DRAPER: Towards a Robust Robot Deployment and Reliable Evaluation for Quasi-Static Pick-and-Place Cloth-Shaping Neural Controllers

TL;DR

This paper introduces the DRAPER framework, enabling reliable real-world evaluation of cloth-manipulation neural controllers trained in simulation, addressing simulation-to-reality gaps and hardware limitations for more consistent comparisons.

Contribution

The study presents DRAPER, a comprehensive framework that improves real-world deployment and evaluation of cloth neural controllers by addressing grasping errors and perception gaps.

Findings

DRAPER enables consistent real-world testing across different controllers and robots.

The framework effectively addresses grasping errors and perception discrepancies.

Results demonstrate improved robustness and generalizability of cloth manipulation controllers.

Abstract

Comparing robotic cloth-manipulation systems in a real-world setup is challenging. The fidelity gap between simulation-trained cloth neural controllers and real-world operation hinders the reliable deployment of these methods in physical trials. Inconsistent experimental setups and hardware limitations among different approaches obstruct objective evaluations. This study demonstrates a reliable real-world comparison of different simulation-trained neural controllers on both flattening and folding tasks with different types of fabrics varying in material, size, and colour. We introduce the DRAPER framework to enable this comprehensive study, which reliably reflects the true capabilities of these neural controllers. It specifically addresses real-world grasping errors, such as misgrasping and multilayer grasping, through real-world adaptations of the simulation environment to provide data trajectories that closely reflect real-world grasping scenarios. It also employs a special set of vision processing techniques to close the simulation-to-reality gap in the perception. Furthermore, it achieves robust grasping by adopting a tweezer-extended gripper and a grasping procedure. We demonstrate DRAPER's generalisability across different deep-learning methods and robotic platforms, offering valuable insights to the cloth manipulation research community.