arXiv preprint / 规划

This&That: This&That: Language-Gesture Controlled Video Generation for Robot Planning

作者：Boyang Wang, Nikhil Sridhar, Chao Feng, Mark Van der Merwe, Adam Fishman, Nima Fazeli, Jeong Joon Park · 单位：University of Michigan University of Washington · 会议/期刊：arXiv preprint · 方向：规划 · 发布日期：2024

扩散策略机器人学习规划语言目标图像目标
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
This&That: This&That: Language-Gesture Controlled Video Generation for Robot Planning figure
AlphaXiv 中文概览（可滚动查看）