Login / Signup

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control.

Anthony BrohanNoah BrownJustice CarbajalYevgen ChebotarXi ChenKrzysztof ChoromanskiTianli DingDanny DriessAvinava DubeyChelsea FinnPete FlorenceChuyuan FuMontse Gonzalez ArenasKeerthana GopalakrishnanKehang HanKarol HausmanAlexander HerzogJasmine HsuBrian IchterAlex IrpanNikhil J. JoshiRyan JulianDmitry KalashnikovYuheng KuangIsabel LealLisa LeeTsang-Wei Edward LeeSergey LevineYao LuHenryk MichalewskiIgor MordatchKarl PertschKanishka RaoKrista ReymannMichael S. RyooGrecia SalazarPannag SanketiPierre SermanetJaspiar SinghAnikait SinghRadu SoricutHuong TranVincent VanhouckeQuan VuongAyzaan WahidStefan WelkerPaul WohlhartJialin WuFei XiaTed XiaoPeng XuSichun XuTianhe YuBrianna Zitkovich
Published in: CoRR (2023)
Keyphrases
  • robotic control
  • action models
  • computer vision
  • knowledge base
  • reinforcement learning
  • knowledge representation