Uncertainty-Aware Suction Grasping for Cluttered Scenes

In this work, we present a multi-stage pipeline that aims to accurately predict suction grasps for objects with varying properties in cluttered and complex scenes. Existing methods face difficulties in generalizing to unseen objects and effectively handling noisy depth/point cloud data, which often leads to inaccurate grasp predictions. To address these challenges, we utilize the Unseen Object Instance Segmentation (UOIS) technique to segment all objects and extract their instance-level point clouds. Additionally, we introduce the Uncertainty-aware Instance-level Scoring Network (UISN) to generate point-wise suction scores with uncertainties for each object. By calibrating the predicted scores using the estimated uncertainties, we further enhance their reliability for unseen objects and noisy data. Finally, the grasping candidates are ranked based on the calibrated scores, then the most promising grasps can be executed. Our approach achieves state-of-the-art performance on the SuctionNet-1Billion benchmark and demonstrates real robotic grasping, showcasing its accuracy and robustness in cluttered scenes.