Reinforcement Learning-Based 3D Beam Adaptation for Underwater Wireless Optical Communication with AUVs

2026-10-05

AI Summary

This study addresses the misalignment and link outage of autonomous underwater vehicle (AUV) transceivers caused by ocean current disturbances in underwater wireless optical communication. To mitigate this, a beam adaptive control strategy based on deep reinforcement learning (DRL) is proposed. First, a three-dimensional dynamic channel model is constructed using the discrete ray method. Subsequently, DRL is employed to jointly optimize the beam pointing angle and divergence angle, enabling precise tracking under complex sea conditions. Experiments based on real-world oceanographic data demonstrate that the proposed approach reduces excess outage probabilities to 8.5% and 16.2% in static and current-drift scenarios, respectively, thereby effectively enhancing the robustness of underwater optical links.

Abstract

Underwater Wireless Optical Communications (UWOC) provide essential high data rates for Autonomous Underwater Vehicles (AUVs), but reliable connectivity is critically affected by transmitter-receiver misalignment. This work addresses the beam pointing problem for a moving AUV subject to unknown ocean currents through a Deep Reinforcement Learning (DRL) framework. We develop a comprehensive 3D UWOC channel model incorporating depth-dependent attenuation, turbulence, and a discrete-ray method to accurately quantify geometric and misalignment losses. The resulting agent jointly optimizes beam steering and divergence angles, learning a policy that prioritizes continuous link maintenance. Evaluated using real oceanographic data, the framework's performance is assessed via the excess outage metric, which isolates outages occurring exclusively due to pointing errors. Relative to perfect alignment between nodes, the proposed method bounds this metric to 8.5% under ocean current-free tracking conditions and limits it to 16.2% when subjected to current-induced drift. The findings obtained in this work confirms that DRL-enabled beam control is capable of adaptive tracking and mitigating link outages in dynamic underwater environments.

Problem

• Underwater Wireless Optical Communication
• Beam Pointing
• Autonomous Underwater Vehicles
• Misalignment
• Ocean Currents

Innovation

• Deep Reinforcement Learning
• Underwater Wireless Optical Communication
• 3D Beam Adaptation
• Autonomous Underwater Vehicles
• Channel Modeling