Language Guided Robotic Grasping with Fine-Grained Instructions

Qiang Sun,Haitao Lin,Ying Fu,Yanwei Fu,Xiangyang Xue,Qiang Sun,Haitao Lin,Ying Fu,Yanwei Fu,Xiangyang Xue

Given a single RGB image and the attribute-rich language instructions, this paper investigates the novel problem of using Fine-grained instructions for the Language guided robotic Grasping (FLarG). This problem is made challenging by learning fine-grained language descriptions to ground target objects. Recent advances have been made in visually grounding the objects simply by several coarse attrib...