AUV Path Planning in Complex Ocean Environment via Deep Reinforcement Learning Assisted by Edge Computing

In recent years, autonomous underwater vehicles (AUVs) have become a key tool for consumer-facing ocean applications, gaining widespread popularity among consumers. AUVs have the characteristics of small size, high autonomy, strong flexibility, and long endurance, and consumers can apply them to environmental monitoring, underwater detection, and recreational diving. However, achieving efficient underwater path planning and obstacle avoidance requires a significant amount of computing resources, which leads to the typically high costs of AUVs and poses a significant barrier to their widespread adoption. To solve this challenge, this paper proposes a low-cost path planning framework that integrates edge computing and deep reinforcement learning, aiming to achieve efficient path planning of AUV in the computing resource-constrained ocean environment. By embedding a lightweight edge computing module in the AUV, we developed a Kalman filter-based obstacle ranging algorithm that enables intelligent real-time processing of imaging sonar data streams. We conducted experiments on the ROS-Gazebo simulation platform that can simulate interactive scenarios involving ocean currents and obstacles. We constructing a realistic marine environment model and an AUV model equipped with imaging sonar. The experimental results show that the proposed method achieves efficient and reliable path planning in dynamic ocean environments with both obstacle and current interference.