# DeFNet: Deconstructed Strategy for Multi-step Fabric Folding Tasks

## TL;DR

DeFNet introduces a modular approach to robotic fabric folding by decomposing the task into simpler sub-tasks, utilizing a latent space planning, flow-based action calculation, and iterative execution, demonstrated in simulation and real systems.

## Contribution

The paper presents a novel deconstruction strategy and a multi-module network for efficient multi-step fabric folding by robots, combining planning, action execution, and iterative refinement.

## Key findings

- Outperforms three baseline methods in simulation.
- Successfully applied to a real robotic system.
- Demonstrates effective multi-step fabric folding.

## Abstract

Fabric folding through robots is complex and challenging due to the deformability of fabric. Based on deconstruction strategy, we split the complex fabric folding task into three relatively simple sub-tasks, and propose a Deconstructed Fabric Folding Network (DeFNet), including corresponding three modules to solve them. (1) We use the Folding Planning Module (FPM), which is based on Latent Space Roadmap, to infer the most straight folding intermediate states from the start to the goal in latent space. (2) We utilize the flow-based approach, Folding Action Module (FAM), to calculate the action coordinates and execute them to reach the inferred intermediate state. (3) We introduce an Iterative Interactive Module (IIM) for fabric folding tasks, which can iteratively execute the FPM and FAM after every grasp-and-place action until the fabric reaches the goal. Experimentally, We demonstrated our method on multi-step fabric folding tasks against three baselines in simulation. We also apply the method to an existing robotic system and present its performance.