When Motion Learns to Listen: Diffusion-Prior Lyapunov Actor-Critic Framework with LLM Guidance for Stable and Robust AUV Control in Underwater Tasks

TL;DR

This paper introduces a novel AUV control framework combining diffusion models, Lyapunov stability, and LLM guidance to improve robustness, adaptability, and efficiency in complex underwater environments.

Contribution

It proposes a diffusion-prior Lyapunov actor-critic method with LLM-driven adaptive Lyapunov function selection for enhanced AUV control.

Findings

Achieves more accurate trajectory tracking

Demonstrates higher task completion rates

Shows improved robustness and energy efficiency

Abstract

Autonomous Underwater Vehicles (AUVs) are indispensable for marine exploration; yet, their control is hindered by nonlinear hydrodynamics, time-varying disturbances, and localization uncertainty. Traditional controllers provide only limited adaptability, while Reinforcement Learning (RL), though promising, suffers from sample inefficiency, weak long-term planning, and lacks stability guarantees, leading to unreliable behavior. To address these challenges, we propose a diffusion-prior Lyapunov actor-critic framework that unifies exploration, stability, and semantic adaptability. Specifically, a diffusion model generates smooth, multimodal, and disturbance-resilient candidate actions; a Lyapunov critic further imposes dual constraints that ensure stability; and a Large Language Model (LLM)-driven outer loop adaptively selects and refines Lyapunov functions based on task semantics and training feedback. This "generation-filtering-optimization" mechanism not only enhances sample efficiency and planning capability but also aligns stability guarantees with diverse mission requirements in the multi-objective optimization task. Extensive simulations under complex ocean dynamics demonstrate that the proposed framework achieves more accurate trajectory tracking, higher task completion rates, improved energy efficiency, faster convergence, and improved robustness compared with conventional RL and diffusion-augmented baselines.