In this paper, we explore whether a robot can learn to regrasp a diverse set of objects to achieve various desired grasp poses. Regrasping is needed whenever a robot's current grasp pose fails to perform desired manipulation tasks. Endowing robots with such an ability has applications in many domains such as manufacturing or domestic services. Yet, it is a challenging task due to the large diversity of geometry in everyday objects and the high dimensionality of the state and action space. In this paper, we propose a system for robots to take partial point clouds of an object and the supporting environment as inputs and output a sequence of pick-and-place operations to transform an initial object grasp pose to the desired object grasp poses. The key technique includes a neural stable placement predictor and a regrasp graph based solution through leveraging and changing the surrounding environment. We introduce a new and challenging synthetic dataset for learning and evaluating the proposed approach. In this dataset, we show that our system is able to achieve 73.3% success rate of regrasping diverse objects.
翻译:在本文中, 我们探讨一个机器人是否可以学会重塑一组不同的对象, 以实现各种想要的抓取配置 。 当一个机器人的当前抓取显示无法执行想要的操作任务时, 需要重新校正 。 拥有这种能力的机器人在制造或家庭服务等许多领域都有应用。 然而, 由于日常物体的几何差异很大, 以及状态和动作空间的高度维度, 这是一项具有挑战性的任务 。 在本文中, 我们提议一个机器人系统, 以一个对象的局部点云和辅助环境作为输入和输出一个选择和位置操作序列, 以将最初的物体抓取显示转换为想要的物体抓取配置 。 关键技术包括一个神经稳定定位预测器, 以及通过利用和改变周围环境来重新绘制图形解决方案 。 我们引入了一个新的具有挑战性的合成数据集, 用于学习和评估拟议的方法 。 在此数据集中, 我们显示我们的系统能够实现73. 3% 的重塑多种对象的成功率 。