DeformerNet: A Deep Learning Approach to 3D Deformable Object Manipulation
This addresses the challenge of precise 3D shape control in robotics, which is incremental as it builds on existing deep learning methods but applies them to a specific domain problem.
The paper tackles the problem of 3D deformable object manipulation by proposing DeformerNet, a deep learning approach that uses 3D point clouds as state representation and maps them to robot end-effector positions, achieving direct control over object shape without relying on 2D approximations or feature points.
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.