A Joint Network for Grasp Detection Conditioned on Natural Language Commands
This addresses the issue of ambiguity in overlapping multi-object cases for robotics and human-robot interaction, representing an incremental improvement over cascaded methods.
The paper tackles the problem of grasping a target object based on natural language commands by proposing CGNet, which directly outputs grasps from RGB images and text, outperforming a cascaded baseline by a large margin on a generated test set.
We consider the task of grasping a target object based on a natural language command query. Previous work primarily focused on localizing the object given the query, which requires a separate grasp detection module to grasp it. The cascaded application of two pipelines incurs errors in overlapping multi-object cases due to ambiguity in the individual outputs. This work proposes a model named Command Grasping Network(CGNet) to directly output command satisficing grasps from RGB image and textual command inputs. A dataset with ground truth (image, command, grasps) tuple is generated based on the VMRD dataset to train the proposed network. Experimental results on the generated test set show that CGNet outperforms a cascaded object-retrieval and grasp detection baseline by a large margin. Three physical experiments demonstrate the functionality and performance of CGNet.