arXiv preprint / 6D位姿

MimicDroid: In-Context Learning for Humanoid Robot Manipulation from Human Play Videos

作者：Rutav Shah, Shuijing Liu, Qi Wang, Zhenyu Jiang, Sateesh Kumar, Amazon Consumer Robotics, NVIDIA · 单位：The University of Texas at Austin Amazon Consumer Robotics NVIDIA · 会议/期刊：arXiv preprint · 方向：6D位姿 · 发布日期：2025-09-11

6D位姿估计机器人操作
新标签打开 AlphaXiv新标签打开 Code
MimicDroid: In-Context Learning for Humanoid Robot Manipulation from Human Play Videos figure
AlphaXiv 中文概览（可滚动查看）