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.

翻译：本文聚焦于遮挡场景中的目标导向抓取任务，其中目标物体由二值掩码指定，目标是以尽可能少的机器人操作次数抓取该物体。大多数现有方法依赖推动-抓取协同来完成此任务。为构建更强大的目标导向抓取流程，我们提出了MPGNet——一个用于学习移动、推动和抓取动作之间协同作用的三分支网络。我们还提出了一种多阶段训练策略来训练MPGNet，该网络包含分别对应三种动作的三个策略网络。通过仿真和真实世界实验验证了我们方法的有效性。