USV Collision Avoidance Decision-Making Based on the Improved PPO Algorithm in Restricted Waters

The study presents an optimized Unmanned Surface Vehicle (USV) collision avoidance decision-making strategy in restricted waters based on the improved Proximal Policy Optimization (PPO) algorithm. This approach effectively integrates the ship domain, the action area of restricted waters, and the International Regulations for Preventing Collisions at Sea (COLREGs), while constructing an autonomous decision-making system. A novel set of reward functions are devised to incentivize USVs to strictly adhere to COLREGs during autonomous decision-making. Also, to enhance convergence performance, this study incorporates the Gated Recurrent Unit (GRU), which is demonstrated to significantly improve algorithmic efficacy compared to both the Long Short-Term Memory (LSTM) network and traditional fully connected network structures. Finally, extensive testing in various constrained environments, such as narrow channels and complex waters with multiple ships, validates the effectiveness and reliability of the proposed strategy.