机器人学arXiv 20252025年2月
GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
Chi-Lam Chehang, Guangzeng Chen, Tao Kong, Kaicheng Lin et al.Google DeepMind
摘要
A generative video-language-action model leveraging web-scale knowledge for robot manipulation tasks.
video-language-actionweb-scale knowledgerobot manipulation