Center Direction Network for Grasping Point Localization on Cloths

TL;DR

This paper introduces CeDiRNet-3DoF, a deep learning model for grasp point detection on cloth objects, and presents the ViCoS Towel Dataset as a new benchmark, achieving top performance in cloth manipulation tasks.

Contribution

The paper presents a novel deep learning model for cloth grasping and introduces a comprehensive benchmark dataset to facilitate future research.

Findings

CeDiRNet-3DoF outperforms state-of-the-art methods.

The ViCoS Towel Dataset enables robust training and evaluation.

Model demonstrates strong real-world robustness.

Abstract

Object grasping is a fundamental challenge in robotics and computer vision, critical for advancing robotic manipulation capabilities. Deformable objects, like fabrics and cloths, pose additional challenges due to their non-rigid nature. In this work, we introduce CeDiRNet-3DoF, a deep-learning model for grasp point detection, with a particular focus on cloth objects. CeDiRNet-3DoF employs center direction regression alongside a localization network, attaining first place in the perception task of ICRA 2023's Cloth Manipulation Challenge. Recognizing the lack of standardized benchmarks in the literature that hinder effective method comparison, we present the ViCoS Towel Dataset. This extensive benchmark dataset comprises 8,000 real and 12,000 synthetic images, serving as a robust resource for training and evaluating contemporary data-driven deep-learning approaches. Extensive evaluation revealed CeDiRNet-3DoF's robustness in real-world performance, outperforming state-of-the-art methods, including the latest transformer-based models. Our work bridges a crucial gap, offering a robust solution and benchmark for cloth grasping in computer vision and robotics. Code and dataset are available at: https://github.com/vicoslab/CeDiRNet-3DoF