Deep Reinforcement Learning Based on Local GNN for Goal-Conditioned Deformable Object Rearranging

Object rearranging is one of the most common deformable manipulation tasks, where the robot needs to rearrange a deformable object into a goal configuration. Previous studies focus on designing an expert system for each specific task by model-based or data-driven approaches and the application scenarios are therefore limited. Some research has been attempting to design a general framework to obtain more advanced manipulation capabilities for deformable rearranging tasks, with lots of progress achieved in simulation. However, transferring from simulation to reality is difficult due to the limitation of the end-to-end CNN architecture. To address these challenges, we design a local GNN (Graph Neural Network) based learning method, which utilizes two representation graphs to encode keypoints detected from images. Self-attention is applied for graph updating and cross-attention is applied for generating manipulation actions. Extensive experiments have been conducted to demonstrate that our framework is effective in multiple 1-D (rope, rope ring) and 2-D (cloth) rearranging tasks in simulation and can be easily transferred to a real robot by fine-tuning a keypoint detector.

I. Introduction

Deformable objects can be seen in many automating tasks such as food handling, assistive dressing and the manufacturing, assembly and sorting of garment [1]–[3]. Rearranging deformable objects is one of the most investigated and fundamental deformable manipulation tasks, where the robot is expected to infer a manipulation sequence to rearrange a deformable object into a goal configuration. Different from rigid object manipulation [4]–[6], rearranging deformable objects poses two new challenges. The first challenge lies in the high dimensionality of the configuration space [7], which makes the observation and representation of deformable objects more complicated for efficient manipulation planning. The second challenge comes from the complex and non-linear dynamics of deformable materials [8], which makes the movements of deformable objects hard to predict.