Ship Collision Avoidance and Anti Grounding Using Parallelized Cost Evaluation in Probabilistic Scenario-Based Model Predictive Control

The ability to effectively process large amounts of information in reasonable time will be important for robust deliberative collision avoidance (COLAV) planning algorithms. Failure do so can lead collision, and compared lack proper supervision from officers on watch (OOW). main contribution this article is a parallelized implementation the Probabilistic Scenario-Based Model Predictive Control (PSB-MPC) Graphical Processing Unit (GPU) platform which incorporates both dynamic obstacle anti-grounding. Simulation results demonstrate that COLAV planner produce collision-free trajectories with respect grounding hazards nearby vessels at relatively low computational cost, also comply COLREGS when deemed possible. Corresponding run-time show algorithm utilizing parallel processing performs better than alternative increasing numbers own-ship control behaviours, static obstacles, prediction scenarios considered.