In this study, we present a novel paradigm for industrial robotic embodied
agents, encapsulating an 'agent as cerebrum, controller as cerebellum'
architecture. Our approach harnesses the power of Large Multimodal Models
(LMMs) within an agent framework known as AeroAgent, tailored for drone
technology in industrial settings. To facilitate seamless integration with
robotic systems, we introduce ROSchain, a bespoke linkage framework connecting
LMM-based agents to the Robot Operating System (ROS). We report findings from
extensive empirical research, including simulated experiments on the Airgen and
real-world case study, particularly in individual search and rescue operations.
The results demonstrate AeroAgent's superior performance in comparison to
existing Deep Reinforcement Learning (DRL)-based agents, highlighting the
advantages of the embodied LMM in complex, real-world scenarios.

本研究提出了一个新的产业机器人具身化代理范例，其采用 “代理为大脑，控制器为小脑” 的架构。我们的方法利用大型多模态模型（LMMs）在名为 AeroAgent 的代理框架中，针对产业环境中的无人机技术进行了针对性的设计。为了实现与机器人系统的无缝集成，我们引入了 ROSchain，这是一个连接基于 LMM 的代理与机器人操作系统（ROS）的专用链接框架。通过广泛的实证研究，包括对 Airgen 的模拟实验和真实案例研究，特别是在个体搜救行动中，我们报告了研究结果。结果表明，与现有的基于深度强化学习（DRL）的代理相比，AeroAgent 在复杂的真实场景中表现出更高的性能，凸显了具身化 LMM 在复杂真实世界情境中的优势。