用语言指令控制多无人机，实现稳定可靠复杂任务
UAVGENT: A Language-Guided Distributed Control Framework
- 分三层架构：人发自然语言指令，大模型动态解析修正任务，底层控制器仅靠局部信息跟踪
- 理论证明在有界扰动和离散跳跃参考下仍能保证追踪性能
- 适合需要高可靠性与人类交互的无人机集群系统
我们研究了多无人机系统中语言驱动的闭环控制，使其在执行动态变化的高层任务时，仍能在物理层保持形式化鲁棒性。提出一种三层架构：(i) 人类操作员发出自然语言指令；(ii) 基于大语言模型（LLM）的监督器周期性地根据最新状态和目标估计，对命令任务进行解释、验证与修正；(iii) 分布式内环控制器仅使用局部相对信息来跟踪生成的参考轨迹。我们推导出一个理论保证，刻画了在有界扰动和由大语言模型更新引发的离散跳跃的分段光滑参考下的跟踪性能。总体而言，结果表明，集中式语言任务推理可与分布式反馈控制结合，实现具有可证明鲁棒性与稳定性的复杂行为。
原文摘要 · Abstract (English)
We study language-in-the-loop control for multi-drone systems that execute evolving, high-level missions while retaining formal robustness guarantees at the physical layer. We propose a three-layer architecture in which (i) a human operator issues natural-language instructions, (ii) an LLM-based supervisor periodically interprets, verifies, and corrects the commanded task in the context of the latest state and target estimates, and (iii) a distributed inner-loop controller tracks the resulting reference using only local relative information. We derive a theoretical guarantee that characterizes tracking performance under bounded disturbances and piecewise-smooth references with discrete jumps induced by LLM updates. Overall, our results illustrate how centralized language-based task reasoning can be combined with distributed feedback control to achieve complex behaviors with provable robustness and stability.
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。