翻译:视觉语言动作模型,将在线知识转化到机器人控制RT-2: Vision-Language-Action ModelsTransfer Web Knowledge2Robotic Control
作者:AnthonyBrohan,NoahBrown,JusticeCarbajal,YevgenChebotar,XiChen,KrzysztofChoromanski,TianliDing,DannyDriess,AvinavaDubey,ChelseaFinn,PeteFlorence,ChuyuanFu,MontseGonzalezArenas,KeerthanaGopalakrishna