation learning for vision-based manipulation with object proposal priors","author":"Zhu","year":"2023"},{"key":"ref132","article-title":"Berkeley UR5 demonstration dataset","author":"Chen"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160594"},{"key":"ref134","article-title":"Task-agnostic real world robot play"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611477.pdf?arnumber=10611477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T17:54:27Z","timestamp":1743789267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":134,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611477","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}