返回
A physics-informed embodied intelligence framework for smart garment manufacturing
DOI:10.1016/j.jmsy.2026.01.015.png)
摘要
En 中文
• This paper presents a physics-informed embodied intelligence framework for planning and robot manipulation in smart garment manufacturing. • The task-aware planning module enables robots to decompose diverse instructions into executable subtasks among production scenes. • The physics-informed manipulation module guided by VLM agents can optimize Bernoulli-based pneumatic gripper distribution for fabric handling. • Experimental results in real-world garment scenarios demonstrate flexibility, advancing the development of human-centric smart manufacturing systems.
期刊
IF:
14.2
论文数:
2.7K
被引数:
1.6W
机构
引用论文
Embodied intelligence in manufacturing: leveraging large language models for autonomous industrial robotics制造业中的具体化智能: 利用大型语言模型实现自主工业机器人
A design framework for high-fidelity human-centric digital twin of collaborative work cell in Industry 5.0面向Industry 5.0的协作工作单元高保真度人本数字孪生设计框架
Tracking cloth deformation: A novel dataset for closing the sim-to-real gap for robotic cloth manipulation learning追踪布料变形:用于缩小机器人布料操作学习中的模拟与现实差距的一个新型数据集
Proactive human-robot collaboration: Mutual-cognitive, predictable, and self-organising perspectives主动人机协作: 相互认知,可预测和自组织的观点

