DRAPER: Towards a Robust Robot Deployment and Reliable Evaluation for Quasi-Static Pick-and-Place Cloth-Shaping Neural Controllers
- 17 August 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3532-3539
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 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. Please visit our project website https://sites.google.com/view/draper-pnp for demonstration videos and code.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- PlaNet-ClothPick: Effective Fabric Flattening Based on Latent Dynamic Planning2024
- Segment Anything2023
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion2023
- Data-Driven Robotic Manipulation of Cloth-like Deformable Objects: The Present, Challenges and Future ProspectsSensors, 2023
- Foldsformer: Learning Sequential Multi-Step Cloth Manipulation With Space-Time AttentionIEEE Robotics and Automation Letters, 2022
- LazyDAgger: Reducing Context Switching in Interactive Imitation Learning2021
- VisuoSpatial Foresight for physical sequential fabric manipulationAutonomous Robots, 2021
- Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor2020
- Domain randomization for transferring deep neural networks from simulation to the real world2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015