Awesome Robotics Manipulation · full_paper

ManiVID-3D: Generalizable View-Invariant Reinforcement Learning for Robotic Manipulation via Disentangled 3D Representations

作者：Zheng Li, Pei Qu, Yufei Jia, Shihui Zhou, Haizhou Ge, Jiahang Cao, Jinni Zhou, Guyue Zhou, Jun Ma · 单位：The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Tsinghua University, The University of Hong Kong, Hong Kong SAR · 会议/期刊：RA-L 2026 · 日期：2026-09-14 · 来源：Bottlenecks / Generalization / SE(3)/SIM(3)-Equivariance/View Changes

三维表征强化学习触觉泛化操作
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
ManiVID-3D: Generalizable View-Invariant Reinforcement Learning for Robotic Manipulation via Disentangled 3D Representations figure
AlphaXiv 中文论文页面（可滚动查看）