Knitting Robots: A Deep Learning Approach for Reverse-Engineering Fabric Patterns
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912335080194048 |
|---|---|
| author | Sheng, Haoliang Cai, Songpu Zheng, Xingyu Lau, Meng Cheng |
| author_facet | Sheng, Haoliang Cai, Songpu Zheng, Xingyu Lau, Meng Cheng |
| contents | Knitting, a cornerstone of textile manufacturing, is uniquely challenging to automate, particularly in terms of converting fabric designs into precise, machine-readable instructions. This research bridges the gap between textile production and robotic automation by proposing a novel deep learning-based pipeline for reverse knitting to integrate vision-based robotic systems into textile manufacturing. The pipeline employs a two-stage architecture, enabling robots to first identify front labels before inferring complete labels, ensuring accurate, scalable pattern generation. By incorporating diverse yarn structures, including single-yarn (sj) and multi-yarn (mj) patterns, this study demonstrates how our system can adapt to varying material complexities. Critical challenges in robotic textile manipulation, such as label imbalance, underrepresented stitch types, and the need for fine-grained control, are addressed by leveraging specialized deep-learning architectures. This work establishes a foundation for fully automated robotic knitting systems, enabling customizable, flexible production processes that integrate perception, planning, and actuation, thereby advancing textile manufacturing through intelligent robotic automation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14007 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Knitting Robots: A Deep Learning Approach for Reverse-Engineering Fabric Patterns Sheng, Haoliang Cai, Songpu Zheng, Xingyu Lau, Meng Cheng Robotics Machine Learning Knitting, a cornerstone of textile manufacturing, is uniquely challenging to automate, particularly in terms of converting fabric designs into precise, machine-readable instructions. This research bridges the gap between textile production and robotic automation by proposing a novel deep learning-based pipeline for reverse knitting to integrate vision-based robotic systems into textile manufacturing. The pipeline employs a two-stage architecture, enabling robots to first identify front labels before inferring complete labels, ensuring accurate, scalable pattern generation. By incorporating diverse yarn structures, including single-yarn (sj) and multi-yarn (mj) patterns, this study demonstrates how our system can adapt to varying material complexities. Critical challenges in robotic textile manipulation, such as label imbalance, underrepresented stitch types, and the need for fine-grained control, are addressed by leveraging specialized deep-learning architectures. This work establishes a foundation for fully automated robotic knitting systems, enabling customizable, flexible production processes that integrate perception, planning, and actuation, thereby advancing textile manufacturing through intelligent robotic automation. |
| title | Knitting Robots: A Deep Learning Approach for Reverse-Engineering Fabric Patterns |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2504.14007 |