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

2024-09-04

arXiv.org

AI Summary

To address the low localization accuracy and poor mission completion rate of single autonomous underwater vehicles (AUVs) in harsh marine environments, this paper proposes a heterogeneous USV-AUV collaborative operation framework. The method innovatively integrates Fisher information matrix–optimized USV-guided path planning with a deep reinforcement learning–driven distributed multi-AUV cooperative decision-making mechanism, augmented by multi-sensor fusion and robust communication recovery strategies. Simulation results demonstrate that, under extreme conditions—including strong ocean currents and high sensor noise—the system achieves centimeter-level cooperative localization accuracy, improves mission completion rate by 37%, and reduces average communication interruption recovery time by 62%. These advancements significantly enhance operational robustness and data acquisition efficiency in complex maritime scenarios.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• AUVs operation
• harsh marine environment
• positioning and task execution

Innovation

• Collaborative Navigation
• Underwater Robotics
• Simulation Validation