SAGE-LLM：面向安全且可泛化的LLM控制器，结合模糊-CBF验证和图结构知识检索用于无人机决策
SAGE-LLM: Towards Safe and Generalizable LLM Controller with Fuzzy-CBF Verification and Graph-Structured Knowledge Retrieval for UAV Decision
AI总结：
SAGE-LLM通过模糊-CBF验证和图结构知识检索，提升无人机决策的安全性和泛化能力，无需在线训练即可在复杂环境中保持性能。
摘要：
在无人机动态决策中，复杂且多变的危险因素对算法的泛化能力提出了严峻挑战。尽管LLM提供了语义理解和场景泛化能力，但其缺乏特定于无人机控制的知识和形式化安全保证，限制了其直接应用。为弥合这一差距，本文提出了一种基于LLM的无训练双层决策架构，整合高层安全规划与低层精确控制。该框架引入了三个关键贡献：1）一种基于语义增强动作的模糊控制屏障函数验证机制，为LLM输出提供可证明的安全认证。2）一种基于星形分层图的检索增强生成系统，实现高效、弹性且可解释的场景适应。3）在追逐-躲避场景中系统性地进行实验验证，面对未知障碍和突发威胁，证明我们的SAGE-LLM在不进行在线训练的情况下，保持性能的同时显著提升了安全性和泛化能力。所提出的框架表现出强大的可扩展性，暗示其在更广泛的身体智能系统和安全关键控制领域中的潜在应用。
英文摘要：
In UAV dynamic decision, complex and variable hazardous factors pose severe challenges to the generalization capability of algorithms. Despite offering semantic understanding and scene generalization, Large Language Models (LLM) lack domain-specific UAV control knowledge and formal safety assurances, restricting their direct applicability. To bridge this gap, this paper proposes a train-free two-layer decision architecture based on LLMs, integrating high-level safety planning with low-level precise control. The framework introduces three key contributions: 1) A fuzzy Control Barrier Function verification mechanism for semantically-augmented actions, providing provable safety certification for LLM outputs. 2) A star-hierarchical graph-based retrieval-augmented generation system, enabling efficient, elastic, and interpretable scene adaptation. 3) Systematic experimental validation in pursuit-evasion scenarios with unknown obstacles and emergent threats, demonstrating that our SAGE-LLM maintains performance while significantly enhancing safety and generalization without online training. The proposed framework demonstrates strong extensibility, suggesting its potential for generalization to broader embodied intelligence systems and safety-critical control domains.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
