This study contributes to addressing the challenge of quickly obtaining an effective and accurate nonparametric model for describing ship maneuvering motion in three degrees of freedom (3-DOF). To achieve this, an intelligent ship dynamics nonparametric modeling method named improved PER-DDPG is proposed. This method leverages the deep deterministic policy gradient algorithm (DDPG) and prioritized experience replay mechanism (PER) and analyzes the characteristics between the goal of deep reinforcement learning (DRL) and the modeling process of the nonparametric model. The PER mechanism is utilized to enhance the agent's understanding of the overall mechanism of ship motion by improving the utilization of samples. The meaning of target value is redefined due to transforming DRL aiming at maximizing cumulative rewards into maximizing the set of immediate rewards at each time step. To validate the performance of the proposed modeling method, we conduct simulation studies using a benchmark ship model i.e., a Mariner cargo ship dynamic model, and experimental studies using a real unmanned surface vehicle (USV). In the simulation test, we demonstrate the effectiveness and generalization of the proposed method through zigzag and turning circle tests. Furthermore, we verify the robustness and applicability of the proposed method by using datasets with uncertain environmental disturbances and datasets with different sampling frequencies. Additionally, the experimental tests conducted on the USV indicate the consistency of the proposed approach.@en

In the inland navigation environment, the serious AIS signal congestion and loss result in the ship AIS trajectory to be sparse and discontinuous. Traditional numerical analysis method is used to fit the lost trajectory of ships, and it cannot adapt to the complicated inland waterways with complicated bend, and is prone to cross the land coast. In this paper, a trajectory estimation method for inland river ship was proposed based on navigation experience. Based on the spatial consistency, time consistency and heading consistency, the history similar ship trajectories were extracted for neighbor sampling points of sparse trajectory, and the navigation experience was estimated by the method of Kernel density estimation, and navigational heat distribution map was modelled. And then the optimal route was calculated as approximate estimation trajectory in consideration of ship movement trend based on navigation heat. Three typical inland river channel scenarios were selected to carry out sparse trajectory restoration experiments. Results show that the proposed method can adapt well to the complex terrain of the inland waterway.@en

At present, the supervision mode of inland ferrying was conducted passively by mainly human analysis and judgement based on VTS and AIS, which is not favorable to reply increasingly serious situation of marine security supervision. The historical AIS data of the ferryboat was analyzed to explore its motion pattern and obtain the probability density spatial distribution of motion characteristics of location, course and speed by using the kernel density estimation. Then on this basis, the detection algorithm of the ferryboat abnormal behaviors was established for location and speed abnormity, and actual AIS data was used to verify the algorithm. Experimental results show that the proposed algorithm can accurately recognize the abnormal behaviors of the ferryboat, which is helpful to the marine supervision.@en

At present, the supervision mode of inland ferrying was conducted passively by mainly human analysis and judgement based on VTS and AIS, which is not favorable to reply increasingly serious situation of marine security supervision. The historical AIS data of the ferryboat was analyzed to explore its motion pattern and obtain the probability density spatial distribution of motion characteristics of location, course and speed by using the kernel density estimation. Then on this basis, the detection algorithm of the ferryboat abnormal behaviors was established for location and speed abnormity, and actual AIS data was used to verify the algorithm. Experimental results show that the proposed algorithm can accurately recognize the abnormal behaviors of the ferryboat, which is helpful to the marine supervision.@en

At present, the supervision mode of inland ferrying was conducted passively by mainly human analysis and judgement based on VTS and AIS, which is not favorable to reply increasingly serious situation of marine security supervision. The historical AIS data of the ferryboat was analyzed to explore its motion pattern and obtain the probability density spatial distribution of motion characteristics of location, course and speed by using the kernel density estimation. Then on this basis, the detection algorithm of the ferryboat abnormal behaviors was established for location and speed abnormity, and actual AIS data was used to verify the algorithm. Experimental results show that the proposed algorithm can accurately recognize the abnormal behaviors of the ferryboat, which is helpful to the marine supervision.@en

At present, the supervision mode of inland ferrying was conducted passively by mainly human analysis and judgement based on VTS and AIS, which is not favorable to reply increasingly serious situation of marine security supervision. The historical AIS data of the ferryboat was analyzed to explore its motion pattern and obtain the probability density spatial distribution of motion characteristics of location, course and speed by using the kernel density estimation. Then on this basis, the detection algorithm of the ferryboat abnormal behaviors was established for location and speed abnormity, and actual AIS data was used to verify the algorithm. Experimental results show that the proposed algorithm can accurately recognize the abnormal behaviors of the ferryboat, which is helpful to the marine supervision.@en

At present, the supervision mode of inland ferrying was conducted passively by mainly human analysis and judgement based on VTS and AIS, which is not favorable to reply increasingly serious situation of marine security supervision. The historical AIS data of the ferryboat was analyzed to explore its motion pattern and obtain the probability density spatial distribution of motion characteristics of location, course and speed by using the kernel density estimation. Then on this basis, the detection algorithm of the ferryboat abnormal behaviors was established for location and speed abnormity, and actual AIS data was used to verify the algorithm. Experimental results show that the proposed algorithm can accurately recognize the abnormal behaviors of the ferryboat, which is helpful to the marine supervision.@en