Preprint
Aug 2026
DexMani: Human-Derived Manipulability Guidance for Dexterous Rotation
This work introduces DexMani, a framework that transfers human demonstrations as contact-conditioned manipulability evolution and uses it to guide downstream reinforcement learning, enabling rotation skills to be acquired across robot embodiments with distinct kinematics and active-contact configurations.
Xiaoyang Chen, Shengcheng Luo, Haoran Guo et al.
· 0 citations