Path Planning of Unmanned Underwater Vehicles Based on Deep Reinforcement Learning Algorithm

This paper implemented path planning for unmanned underwater vehicle (UUV) using deep reinforcement learning (DRL)algorithms with the UUV Simulator. We used three different algorithms, including twin delayed deep deterministic policy gradient (TD3), Soft Actor-Critic (SAC), and Proximal Policy Optimization (PPO). By conducting multiple experiments in a simulation environment and evaluating their results, we found that all three algorithms have good performance and robustness, and each has its own advantages in different test cases. The research results of this paper can provide some reference and guidance for UUV path planning.