Agent as Cerebrum, Controller as Cerebellum: Implementing an Embodied LMM-based Agent on Drones
This addresses the need for more effective robotic agents in industrial applications like search and rescue, though it appears incremental as it builds on existing LMM and drone technologies.
The study tackled the problem of implementing embodied agents for drones in industrial settings by proposing a novel 'agent as cerebrum, controller as cerebellum' architecture using Large Multimodal Models (LMMs), resulting in AeroAgent outperforming existing Deep Reinforcement Learning-based agents in search and rescue operations.
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.