6-DoF Contrastive Grasp Proposal Network
Xinghao Zhu,Lingfeng Sun,Yongxiang Fan,Masayoshi Tomizuka,Xinghao Zhu,Lingfeng Sun,Yongxiang Fan,Masayoshi Tomizuka
Proposing grasp poses for novel objects is an essential component for any robot manipulation task. Planning six degrees of freedom (DoF) grasps with a single camera, however, is challenging due to the complex object shape, incomplete object information, and sensor noise. In this paper, we present a 6-DoF contrastive grasp proposal network (CGPN) to infer 6-DoF grasps from a single-view depth image...