Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions
This work addresses the challenge of unpredictable disturbances and strong coupling in AUVs for oceanic research, representing an incremental improvement by integrating LLMs with RL and S-surface control.
The paper tackled the problem of controlling Autonomous Underwater Vehicles (AUVs) under extreme sea conditions by developing an LLM-enhanced RL-based adaptive S-surface controller, which outperformed traditional PID and SMC controllers in tasks like underwater target tracking and data collection.
The adaptivity and maneuvering capabilities of Autonomous Underwater Vehicles (AUVs) have drawn significant attention in oceanic research, due to the unpredictable disturbances and strong coupling among the AUV's degrees of freedom. In this paper, we developed large language model (LLM)-enhanced reinforcement learning (RL)-based adaptive S-surface controller for AUVs. Specifically, LLMs are introduced for the joint optimization of controller parameters and reward functions in RL training. Using multi-modal and structured explicit task feedback, LLMs enable joint adjustments, balance multiple objectives, and enhance task-oriented performance and adaptability. In the proposed controller, the RL policy focuses on upper-level tasks, outputting task-oriented high-level commands that the S-surface controller then converts into control signals, ensuring cancellation of nonlinear effects and unpredictable external disturbances in extreme sea conditions. Under extreme sea conditions involving complex terrain, waves, and currents, the proposed controller demonstrates superior performance and adaptability in high-level tasks such as underwater target tracking and data collection, outperforming traditional PID and SMC controllers.