ICGNet: A Unified Approach for Instance-Centric Grasping
This addresses the challenge of accurate grasping for robotics tasks like assembly and household use, but it is incremental as it builds on existing grasp detection methods with a more composable approach.
The paper tackles the problem of robotic grasping in cluttered environments by introducing ICGNet, an end-to-end architecture that generates instance-centric representations from pointcloud data for object reconstruction and grasp detection, showing superior performance on synthetic datasets and real-world applicability.
Accurate grasping is the key to several robotic tasks including assembly and household robotics. Executing a successful grasp in a cluttered environment requires multiple levels of scene understanding: First, the robot needs to analyze the geometric properties of individual objects to find feasible grasps. These grasps need to be compliant with the local object geometry. Second, for each proposed grasp, the robot needs to reason about the interactions with other objects in the scene. Finally, the robot must compute a collision-free grasp trajectory while taking into account the geometry of the target object. Most grasp detection algorithms directly predict grasp poses in a monolithic fashion, which does not capture the composability of the environment. In this paper, we introduce an end-to-end architecture for object-centric grasping. The method uses pointcloud data from a single arbitrary viewing direction as an input and generates an instance-centric representation for each partially observed object in the scene. This representation is further used for object reconstruction and grasp detection in cluttered table-top scenes. We show the effectiveness of the proposed method by extensively evaluating it against state-of-the-art methods on synthetic datasets, indicating superior performance for grasping and reconstruction. Additionally, we demonstrate real-world applicability by decluttering scenes with varying numbers of objects.