FuncGrasp: Learning Object-Centric Neural Grasp Functions from Single Annotated Example Object
This work addresses robotic grasping by enabling efficient transfer of grasp functions across objects, though it is incremental in improving grasp density and reliability.
The paper tackles the problem of generating dense and reliable grasp configurations for unseen objects using only one annotated example and a single-view RGB-D observation, achieving significant outperformance over baseline methods in density and reliability.
We present FuncGrasp, a framework that can infer dense yet reliable grasp configurations for unseen objects using one annotated object and single-view RGB-D observation via categorical priors. Unlike previous works that only transfer a set of grasp poses, FuncGrasp aims to transfer infinite configurations parameterized by an object-centric continuous grasp function across varying instances. To ease the transfer process, we propose Neural Surface Grasping Fields (NSGF), an effective neural representation defined on the surface to densely encode grasp configurations. Further, we exploit function-to-function transfer using sphere primitives to establish semantically meaningful categorical correspondences, which are learned in an unsupervised fashion without any expert knowledge. We showcase the effectiveness through extensive experiments in both simulators and the real world. Remarkably, our framework significantly outperforms several strong baseline methods in terms of density and reliability for generated grasps.