一句话：提出基于 LLM 的方法、工具与分类法，自动识别自适应机器人中的不确定性，并分享工业实践体验。
自适应机器人等复杂系统存在多种不确定性，其潜在影响与缓解策略难以被研究人员和工业人员理解，如何系统、自动地识别这些不确定性是一大挑战。作为欧盟 RoboSAPIENS 项目的一部分，本文提出一种基于大语言模型（LLM）的不确定性识别方法，结合提示技术，并实现为工具，同时给出不确定性分类法。该技术简报将介绍 LLM 辅助的不确定性识别、提示技巧、分类法、动手工具环节，以及与工业专业人员互动的经验，目标是帮助从业人员识别不确定性，提升自适应机器人的可信度。
Understanding uncertainties present in complex systems, such as self-adaptive robotics, their potential impacts, and mitigation strategies has always been a major challenge for researchers and industry professionals. This hands-on technical briefing will present novel approaches, a tool, and a taxonomy to systematically and automatically identify uncertainty in self-adaptive robotics using large language models (LLMs). The content of this briefing is being developed as part of an EU project named RoboSAPIENS, which aims at ensuring the trustworthiness of self-adaptive robots. To assist industry professionals in the uncertainty identification process, we developed an LLM-based uncertainty identification approach and implemented it in a tool. This briefing will cover LLM-based uncertainty identification, prompting techniques, uncertainty taxonomy, hands-on tool sessions, and experiences from our interactions with industry professionals.