AdvDex: Learning Dexterous Manipulation from Human Demonstrations via Joint-Aligned Actions and Adversarial Learning
AdvDex is presented, a unified Vision-Language-Action framework for learning dexterous manipulation from human and robot demonstrations and the Joint-Aligned Action Space (JAAS) is proposed, a canonical action representation comprising an $\mathrm{SE}(3)$ wrist pose and 15 finger joints, thereby functionally aligning h...