To test and evaluate the decision-making capabilities of intelligent ships during navigation under varying collision risk conditions and increase the likelihood of encountering scenarios with controllable risk levels, this paper proposes a method for generating ship collision risk test scenarios based on conditional variational autoencoder (CVAE).

Using ship data from the automatic identification system (AIS), the relative motion parameters of ships are calculated. Combined with the "International Regulations for Preventing Collision at Sea （COLREGs）" and a fuzzy rule base, ship encounter situations and ship collision risk levels are classified to construct a ship encounter-risk dataset. The CVAE model is then trained on this dataset, with the relative motion parameters serving as input features and the encounter situation and the collision risk level as conditional variables. After training, the model generates corresponding test scenarios by inputting the conditional variables and the initial state of the test vessel. Additionally, during navigation, the distance to closest point of approach（DCPA）, time to closest point of approach (TCPA), and collision risk index (CRI) are dynamically displayed with a 10-second time step. Comparative experiments with a variational autoencoder (VAE) and random sampling methods are conducted to verify the accuracy and similarity of scenario generation across different models.

The results indicate that, under the specified encounter situations and collision risk levels, the CVAE model generates test scenarios that simultaneously satisfy both preset conditions with an accuracy of 93.54%. In comparison, the VAE model achieves only 0.08%, and the random sampling method 0.83%, representing improvements of 93.46% and 92.71%, respectively.

The proposed method improves the effectiveness, diversity, and realism of the generated encounter situations and ship collision risk scenarios, demonstrating superior accuracy in scenario generation for intelligent ship navigation.

In order to solve the problems of safety and smoothness in the path planning of an unmanned surface vehicle (USV), a path planning method with a controllable distance from obstacles is proposed.

First, the raster environment information is generated in combination with the radar image, and the Voronoi field algorithm (VFA) is used to add the danger potential field to each grid and establish the navigation boundary; second, the risk function associated with the navigation boundary is established to improve the evaluation function of the A-star algorithm, and the improved A-star algorithm is used for path planning; finally, for the problem of the large course altering of the navigation path, the gradient descent method (GDM) is used to plot a continuous smooth navigation path that satisfies the actual navigation requirements of the USV.

The simulation results show that the proposed path planning method can control the distance between the path and obstacles by setting different navigation boundaries, and the smoothness meets the navigation requirements.

The method proposed herein is reasonable and effective in the path planning process of USVs, and can provide references for USV autonomous obstacle avoidance decision-making.