GPT-Fabric: Smoothing and Folding Fabric by Leveraging Pre-Trained Foundation Models

TL;DR

GPT-Fabric leverages pre-trained foundation models to enable robots to perform fabric smoothing and folding tasks with high precision, achieving state-of-the-art results without specialized training data.

Contribution

The paper introduces GPT-Fabric, a novel approach that uses foundation models for fabric manipulation, eliminating the need for fabric-specific training datasets.

Findings

Matches state-of-the-art in fabric smoothing

Achieves comparable performance in fabric folding without training on fabric data

Demonstrates successful physical robot experiments with high-precision manipulation

Abstract

Fabric manipulation has applications in folding blankets, handling patient clothing, and protecting items with covers. It is challenging for robots to perform fabric manipulation since fabrics have infinite-dimensional configuration spaces, complex dynamics, and may be in folded or crumpled configurations with severe self-occlusions. Prior work on robotic fabric manipulation relies either on heavily engineered setups or learning-based approaches that create and train on robot-fabric interaction data. In this paper, we propose GPT-Fabric for the canonical tasks of fabric smoothing and folding, where GPT directly outputs an action informing a robot where to grasp and pull a fabric. We perform extensive experiments in simulation to test GPT-Fabric against prior methods for smoothing and folding. GPT-Fabric matches the state-of-the-art in fabric smoothing, and also achieves comparable performance with most prior fabric folding methods tested, even without explicitly training on a fabric-specific dataset (i.e., zero-shot manipulation). Furthermore, we apply GPT-Fabric in physical experiments over 10 smoothing and 12 folding rollouts. Our results suggest that GPT-Fabric is a promising approach for high-precision fabric manipulation tasks