RSS2025 Paper 155

Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization

Jonathan Heewon Yang, Chuyuan Fu, Dhruv Shah, Dorsa Sadigh, Fei Xia, Tingnan Zhang

感知灵巧手扩散策略机器人学习操作模仿学习
新标签打开 AlphaXiv新标签打开 arXiv
Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization figure
AlphaXiv 中文概览（可滚动查看）