In this paper, we propose a novel approach to 3D deformable object manipulation leveraging a deep neural network called DeformerNet. Controlling the shape of a 3D object requires an effective state representation that can capture the full 3D geometry of the object. Current methods work around this problem by defining a set of feature points on the object or only deforming the object in 2D image space, which does not truly address the 3D shape control problem. Instead, we explicitly use 3D point clouds as the state representation and apply Convolutional Neural Network on point clouds to learn the 3D features. These features are then mapped to the robot end-effector's position using a fully-connected neural network. Once trained in an end-to-end fashion, DeformerNet directly maps the current point cloud of a deformable object, as well as a target point cloud shape, to the desired displacement in robot gripper position. In addition, we investigate the problem of predicting the manipulation point location given the initial and goal shape of the object.
翻译:在本文中,我们提出了一个3D变形物体操纵的新办法, 利用名为 DeextenNet 的深神经网络进行3D变形物体操纵。 控制 3D 物体的形状需要有效的状态代表, 能够捕捉到该物体的全部 3D 几何。 当前的方法是围绕这个问题开展工作, 定义物体上的一系列特征点, 或只在 2D 图像空间里对物体进行变形, 这并不能真正解决 3D 形状控制问题 。 相反, 我们明确使用 3D 点云作为国家代表, 并在点云上应用 Convolution 神经网络来学习 3D 特征 。 这些特征然后使用完全连接的神经网络绘制到机器人的终端效应位置 。 一旦受过培训, 将一个变形物体的当前点云以及一个目标点云形状直接绘制到机器人控制器的位置。 此外, 我们调查根据该物体的初始和目标形状预测操纵点位置的问题 。