首页 >

大语言模型驱动的多无人机协同任务规划(飞行器协同作战技术专栏)

钟建鑫1,孙景亮2,罗野2,李俊志2,龙腾2   

  1. 1. 北京理工大学宇航学院
    2. 北京理工大学
  • 收稿日期:2026-03-24 修回日期:2026-10-21 出版日期:2026-10-23 发布日期:2026-10-23
  • 通讯作者: 孙景亮
  • 基金资助:
    国家自然科学基金;北京市科技新星

LLM-Driven Collaborative Task Planning for Multi-UAV Systems

  • Received:2026-03-24 Revised:2026-10-21 Online:2026-10-23 Published:2026-10-23
  • Contact: Jing-Liang Sun

摘要: 以大语言模型(Large Language Model, LLM)为代表的生成式人工智能具备任务语义理解与复杂推理等优势,在多无人机协同任务规划领域展现出巨大的发展潜力。然而,受限于上下文长度限制与规划知识图谱缺失,基于大语言模型的集群任务规划仍面临规划约束难以满足、任务执行意图易漂移以及动态环境适应性不足等问题。针对上述挑战,本文提出一种基于大语言模型驱动的多无人机协同规划方法,构建“顶层任务决策—态势感知分析—底层指令执行”多智能体协作框架。顶层结合领域知识库与任务规划工具,解析任务语义输入为图结构化原子任务序列,实现从抽象语义意图到可执行动作的高效映射;构建基于上下文管理的动态闭环执行机制,实时感知监控态势变化,采用增量调整策略应对突发任务,确保任务执行的长程逻辑一致性与动态适应性;设计“监督微调+强化学习”的大模型微调方案,提升模型在多无人机任务场景下的逻辑推理能力与决策一致性。仿真结果表明,相较于经典LLM自主决策框架ReAct,任务成功率提升了约30%,工具调用成功率达到95.2%,能够高效完成语义输入到多无人机自主协同任务执行的完整闭环。

关键词: 大语言模型, 多智能体系统, 任务规划, 无人机集群, 模型微调

Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in semantic understanding and complex rea-soning, showing great potential for multi-UAV cooperative task planning. However, existing LLM-driven planning ap-proaches still face significant challenges, including constraint violations, semantic drift during long-horizon execution, and limited adaptability to dynamic environments due to insufficient structured planning mechanisms and constrained context capacity. To address these issues, this paper proposes an LLM-driven collaborative task planning framework for multi-UAV systems based on a multi-agent architecture. The framework integrates task decision, situational awareness analysis, and UAV-level execution into a unified cooperative process. High-level semantic instructions are transformed into graph-structured atomic task representations, enabling a structured mapping from abstract intentions to executable actions. A context-aware closed-loop mechanism is introduced to continuously monitor environmental changes and support incremental task adjustment under unexpected events, thereby maintaining logical consistency and improving dynamic responsiveness during long-horizon missions. Furthermore, a two-stage alignment strategy combining supervised fine-tuning and reinforcement learning is adopted to enhance the reasoning capability and deci-sion reliability of the LLM in multi-UAV task scenarios. Simulation results demonstrate that, compared with the classi-cal LLM-based planning framework ReAct, the proposed method improves task success rate by approximately 30% and achieves a 95.2% tool invocation success rate, effectively realizing a complete closed-loop process from semantic task input to autonomous multi-UAV cooperative execution.

Key words: large language models, multi-agent system, task planning, UAV swarm, model fine-tuning