No abstract

Based on the advantages of small size, easy to carry by large ship, high speed, flexible mobility, no need to drive by human, high autonomy, the Unmanned Surface Vehicle (USV) is very suitable for the sea emergency rescue. During rescue, the USV needs to track the castaway, and it needs to sail to the downstream position of the castaway in the shortest time to release the life-saving equipment. In this paper, the technology of sea emergency rescue of USV is researched, the motion of the castaway is established, and the downstream position and velocity of the castaway is predicted based on Kalman Filter (KF). In addition, the motion model of the USV is established, and the target tracking based on the Dynamic Window Approach (DWA) is carried out, which will guide the USV to reach the rescue position, and local obstacle avoidance is carried out near the castaway to avoid collision. The rescue strategy does not need to consider the influence of the weather on the position of rescue, so it has high adaptability. Finally, the rescue strategy is simulated, the simulation results validate it works effectively.

Due to the continuous upgrading and optimization of fishing technology and tools, and the diversification of fishing vessel operation methods, marine fishery resources are continuously depleted. Precise prediction of the operation methods of marine fishing vessels is helpful to realize effective supervision of fishing behavior of fishing vessels. In order to improve the prediction accuracy, when doing feature engineering, this paper uses a vector encoding scheme based on trajectory sequence, and uses text vectors to train the word2vec model to calculate the embedding features of each position. At present, the single method needs to be improved in terms of forecasting accuracy. This paper proposes a forecasting method based on Stacking model fusion in order to further improve the forecasting accuracy of marine fishing vessel operations. The experimental results show that the Stacking fusion model using the vector coding scheme based on the trajectory sequence has a greater improvement in prediction accuracy than a single model.