Bimanual Shelf Picking Planner Based on Collapse Prediction
This addresses a specific challenge in logistics warehouses for robots, but is incremental as it builds on prior rearrangement methods by adding bimanual support.
The paper tackled the problem of robots safely extracting objects from cluttered shelves without causing collapses, and achieved over 80% success rate in real-world experiments using a dual-arm manipulator.
In logistics warehouse, since many objects are randomly stacked on shelves, it becomes difficult for a robot to safely extract one of the objects without other objects falling from the shelf. In previous works, a robot needed to extract the target object after rearranging the neighboring objects. In contrast, humans extract an object from a shelf while supporting other neighboring objects. In this paper, we propose a bimanual manipulation planner based on collapse prediction trained with data generated from a physics simulator, which can safely extract a single object while supporting the other object. We confirmed that the proposed method achieves more than 80% success rate for safe extraction by real-world experiments using a dual-arm manipulator.