📄 中文摘要
增强现实（AR）为工业机器人培训提供了强大的可视化能力，但现有接口仍然以静态为主，未能考虑学习者的多样化认知特征。研究提出了一种用于机器人培训的AR应用，并提出了一个多智能体AI框架，以实现静态可视化与教学智能之间的连接。对36名参与者进行的基线AR接口评估显示，尽管整体可用性较高，但任务持续时间和学习者特征的显著差异突显了动态适应的必要性。为此，提出了一个多智能体框架，以协调不同智能体的互动，从而实现个性化的学习体验。
超越静态指令：一种用于自适应增强现实机器人培训的多智能体 AI 框架
📄 English Summary
Beyond Static Instruction: A Multi-agent AI Framework for Adaptive Augmented Reality Robot Training
Augmented Reality (AR) provides powerful visualization capabilities for industrial robot training, yet existing interfaces remain predominantly static, failing to accommodate the diverse cognitive profiles of learners. This research presents an AR application for robot training and proposes a multi-agent AI framework designed to bridge the gap between static visualization and pedagogical intelligence. An evaluation of the baseline AR interface with 36 participants performing a robotic pick-and-place task revealed high overall usability; however, significant disparities in task duration and learner characteristics underscored the necessity for dynamic adaptation. To address this issue, a multi-agent framework is proposed to orchestrate the interactions of different agents, facilitating a personalized learning experience.