发表机构
Aalborg University; University of Southern Denmark（奥尔堡大学; 南丹麦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对安全关键多无人机系统应用受限问题，结合NAMUR、PERSIST项目经验，提出将智能体AI作为社会技术设计问题，采用以人为本的迭代方法开发可迁移的概念验证系统与评估策略。
AI 中文摘要
多无人机系统正越来越多地被应用于搜索与救援（SAR）、关键基础设施监测等安全关键任务。然而，其在现实中的应用不仅受限于自主性能，还受限于将智能体行为集成到专业工作中的难度：操作人员必须在不确定性、时间压力和问责制下理解、信任并管控自动化系统。本文立场论文综合了两项正在开展的研究的目标与经验：NAMUR项目探索在SAR和消防场景中由大语言模型（LLM）支持的机器人控制，PERSIST项目探索用于关键基础设施站点监测与安保的持久无人机作业。我们认为，智能体人工智能应被视为一个社会技术设计问题，其中界面、监督机制和评估实践与算法同等重要。我们概述了一种以人为本、参与式且迭代的研究方法，旨在明确利益相关者需求、通过连续原型塑造智能体能力，并为其他安全关键场景生成可迁移的概念验证系统与评估策略。
英文摘要
Multi-drone systems are increasingly positioned for safety-critical missions such as search and rescue (SAR) and critical infrastructure monitoring. Yet, real-world adoption remains constrained not only by autonomy performance, but by the difficulty of integrating agentic behavior into professional work: operators must understand, trust, and govern automation under uncertainty, time pressure, and accountability. This position paper synthesizes the ambitions and lessons from two ongoing efforts: NAMUR, which explores LLM-supported robot control in SAR and firefighting contexts, and PERSIST, which explores persistent drone operations for monitoring and security at critical infrastructure sites. We argue that agentic AI should be approached as a socio-technical design problem, where interfaces, oversight mechanisms, and evaluation practices are as critical as algorithms. We outline a human-centered, participatory, and iterative research approach aimed at uncovering stakeholder needs, shaping agent capabilities through successive prototypes, and producing transferable proof-of-concept systems and evaluation strategies for other safety-critical contexts.
Comments9 pages, 4 figures, presented at the AgentCraft Workshop at IUI2026 Conference, https://agentcraft-iui.github.io/2026/ - CEUR-WS.org proceedings forthcoming
