Mesh-based Dynamics with Occlusion Reasoning for Cloth Manipulation

TL;DR

This paper presents a system for cloth manipulation that uses mesh reconstruction, occlusion reasoning, and test-time finetuning to improve unfolding and flattening of crumpled cloth, outperforming prior methods.

Contribution

The novel integration of explicit occlusion reasoning with mesh-based dynamics and test-time self-supervised refinement for cloth manipulation.

Findings

Significant improvement over prior methods in cloth flattening and canonicalization.

Effective use of test-time finetuning to refine mesh reconstructions.

Robust handling of occlusions in cloth manipulation tasks.

Abstract

Self-occlusion is challenging for cloth manipulation, as it makes it difficult to estimate the full state of the cloth. Ideally, a robot trying to unfold a crumpled or folded cloth should be able to reason about the cloth's occluded regions. We leverage recent advances in pose estimation for cloth to build a system that uses explicit occlusion reasoning to unfold a crumpled cloth. Specifically, we first learn a model to reconstruct the mesh of the cloth. However, the model will likely have errors due to the complexities of the cloth configurations and due to ambiguities from occlusions. Our main insight is that we can further refine the predicted reconstruction by performing test-time finetuning with self-supervised losses. The obtained reconstructed mesh allows us to use a mesh-based dynamics model for planning while reasoning about occlusions. We evaluate our system both on cloth flattening as well as on cloth canonicalization, in which the objective is to manipulate the cloth into a canonical pose. Our experiments show that our method significantly outperforms prior methods that do not explicitly account for occlusions or perform test-time optimization. Videos and visualizations can be found on our $\href{https://sites.google.com/view/occlusion-reason/home}{\text{project website}}.$