RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control.
Brianna ZitkovichTianhe YuSichun XuPeng XuTed XiaoFei XiaJialin WuPaul WohlhartStefan WelkerAyzaan WahidQuan VuongVincent VanhouckeHuong T. TranRadu SoricutAnikait SinghJaspiar SinghPierre SermanetPannag R. SanketiGrecia SalazarMichael S. RyooKrista ReymannKanishka RaoKarl PertschIgor MordatchHenryk MichalewskiYao LuSergey LevineLisa LeeTsang-Wei Edward LeeIsabel LealYuheng KuangDmitry KalashnikovRyan JulianNikhil J. JoshiAlex IrpanBrian IchterJasmine HsuAlexander HerzogKarol HausmanKeerthana GopalakrishnanChuyuan FuPete FlorenceChelsea FinnKumar Avinava DubeyDanny DriessTianli DingKrzysztof Marcin ChoromanskiXi ChenYevgen ChebotarJustice CarbajalNoah BrownAnthony BrohanMontserrat Gonzalez ArenasKehang HanPublished in: CoRL (2023)