Instance Segmentation of Visible and Occluded Regions for Finding and Picking Target from a Pile of Objects
This addresses the challenge of robotic manipulation in cluttered environments, enabling more efficient target retrieval, though it appears incremental as it builds on existing instance segmentation methods.
The paper tackles the problem of picking a target object from a cluttered pile by segmenting both visible and occluded regions, using a novel 'relook' architecture and image synthesis to handle new objects without human annotations. Experimental results show the effectiveness of the relook architecture compared to conventional models and the image synthesis compared to human-annotated datasets, with demonstrations on a real robot.
We present a robotic system for picking a target from a pile of objects that is capable of finding and grasping the target object by removing obstacles in the appropriate order. The fundamental idea is to segment instances with both visible and occluded masks, which we call `instance occlusion segmentation'. To achieve this, we extend an existing instance segmentation model with a novel `relook' architecture, in which the model explicitly learns the inter-instance relationship. Also, by using image synthesis, we make the system capable of handling new objects without human annotations. The experimental results show the effectiveness of the relook architecture when compared with a conventional model and of the image synthesis when compared to a human-annotated dataset. We also demonstrate the capability of our system to achieve picking a target in a cluttered environment with a real robot.