ClothPPO: A Proximal Policy Optimization Enhancing Framework for Robotic Cloth Manipulation with Observation-Aligned Action Spaces

TL;DR

ClothPPO introduces a policy gradient framework with observation-aligned action spaces to improve robotic cloth unfolding, leveraging pre-training and PPO to enhance performance in soft-body manipulation tasks.

Contribution

The paper presents ClothPPO, a novel policy gradient approach with large, observation-aligned action spaces for improved cloth manipulation in robotics.

Findings

Enhanced cloth unfolding performance over state-of-the-art methods.

Effective use of PPO with large action spaces in cloth manipulation.

Improved surface area coverage in cloth unfolding tasks.

Abstract

Vision-based robotic cloth unfolding has made great progress recently. However, prior works predominantly rely on value learning and have not fully explored policy-based techniques. Recently, the success of reinforcement learning on the large language model has shown that the policy gradient algorithm can enhance policy with huge action space. In this paper, we introduce ClothPPO, a framework that employs a policy gradient algorithm based on actor-critic architecture to enhance a pre-trained model with huge 10^6 action spaces aligned with observation in the task of unfolding clothes. To this end, we redefine the cloth manipulation problem as a partially observable Markov decision process. A supervised pre-training stage is employed to train a baseline model of our policy. In the second stage, the Proximal Policy Optimization (PPO) is utilized to guide the supervised model within the observation-aligned action space. By optimizing and updating the strategy, our proposed method increases the garment's surface area for cloth unfolding under the soft-body manipulation task. Experimental results show that our proposed framework can further improve the unfolding performance of other state-of-the-art methods.