用多模态大模型实现布料智能分类与选择，提升纺织机器人精度。
MLLM-Fabric: Multimodal Large Language Model-Driven Robotic Framework for Fabric Sorting and Selection
- 基于多模态大模型与视觉触觉数据，实现布料属性排序。
- 在220种布料上验证，性能优于现有视觉语言模型。
- 适合智能制造、智能零售领域研究者参考。
在机器人纺织制造、服装生产和智能零售中，选择合适的布料对满足功能与质量要求至关重要。我们提出MLLM-Fabric，一个基于多模态大语言模型（MLLM）的布料分类与选择机器人框架。该系统构建于多模态机器人平台之上，通过监督微调和解释引导的蒸馏方法训练，用于布料属性排序。我们还发布了包含220种多样布料的数据集，每种布料均配有RGB图像以及同步的视觉-触觉和压力数据。实验表明，Fabric-Llama-90B在属性排序和选择可靠性方面均持续优于预训练的视觉-语言基线模型。代码与数据集已公开：https://github.com/limanwang/MLLM-Fabric。
原文摘要 · Abstract (English)
Choosing appropriate fabrics is critical for meeting functional and quality demands in robotic textile manufacturing, apparel production, and smart retail. We propose MLLM-Fabric, a robotic framework leveraging multimodal large language models (MLLMs) for fabric sorting and selection. Built on a multimodal robotic platform, the system is trained through supervised fine-tuning and explanation-guided distillation to rank fabric properties. We also release a dataset of 220 diverse fabrics, each with RGB images and synchronized visuotactile and pressure data. Experiments show that our Fabric-Llama-90B consistently outperforms pretrained vision-language baselines in both attribute ranking and selection reliability. Code and dataset are publicly available at https://github.com/limanwang/MLLM-Fabric.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。