Generalizable Category-Level Topological Structure Learning for Clothing Recognition in Robotic Grasping

Xingyu Zhu, Yan Wu, Zhiwen Tu, Haifeng Zhong, Yixing Gao

Attend In Person: Yes

Keywords: Clothing Recognition, Robotic Clothing Grasping

TL;DR: A category-level topological structure learning-based method for robotic clothing recognition and grasping.

Abstract: Recognizing various types of clothing is crucial for robotic clothing manipulation tasks. Existing classification models primarily focus on clothing color and texture while overlooking structural features, limiting their ability to distinguish between deformable clothing categories with similar color and texture. Moreover, these models heavily rely on manually annotated labels, making it difficult to accurately recognize unseen clothing items with new colors or textures. To address these challenges, we propose a novel topological structure representation and optimization strategy for category-level clothing structural feature learning. Then, we introduce a fabric-specific grasping position estimation method and develop a corresponding robotic grasping system capable of selecting and grasping specified clothing items based on user instructions. Extensive real-world robotic experiments demonstrate the effectiveness of our system.

Submission Number: 8