Bimanual Shelf Picking Planner Based on Collapse Prediction

Tomohiro Motoda*, Petit Damien, Weiwei Wan, and Kensuke Harada
Osaka University
IEEE CASE 2021 Accepted
*Corresponding author
Paper Code arXiv
MY ALT TEXT

A Fully Convolutional Networks to infer the pixel- wise probability map of the collapsing region while extracting a selected object from a shelf

Abstract

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 objects. We confirmed that the proposed method achieves more than 80% success rate for safe extraction by real-world experiments using a dual-arm manipulator.

Video Presentation

BibTeX

@inproceedings{motoda2021collapse,
        author={Motoda, Tomohiro and Petit, Damien and Wan, Weiwei and Harada, Kensuke},
        booktitle={2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)}, 
        title={Bimanual Shelf Picking Planner Based on Collapse Prediction}, 
        year={2021},
        volume={},
        number={},
        pages={510-515},
        doi={10.1109/CASE49439.2021.9551507}
      }