Explore the vast range of titles available.

Model Predictive Control (MPC) predicts the vehicle’s motion within a fixed time window, known as the prediction horizon, and calculates potential collision risks with obstacles in advance. It then determines the optimal steering input to guide the vehicle safely around obstacles. For example, when a sudden obstacle appears, sensors detect it, and MPC uses the vehicle’s current speed, position, and heading to predict its driving trajectory over the next few hundred milliseconds to several seconds. If a collision is predicted, MPC computes the optimal steering path among possible avoidance trajectories that are feasible within the vehicle’s dynamics. The vehicle then follows this input to steer away from the obstacle. In the proposed method, MPC is combined with Adaptive Artificial Potential Field (APF). The APF dynamically adjusts the repulsive force based on the distance and relative speed to the obstacle. MPC predicts the optimal driving path and generates control inputs, while the avoidance vector from APF is integrated into MPC’s constraints or cost function. Simulation results demonstrate that the proposed method significantly improves obstacle avoidance response, steering smoothness, and path stability compared to the baseline MPC approach.

To address the global path planning challenge for Unmanned Surface Vehicles in complex maritime environments characterized by dense islands and narrow waterways, this paper proposes a Hybrid Multi-Strategy Adaptive RRT* algorithm. The method combines a dynamic region-based sampling strategy with an improved artificial potential field based dynamic extension strategy, which introduces random-node attraction, dynamic repulsion adjustments, and additional repulsive forces. Additionally, a hierarchical side-retreat escape mechanism is applied to enhance obstacle avoidance and search efficiency in complex environments. The algorithm also incorporates heading-angle constraints and adaptive step-size adjustment to ensure the path complies with USV kinematic properties. Furthermore, an improved NSGA-II algorithm is proposed to perform multi-objective optimization of path length, smoothness, and safety, and B-spline interpolation is used to generate continuous and executable paths. Simulation results show that, compared with the standard RRT* algorithm, the proposed HMA-RRT* algorithm achieves average reductions of 7.85% in path length, 66.96% in node count, 48.73% in computation time, and 25.7% in mean turning angle across four representative complex maritime environments. These improvements significantly enhance search efficiency, path smoothness, and planning feasibility, thereby providing a reliable and efficient path-planning solution for autonomous USV navigation in complex maritime conditions. Graphical abstract