脳としてのエージェント、小脳としてのコントローラ:ドローン上に実装する身体性を持つLMMベースエージェント
Agent as Cerebrum, Controller as Cerebellum: Implementing an Embodied LMM-based Agent on Drones
LMMを「脳」、従来の制御器を「小脳」と見立てた階層型エージェントAeroAgentをドローン向けに構築し、ROS連携フレームワークROSchainで実装。探索救助タスクでDRLベース手法を上回る性能を示した。
著者: Haoran Zhao, Fengxing Pan, Huqiuyue Ping, Yaoming Zhou
分類: cs.RO, cs.AI
原文アブストラクト
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.
