Data-driven technologies and automated identification systems (AISs) provide unprecedented opportunities for maritime surveillance. As part of enhancing maritime situational awareness and safety, in this paper, we address the issue of predicting a ship’s future trajectory using historical AIS observations. The objective is to use past data in the training phase to learn the predictive distribution of marine traffic patterns and then use that information to forecast future trajectories. To achieve this, we investigate an encoder–decoder architecture-based sequence-to-sequence prediction model and CNN model. This architecture includes a long short-term memory (LSTM) RNN that encodes sequential AIS data from the past and generates future trajectory samples. The effectiveness of sequence-to-sequence neural networks (RNNs) for forecasting future vessel trajectories is demonstrated through an experimental assessment using an AIS dataset.

On 25 July 2021, the AUV of the Marine Science and Technology Research Center was lost under the sea due to a fracture of the wire rope when it was performing a mission offshore of China. A model is presented in the paper for predicting the trajectory of a lost AUV based on ABiLSTM. To increase the precision of model prediction, the model incorporates the soft attention mechanism and is based on the bidirectional Long Short-Term Memory (BiLSTM) network. In comparison to LSTM, BiLSTM, and attention-LSTM models, experiments have demonstrated that the proposed model enhanced prediction accuracy in terms of longitude, latitude, and altitude by 0.009° E, 0.008° N, and 2 m using representative root mean squared error as an assessment indicator. The findings of the study can improve marine rescue efforts and aid in the search and recovery of AUVs that have crashed.

Emergency braking systems (EBSs) are critical for maintaining vehicle stability and safety during severe braking maneuvers; however, conventional EBS controllers often rely on wheel-slip feedback and exhibit conservative braking performance due to the highly nonlinear and time-varying nature of tire–road interactions.To address these limitations, this paper proposes a direct torque-level emergency braking framework for electric vehicles that maps readily available onboard measurements directly to four-wheel braking torques without requiring explicit estimation of wheel slip, tire–road friction, or vehicle sideslip states. An expert policy is first constructed using residual reinforcement learning, in which a modified twin delayed deep deterministic policy gradient variant (TD7) agent learns corrective braking actions on top of a model-based controller. The resulting expert policy is subsequently distilled into a lightweight student controller through a teacher–student learning framework. The proposed approach is evaluated in a high-fidelity vehicle dynamics environment and further validated through cross-platform verification. Experimental results demonstrate superior braking performance compared with a conventional MPC controller in terms of stopping distance, braking time, and vehicle stability under diverse road-friction conditions. The results further confirm the robustness and cross-platform generalization capability of the proposed framework, highlighting its potential as an effective and computationally efficient solution for intelligent emergency braking control in future electric vehicles.