With the development of artificial intelligence technology, the behavior decision-making of an intelligent smart marine autonomous surface ship (SMASS) has become particularly important. This research proposed local path planning and a behavior decision-making approach based on improved Proximal Policy Optimization (PPO), which could drive an unmanned SMASS to the target without requiring any human experiences. In addition, a generalized advantage estimation was added to the loss function of the PPO algorithm, which allowed baselines in PPO algorithms to be self-adjusted. At first, the SMASS was modeled with the Nomoto model in a simulation waterway. Then, distances, obstacles, and prohibited areas were regularized as rewards or punishments, which were used to judge the performance and manipulation decisions of the vessel Subsequently, improved PPO was introduced to learn the action–reward model, and the neural network model after training was used to manipulate the SMASS’s movement. To achieve higher reward values, the SMASS could find an appropriate path or navigation strategy by itself. After a sufficient number of rounds of training, a convincing path and manipulation strategies would likely be produced. Compared with the proposed approach of the existing methods, this approach is more effective in self-learning and continuous optimization and thus closer to human manipulation.

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.