GeoMatch++: Morphology Conditioned Geometry Matching for Multi-Embodiment Grasping

Yunze Wei, Maria Attarian, Igor Gilitschenski

Keywords: Robot Morphology, Dexterous Grasping, Multi-Embodiment

TL;DR: GeoMatch++ improves generalization to unseen grippers in the multi-embodiment dexterous grasping problem by leveraging end-effector morphology.

Abstract: Despite recent progress on multi-finger dexterous grasping, current methods focus on single grippers and unseen objects, and even the ones that explore cross-embodiment, often fail to generalize well to unseen end-effectors. This work addresses the problem of dexterous grasping generalization to unseen end-effectors via a unified policy that learns correlation between gripper morphology and object geometry. Robot morphology contains rich information representing how joints and links connect and move with respect to each other and thus, we leverage it through attention to learn better end-effector geometry features. Our experiments show an average of 9.64% improvement in grasp success across 3 out-of-domain end-effectors compared to previous methods.

Submission Number: 34