Description:
Unmanned Surface Vehicles (USVs) are increasingly vital in marine applications, but their navigation in dynamic and unpredictable environments poses significant challenges. This research focuses on energy-efficient motion planning for USVs, integrating multi-constraint dynamic collision avoidance to ensure safe operations. By leveraging Gaussian process-based models, it enhances route planning in high-fidelity environments, with augmented reality providing a deeper level of environmental interaction. Additionally, the work addresses multi-task planning for fleets of USVs, allowing for coordinated and efficient operations in complex missions. These innovations aim to improve the autonomy and reliability of USVs in real-world marine conditions.