Fabric folding through robots is complex and challenging due to the deformability of the fabric. Based on the deconstruction strategy, we split the tough multi-step fabric folding task into three relatively simple sub-tasks and propose a Deconstructed Fabric Folding Network (DeFNet), including three corresponding modules to solve them. (1) We use the Folding Planning Module (FPM), which is based on the Latent Space Roadmap, to infer the shortest 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 multi-step 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 demonstrate our method on fabric folding tasks against three baselines in simulation. We also apply the method to an existing robotic system and present its performance.
Read full abstract