Graph-Transporter: A Graph-based Learning Method for Goal-Conditioned Deformable Object Rearranging Task

TL;DR

Graph-Transporter introduces a graph-based learning framework utilizing graph convolutional networks and FCN architecture to effectively solve goal-conditioned deformable object rearranging tasks from visual input.

Contribution

The paper presents a novel graph-based representation and a fully convolutional network architecture for deformable object manipulation, improving effectiveness and generality.

Findings

Effective graph representation of deformable objects.

Successful goal-conditioned rearranging from visual input.

Framework outperforms existing methods in experiments.

Abstract

Rearranging deformable objects is a long-standing challenge in robotic manipulation for the high dimensionality of configuration space and the complex dynamics of deformable objects. We present a novel framework, Graph-Transporter, for goal-conditioned deformable object rearranging tasks. To tackle the challenge of complex configuration space and dynamics, we represent the configuration space of a deformable object with a graph structure and the graph features are encoded by a graph convolution network. Our framework adopts an architecture based on Fully Convolutional Network (FCN) to output pixel-wise pick-and-place actions from only visual input. Extensive experiments have been conducted to validate the effectiveness of the graph representation of deformable object configuration. The experimental results also demonstrate that our framework is effective and general in handling goal-conditioned deformable object rearranging tasks.