Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions

2025-03-01

AI Summary

Autonomous underwater vehicles (AUVs) suffer degraded adaptability and maneuverability in extreme marine environments due to strong hydrodynamic coupling and unpredictable disturbances. Method: This paper proposes an LLM-enhanced hierarchical control architecture: a high-level task planner using PPO/SAC reinforcement learning, and a low-level adaptive S-surface controller for nonlinear disturbance rejection. We introduce a novel LLM-driven co-optimization mechanism for reward shaping and controller parameter tuning, integrating hydrodynamic modeling with multi-source environmental simulations (waves, currents, seabed topography), and enabling multi-objective trade-offs and mission-oriented adaptation via multimodal structured feedback. Results: Simulation results demonstrate a 62% reduction in target tracking error and a 41% increase in data acquisition success rate compared to PID and sliding-mode controllers, significantly improving system robustness and mission-level adaptability under high-interference, strongly coupled conditions.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Learning to Search
• Intelligent Robots: Behavior Learning & Control

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

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.

Problem

• Enhances AUV control under extreme sea conditions
• Optimizes controller parameters and reward functions using LLMs
• Improves adaptability and performance in complex oceanic tasks

Innovation

• LLM-enhanced RL optimizes controller parameters.
• S-surface controller cancels nonlinear disturbances.
• Superior performance in extreme sea conditions.