Awesome Robotics Manipulation · full_paper

SG-VLA: Learning Spatially-Grounded Vision-Language-Action Models for Mobile Manipulation

作者：Ruisen Tu, Arth Shukla, Sohyun Yoo, Xuanlin Li, Junxi Li, Jianwen Xie, Hao Su, Zhuowen Tu UC San Diego · 会议/期刊：arXiv · 日期：2026-03-24 · 来源：Manipulation Tasks | Mobile Manipulation / Mobile Manipulation / VLA | VLA

移动操作视觉语言动作操作
新标签打开 AlphaXiv新标签打开 Paper
SG-VLA: Learning Spatially-Grounded Vision-Language-Action Models for Mobile Manipulation figure
AlphaXiv 中文论文页面（可滚动查看）