Optimizing AUV Path Planning for Data Collection in UWSNs: A Review of Energy Efficient Approaches

Abstract

Underwater Wireless Sensor Networks (UWSNs) are critical for monitoring and exploring aquatic ecosystems, with Autonomous Underwater Vehicles (AUVs) playing a pivotal role in data collection. This review focuses on optimizing AUV path planning for efficient data gathering in UWSNs, emphasizing energy-efficient methods. Key approaches discussed include the K-Means algorithm for path optimization and geometric search techniques for precise sensor node localization. Comparative analyses of optimization methods, such as Particle Swarm Optimization (PSO), Genetic Algorithms (GAs), and Reinforcement Learning (RL), are presented, evaluating their impact on energy usage, data collection efficiency, and trajectory precision. This study provides a comprehensive understanding of current advancements and identifies potential research avenues, offering valuable insights for advancing energy-efficient AUV path planning in real-world applications.