AerialClaw：一个用于LLM驱动的自主空中智能体的开源框架
AerialClaw: An Open-Source Framework for LLM-Driven Autonomous Aerial Agents
AI总结：
提出AerialClaw开源框架，采用模块化脑-技能-运行时架构，使基于LLM的智能体能够理解自然语言任务、调用空中技能、闭环决策，提升无人机系统的灵活性、可复现性和可扩展性。
摘要：
无人机（UAV）越来越多地用于检查、搜索救援、环境监测和应急响应。然而，大多数无人机应用仍然依赖于预定义的命令序列或特定任务的管道，开发者手动连接感知、规划、飞行控制、仿真、日志记录和安全模块。这限制了自主空中系统的灵活性、可复现性和可扩展性。本文提出了AerialClaw，一个开源软件框架，使无人机能够作为决策型空中智能体运行，而不仅仅是遵循命令的平台。给定自然语言任务，AerialClaw允许基于LLM的智能体理解任务、维护上下文、调用可执行的空中技能、观察感知和运行时反馈，并在闭环中迭代更新其决策。该框架采用模块化的脑-技能-运行时架构，结合了用于原子无人机操作的硬技能、基于Markdown的可重用任务策略软技能、文档驱动的智能体状态和能力边界、记忆驱动的反思、面向安全的运行时验证以及平台无关的执行适配器。AerialClaw支持轻量级模拟执行、PX4 SITL与Gazebo以及基于AirSim的仿真，同时提供Web控制台、可插拔模型后端、示例任务、仿真资产和分阶段部署脚本。通过结合标准化的空中技能、文档驱动的智能体状态、记忆和闭环LLM决策，AerialClaw提供了一个可复现且可扩展的开源框架，用于构建能够解释任务、做出决策、执行技能并根据反馈调整行为的无人机系统。
英文摘要：
Unmanned aerial vehicles (UAVs) are increasingly used in inspection, search and rescue, environmental monitoring, and emergency response. However, most UAV applications still rely on pre-defined command sequences or task-specific pipelines, where developers manually connect perception, planning, flight control, simulation, logging, and safety modules. This limits the flexibility, reproducibility, and extensibility of autonomous aerial systems. This paper presents AerialClaw, an open-source software framework that enables UAVs to operate as decision-making aerial agents rather than merely command-following platforms. Given a natural-language mission, AerialClaw allows an LLM-based agent to understand the task, maintain context, invoke executable aerial skills, observe perception and runtime feedback, and iteratively update its decisions in a closed loop. The framework adopts a modular brain-skill-runtime architecture, combining hard skills for atomic UAV operations, Markdown-based soft skills for reusable task strategies, document-driven agent state and capability boundaries, memory-driven reflection, safety-oriented runtime validation, and platform-agnostic execution adapters. AerialClaw supports lightweight mock execution, PX4 SITL with Gazebo, and AirSim-based simulation, together with a web console, pluggable model backends, example missions, simulation assets, and staged deployment scripts. By combining standardized aerial skills, document-driven agent state, memory, and closed-loop LLM decision-making, AerialClaw provides a reproducible and extensible open-source framework for building UAV systems that can interpret missions, make decisions, execute skills, and adapt their behavior from feedback.
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。
