USV-AUV Collaboration Framework for Underwater Tasks under Extreme Sea Conditions

TL;DR

This paper presents a USV-AUV collaboration framework that enhances underwater data collection in extreme sea conditions through advanced path planning and reinforcement learning, validated by extensive simulations.

Contribution

Introduces a novel USV-AUV collaboration framework with optimized path planning and reinforcement learning for robust underwater tasks in harsh environments.

Findings

Framework demonstrates superior coordination under extreme conditions

Simulation results validate high-precision multi-AUV positioning

Open-source code accelerates research in underwater vehicle collaboration

Abstract

Autonomous underwater vehicles (AUVs) are valuable for ocean exploration due to their flexibility and ability to carry communication and detection units. Nevertheless, AUVs alone often face challenges in harsh and extreme sea conditions. This study introduces a unmanned surface vehicle (USV)-AUV collaboration framework, which includes high-precision multi-AUV positioning using USV path planning via Fisher information matrix optimization and reinforcement learning for multi-AUV cooperative tasks. Applied to a multi-AUV underwater data collection task scenario, extensive simulations validate the framework's feasibility and superior performance, highlighting exceptional coordination and robustness under extreme sea conditions. To accelerate relevant research in this field, we have made the simulation code (demo version) available as open-source.