This paper focuses on target-oriented grasping in occluded scenes, where the target object is specified by a binary mask and the goal is to grasp the target object with as few robotic manipulations as possible. Most existing methods rely on a push-grasping synergy to complete this task. To deliver a more powerful target-oriented grasping pipeline, we present MPGNet, a three-branch network for learning a synergy between moving, pushing, and grasping actions. We also propose a multi-stage training strategy to train the MPGNet which contains three policy networks corresponding to the three actions. The effectiveness of our method is demonstrated via both simulated and real-world experiments.
@article{arxiv.2408.10525,
title = {MPGNet: Learning Move-Push-Grasping Synergy for Target-Oriented Grasping in Occluded Scenes},
author = {Dayou Li and Chenkun Zhao and Shuo Yang and Ran Song and Xiaolei Li and Wei Zhang},
journal= {arXiv preprint arXiv:2408.10525},
year = {2024}
}