VLA / 视觉-语言-动作模型

Transforming Monolithic Foundation Models into Embodied Multi-Agent Architectures for Human-Robot Collaboration

将单体基础模型转化为具身体验的多智能体架构以实现人机协作

Nan Sun, Bo Mao, Yongchang Li, Chenxu Wang, Di Guo, Huaping Liu

机构 * Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学） ； School of Artificial Intelligence, Beijing University of Posts and Telecommunications（人工智能学院，北京邮电大学） 纠错

专题命中 部署与泛化 ：vision-language-action(abstract)；分类 cs.RO

AI总结 InteractGen通过分解机器人智能为多个智能体，提升服务机器人在人类环境中的自主性和协作能力。

Comments 21 pages, 16 figures, 4 tables