让无人机群在救援与安防中可靠自主，关键在人机协同设计。
Agentic AI for Safety-critical Multi-drone Systems: Challenges and Opportunities
- 以用户参与式设计构建可信赖的智能无人机系统
- 提出面向真实场景的多无人机自主决策框架
- 适合应急响应与关键设施监控领域的研究者
多无人机系统正被用于搜救（SAR）和关键基础设施监控等安全敏感任务。然而，实际应用受限于自主性能，更在于如何将智能体行为融入专业工作流程：操作员需在不确定性、时间压力和责任约束下理解、信任并管控自动化系统。本文综合了两项正在进行的研究——NAMUR（探索大语言模型支持的机器人在搜救与灭火中的应用）和PERSIST（探索关键设施持续监控与安保的无人机运行）——提出，智能体人工智能应作为社会技术系统设计问题来对待，界面、监督机制与评估方法与算法同等重要。我们倡导一种以人为中心、参与式、迭代的研究路径，通过多轮原型验证，揭示利益相关者需求，逐步塑造智能体能力，并为其他安全敏感场景提供可复用的原型系统与评估策略。
原文摘要 · Abstract (English)
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.
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。